refactor boardPutConfigs

regenerate easyjson file for router_opentsdb

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,12 +0,0 @@
----
-name: Bug Report
-about: Report a bug encountered while operating Nightingale
-labels: kind/bug
----
-
-**夜莺版本**:
-
-
-**问题和复现方法**:
-
-

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,67 @@
+name: Bug Report
+description: Report a bug encountered while running Nightingale
+labels: ["kind/bug"]
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking time to fill out this bug report! 
+        The more detailed the form is filled in, the easier the problem will be solved.
+  - type: textarea
+    id: config
+    attributes:
+      label: Relevant server.conf | webapi.conf
+      description: Place config in the toml code section. This will be automatically formatted into toml, so no need for backticks.
+      render: toml
+    validations:
+      required: true
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant logs
+      description: categraf | telegraf | server | webapi | prometheus | chrome request/response ...
+      render: text
+    validations:
+      required: true
+  - type: input
+    id: system-info
+    attributes:
+      label: System info
+      description: Include nightingale version, operating system, and other relevant details
+      placeholder: ex. n9e 5.9.2, n9e-fe 5.5.0, categraf 0.1.0, Ubuntu 20.04, Docker 20.10.8
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Describe the steps to reproduce the bug.
+      value: |
+        1.
+        2.
+        3.
+        ...
+    validations:
+      required: true
+  - type: textarea
+    id: expected-behavior
+    attributes:
+      label: Expected behavior
+      description: Describe what you expected to happen when you performed the above steps.
+    validations:
+      required: true
+  - type: textarea
+    id: actual-behavior
+    attributes:
+      label: Actual behavior
+      description: Describe what actually happened when you performed the above steps.
+    validations:
+      required: true
+  - type: textarea
+    id: additional-info
+    attributes:
+      label: Additional info
+      description: Include gist of relevant config, logs, etc.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -1,5 +1,5 @@
 blank_issues_enabled: false
 contact_links:
-  - name: Nightingale community
-    url: https://n9e.didiyun.com/community/
-    about: List of communication channels for the Nightingale community.
+  - name: Nightingale docs
+    url: https://n9e.github.io/
+    about: You may want to read through the document before asking questions.

.github/workflows/n9e.yml

@@ -1,26 +1,32 @@
-name: Go
+name: Release
 
 on:
   push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
+    tags:
+      - 'v*'
+env:
+  GO_VERSION: 1.18
 
 jobs:
-
-  build:
-    name: Build
+  goreleaser:
     runs-on: ubuntu-latest
     steps:
-
-    - name: Set up Go 1.17
-      uses: actions/setup-go@v1
-      with:
-        go-version: 1.17
-      id: go
-
-    - name: Check out code into the Go module directory
-      uses: actions/checkout@v2
-
-    - name: Build
-      run: make
+      - name: Checkout Source Code
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Setup Go Environment
+        uses: actions/setup-go@v3
+        with:
+          go-version: ${{ env.GO_VERSION }}
+      - uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Run GoReleaser
+        uses: goreleaser/goreleaser-action@v3
+        with:
+          version: latest
+          args: release --rm-dist
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.goreleaser.yaml

@@ -0,0 +1,88 @@
+before:
+  hooks:
+    # You may remove this if you don't use go modules.
+    - go mod tidy
+
+snapshot:
+  name_template: '{{ .Tag }}'
+checksum:
+  name_template: 'checksums.txt'
+changelog:
+  skip: true
+
+builds:
+  - id: build
+    hooks:
+      pre:
+       - ./fe.sh
+    main: ./src/
+    binary: n9e
+    env:
+      - CGO_ENABLED=0
+    goos:
+      - linux
+    goarch:
+      - amd64
+      - arm64
+    ldflags:
+      - -s -w
+      - -X github.com/didi/nightingale/v5/src/pkg/version.VERSION={{ .Tag }}-{{.Commit}}
+
+archives:
+  - id: n9e
+    builds:
+      - build
+    format: tar.gz
+    format_overrides:
+      - goos: windows
+        format: zip
+    name_template: "n9e-v{{ .Version }}-{{ .Os }}-{{ .Arch }}"
+    wrap_in_directory: false
+    files:
+      - docker/*
+      - etc/*
+      - pub/*
+
+release:
+  github:
+    owner: ccfos
+    name: nightingale
+  name_template: "v{{ .Version }}"
+
+dockers:
+  - image_templates:
+      - flashcatcloud/nightingale:{{ .Version }}-amd64
+    goos: linux
+    goarch: amd64
+    ids:
+      - build
+    dockerfile: docker/Dockerfile.goreleaser
+    extra_files:
+      - pub
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/amd64"
+  - image_templates:
+      - flashcatcloud/nightingale:{{ .Version }}-arm64v8
+    goos: linux
+    goarch: arm64
+    ids:
+      - build
+    dockerfile: docker/Dockerfile.goreleaser
+    extra_files:
+      - pub
+    use: buildx
+    build_flag_templates:
+      - "--platform=linux/arm64/v8"
+
+docker_manifests:
+
+  - name_template: flashcatcloud/nightingale:{{ .Version }}
+    image_templates:
+      - flashcatcloud/nightingale:{{ .Version }}-amd64
+      - flashcatcloud/nightingale:{{ .Version }}-arm64v8
+
+  - name_template: flashcatcloud/nightingale:latest
+    image_templates:
+      - flashcatcloud/nightingale:{{ .Version }}-amd64
+      - flashcatcloud/nightingale:{{ .Version }}-arm64v8

Makefile

@@ -2,10 +2,15 @@
 
 NOW = $(shell date -u '+%Y%m%d%I%M%S')
 
-RELEASE_VERSION = 5.9.0
 
 APP 			= n9e
 SERVER_BIN  	= $(APP)
+ROOT:=$(shell pwd -P)
+GIT_COMMIT:=$(shell git --work-tree ${ROOT}  rev-parse 'HEAD^{commit}')
+_GIT_VERSION:=$(shell git --work-tree ${ROOT} describe --tags --abbrev=14 "${GIT_COMMIT}^{commit}" 2>/dev/null)
+TAG=$(shell echo "${_GIT_VERSION}" |  awk -F"-" '{print $$1}')
+RELEASE_VERSION:="$(TAG)-$(GIT_COMMIT)"
+
 # RELEASE_ROOT 	= release
 # RELEASE_SERVER 	= release/${APP}
 # GIT_COUNT 		= $(shell git rev-list --all --count)
@@ -17,6 +22,9 @@ all: build
 build:
 	go build -ldflags "-w -s -X github.com/didi/nightingale/v5/src/pkg/version.VERSION=$(RELEASE_VERSION)" -o $(SERVER_BIN) ./src
 
+build-linux:
+	GOOS=linux GOARCH=amd64 go build -ldflags "-w -s -X github.com/didi/nightingale/v5/src/pkg/version.VERSION=$(RELEASE_VERSION)" -o $(SERVER_BIN) ./src
+
 # start:
 # 	@go run -ldflags "-X main.VERSION=$(RELEASE_TAG)" ./cmd/${APP}/main.go web -c ./configs/config.toml -m ./configs/model.conf --menu ./configs/menu.yaml
 run_webapi:

README.md

@@ -1,84 +1,121 @@
-<img src="doc/img/ccf-n9e.png" width="240">
+<p align="center">
+  <a href="https://github.com/ccfos/nightingale">
+    <img src="doc/img/ccf-n9e.png" alt="nightingale - cloud native monitoring" width="240" /></a>
+  <p align="center">夜莺是一款开源的云原生监控系统，采用 all-in-one 的设计，提供企业级的功能特性，开箱即用的产品体验。推荐升级您的 Prometheus + AlertManager + Grafana 组合方案到夜莺</p>
+</p>
 
-# Nightingale
+<p align="center">
+<img alt="GitHub latest release" src="https://img.shields.io/github/v/release/ccfos/nightingale"/>
+<a href="https://n9e.github.io">
+  <img alt="Docs" src="https://img.shields.io/badge/docs-get%20started-brightgreen"/></a>
+<a href="https://hub.docker.com/u/flashcatcloud">
+  <img alt="Docker pulls" src="https://img.shields.io/docker/pulls/flashcatcloud/nightingale"/></a>
+<img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/ccfos/nightingale">
+<img alt="GitHub forks" src="https://img.shields.io/github/forks/ccfos/nightingale">
+<a href="https://github.com/ccfos/nightingale/graphs/contributors">
+  <img alt="GitHub contributors" src="https://img.shields.io/github/contributors-anon/ccfos/nightingale"/></a>
+<img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"/>
+</p>
 
- Nightingale is an enterprise-level cloud-native monitoring system, which can be used as drop-in replacement of Prometheus for alerting and management.   
+[English](./README_EN.md) | [中文](./README.md)
 
-[English](./README.md) | [中文](./README_ZH.md)
+## Highlighted Features
 
-## Introduction
-Nightingale is an cloud-native monitoring system by All-In-On design, support enterprise-class functional features with an out-of-the-box experience. We recommend upgrading your `Prometheus` + `AlertManager` + `Grafana` combo solution to Nightingale.
+- **开箱即用**
+  - 支持 Docker、Helm Chart、云服务等多种部署方式，集数据采集、监控告警、可视化为一体，内置多种监控仪表盘、快捷视图、告警规则模板，导入即可快速使用，**大幅降低云原生监控系统的建设成本、学习成本、使用成本**；
+- **专业告警**
+  - 可视化的告警配置和管理，支持丰富的告警规则，提供屏蔽规则、订阅规则的配置能力，支持告警多种送达渠道，支持告警自愈、告警事件管理等；
+- **云原生**
+  - 以交钥匙的方式快速构建企业级的云原生监控体系，支持 [**Categraf**](https://github.com/flashcatcloud/categraf)、Telegraf、Grafana-agent 等多种采集器，支持 Prometheus、VictoriaMetrics、M3DB、ElasticSearch 等多种数据库，兼容支持导入 Grafana 仪表盘，**与云原生生态无缝集成**；
+- **高性能，高可用**
+  - 得益于夜莺的多数据源管理引擎，和夜莺引擎侧优秀的架构设计，借助于高性能时序库，可以满足数亿时间线的采集、存储、告警分析场景，节省大量成本；
+  - 夜莺监控组件均可水平扩展，无单点，已在上千家企业部署落地，经受了严苛的生产实践检验。众多互联网头部公司，夜莺集群机器达百台，处理数亿级时间线，重度使用夜莺监控；
+- **灵活扩展，中心化管理**
+  - 夜莺监控，可部署在 1 核 1G 的云主机，可在上百台机器集群化部署，可运行在 K8s 中；也可将时序库、告警引擎等组件下沉到各机房、各 Region，兼顾边缘部署和中心化统一管理，**解决数据割裂，缺乏统一视图的难题**；
+- **开放社区**
+  - 托管于[中国计算机学会开源发展委员会](https://www.ccf.org.cn/kyfzwyh/)，有[**快猫星云**](https://flashcat.cloud)和众多公司的持续投入，和数千名社区用户的积极参与，以及夜莺监控项目清晰明确的定位，都保证了夜莺开源社区健康、长久的发展。活跃、专业的社区用户也在持续迭代和沉淀更多的最佳实践于产品中；
 
-- **Multiple prometheus data sources management**: manage all alerts and dashboards in one centralized visually view;
-- **Out-of-the-box alert rule**: built-in multiple alert rules, reuse alert rules template by one-click import with detailed explanation of metrics;
-- **Multiple modes for visualizing data**: out-of-the-box dashboards, instance customize views, expression browser and Grafana integration;
-- **Multiple collection clients**: support using Promethues Exporter、Telegraf、Datadog Agent to collecting metrics;
-- **Integration of multiple storage**: support Prometheus, M3DB, VictoriaMetrics, Influxdb, TDEngine as storage solutions, and original support for PromQL;
-- **Fault self-healing**: support the ability to self-heal from failures by configuring webhook;
+> 如果您在使用 Prometheus 过程中，有以下的一个或者多个需求场景，推荐您无缝升级到夜莺：
 
-#### If you are using Prometheus and have one or more of the following requirement scenarios, it is recommended that you upgrade to Nightingale:
+- Prometheus、Alertmanager、Grafana 等多个系统较为割裂，缺乏统一视图，无法开箱即用;
+- 通过修改配置文件来管理 Prometheus、Alertmanager 的方式，学习曲线大，协同有难度;
+- 数据量过大而无法扩展您的 Prometheus 集群；
+- 生产环境运行多套 Prometheus 集群，面临管理和使用成本高的问题；
 
-- Multiple systems such as Prometheus, Alertmanager, Grafana, etc. are fragmented and lack a unified view and cannot be used out of the box;
-- The way to manage Prometheus and Alertmanager by modifying configuration files has a big learning curve and is difficult to collaborate;
-- Too much data to scale-up your Prometheus cluster;
-- Multiple Prometheus clusters running in production environments, which faced high management and usage costs;
+> 如果您在使用 Zabbix，有以下的场景，推荐您升级到夜莺：
 
-#### If you are using Zabbix and have the following scenarios, it is recommended that you upgrade to Nightingale:
+- 监控的数据量太大，希望有更好的扩展解决方案；
+- 学习曲线高，多人多团队模式下，希望有更好的协同使用效率；
+- 微服务和云原生架构下，监控数据的生命周期多变、监控数据维度基数高，Zabbix 数据模型不易适配；
 
-- Monitoring too much data and wanting a better scalable solution;
-- A high learning curve and a desire for better efficiency of collaborative use in a multi-person, multi-team model;
-- Microservice and cloud-native architectures with variable monitoring data lifecycles and high monitoring data dimension bases, which are not easily adaptable to the Zabbix data model;
+> 如果您在使用 [Open-Falcon](https://github.com/open-falcon/falcon-plus)，我们更推荐您升级到夜莺：
+
+- 关于 Open-Falcon 和夜莺的详细介绍，请参考阅读：[云原生监控的十个特点和趋势](https://mp.weixin.qq.com/s?__biz=MzkzNjI5OTM5Nw==&mid=2247483738&idx=1&sn=e8bdbb974a2cd003c1abcc2b5405dd18&chksm=c2a19fb0f5d616a63185cd79277a79a6b80118ef2185890d0683d2bb20451bd9303c78d083c5#rd)。
+
+> 我们推荐您使用 [Categraf](https://github.com/flashcatcloud/categraf) 作为首选的监控数据采集器：
+
+- [Categraf](https://github.com/flashcatcloud/categraf) 是夜莺监控的默认采集器，采用开放插件机制和 all-in-one 的设计，同时支持 metric、log、trace、event 的采集。Categraf 不仅可以采集 CPU、内存、网络等系统层面的指标，也集成了众多开源组件的采集能力，支持K8s生态。Categraf 内置了对应的仪表盘和告警规则，开箱即用。
+ 
+
+## Getting Started
+
+- [快速安装](https://mp.weixin.qq.com/s/iEC4pfL1TgjMDOWYh8H-FA)
+- [详细文档](https://n9e.github.io/)
+- [社区分享](https://n9e.github.io/docs/prologue/share/)
+
+## Screenshots
+
+<img src="doc/img/intro.gif" width="480">
 
 
-#### If you are using [open-falcon](https://github.com/open-falcon/falcon-plus), we recommend you to upgrade to Nightingale：
-- For more information about open-falcon and Nightingale, please refer to read [Ten features and trends of cloud-native monitoring](https://mp.weixin.qq.com/s?__biz=MzkzNjI5OTM5Nw==&mid=2247483738&idx=1&sn=e8bdbb974a2cd003c1abcc2b5405dd18&chksm=c2a19fb0f5d616a63185cd79277a79a6b80118ef2185890d0683d2bb20451bd9303c78d083c5#rd)。
+## Architecture
 
-## Quickstart
-- [n9e.github.io/quickstart](https://n9e.github.io/quickstart/)
+<img src="doc/img/arch-product.png" width="480">
 
-## Documentation
-- [n9e.github.io](https://n9e.github.io/)
+夜莺监控可以接收各种采集器上报的监控数据（比如 [Categraf](https://github.com/flashcatcloud/categraf)、telegraf、grafana-agent、Prometheus），并写入多种流行的时序数据库中（可以支持Prometheus、M3DB、VictoriaMetrics、Thanos、TDEngine等），提供告警规则、屏蔽规则、订阅规则的配置能力，提供监控数据的查看能力，提供告警自愈机制（告警触发之后自动回调某个webhook地址或者执行某个脚本），提供历史告警事件的存储管理、分组查看的能力。
 
-## Example of use
-#### You can import and set MySQL-related alert rules:
-<img src="doc/img/mysql-alerts.png" width="680">
+<img src="doc/img/arch-system.png" width="480">
 
-#### You can import and set the host-related dashboard：
-<img src="doc/img/n9e-node-dashboard.png" width="680">
-
-#### You can also easily view all active alerts and historical alerts in Nightingale:
-<img src="https://n9e.github.io/intro/alert-events.png" width="680">
-
-## System Architecture
-#### A typical Nightingale deployment architecture:
-<img src="https://n9e.github.io/intro/arch-system.png" width="680">
-
-#### Typical deployment architecture using VictoriaMetrics as storage:
-<img src="https://n9e.github.io/fc-monitoring-vm.png" width="680">
-
-## Contact us and feedback questions
-- We recommend that you use [github issue](https://github.com/didi/nightingale/issues) as the preferred channel for issue feedback and requirement submission;
-- You can join our WeChat group - [Nightingale WeChat Group](https://s3-gz01.didistatic.com/n9e-pub/image/n9e-wx.png);
-
-<img src="https://n9e.github.io/cloudmon.png" width="180">
+夜莺 v5 版本的设计非常简单，核心是 server 和 webapi 两个模块，webapi 无状态，放到中心端，承接前端请求，将用户配置写入数据库；server 是告警引擎和数据转发模块，一般随着时序库走，一个时序库就对应一套 server，每套 server 可以只用一个实例，也可以多个实例组成集群，server 可以接收 Categraf、Telegraf、Grafana-Agent、Datadog-Agent、Falcon-Plugins 上报的数据，写入后端时序库，周期性从数据库同步告警规则，然后查询时序库做告警判断。每套 server 依赖一个 redis。
 
 
-## Contributing
-We welcome your participation in the Nightingale open source project and open source community in a variety of ways:
-- Feedback on problems and bugs  => [github issue](https://github.com/didi/nightingale/issues)
-- Additional and improved documentation => [n9e.github.io](https://n9e.github.io/)
-- Share your best practices and insights on using Nightingale => [User Story](https://github.com/didi/nightingale/issues/897)
-- Join our community events => [Nightingale wechat group](https://s3-gz01.didistatic.com/n9e-pub/image/n9e-wx.png)
-- Submit code to make Nightingale better =>[github PR](https://github.com/didi/nightingale/pulls)
+<img src="doc/img/install-vm.png" width="480">
 
-## TODO
-- [x] deploy nightingale in docker
-- [x] export /metrics endpoint
-- [x] notify.py support feishu
-- [ ] notify.py support sms
-- [ ] notify.py support voice
-- [x] support remote write api
-- [ ] support pushgateway api
+如果单机版本的时序数据库（比如 Prometheus） 性能有瓶颈或容灾较差，我们推荐使用 [VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics)，VictoriaMetrics 架构较为简单，性能优异，易于部署和运维，架构图如上。VictoriaMetrics 更详尽的文档，还请参考其[官网](https://victoriametrics.com/)。
+
+
+## Community
+
+开源项目要更有生命力，离不开开放的治理架构和源源不断的开发者和用户共同参与，我们致力于建立开放、中立的开源治理架构，吸纳更多来自企业、高校等各方面对云原生监控感兴趣、有热情的开发者，一起打造有活力的夜莺开源社区。关于《夜莺开源项目和社区治理架构（草案）》，请查阅 [COMMUNITY GOVERNANCE](./doc/community-governance.md).
+
+**我们欢迎您以各种方式参与到夜莺开源项目和开源社区中来，工作包括不限于**：
+- 补充和完善文档 => [n9e.github.io](https://n9e.github.io/)
+- 分享您在使用夜莺监控过程中的最佳实践和经验心得 => [文章分享](https://n9e.github.io/docs/prologue/share/)
+- 提交产品建议 =》 [github issue](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Ffeature&template=enhancement.md)
+- 提交代码，让夜莺监控更快、更稳、更好用 => [github pull request](https://github.com/didi/nightingale/pulls)
+
+**尊重、认可和记录每一位贡献者的工作**是夜莺开源社区的第一指导原则，我们提倡**高效的提问**，这既是对开发者时间的尊重，也是对整个社区知识沉淀的贡献：
+- 提问之前请先查阅 [FAQ](https://www.gitlink.org.cn/ccfos/nightingale/wiki/faq) 
+- 我们使用[GitHub Discussions](https://github.com/ccfos/nightingale/discussions)作为交流论坛，有问题可以到这里搜索、提问
+- 我们也推荐你加入微信群，和其他夜莺用户交流经验 (请先加好友：[UlricGO](https://www.gitlink.org.cn/UlricQin/gist/tree/master/self.jpeg) 备注：夜莺加群+姓名+公司)
+
+
+## Who is using
+
+您可以通过在 **[Who is Using Nightingale](https://github.com/ccfos/nightingale/issues/897)** 登记您的使用情况，分享您的使用经验。
+
+## Stargazers
+[![Stargazers over time](https://starchart.cc/ccfos/nightingale.svg)](https://starchart.cc/ccfos/nightingale)
+
+## Contributors
+<a href="https://github.com/ccfos/nightingale/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=ccfos/nightingale" />
+</a>
 
 ## License
-Nightingale with [Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE) open source license.
+[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)
+
+## Contact Us
+推荐您关注夜莺监控公众号，及时获取相关产品和社区动态：
+
+<img src="doc/img/n9e-vx-new.png" width="120">

README_EN.md

@@ -0,0 +1,68 @@
+<img src="doc/img/ccf-n9e.png" width="240">
+
+ Nightingale is an enterprise-level cloud-native monitoring system, which can be used as drop-in replacement of Prometheus for alerting and management.   
+
+[English](./README_EN.md) | [中文](./README.md)
+
+## Introduction
+Nightingale is an cloud-native monitoring system by All-In-On design, support enterprise-class functional features with an out-of-the-box experience. We recommend upgrading your `Prometheus` + `AlertManager` + `Grafana` combo solution to Nightingale.
+
+- **Multiple prometheus data sources management**: manage all alerts and dashboards in one centralized visually view;
+- **Out-of-the-box alert rule**: built-in multiple alert rules, reuse alert rules template by one-click import with detailed explanation of metrics;
+- **Multiple modes for visualizing data**: out-of-the-box dashboards, instance customize views, expression browser and Grafana integration;
+- **Multiple collection clients**: support using Promethues Exporter、Telegraf、Datadog Agent to collecting metrics;
+- **Integration of multiple storage**: support Prometheus, M3DB, VictoriaMetrics, Influxdb, TDEngine as storage solutions, and original support for PromQL;
+- **Fault self-healing**: support the ability to self-heal from failures by configuring webhook;
+
+#### If you are using Prometheus and have one or more of the following requirement scenarios, it is recommended that you upgrade to Nightingale:
+
+- Multiple systems such as Prometheus, Alertmanager, Grafana, etc. are fragmented and lack a unified view and cannot be used out of the box;
+- The way to manage Prometheus and Alertmanager by modifying configuration files has a big learning curve and is difficult to collaborate;
+- Too much data to scale-up your Prometheus cluster;
+- Multiple Prometheus clusters running in production environments, which faced high management and usage costs;
+
+#### If you are using Zabbix and have the following scenarios, it is recommended that you upgrade to Nightingale:
+
+- Monitoring too much data and wanting a better scalable solution;
+- A high learning curve and a desire for better efficiency of collaborative use in a multi-person, multi-team model;
+- Microservice and cloud-native architectures with variable monitoring data lifecycles and high monitoring data dimension bases, which are not easily adaptable to the Zabbix data model;
+
+
+#### If you are using [open-falcon](https://github.com/open-falcon/falcon-plus), we recommend you to upgrade to Nightingale：
+- For more information about open-falcon and Nightingale, please refer to read [Ten features and trends of cloud-native monitoring](https://mp.weixin.qq.com/s?__biz=MzkzNjI5OTM5Nw==&mid=2247483738&idx=1&sn=e8bdbb974a2cd003c1abcc2b5405dd18&chksm=c2a19fb0f5d616a63185cd79277a79a6b80118ef2185890d0683d2bb20451bd9303c78d083c5#rd)。
+
+## Quickstart
+- [n9e.github.io/quickstart](https://n9e.github.io/docs/install/compose/)
+
+## Documentation
+- [n9e.github.io](https://n9e.github.io/)
+
+## Example of use
+
+<img src="doc/img/intro.gif" width="680">
+
+## System Architecture
+#### A typical Nightingale deployment architecture:
+<img src="doc/img/arch-system.png" width="680">
+
+#### Typical deployment architecture using VictoriaMetrics as storage:
+<img src="doc/img/install-vm.png" width="680">
+
+## Contact us and feedback questions
+- We recommend that you use [github issue](https://github.com/didi/nightingale/issues) as the preferred channel for issue feedback and requirement submission;
+- You can join our WeChat group
+
+<img src="doc/img/n9e-vx-new.png" width="180">
+
+
+## Contributing
+We welcome your participation in the Nightingale open source project and open source community in a variety of ways:
+- Feedback on problems and bugs  => [github issue](https://github.com/didi/nightingale/issues)
+- Additional and improved documentation => [n9e.github.io](https://n9e.github.io/)
+- Share your best practices and insights on using Nightingale => [User Story](https://github.com/didi/nightingale/issues/897)
+- Join our community events => [Nightingale wechat group](https://s3-gz01.didistatic.com/n9e-pub/image/n9e-wx.png)
+- Submit code to make Nightingale better =>[github PR](https://github.com/didi/nightingale/pulls)
+
+
+## License
+Nightingale with [Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE) open source license.

README_ZH.md

@@ -1,89 +0,0 @@
-<img src="doc/img/ccf-n9e.png" width="240">
-
-# Nightingale
-[English](./README.md) | [中文](./README_ZH.md)
-
-## 介绍
-
-> Nightingale is an enterprise-level cloud-native monitoring system, which can be used as drop-in replacement of Prometheus for alerting and management.
->
->夜莺是一款开源的云原生监控系统，采用 All-In-One 的设计，提供企业级的功能特性，开箱即用的产品体验。推荐升级您的 `Prometheus` + `AlertManager` + `Grafana` 组合方案到夜莺。
-
-- 内置丰富的Dashboard、好用实用的告警管理、自定义视图、故障自愈；
-- Dashboard和告警策略支持一键导入，详细的指标分类和解释；
-- 支持多 Prometheus 数据源管理，以一个集中的视图来管理所有的告警和dashboard；
-- 支持 Prometheus、M3DB、VictoriaMetrics、Influxdb、TDEngine 等多种时序库作为存储方案；
-- 原生支持 PromQL；
-- 支持 Exporter 作为数据采集方案；
-- 支持 Telegraf 作为监控数据采集方案；
-- 支持对接 Grafana 作为补充可视化方案；
-
-
-#### 如果您在使用 Prometheus 过程中，有以下的一个或者多个需求场景，推荐您升级到夜莺：
-
-- Prometheus、Alertmanager、Grafana 等多个系统较为割裂，缺乏统一视图，无法开箱即用;
-- 通过修改配置文件来管理 Prometheus、Alertmanager 的方式，学习曲线大，协同有难度;
-- 数据量过大而无法扩展您的 Prometheus 集群；
-- 生产环境运行多套 Prometheus 集群，面临管理和使用成本高的问题；
-
-#### 如果您在使用Zabbix，有以下的场景，推荐您升级到夜莺：
-
-- 监控的数据量太大，希望有更好的扩展解决方案；
-- 学习曲线高，多人多团队模式下，希望有更好的协同使用效率；
-- 微服务和云原生架构下，监控数据的生命周期多变、监控数据维度基数高，Zabbix数据模型不易适配；
-
-
-#### 如果您在使用[open-falcon](https://github.com/open-falcon/falcon-plus)，我们更推荐您升级到夜莺：
-- 关于open-falcon和夜莺的详细介绍，请参考阅读[云原生监控的十个特点和趋势](https://mp.weixin.qq.com/s?__biz=MzkzNjI5OTM5Nw==&mid=2247483738&idx=1&sn=e8bdbb974a2cd003c1abcc2b5405dd18&chksm=c2a19fb0f5d616a63185cd79277a79a6b80118ef2185890d0683d2bb20451bd9303c78d083c5#rd)。
-
-## 快速安装部署
-- [n9e.github.io/quickstart](https://n9e.github.io/quickstart/)
-
-## 详细文档
-- [n9e.github.io](https://n9e.github.io/)
-
-## 产品演示
-#### 您可以直接导入并生成 MySQL 相关的告警策略：
-<img src="doc/img/mysql-alerts.png" width="680">
-
-#### 您可以直接导入并生成主机相关的 dashboard：
-<img src="doc/img/n9e-node-dashboard.png" width="680">
-
-#### 您也可以在夜莺中方便的查看所有活跃的告警以及历史告警：
-<img src="https://n9e.github.io/intro/alert-events.png" width="680">
-
-## 系统架构
-#### 一个典型的 Nightingale 部署架构:
-<img src="https://n9e.github.io/intro/arch-system.png" width="680">
-
-#### 使用 VictoriaMetrics 作为时序数据库的典型部署架构:
-<img src="https://n9e.github.io/fc-monitoring-vm.png" width="680">
-
-
-## 联系我们和反馈问题
-- 我们推荐您优先使用[github issue](https://github.com/didi/nightingale/issues)作为首选问题反馈和需求提交的通道；
-- 您可以加入我们的微信群组——[Nightingale 微信群组](https://s3-gz01.didistatic.com/n9e-pub/image/n9e-wx.png)；
-- 当然，推荐您关注夜莺监控公众号，及时获取相关产品动态 
-
-<img src="https://n9e.github.io/cloudmon.png" width="180">
-
-
-## 参与到夜莺开源项目和社区
-我们欢迎您以各种方式参与到夜莺开源项目和开源社区中来，工作包括不限于：
-- 反馈使用中遇到的问题和Bug => [github issue](https://github.com/didi/nightingale/issues)
-- 补充和完善文档 => [n9e.github.io](https://n9e.github.io/)
-- 分享您在使用夜莺监控过程中的最佳实践和经验心得 => [夜莺User Story](https://github.com/didi/nightingale/issues/897)
-- 参与我们的社区活动 => [Nightingale 微信群组](https://s3-gz01.didistatic.com/n9e-pub/image/n9e-wx.png)
-- 提交代码，让夜莺监控更快、更稳、更好用 =>[github PR](https://github.com/didi/nightingale/pulls)
-
-## TODO
-- [x] deploy nightingale in docker
-- [x] export /metrics endpoint
-- [x] notify.py support feishu
-- [ ] notify.py support sms
-- [ ] notify.py support voice
-- [x] support remote write api
-- [ ] support pushgateway api
-
-## License
-夜莺监控，采用[Apache License V2.0](https://github.com/didi/nightingale/blob/main/LICENSE)开源许可证。

doc/active-contributors.md

@@ -0,0 +1,7 @@
+## Active Contributors
+
+- [xiaoziv](https://github.com/xiaoziv)
+- [tanxiao1990](https://github.com/tanxiao1990)
+- [bbaobelief](https://github.com/bbaobelief)
+- [freedomkk-qfeng](https://github.com/freedomkk-qfeng)
+- [lsy1990](https://github.com/lsy1990)

doc/committers.md

@@ -0,0 +1,5 @@
+## Committers
+
+- [YeningQin](https://github.com/710leo)
+- [FeiKong](https://github.com/kongfei605)
+- [XiaqingDai](https://github.com/jsers)

doc/community-governance.md

@@ -0,0 +1,80 @@
+[夜莺监控](https://github.com/ccfos/nightingale "夜莺监控")是一款开源云原生监控系统，由滴滴设计开发，2020 年 3 月份开源之后，凭借其优秀的产品设计、灵活性架构和明确清晰的定位，夜莺监控快速发展为国内最活跃的企业级云原生监控方案。[截止当前](具体指2022年8月 "截止当前")，在 [Github](https://github.com/ccfos/nightingale "Github") 上已经迭代发布了 **70** 多个版本，获得了 **5K** 多个 Star，**80** 多位代码贡献者。快速的迭代，也让夜莺监控的用户群越来越大，涉及各行各业。
+
+更进一步，夜莺监控于 2022 年 5 月 11 日，正式捐赠予中国计算机学会开源发展委员会 [CCF ODC](https://www.ccf.org.cn/kyfzwyh/ "CCF ODC")，为 CCF ODC 成立后接受捐赠的第一个开源项目。
+
+开源项目要更有生命力，离不开开放的治理架构和源源不断的开发者共同参与。夜莺监控项目加入 CCF 开源大家庭后，能在计算机学会的支持和带动下，进一步结合云原生、可观测、国产化等多个技术发展的需求，建立开放、中立的开源治理架构，打造更专业、有活力的开发者社区。
+
+**今天，我们郑重发布夜莺监控开源社区治理架构，并公示相关的任命和社区荣誉，期待开源的道路上，一起同行。**
+
+# 夜莺监控开源社区架构
+
+### User|用户
+
+> 欢迎任何个人、公司以及组织，使用夜莺监控，并积极的反馈 bug、提交功能需求、以及相互帮助，我们推荐使用 [Github Issue](https://github.com/ccfos/nightingale/issues "Github Issue") 来跟踪 bug 和管理需求。
+
+社区用户，可以通过在 **[Who is Using Nightingale](https://github.com/ccfos/nightingale/issues/897 "Who is Using Nightingale")** 登记您的使用情况，并分享您使用夜莺监控的经验，将会自动进入 **[END USERS](https://github.com/ccfos/nightingale/blob/main/doc/end-users.md "END USERS")** 文件列表，并获得社区的 **VIP Support**。
+
+### Contributor|贡献者
+
+> 欢迎每一位用户，包括但不限于以下方式参与到夜莺开源社区并做出贡献：
+
+1. 在 [Github Issue](https://github.com/ccfos/nightingale/issues "Github Issue") 中积极参与讨论，参与社区活动；
+1. 提交代码补丁；
+1. 翻译、修订、补充和完善[文档](https://n9e.github.io "文档")；
+1. 分享夜莺监控的使用经验，积极布道；
+1. 提交建议 / 批评；
+
+年度累计向 [CCFOS/NIGHTINGALE](https://github.com/ccfos/nightingale "CCFOS/NIGHTINGALE") 提交 **5** 个PR（被合并），或者因为其他贡献被**项目管委会**一致认可，将会自动进入到 **[ACTIVE CONTRIBUTORS](https://github.com/ccfos/nightingale/blob/main/doc/active-contributors.md "ACTIVE CONTRIBUTORS")** 列表，并获得夜莺开源社区颁发的证书，享有夜莺开源社区一定的权益和福利。
+
+所有向 [CCFOS/NIGHTINGALE](https://github.com/ccfos/nightingale "CCFOS/NIGHTINGALE") 提交过PR（被合并），或者做出过重要贡献的 Contributor，都会被永久记载于 [CONTRIBUTORS](https://github.com/ccfos/nightingale/blob/main/doc/contributors.md "CONTRIBUTORS") 列表。
+
+### Committer|提交者
+
+> Committer 是指拥有 [CCFOS/NIGHTINGALE](https://github.com/ccfos/nightingale "CCFOS/NIGHTINGALE") 代码仓库写操作权限的贡献者。原则上 Committer 能够自主决策某个代码补丁是否可以合入到夜莺代码仓库，但是项目管委会拥有最终的决策权。
+
+Committer 承担以下一个或多个职责：
+- 积极回应 Issues；
+- Review PRs；
+- 参加开发者例行会议，积极讨论项目规划和技术方案；
+- 代表夜莺开源社区出席相关技术会议并做演讲；
+
+Committer 记录并公示于 **[COMMITTERS](https://github.com/ccfos/nightingale/blob/main/doc/committers.md "COMMITTERS")** 列表，并获得夜莺开源社区颁发的证书，以及享有夜莺开源社区的各种权益和福利。
+
+
+### PMC|项目管委会
+
+> PMC（项目管委会）作为一个实体，来管理和领导夜莺项目，为整个项目的发展全权负责。项目管委会相关内容记录并公示于文件[PMC](https://github.com/ccfos/nightingale/blob/main/doc/pmc.md "PMC").
+
+- 项目管委会成员(PMC Member)，从 Contributor 或者 Committer 中选举产生，他们拥有 [CCFOS/NIGHTINGALE](https://github.com/ccfos/nightingale "CCFOS/NIGHTINGALE") 代码仓库的写操作权限，拥有 Nightingale 社区相关事务的投票权、以及提名 Committer 候选人的权利。
+- 项目管委会主席(PMC Chair)，从项目管委会成员中投票产生。管委会主席是 **[CCF ODC](https://www.ccf.org.cn/kyfzwyh/ "CCF ODC")** 和项目管委会之间的沟通桥梁，履行特定的项目管理职责。
+
+## Communication|沟通机制
+1. 我们推荐使用邮件列表来反馈建议（待发布）；
+2. 我们推荐使用 [Github Issue](https://github.com/ccfos/nightingale/issues "Github Issue") 跟踪 bug 和管理需求；
+3. 我们推荐使用 [Github Milestone](https://github.com/ccfos/nightingale/milestones "Github Milestone") 来管理项目进度和规划；
+4. 我们推荐使用腾讯会议来定期召开项目例会（会议 ID 待发布）；
+
+## Documentation|文档
+1. 我们推荐使用 [Github Pages](https://n9e.github.io "Github Pages") 来沉淀文档；
+2. 我们推荐使用 [Gitlink Wiki](https://www.gitlink.org.cn/ccfos/nightingale/wiki/faq "Gitlink Wiki") 来沉淀 FAQ；
+
+
+## Operation|运营机制
+
+1. 我们定期组织用户、贡献者、项目管委会成员之间的沟通会议，讨论项目开发的目标、方案、进度，以及讨论相关需求的合理性、优先级等议题；
+2. 我们定期组织 meetup （线上&线下），创造良好的用户交流分享环境，并沉淀相关内容到文档站点；
+3. 我们定期组织夜莺开发者大会，分享 [best user story](https://n9e.github.io/docs/prologue/share/ "best user story")、同步年度开发目标和计划、讨论新技术方向等；
+
+## Philosophy|社区指导原则
+
+>尊重、认可和记录每一位贡献者的工作。
+
+## 关于提问的原则
+
+按照**尊重、认可、记录每一位贡献者的工作**原则，我们提倡**高效的提问**，这既是对开发者时间的尊重，也是对整个社区的知识沉淀的贡献：
+
+1. 提问之前请先查阅 [FAQ](https://www.gitlink.org.cn/ccfos/nightingale/wiki/faq "FAQ") ；
+2. 提问之前请先搜索 [Github Issues](https://github.com/ccfos/nightingale/issues "Github Issue")；
+3. 我们优先推荐通过提交 [Github Issue](https://github.com/ccfos/nightingale/issues "Github Issue") 来提问，如果[有问题点击这里](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Fbug&template=bug_report.yml "有问题点击这里") | [有需求建议点击这里](https://github.com/ccfos/nightingale/issues/new?assignees=&labels=kind%2Ffeature&template=enhancement.md "有需求建议点击这里")；
+
+最后，我们推荐你加入微信群，针对相关开放式问题，相互交流咨询 (请先加好友：[UlricGO](https://www.gitlink.org.cn/UlricQin/gist/tree/master/self.jpeg "UlricGO") 备注：夜莺加群+姓名+公司，交流群里会有开发者团队和专业、热心的群友回答问题)。

doc/contributors.md

@@ -0,0 +1,5 @@
+## Contributors
+
+<a href="https://github.com/ccfos/nightingale/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=ccfos/nightingale" />
+</a>

doc/end-users.md

@@ -0,0 +1,5 @@
+## End Users
+
+- [中移动](https://github.com/ccfos/nightingale/issues/897#issuecomment-1086573166)
+- [inke](https://github.com/ccfos/nightingale/issues/897#issuecomment-1099840636)
+- [方正证券](https://github.com/ccfos/nightingale/issues/897#issuecomment-1110492461)

doc/jvm-dash.json

@@ -1,211 +0,0 @@
-[
-  {
-    "name": "JVM监控大盘",
-    "tags": "",
-    "configs": "{\"var\":[{\"name\":\"java_app\",\"definition\":\"label_values(jvm_info, label)\",\"selected\":[],\"multi\":true,\"allOption\":true}]}",
-    "chart_groups": [
-      {
-        "name": "JVM统计信息",
-        "weight": 0,
-        "charts": [
-          {
-            "configs": "{\"name\":\"jvm版本信息\",\"QL\":[{\"PromQL\":\"avg(jvm_info{java_app=~\\\"$java_app\\\"}) without (runtime,vendor)\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"Java进程启动时间\",\"link\":\"\",\"QL\":[{\"PromQL\":\"(time() - process_start_time_seconds{java_app=~\\\"$java_app\\\"})/3600\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":\"humantime\"},\"version\":1,\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
-            "weight": 0
-          }
-        ]
-      },
-      {
-        "name": "JVM内存使用",
-        "weight": 1,
-        "charts": [
-          {
-            "configs": "{\"name\":\"nonheap 非堆区\",\"QL\":[{\"PromQL\":\"jvm_memory_bytes_used{java_app=~\\\"$java_app\\\",area=\\\"nonheap\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"0\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"heap堆区\",\"QL\":[{\"PromQL\":\"jvm_memory_bytes_used{java_app=~\\\"$java_app\\\",area=\\\"heap\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"1\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"提交给 Java虚拟机使用的内存量 heap 堆区\",\"QL\":[{\"PromQL\":\"jvm_memory_bytes_committed{java_app=~\\\"$java_app\\\",area=\\\"heap\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"提交给 Java虚拟机使用的内存量 nonheap 非堆区\",\"QL\":[{\"PromQL\":\"jvm_memory_bytes_committed{java_app=~\\\"$java_app\\\",area=\\\"nonheap\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"jvm最大内存\",\"QL\":[{\"PromQL\":\"jvm_memory_bytes_max{java_app=~\\\"$java_app\\\",area=\\\"heap\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":2,\"i\":\"4\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"jvm初始化内存\",\"QL\":[{\"PromQL\":\"jvm_memory_bytes_init{java_app=~\\\"$java_app\\\",area=\\\"heap\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":2,\"i\":\"5\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"jvm内存使用百分比% heap堆区\",\"QL\":[{\"PromQL\":\"100 * jvm_memory_bytes_used{java_app=~\\\"$java_app\\\",area=\\\"heap\\\"}/jvm_memory_bytes_max{java_app=~\\\"$java_app\\\",area=\\\"heap\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":2,\"i\":\"6\"}}",
-            "weight": 0
-          }
-        ]
-      },
-      {
-        "name": "JVM内存池",
-        "weight": 2,
-        "charts": [
-          {
-            "configs": "{\"name\":\"jvm内存池分pool展示\",\"QL\":[{\"PromQL\":\"jvm_memory_pool_bytes_max{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"JVM 缓冲池使用缓存大小\",\"QL\":[{\"PromQL\":\"jvm_buffer_pool_used_bytes{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":2,\"i\":\"1\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"JVM 缓冲池的字节容量\",\"QL\":[{\"PromQL\":\"jvm_buffer_pool_capacity_bytes{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":2,\"i\":\"2\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"JVM 缓冲池使用的字节大小\",\"QL\":[{\"PromQL\":\"jvm_buffer_pool_used_bytes{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":2,\"i\":\"3\"}}",
-            "weight": 0
-          }
-        ]
-      },
-      {
-        "name": "jvm gc情况",
-        "weight": 3,
-        "charts": [
-          {
-            "configs": "{\"name\":\"新生代gc耗时 1分钟\",\"QL\":[{\"PromQL\":\"increase(jvm_gc_collection_seconds_sum{java_app=~\\\"$java_app\\\",gc=\\\"G1 Young Generation\\\" }[1m])\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"老生代gc耗时 1分钟\",\"QL\":[{\"PromQL\":\"increase(jvm_gc_collection_seconds_sum{java_app=~\\\"$java_app\\\",gc=\\\"G1 Old Generation\\\" }[1m])\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"新生代gc次数 1分钟\",\"QL\":[{\"PromQL\":\"increase(jvm_gc_collection_seconds_count{java_app=~\\\"$java_app\\\",gc=\\\"G1 Young Generation\\\" }[1m])\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"老生代gc次数 1分钟\",\"QL\":[{\"PromQL\":\"increase(jvm_gc_collection_seconds_count{java_app=~\\\"$java_app\\\",gc=\\\"G1 Old Generation\\\" }[1m])\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"新生代平均gc耗时 秒\",\"QL\":[{\"PromQL\":\"jvm_gc_collection_seconds_sum{java_app=~\\\"$java_app\\\",gc=\\\"G1 Young Generation\\\" }/jvm_gc_collection_seconds_count{java_app=~\\\"$java_app\\\",gc=\\\"G1 Young Generation\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":2,\"i\":\"4\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"老生代平均gc耗时\",\"QL\":[{\"PromQL\":\"jvm_gc_collection_seconds_sum{java_app=~\\\"$java_app\\\",gc=\\\"G1 Old Generation\\\"}/jvm_gc_collection_seconds_count{java_app=~\\\"$java_app\\\",gc=\\\"G1 Old Generation\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":2,\"i\":\"5\"}}",
-            "weight": 0
-          }
-        ]
-      },
-      {
-        "name": "jvm线程情况",
-        "weight": 4,
-        "charts": [
-          {
-            "configs": "{\"name\":\"当前线程数\",\"QL\":[{\"PromQL\":\"jvm_threads_current{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"守护线程数\",\"QL\":[{\"PromQL\":\"jvm_threads_daemon{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"死锁线程数\",\"QL\":[{\"PromQL\":\"jvm_threads_deadlocked{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"活动线程峰值\",\"QL\":[{\"PromQL\":\"jvm_threads_peak{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"自JVM启动后，启动的线程总量（包括daemon,non-daemon和终止了的）\",\"QL\":[{\"PromQL\":\"jvm_threads_started_total{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":2,\"i\":\"4\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"当前TERMINATED线程个数\",\"QL\":[{\"PromQL\":\"jvm_threads_state{java_app=~\\\"$java_app\\\",state=\\\"TERMINATED\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":2,\"i\":\"5\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"当前RUNNABLE线程个数\",\"QL\":[{\"PromQL\":\"jvm_threads_state{java_app=~\\\"$java_app\\\",state=\\\"RUNNABLE\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":2,\"i\":\"6\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"当前NEW线程个数\",\"QL\":[{\"PromQL\":\"jvm_threads_state{java_app=~\\\"$java_app\\\",state=\\\"NEW\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":2,\"i\":\"7\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"当前TIMED_WAITING线程个数\",\"QL\":[{\"PromQL\":\"jvm_threads_state{java_app=~\\\"$java_app\\\",state=\\\"TIMED_WAITING\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":4,\"i\":\"8\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"当前BLOCKED线程个数\",\"QL\":[{\"PromQL\":\"jvm_threads_state{java_app=~\\\"$java_app\\\",state=\\\"BLOCKED\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":4,\"i\":\"9\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"当前WAITING线程个数\",\"QL\":[{\"PromQL\":\"jvm_threads_state{java_app=~\\\"$java_app\\\",state=\\\"WAITING\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":4,\"i\":\"10\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"当前线程状态汇总\",\"QL\":[{\"PromQL\":\"jvm_threads_state{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":4,\"i\":\"11\"}}",
-            "weight": 0
-          }
-        ]
-      },
-      {
-        "name": "加载类情况",
-        "weight": 5,
-        "charts": [
-          {
-            "configs": "{\"name\":\"jvm 当前加载的类个数\",\"QL\":[{\"PromQL\":\"jvm_classes_loaded{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"jvm启动以来加载的类总个数\",\"QL\":[{\"PromQL\":\"jvm_classes_loaded_total{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"jvm启动以来卸载的类总个数\",\"QL\":[{\"PromQL\":\"jvm_classes_unloaded_total{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
-            "weight": 0
-          }
-        ]
-      },
-      {
-        "name": "机器指标(配置了java.lang才有)",
-        "weight": 6,
-        "charts": [
-          {
-            "configs": "{\"name\":\"java进程打开fd数\",\"QL\":[{\"PromQL\":\"os_open_file_descriptor_count{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"机器总内存\",\"QL\":[{\"PromQL\":\"os_total_memory_size{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"机器可用内存\",\"QL\":[{\"PromQL\":\"os_free_memory_size{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"机器近期cpu使用率%\",\"link\":\"https://docs.oracle.com/javase/7/docs/jre/api/management/extension/com/sun/management/OperatingSystemMXBean.html#getSystemCpuLoad()\",\"QL\":[{\"PromQL\":\"100 * os_system_cpu_load{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"java进程cpu使用\",\"link\":\"https://docs.oracle.com/javase/7/docs/jre/api/management/extension/com/sun/management/OperatingSystemMXBean.html#getProcessCpuLoad()\",\"QL\":[{\"PromQL\":\"os_process_cpu_load{java_app=~\\\"$java_app\\\"}\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":2,\"i\":\"4\"}}",
-            "weight": 0
-          },
-          {
-            "configs": "{\"name\":\"jvm cpu百分比\",\"QL\":[{\"PromQL\":\"100 *(os_process_cpu_load{java_app=~\\\"$java_app\\\"}/os_system_cpu_load{java_app=~\\\"$java_app\\\"})\"}],\"legend\":false,\"highLevelConfig\":{\"shared\":true,\"sharedSortDirection\":\"desc\",\"precision\":\"short\",\"formatUnit\":1000},\"version\":1,\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":2,\"i\":\"5\"}}",
-            "weight": 0
-          }
-        ]
-      }
-    ]
-  }
-]

doc/pmc.md

@@ -0,0 +1,7 @@
+### PMC Chair
+- [laiwei](https://github.com/laiwei)
+
+### PMC Co-Chair
+- [UlricQin](https://github.com/UlricQin)
+
+### PMC Member

doc/server-dash.json

@@ -0,0 +1,234 @@
+{
+    "name": "夜莺大盘",
+    "tags": "",
+    "configs": {
+        "var": [],
+        "panels": [
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "rate(n9e_server_samples_received_total[1m])"
+                    }
+                ],
+                "name": "每秒接收的数据点个数",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 0,
+                    "i": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4",
+                    "isResizable": true
+                },
+                "id": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "rate(n9e_server_alerts_total[10m])"
+                    }
+                ],
+                "name": "每秒产生的告警事件个数",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 0,
+                    "i": "47fc6252-9cc8-4b53-8e27-0c5c59a47269",
+                    "isResizable": true
+                },
+                "id": "f70dcb8b-b58b-4ef9-9e48-f230d9e17140"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_alert_queue_size"
+                    }
+                ],
+                "name": "告警事件内存队列长度",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 4,
+                    "i": "ad1af16c-de0c-45f4-8875-cea4e85d51d0",
+                    "isResizable": true
+                },
+                "id": "caf23e58-d907-42b0-9ed6-722c8c6f3c5f"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_http_request_duration_seconds_sum/n9e_server_http_request_duration_seconds_count"
+                    }
+                ],
+                "name": "数据接收接口平均响应时间（单位：秒）",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "noraml"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 4,
+                    "i": "64c3abc2-404c-4462-a82f-c109a21dac91",
+                    "isResizable": true
+                },
+                "id": "6b8d2db1-efca-4b9e-b429-57a9d2272bc5"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_sample_queue_size"
+                    }
+                ],
+                "name": "内存数据队列长度",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 8,
+                    "i": "1c7da942-58c2-40dc-b42f-983e4a35b89b",
+                    "isResizable": true
+                },
+                "id": "bd41677d-40d3-482e-bb6e-fbd25df46d87"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "avg(n9e_server_forward_duration_seconds_sum/n9e_server_forward_duration_seconds_count)"
+                    }
+                ],
+                "name": "数据发往TSDB平均耗时（单位：秒）",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "decimals": 8
+                    },
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "noraml"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 8,
+                    "i": "eed94a0b-954f-48ac-82e5-a2eada1c8a3d",
+                    "isResizable": true
+                },
+                "id": "c8642e72-f384-46a5-8410-1e6be2953c3c"
+            }
+        ],
+        "version": "2.0.0"
+    }
+}

docker/Dockerfile

@@ -1,4 +1,5 @@
-FROM python:2
+FROM python:2.7.8-slim
+#FROM python:2
 #FROM ubuntu:21.04
 
 WORKDIR /app

docker/Dockerfile.goreleaser

@@ -0,0 +1,14 @@
+FROM --platform=$BUILDPLATFORM python:2.7.8-slim
+
+
+WORKDIR /app
+ADD n9e /app
+ADD http://download.flashcat.cloud/wait /wait
+RUN mkdir -p /app/pub && chmod +x /wait
+ADD pub /app/pub/
+RUN chmod +x n9e
+
+EXPOSE 19000
+EXPOSE 18000
+
+CMD ["/app/n9e", "-h"]

docker/build.sh

@@ -1,5 +1,4 @@
 #!/bin/sh
-
 if [ $# -ne 1 ]; then
 	echo "$0 <tag>"
 	exit 0

docker/categraf/conf/config.toml

@@ -0,0 +1,51 @@
+[global]
+# whether print configs
+print_configs = false
+
+# add label(agent_hostname) to series
+# "" -> auto detect hostname
+# "xx" -> use specified string xx
+# "$hostname" -> auto detect hostname
+# "$ip" -> auto detect ip
+# "$hostname-$ip" -> auto detect hostname and ip to replace the vars
+hostname = "$HOSTNAME"
+
+# will not add label(agent_hostname) if true
+omit_hostname = false
+
+# s | ms
+precision = "ms"
+
+# global collect interval
+interval = 15
+
+[global.labels]
+source="categraf"
+# region = "shanghai"
+# env = "localhost"
+
+[writer_opt]
+# default: 2000
+batch = 2000
+# channel(as queue) size
+chan_size = 10000
+
+[[writers]]
+url = "http://nserver:19000/prometheus/v1/write"
+
+# Basic auth username
+basic_auth_user = ""
+
+# Basic auth password
+basic_auth_pass = ""
+
+# timeout settings, unit: ms
+timeout = 5000
+dial_timeout = 2500
+max_idle_conns_per_host = 100
+
+[http]
+enable = false
+address = ":9100"
+print_access = false
+run_mode = "release"

docker/categraf/conf/input.cpu/cpu.toml

@@ -0,0 +1,5 @@
+# # collect interval
+# interval = 15
+
+# # whether collect per cpu
+# collect_per_cpu = false

docker/categraf/conf/input.disk/disk.toml

@@ -0,0 +1,11 @@
+# # collect interval
+# interval = 15
+
+# # By default stats will be gathered for all mount points.
+# # Set mount_points will restrict the stats to only the specified mount points.
+# mount_points = ["/"]
+
+# Ignore mount points by filesystem type.
+ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
+
+ignore_mount_points = ["/boot"]

docker/categraf/conf/input.diskio/diskio.toml

@@ -0,0 +1,6 @@
+# # collect interval
+# interval = 15
+
+# # By default, categraf will gather stats for all devices including disk partitions.
+# # Setting devices will restrict the stats to the specified devices.
+# devices = ["sda", "sdb", "vd*"]

docker/categraf/conf/input.docker/docker.toml

@@ -0,0 +1,63 @@
+# # collect interval
+# interval = 15
+
+[[instances]]
+# # append some labels for series
+# labels = { region="cloud", product="n9e" }
+
+# # interval = global.interval * interval_times
+# interval_times = 1
+
+## Docker Endpoint
+##   To use TCP, set endpoint = "tcp://[ip]:[port]"
+##   To use environment variables (ie, docker-machine), set endpoint = "ENV"
+endpoint = "unix:///var/run/docker.sock"
+
+## Set to true to collect Swarm metrics(desired_replicas, running_replicas)
+gather_services = false
+gather_extend_memstats = false
+
+container_id_label_enable = true
+container_id_label_short_style = true
+
+## Containers to include and exclude. Globs accepted.
+## Note that an empty array for both will include all containers
+container_name_include = []
+container_name_exclude = []
+
+## Container states to include and exclude. Globs accepted.
+## When empty only containers in the "running" state will be captured.
+## example: container_state_include = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
+## example: container_state_exclude = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
+# container_state_include = []
+# container_state_exclude = []
+
+## Timeout for docker list, info, and stats commands
+timeout = "5s"
+
+## Specifies for which classes a per-device metric should be issued
+## Possible values are 'cpu' (cpu0, cpu1, ...), 'blkio' (8:0, 8:1, ...) and 'network' (eth0, eth1, ...)
+## Please note that this setting has no effect if 'perdevice' is set to 'true'
+perdevice_include = []
+
+## Specifies for which classes a total metric should be issued. Total is an aggregated of the 'perdevice' values.
+## Possible values are 'cpu', 'blkio' and 'network'
+## Total 'cpu' is reported directly by Docker daemon, and 'network' and 'blkio' totals are aggregated by this plugin.
+## Please note that this setting has no effect if 'total' is set to 'false'
+total_include = ["cpu", "blkio", "network"]
+
+## Which environment variables should we use as a tag
+##tag_env = ["JAVA_HOME", "HEAP_SIZE"]
+
+## docker labels to include and exclude as tags. Globs accepted.
+## Note that an empty array for both will include all labels as tags
+docker_label_include = []
+docker_label_exclude = ["annotation*", "io.kubernetes*", "*description*", "*maintainer*", "*hash", "*author*"]
+
+## Optional TLS Config
+# use_tls = false
+# tls_ca = "/etc/telegraf/ca.pem"
+# tls_cert = "/etc/telegraf/cert.pem"
+# tls_key = "/etc/telegraf/key.pem"
+## Use TLS but skip chain & host verification
+# insecure_skip_verify = false

docker/categraf/conf/input.kernel/kernel.toml

@@ -0,0 +1,2 @@
+# # collect interval
+# interval = 15

docker/categraf/conf/input.kernel_vmstat/kernel_vmstat.toml

@@ -0,0 +1,124 @@
+# # collect interval
+# interval = 15
+
+# file: /proc/vmstat
+[white_list]
+oom_kill = 1
+nr_free_pages = 0
+nr_alloc_batch = 0
+nr_inactive_anon = 0
+nr_active_anon = 0
+nr_inactive_file = 0
+nr_active_file = 0
+nr_unevictable = 0
+nr_mlock = 0
+nr_anon_pages = 0
+nr_mapped = 0
+nr_file_pages = 0
+nr_dirty = 0
+nr_writeback = 0
+nr_slab_reclaimable = 0
+nr_slab_unreclaimable = 0
+nr_page_table_pages = 0
+nr_kernel_stack = 0
+nr_unstable = 0
+nr_bounce = 0
+nr_vmscan_write = 0
+nr_vmscan_immediate_reclaim = 0
+nr_writeback_temp = 0
+nr_isolated_anon = 0
+nr_isolated_file = 0
+nr_shmem = 0
+nr_dirtied = 0
+nr_written = 0
+numa_hit = 0
+numa_miss = 0
+numa_foreign = 0
+numa_interleave = 0
+numa_local = 0
+numa_other = 0
+workingset_refault = 0
+workingset_activate = 0
+workingset_nodereclaim = 0
+nr_anon_transparent_hugepages = 0
+nr_free_cma = 0
+nr_dirty_threshold = 0
+nr_dirty_background_threshold = 0
+pgpgin = 0
+pgpgout = 0
+pswpin = 0
+pswpout = 0
+pgalloc_dma = 0
+pgalloc_dma32 = 0
+pgalloc_normal = 0
+pgalloc_movable = 0
+pgfree = 0
+pgactivate = 0
+pgdeactivate = 0
+pgfault = 0
+pgmajfault = 0
+pglazyfreed = 0
+pgrefill_dma = 0
+pgrefill_dma32 = 0
+pgrefill_normal = 0
+pgrefill_movable = 0
+pgsteal_kswapd_dma = 0
+pgsteal_kswapd_dma32 = 0
+pgsteal_kswapd_normal = 0
+pgsteal_kswapd_movable = 0
+pgsteal_direct_dma = 0
+pgsteal_direct_dma32 = 0
+pgsteal_direct_normal = 0
+pgsteal_direct_movable = 0
+pgscan_kswapd_dma = 0
+pgscan_kswapd_dma32 = 0
+pgscan_kswapd_normal = 0
+pgscan_kswapd_movable = 0
+pgscan_direct_dma = 0
+pgscan_direct_dma32 = 0
+pgscan_direct_normal = 0
+pgscan_direct_movable = 0
+pgscan_direct_throttle = 0
+zone_reclaim_failed = 0
+pginodesteal = 0
+slabs_scanned = 0
+kswapd_inodesteal = 0
+kswapd_low_wmark_hit_quickly = 0
+kswapd_high_wmark_hit_quickly = 0
+pageoutrun = 0
+allocstall = 0
+pgrotated = 0
+drop_pagecache = 0
+drop_slab = 0
+numa_pte_updates = 0
+numa_huge_pte_updates = 0
+numa_hint_faults = 0
+numa_hint_faults_local = 0
+numa_pages_migrated = 0
+pgmigrate_success = 0
+pgmigrate_fail = 0
+compact_migrate_scanned = 0
+compact_free_scanned = 0
+compact_isolated = 0
+compact_stall = 0
+compact_fail = 0
+compact_success = 0
+htlb_buddy_alloc_success = 0
+htlb_buddy_alloc_fail = 0
+unevictable_pgs_culled = 0
+unevictable_pgs_scanned = 0
+unevictable_pgs_rescued = 0
+unevictable_pgs_mlocked = 0
+unevictable_pgs_munlocked = 0
+unevictable_pgs_cleared = 0
+unevictable_pgs_stranded = 0
+thp_fault_alloc = 0
+thp_fault_fallback = 0
+thp_collapse_alloc = 0
+thp_collapse_alloc_failed = 0
+thp_split = 0
+thp_zero_page_alloc = 0
+thp_zero_page_alloc_failed = 0
+balloon_inflate = 0
+balloon_deflate = 0
+balloon_migrate = 0

docker/categraf/conf/input.linux_sysctl_fs/linux_sysctl_fs.toml

@@ -0,0 +1,2 @@
+# # collect interval
+# interval = 15

docker/categraf/conf/input.mem/mem.toml

@@ -0,0 +1,5 @@
+# # collect interval
+# interval = 15
+
+# # whether collect platform specified metrics
+collect_platform_fields = true

docker/categraf/conf/input.net/net.toml

@@ -0,0 +1,8 @@
+# # collect interval
+# interval = 15
+
+# # whether collect protocol stats on Linux
+# collect_protocol_stats = false
+
+# # setting interfaces will tell categraf to gather these explicit interfaces
+# interfaces = ["eth0"]

docker/categraf/conf/input.netstat/netstat.toml

@@ -0,0 +1,2 @@
+# # collect interval
+# interval = 15

docker/categraf/conf/input.processes/processes.toml

@@ -0,0 +1,8 @@
+# # collect interval
+# interval = 15
+
+# # force use ps command to gather
+# force_ps = false
+
+# # force use /proc to gather
+# force_proc = false

docker/categraf/conf/input.system/system.toml

@@ -0,0 +1,5 @@
+# # collect interval
+# interval = 15
+
+# # whether collect metric: system_n_users
+# collect_user_number = false

docker/categraf/conf/logs.toml

@@ -0,0 +1,35 @@
+[logs]
+## key 占位符
+api_key = "ef4ahfbwzwwtlwfpbertgq1i6mq0ab1q"
+## 是否开启日志采集
+enable = false
+## 接受日志的server地址
+send_to = "127.0.0.1:17878"
+## 发送日志的协议 http/tcp
+send_type = "http"
+## 是否压缩发送
+use_compress = false
+## 是否采用ssl
+send_with_tls = false
+##
+batch_wait = 5
+## 日志offset信息保存目录
+run_path = "/opt/categraf/run"
+## 最多同时采集多少个日志文件
+open_files_limit = 100
+## 定期扫描目录下是否有新增日志
+scan_period = 10
+##
+frame_size = 10
+##
+collect_container_all = true
+  ## 全局的处理规则
+  [[logs.Processing_rules]]
+  ## 单个日志采集配置
+  [[logs.items]]
+  ## file/journald
+  type = "file"
+  ## type=file时 path必填，type=journald时 port必填
+  path = "/opt/tomcat/logs/*.txt"
+  source = "tomcat"
+  service = "my_service"

docker/docker-compose.yaml

@@ -6,6 +6,7 @@ networks:
 
 services:
   mysql:
+    platform: linux/x86_64
     image: "mysql:5.7"
     container_name: mysql
     hostname: mysql
@@ -79,7 +80,7 @@ services:
       sh -c "/wait && /app/ibex server"
 
   nwebapi:
-    image: ulric2019/nightingale:5.8.0
+    image: flashcatcloud/nightingale:latest
     container_name: nwebapi
     hostname: nwebapi
     restart: always
@@ -107,7 +108,7 @@ services:
       sh -c "/wait && /app/n9e webapi"
 
   nserver:
-    image: ulric2019/nightingale:5.8.0
+    image: flashcatcloud/nightingale:latest
     container_name: nserver
     hostname: nserver
     restart: always
@@ -134,19 +135,22 @@ services:
     command: >
       sh -c "/wait && /app/n9e server"
 
-  telegraf:
-    image: "telegraf:1.20.3"
-    container_name: "telegraf"
-    hostname: "telegraf01"
+  categraf:
+    image: "flashcatcloud/categraf:latest"
+    container_name: "categraf"
+    hostname: "categraf01"
     restart: always
     environment:
       TZ: Asia/Shanghai
+      HOST_PROC: /hostfs/proc
+      HOST_SYS: /hostfs/sys
+      HOST_MOUNT_PREFIX: /hostfs
     volumes:
-      - ./telegrafetc/telegraf.conf:/etc/telegraf/telegraf.conf
+      - ./categraf/conf:/etc/categraf/conf
+      - /:/hostfs
+      - /var/run/docker.sock:/var/run/docker.sock
     ports:
-      - "8125:8125/udp"
-      - "8092:8092/udp"
-      - "8094:8094/tcp"
+      - "9100:9100/tcp"
     networks:
       - nightingale
     depends_on:

docker/ibexetc/agentd.conf

@@ -35,4 +35,4 @@ Interval = 1000
 # rpc servers
 Servers = ["ibex:20090"]
 # $ip or $hostname or specified string
-Host = "telegraf01"
+Host = "categraf01"

docker/initsql/a-n9e.sql

@@ -41,10 +41,12 @@ CREATE TABLE `user_group` (
 insert into user_group(id, name, create_at, create_by, update_at, update_by) values(1, 'demo-root-group', unix_timestamp(now()), 'root', unix_timestamp(now()), 'root');
 
 CREATE TABLE `user_group_member` (
+    `id` bigint unsigned not null auto_increment,
     `group_id` bigint unsigned not null,
     `user_id` bigint unsigned not null,
     KEY (`group_id`),
-    KEY (`user_id`)
+    KEY (`user_id`),
+    PRIMARY KEY(`id`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
 
 insert into user_group_member(group_id, user_id) values(1, 1);
@@ -52,7 +54,7 @@ insert into user_group_member(group_id, user_id) values(1, 1);
 CREATE TABLE `configs` (
     `id` bigint unsigned not null auto_increment,
     `ckey` varchar(191) not null,
-    `cval` varchar(1024) not null default '',
+    `cval` varchar(4096) not null default '',
     PRIMARY KEY (`id`),
     UNIQUE KEY (`ckey`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
@@ -70,10 +72,12 @@ insert into `role`(name, note) values('Standard', 'Ordinary user role');
 insert into `role`(name, note) values('Guest', 'Readonly user role');
 
 CREATE TABLE `role_operation`(
+    `id` bigint unsigned not null auto_increment,
     `role_name` varchar(128) not null,
     `operation` varchar(191) not null,
     KEY (`role_name`),
-    KEY (`operation`)
+    KEY (`operation`),
+    PRIMARY KEY(`id`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
 
 -- Admin is special, who has no concrete operation but can do anything.
@@ -123,7 +127,10 @@ insert into `role_operation`(role_name, operation) values('Standard', '/job-tpls
 insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks');
 insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks/add');
 insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks/put');
-
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules');
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/add');
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/put');
+insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/del');
 
 -- for alert_rule | collect_rule | mute | dashboard grouping
 CREATE TABLE `busi_group` (
@@ -158,13 +165,16 @@ CREATE TABLE `board` (
     `id` bigint unsigned not null auto_increment,
     `group_id` bigint not null default 0 comment 'busi group id',
     `name` varchar(191) not null,
+    `ident` varchar(200) not null default '',
     `tags` varchar(255) not null comment 'split by space',
+    `public` tinyint(1) not null default 0 comment '0:false 1:true',
     `create_at` bigint not null default 0,
     `create_by` varchar(64) not null default '',
     `update_at` bigint not null default 0,
     `update_by` varchar(64) not null default '',
     PRIMARY KEY (`id`),
-    UNIQUE KEY (`group_id`, `name`)
+    UNIQUE KEY (`group_id`, `name`),
+    KEY(`ident`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
 
 -- for dashboard new version
@@ -223,6 +233,7 @@ CREATE TABLE `chart_share` (
 CREATE TABLE `alert_rule` (
     `id` bigint unsigned not null auto_increment,
     `group_id` bigint not null default 0 comment 'busi group id',
+    `cate` varchar(128) not null,
     `cluster` varchar(128) not null,
     `name` varchar(255) not null,
     `note` varchar(1024) not null default '',
@@ -230,10 +241,10 @@ CREATE TABLE `alert_rule` (
     `algorithm` varchar(255) not null default '',
     `algo_params` varchar(255),
     `delay` int not null default 0,
-    `severity` tinyint(1) not null comment '0:Emergency 1:Warning 2:Notice',
+    `severity` tinyint(1) not null comment '1:Emergency 2:Warning 3:Notice',
     `disabled` tinyint(1) not null comment '0:enabled 1:disabled',
     `prom_for_duration` int not null comment 'prometheus for, unit:s',
-    `prom_ql` varchar(8192) not null comment 'promql',
+    `prom_ql` text not null comment 'promql',
     `prom_eval_interval` int not null comment 'evaluate interval',
     `enable_stime` char(5) not null default '00:00',
     `enable_etime` char(5) not null default '23:59',
@@ -243,6 +254,7 @@ CREATE TABLE `alert_rule` (
     `notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
     `notify_groups` varchar(255) not null default '' comment 'split by space: 233 43',
     `notify_repeat_step` int not null default 0 comment 'unit: min',
+    `notify_max_number` int not null default 0 comment '',
     `recover_duration` int not null default 0 comment 'unit: s',
     `callbacks` varchar(255) not null default '' comment 'split by space: http://a.com/api/x http://a.com/api/y',
     `runbook_url` varchar(255),
@@ -259,13 +271,19 @@ CREATE TABLE `alert_rule` (
 CREATE TABLE `alert_mute` (
     `id` bigint unsigned not null auto_increment,
     `group_id` bigint not null default 0 comment 'busi group id',
+    `prod` varchar(255) not null default '',
+    `note` varchar(1024) not null default '',
+    `cate` varchar(128) not null,
     `cluster` varchar(128) not null,
     `tags` varchar(4096) not null default '' comment 'json,map,tagkey->regexp|value',
     `cause` varchar(255) not null default '',
     `btime` bigint not null default 0 comment 'begin time',
     `etime` bigint not null default 0 comment 'end time',
+    `disabled` tinyint(1) not null default 0 comment '0:enabled 1:disabled',
     `create_at` bigint not null default 0,
     `create_by` varchar(64) not null default '',
+    `update_at` bigint not null default 0,
+    `update_by` varchar(64) not null default '',
     PRIMARY KEY (`id`),
     KEY (`create_at`),
     KEY (`group_id`)
@@ -273,7 +291,10 @@ CREATE TABLE `alert_mute` (
 
 CREATE TABLE `alert_subscribe` (
     `id` bigint unsigned not null auto_increment,
+    `name` varchar(255) not null default '',
+    `disabled` tinyint(1) not null default 0 comment '0:enabled 1:disabled',
     `group_id` bigint not null default 0 comment 'busi group id',
+    `cate` varchar(128) not null,
     `cluster` varchar(128) not null,
     `rule_id` bigint not null default 0,
     `tags` varchar(4096) not null default '' comment 'json,map,tagkey->regexp|value',
@@ -339,6 +360,25 @@ CREATE TABLE `metric_view` (
 
 insert into metric_view(name, cate, configs) values('Host View', 0, '{"filters":[{"oper":"=","label":"__name__","value":"cpu_usage_idle"}],"dynamicLabels":[],"dimensionLabels":[{"label":"ident","value":""}]}');
 
+CREATE TABLE `recording_rule` (
+    `id` bigint unsigned not null auto_increment,
+    `group_id` bigint not null default '0' comment 'group_id',
+    `cluster` varchar(128) not null,
+    `name` varchar(255) not null comment 'new metric name',
+    `note` varchar(255) not null comment 'rule note',
+    `disabled` tinyint(1) not null default 0 comment '0:enabled 1:disabled',
+    `prom_ql` varchar(8192) not null comment 'promql',
+    `prom_eval_interval` int not null comment 'evaluate interval',
+    `append_tags` varchar(255) default '' comment 'split by space: service=n9e mod=api',
+    `create_at` bigint default '0',
+    `create_by` varchar(64) default '',
+    `update_at` bigint default '0',
+    `update_by` varchar(64) default '',
+    PRIMARY KEY (`id`),
+    KEY `group_id` (`group_id`),
+    KEY `update_at` (`update_at`)
+) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
+
 CREATE TABLE `alert_aggr_view` (
     `id` bigint unsigned not null auto_increment,
     `name` varchar(191) not null default '',
@@ -356,6 +396,7 @@ insert into alert_aggr_view(name, rule, cate) values('By RuleName', 'field:rule_
 
 CREATE TABLE `alert_cur_event` (
     `id` bigint unsigned not null comment 'use alert_his_event.id',
+    `cate` varchar(128) not null,
     `cluster` varchar(128) not null,
     `group_id` bigint unsigned not null comment 'busi group id of rule',
     `group_name` varchar(255) not null default '' comment 'busi group name',
@@ -375,8 +416,10 @@ CREATE TABLE `alert_cur_event` (
     `notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
     `notify_groups` varchar(255) not null default '' comment 'split by space: 233 43',
     `notify_repeat_next` bigint not null default 0 comment 'next timestamp to notify, get repeat settings from rule',
+    `notify_cur_number` int not null default 0 comment '',
     `target_ident` varchar(191) not null default '' comment 'target ident, also in tags',
     `target_note` varchar(191) not null default '' comment 'target note',
+    `first_trigger_time` bigint,
     `trigger_time` bigint not null,
     `trigger_value` varchar(255) not null,
     `tags` varchar(1024) not null default '' comment 'merge data_tags rule_tags, split by ,,',
@@ -390,6 +433,7 @@ CREATE TABLE `alert_cur_event` (
 CREATE TABLE `alert_his_event` (
     `id` bigint unsigned not null AUTO_INCREMENT,
     `is_recovered` tinyint(1) not null,
+    `cate` varchar(128) not null,
     `cluster` varchar(128) not null,
     `group_id` bigint unsigned not null comment 'busi group id of rule',
     `group_name` varchar(255) not null default '' comment 'busi group name',
@@ -408,8 +452,10 @@ CREATE TABLE `alert_his_event` (
     `notify_recovered` tinyint(1) not null comment 'whether notify when recovery',
     `notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
     `notify_groups` varchar(255) not null default '' comment 'split by space: 233 43',
+    `notify_cur_number` int not null default 0 comment '',
     `target_ident` varchar(191) not null default '' comment 'target ident, also in tags',
     `target_note` varchar(191) not null default '' comment 'target note',
+    `first_trigger_time` bigint,
     `trigger_time` bigint not null,
     `trigger_value` varchar(255) not null,
     `recover_time` bigint not null default 0,
@@ -472,3 +518,13 @@ CREATE TABLE `task_record`
     KEY (`create_at`, `group_id`),
     KEY (`create_by`)
 ) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
+
+CREATE TABLE `alerting_engines`
+(
+    `id` int unsigned NOT NULL AUTO_INCREMENT,
+    `instance` varchar(128) not null default '' comment 'instance identification, e.g. 10.9.0.9:9090',
+    `cluster` varchar(128) not null default '' comment 'target reader cluster',
+    `clock` bigint not null,
+    PRIMARY KEY (`id`),
+    UNIQUE KEY (`instance`)
+) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;

docker/initsql_for_postgres/a-n9e-for-Postgres.sql

@@ -0,0 +1,615 @@
+-- n9e version 5.8 for postgres 
+CREATE TABLE users (
+    id bigserial,
+    username varchar(64) not null ,
+    nickname varchar(64) not null ,
+    password varchar(128) not null default '',
+    phone varchar(16) not null default '',
+    email varchar(64) not null default '',
+    portrait varchar(255) not null default '' ,
+    roles varchar(255) not null ,
+    contacts varchar(1024) ,
+    maintainer smallint not null default 0,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE users ADD CONSTRAINT users_pk PRIMARY KEY (id);
+ALTER TABLE users ADD CONSTRAINT users_un UNIQUE (username);
+
+COMMENT ON COLUMN users.username IS 'login name, cannot rename';
+COMMENT ON COLUMN users.nickname IS 'display name, chinese name';
+COMMENT ON COLUMN users.portrait IS 'portrait image url';
+COMMENT ON COLUMN users.roles IS 'Admin | Standard | Guest, split by space';
+COMMENT ON COLUMN users.contacts IS 'json e.g. {wecom:xx, dingtalk_robot_token:yy}';
+
+insert into users(id, username, nickname, password, roles, create_at, create_by, update_at, update_by) values(1, 'root', '超管', 'root.2020', 'Admin', date_part('epoch',current_timestamp)::int, 'system', date_part('epoch',current_timestamp)::int, 'system');
+
+
+CREATE TABLE user_group (
+    id bigserial,
+    name varchar(128) not null default '',
+    note varchar(255) not null default '',
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE user_group ADD CONSTRAINT user_group_pk PRIMARY KEY (id);
+CREATE INDEX user_group_create_by_idx ON user_group (create_by);
+CREATE INDEX user_group_update_at_idx ON user_group (update_at);
+
+insert into user_group(id, name, create_at, create_by, update_at, update_by) values(1, 'demo-root-group', date_part('epoch',current_timestamp)::int, 'root', date_part('epoch',current_timestamp)::int, 'root');
+
+CREATE TABLE user_group_member (
+    id bigserial,
+    group_id bigint  not null,
+    user_id bigint  not null
+) ;
+ALTER TABLE user_group_member ADD CONSTRAINT user_group_member_pk PRIMARY KEY (id);
+CREATE INDEX user_group_member_group_id_idx ON user_group_member (group_id);
+CREATE INDEX user_group_member_user_id_idx ON user_group_member (user_id);
+
+insert into user_group_member(group_id, user_id) values(1, 1);
+
+CREATE TABLE configs (
+    id bigserial,
+    ckey varchar(191) not null,
+    cval varchar(4096) not null default ''
+) ;
+ALTER TABLE configs ADD CONSTRAINT configs_pk PRIMARY KEY (id);
+ALTER TABLE configs ADD CONSTRAINT configs_un UNIQUE (ckey);
+
+CREATE TABLE role (
+    id bigserial,
+    name varchar(191) not null default '',
+    note varchar(255) not null default ''
+) ;
+ALTER TABLE role ADD CONSTRAINT role_pk PRIMARY KEY (id);
+ALTER TABLE role ADD CONSTRAINT role_un UNIQUE ("name");
+
+insert into role(name, note) values('Admin', 'Administrator role');
+insert into role(name, note) values('Standard', 'Ordinary user role');
+insert into role(name, note) values('Guest', 'Readonly user role');
+
+CREATE TABLE role_operation(
+    id bigserial,
+    role_name varchar(128) not null,
+    operation varchar(191) not null
+) ;
+ALTER TABLE role_operation ADD CONSTRAINT role_operation_pk PRIMARY KEY (id);
+CREATE INDEX role_operation_role_name_idx ON role_operation (role_name);
+CREATE INDEX role_operation_operation_idx ON role_operation (operation);
+
+
+-- Admin is special, who has no concrete operation but can do anything.
+insert into role_operation(role_name, operation) values('Guest', '/metric/explorer');
+insert into role_operation(role_name, operation) values('Guest', '/object/explorer');
+insert into role_operation(role_name, operation) values('Guest', '/help/version');
+insert into role_operation(role_name, operation) values('Guest', '/help/contact');
+insert into role_operation(role_name, operation) values('Standard', '/metric/explorer');
+insert into role_operation(role_name, operation) values('Standard', '/object/explorer');
+insert into role_operation(role_name, operation) values('Standard', '/help/version');
+insert into role_operation(role_name, operation) values('Standard', '/help/contact');
+insert into role_operation(role_name, operation) values('Standard', '/users');
+insert into role_operation(role_name, operation) values('Standard', '/user-groups');
+insert into role_operation(role_name, operation) values('Standard', '/user-groups/add');
+insert into role_operation(role_name, operation) values('Standard', '/user-groups/put');
+insert into role_operation(role_name, operation) values('Standard', '/user-groups/del');
+insert into role_operation(role_name, operation) values('Standard', '/busi-groups');
+insert into role_operation(role_name, operation) values('Standard', '/busi-groups/add');
+insert into role_operation(role_name, operation) values('Standard', '/busi-groups/put');
+insert into role_operation(role_name, operation) values('Standard', '/busi-groups/del');
+insert into role_operation(role_name, operation) values('Standard', '/targets');
+insert into role_operation(role_name, operation) values('Standard', '/targets/add');
+insert into role_operation(role_name, operation) values('Standard', '/targets/put');
+insert into role_operation(role_name, operation) values('Standard', '/targets/del');
+insert into role_operation(role_name, operation) values('Standard', '/dashboards');
+insert into role_operation(role_name, operation) values('Standard', '/dashboards/add');
+insert into role_operation(role_name, operation) values('Standard', '/dashboards/put');
+insert into role_operation(role_name, operation) values('Standard', '/dashboards/del');
+insert into role_operation(role_name, operation) values('Standard', '/alert-rules');
+insert into role_operation(role_name, operation) values('Standard', '/alert-rules/add');
+insert into role_operation(role_name, operation) values('Standard', '/alert-rules/put');
+insert into role_operation(role_name, operation) values('Standard', '/alert-rules/del');
+insert into role_operation(role_name, operation) values('Standard', '/alert-mutes');
+insert into role_operation(role_name, operation) values('Standard', '/alert-mutes/add');
+insert into role_operation(role_name, operation) values('Standard', '/alert-mutes/del');
+insert into role_operation(role_name, operation) values('Standard', '/alert-subscribes');
+insert into role_operation(role_name, operation) values('Standard', '/alert-subscribes/add');
+insert into role_operation(role_name, operation) values('Standard', '/alert-subscribes/put');
+insert into role_operation(role_name, operation) values('Standard', '/alert-subscribes/del');
+insert into role_operation(role_name, operation) values('Standard', '/alert-cur-events');
+insert into role_operation(role_name, operation) values('Standard', '/alert-cur-events/del');
+insert into role_operation(role_name, operation) values('Standard', '/alert-his-events');
+insert into role_operation(role_name, operation) values('Standard', '/job-tpls');
+insert into role_operation(role_name, operation) values('Standard', '/job-tpls/add');
+insert into role_operation(role_name, operation) values('Standard', '/job-tpls/put');
+insert into role_operation(role_name, operation) values('Standard', '/job-tpls/del');
+insert into role_operation(role_name, operation) values('Standard', '/job-tasks');
+insert into role_operation(role_name, operation) values('Standard', '/job-tasks/add');
+insert into role_operation(role_name, operation) values('Standard', '/job-tasks/put');
+insert into role_operation(role_name, operation) values('Standard', '/recording-rules');
+insert into role_operation(role_name, operation) values('Standard', '/recording-rules/add');
+insert into role_operation(role_name, operation) values('Standard', '/recording-rules/put');
+insert into role_operation(role_name, operation) values('Standard', '/recording-rules/del');
+
+CREATE TABLE recording_rule (
+    id bigserial NOT NULL,
+    group_id bigint not null default 0,
+    cluster varchar(128) not null,
+    name varchar(255) not null,
+    note varchar(255) not null,
+    disabled smallint not null,
+    prom_ql varchar(8192) not null,
+    prom_eval_interval int not null,
+    append_tags varchar(255) default '',
+    create_at bigint default 0,
+    create_by varchar(64) default '',
+    update_at bigint default 0,
+    update_by varchar(64) default '',
+    CONSTRAINT recording_rule_pk PRIMARY KEY (id)
+) ;
+CREATE INDEX recording_rule_group_id_idx ON recording_rule (group_id);
+CREATE INDEX recording_rule_update_at_idx ON recording_rule (update_at);
+COMMENT ON COLUMN recording_rule.group_id IS 'group_id';
+COMMENT ON COLUMN recording_rule.name IS 'new metric name';
+COMMENT ON COLUMN recording_rule.note IS 'rule note';
+COMMENT ON COLUMN recording_rule.disabled IS '0:enabled 1:disabled';
+COMMENT ON COLUMN recording_rule.prom_ql IS 'promql';
+COMMENT ON COLUMN recording_rule.prom_eval_interval IS 'evaluate interval';
+COMMENT ON COLUMN recording_rule.append_tags IS 'split by space: service=n9e mod=api';
+
+-- for alert_rule | collect_rule | mute | dashboard grouping
+CREATE TABLE busi_group (
+    id bigserial,
+    name varchar(191) not null,
+    label_enable smallint not null default 0,
+    label_value varchar(191) not null default '' ,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE busi_group ADD CONSTRAINT busi_group_pk PRIMARY KEY (id);
+ALTER TABLE busi_group ADD CONSTRAINT busi_group_un UNIQUE ("name");
+COMMENT ON COLUMN busi_group.label_value IS 'if label_enable: label_value can not be blank';
+
+insert into busi_group(id, name, create_at, create_by, update_at, update_by) values(1, 'Default Busi Group', date_part('epoch',current_timestamp)::int, 'root', date_part('epoch',current_timestamp)::int, 'root');
+
+CREATE TABLE busi_group_member (
+    id bigserial,
+    busi_group_id bigint not null ,
+    user_group_id bigint not null ,
+    perm_flag char(2) not null 
+) ;
+ALTER TABLE busi_group_member ADD CONSTRAINT busi_group_member_pk PRIMARY KEY (id);
+CREATE INDEX busi_group_member_busi_group_id_idx ON busi_group_member (busi_group_id);
+CREATE INDEX busi_group_member_user_group_id_idx ON busi_group_member (user_group_id);
+COMMENT ON COLUMN busi_group_member.busi_group_id IS 'busi group id';
+COMMENT ON COLUMN busi_group_member.user_group_id IS 'user group id';
+COMMENT ON COLUMN busi_group_member.perm_flag IS 'ro | rw';
+
+insert into busi_group_member(busi_group_id, user_group_id, perm_flag) values(1, 1, 'rw');
+
+-- for dashboard new version
+CREATE TABLE board (
+    id bigserial  not null ,
+    group_id bigint not null default 0 ,
+    name varchar(191) not null,
+    ident varchar(200) not null default '',
+    tags varchar(255) not null ,
+    public smallint not null default 0,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE board ADD CONSTRAINT board_pk PRIMARY KEY (id);
+ALTER TABLE board ADD CONSTRAINT board_un UNIQUE (group_id,"name");
+COMMENT ON COLUMN board.group_id IS 'busi group id';
+COMMENT ON COLUMN board.tags IS 'split by space';
+COMMENT ON COLUMN board.public IS '0:false 1:true';
+CREATE INDEX board_ident_idx ON board (ident);
+
+-- for dashboard new version
+CREATE TABLE board_payload (
+    id bigint  not null ,
+    payload text not null
+);
+ALTER TABLE board_payload ADD CONSTRAINT board_payload_un UNIQUE (id);
+COMMENT ON COLUMN board_payload.id IS 'dashboard id';
+
+-- deprecated
+CREATE TABLE dashboard (
+    id bigserial,
+    group_id bigint not null default 0 ,
+    name varchar(191) not null,
+    tags varchar(255) not null ,
+    configs varchar(8192) ,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE dashboard ADD CONSTRAINT dashboard_pk PRIMARY KEY (id);
+
+-- deprecated
+-- auto create the first subclass 'Default chart group' of dashboard
+CREATE TABLE chart_group (
+    id bigserial,
+    dashboard_id bigint  not null,
+    name varchar(255) not null,
+    weight int not null default 0
+) ;
+ALTER TABLE chart_group ADD CONSTRAINT chart_group_pk PRIMARY KEY (id);
+
+-- deprecated
+CREATE TABLE chart (
+    id bigserial,
+    group_id bigint  not null ,
+    configs text,
+    weight int not null default 0
+) ;
+ALTER TABLE chart ADD CONSTRAINT chart_pk PRIMARY KEY (id);
+
+CREATE TABLE chart_share (
+    id bigserial,
+    cluster varchar(128) not null,
+    configs text,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default ''
+) ;
+ALTER TABLE chart_share ADD CONSTRAINT chart_share_pk PRIMARY KEY (id);
+CREATE INDEX chart_share_create_at_idx ON chart_share (create_at);
+
+CREATE TABLE alert_rule (
+    id bigserial NOT NULL,
+    group_id int8 NOT NULL DEFAULT 0,
+    cate varchar(128) not null default '' ,
+    "cluster" varchar(128) NOT NULL,
+    "name" varchar(255) NOT NULL,
+    note varchar(1024) NOT NULL,
+    severity int2 NOT NULL,
+    disabled int2 NOT NULL,
+    prom_for_duration int4 NOT NULL,
+    prom_ql text NOT NULL,
+    prom_eval_interval int4 NOT NULL,
+    enable_stime bpchar(5) NOT NULL DEFAULT '00:00'::bpchar,
+    enable_etime bpchar(5) NOT NULL DEFAULT '23:59'::bpchar,
+    enable_days_of_week varchar(32) NOT NULL DEFAULT ''::character varying,
+    enable_in_bg int2 NOT NULL DEFAULT 0,
+    notify_recovered int2 NOT NULL,
+    notify_channels varchar(255) NOT NULL DEFAULT ''::character varying,
+    notify_groups varchar(255) NOT NULL DEFAULT ''::character varying,
+    notify_repeat_step int4 NOT NULL DEFAULT 0,
+    notify_max_number int4 not null default 0,
+    recover_duration int4 NOT NULL DEFAULT 0,
+    callbacks varchar(255) NOT NULL DEFAULT ''::character varying,
+    runbook_url varchar(255) NULL,
+    append_tags varchar(255) NOT NULL DEFAULT ''::character varying,
+    create_at int8 NOT NULL DEFAULT 0,
+    create_by varchar(64) NOT NULL DEFAULT ''::character varying,
+    update_at int8 NOT NULL DEFAULT 0,
+    update_by varchar(64) NOT NULL DEFAULT ''::character varying,
+    prod varchar(255) NOT NULL DEFAULT ''::character varying,
+    algorithm varchar(255) NOT NULL DEFAULT ''::character varying,
+    algo_params varchar(255) NULL,
+    delay int4 NOT NULL DEFAULT 0,
+    CONSTRAINT alert_rule_pk PRIMARY KEY (id)
+);
+CREATE INDEX alert_rule_group_id_idx ON alert_rule USING btree (group_id);
+CREATE INDEX alert_rule_update_at_idx ON alert_rule USING btree (update_at);
+
+COMMENT ON COLUMN alert_rule.group_id IS 'busi group id';
+COMMENT ON COLUMN alert_rule.severity IS '0:Emergency 1:Warning 2:Notice';
+COMMENT ON COLUMN alert_rule.disabled IS '0:enabled 1:disabled';
+COMMENT ON COLUMN alert_rule.prom_for_duration IS 'prometheus for, unit:s';
+COMMENT ON COLUMN alert_rule.prom_ql IS 'promql';
+COMMENT ON COLUMN alert_rule.prom_eval_interval IS 'evaluate interval';
+COMMENT ON COLUMN alert_rule.enable_stime IS '00:00';
+COMMENT ON COLUMN alert_rule.enable_etime IS '23:59';
+COMMENT ON COLUMN alert_rule.enable_days_of_week IS 'split by space: 0 1 2 3 4 5 6';
+COMMENT ON COLUMN alert_rule.enable_in_bg IS '1: only this bg 0: global';
+COMMENT ON COLUMN alert_rule.notify_recovered IS 'whether notify when recovery';
+COMMENT ON COLUMN alert_rule.notify_channels IS 'split by space: sms voice email dingtalk wecom';
+COMMENT ON COLUMN alert_rule.notify_groups IS 'split by space: 233 43';
+COMMENT ON COLUMN alert_rule.notify_repeat_step IS 'unit: min';
+COMMENT ON COLUMN alert_rule.recover_duration IS 'unit: s';
+COMMENT ON COLUMN alert_rule.callbacks IS 'split by space: http://a.com/api/x http://a.com/api/y';
+COMMENT ON COLUMN alert_rule.append_tags IS 'split by space: service=n9e mod=api';
+
+CREATE TABLE alert_mute (
+    id bigserial,
+    group_id bigint not null default 0 ,
+    cate varchar(128) not null default '' ,
+    prod varchar(255) NOT NULL DEFAULT '' ,
+    note varchar(1024) not null default '',
+    cluster varchar(128) not null,
+    tags varchar(4096) not null default '' ,
+    cause varchar(255) not null default '',
+    btime bigint not null default 0 ,
+    etime bigint not null default 0 ,
+    disabled smallint not null default 0 ,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE alert_mute ADD CONSTRAINT alert_mute_pk PRIMARY KEY (id);
+CREATE INDEX alert_mute_create_at_idx ON alert_mute (create_at);
+CREATE INDEX alert_mute_group_id_idx ON alert_mute (group_id);
+COMMENT ON COLUMN alert_mute.group_id IS 'busi group id';
+COMMENT ON COLUMN alert_mute.tags IS 'json,map,tagkey->regexp|value';
+COMMENT ON COLUMN alert_mute.btime IS 'begin time';
+COMMENT ON COLUMN alert_mute.etime IS 'end time';
+COMMENT ON COLUMN alert_mute.disabled IS '0:enabled 1:disabled';
+
+CREATE TABLE alert_subscribe (
+    id bigserial,
+    "name" varchar(255) NOT NULL default '',
+    disabled int2 NOT NULL default 0 ,
+    group_id bigint not null default 0 ,
+    cate varchar(128) not null default '' ,
+    cluster varchar(128) not null,
+    rule_id bigint not null default 0,
+    tags jsonb not null ,
+    redefine_severity smallint default 0 ,
+    new_severity smallint not null ,
+    redefine_channels smallint default 0 ,
+    new_channels varchar(255) not null default '' ,
+    user_group_ids varchar(250) not null ,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE alert_subscribe ADD CONSTRAINT alert_subscribe_pk PRIMARY KEY (id);
+CREATE INDEX alert_subscribe_group_id_idx ON alert_subscribe (group_id);
+CREATE INDEX alert_subscribe_update_at_idx ON alert_subscribe (update_at);
+COMMENT ON COLUMN alert_subscribe.disabled IS '0:enabled 1:disabled';
+COMMENT ON COLUMN alert_subscribe.group_id IS 'busi group id';
+COMMENT ON COLUMN alert_subscribe.tags IS 'json,map,tagkey->regexp|value';
+COMMENT ON COLUMN alert_subscribe.redefine_severity IS 'is redefine severity?';
+COMMENT ON COLUMN alert_subscribe.new_severity IS '0:Emergency 1:Warning 2:Notice';
+COMMENT ON COLUMN alert_subscribe.redefine_channels IS 'is redefine channels?';
+COMMENT ON COLUMN alert_subscribe.new_channels IS 'split by space: sms voice email dingtalk wecom';
+COMMENT ON COLUMN alert_subscribe.user_group_ids IS 'split by space 1 34 5, notify cc to user_group_ids';
+
+
+CREATE TABLE target (
+    id bigserial,
+    group_id bigint not null default 0 ,
+    cluster varchar(128) not null ,
+    ident varchar(191) not null ,
+    note varchar(255) not null default '' ,
+    tags varchar(512) not null default '' ,
+    update_at bigint not null default 0
+) ;
+ALTER TABLE target ADD CONSTRAINT target_pk PRIMARY KEY (id);
+ALTER TABLE target ADD CONSTRAINT target_un UNIQUE (ident);
+CREATE INDEX target_group_id_idx ON target (group_id);
+
+COMMENT ON COLUMN target.group_id IS 'busi group id';
+COMMENT ON COLUMN target."cluster" IS 'append to alert event as field';
+COMMENT ON COLUMN target.ident IS 'target id';
+COMMENT ON COLUMN target.note IS 'append to alert event as field';
+COMMENT ON COLUMN target.tags IS 'append to series data as tags, split by space, append external space at suffix';
+
+
+CREATE TABLE metric_view (
+    id bigserial,
+    name varchar(191) not null default '',
+    cate smallint not null ,
+    configs varchar(8192) not null default '',
+    create_at bigint not null default 0,
+    create_by bigint not null default 0 ,
+    update_at bigint not null default 0
+) ;
+ALTER TABLE metric_view ADD CONSTRAINT metric_view_pk PRIMARY KEY (id);
+CREATE INDEX metric_view_create_by_idx ON metric_view (create_by);
+
+COMMENT ON COLUMN metric_view.cate IS '0: preset 1: custom';
+COMMENT ON COLUMN metric_view.create_by IS 'user id';
+
+insert into metric_view(name, cate, configs) values('Host View', 0, '{"filters":[{"oper":"=","label":"__name__","value":"cpu_usage_idle"}],"dynamicLabels":[],"dimensionLabels":[{"label":"ident","value":""}]}');
+
+CREATE TABLE alert_aggr_view (
+    id bigserial,
+    name varchar(191) not null default '',
+    rule varchar(2048) not null default '',
+    cate smallint not null ,
+    create_at bigint not null default 0,
+    create_by bigint not null default 0 ,
+    update_at bigint not null default 0
+) ;
+ALTER TABLE alert_aggr_view ADD CONSTRAINT alert_aggr_view_pk PRIMARY KEY (id);
+CREATE INDEX alert_aggr_view_create_by_idx ON alert_aggr_view (create_by);
+
+COMMENT ON COLUMN alert_aggr_view.cate IS '0: preset 1: custom';
+COMMENT ON COLUMN alert_aggr_view.create_by IS 'user id';
+
+insert into alert_aggr_view(name, rule, cate) values('By BusiGroup, Severity', 'field:group_name::field:severity', 0);
+insert into alert_aggr_view(name, rule, cate) values('By RuleName', 'field:rule_name', 0);
+
+CREATE TABLE alert_cur_event (
+    id bigserial NOT NULL,
+    cate varchar(128) not null default '' ,
+    "cluster" varchar(128) NOT NULL,
+    group_id int8 NOT NULL,
+    group_name varchar(255) NOT NULL DEFAULT ''::character varying,
+    hash varchar(64) NOT NULL,
+    rule_id int8 NOT NULL,
+    rule_name varchar(255) NOT NULL,
+    rule_note varchar(2048) NOT NULL DEFAULT 'alert rule note'::character varying,
+    severity int2 NOT NULL,
+    prom_for_duration int4 NOT NULL,
+    prom_ql varchar(8192) NOT NULL,
+    prom_eval_interval int4 NOT NULL,
+    callbacks varchar(255) NOT NULL DEFAULT ''::character varying,
+    runbook_url varchar(255) NULL,
+    notify_recovered int2 NOT NULL,
+    notify_channels varchar(255) NOT NULL DEFAULT ''::character varying,
+    notify_groups varchar(255) NOT NULL DEFAULT ''::character varying,
+    notify_repeat_next int8 NOT NULL DEFAULT 0,
+    notify_cur_number int4 not null default 0,
+    target_ident varchar(191) NOT NULL DEFAULT ''::character varying,
+    target_note varchar(191) NOT NULL DEFAULT ''::character varying,
+    first_trigger_time int8,
+    trigger_time int8 NOT NULL,
+    trigger_value varchar(255) NOT NULL,
+    tags varchar(1024) NOT NULL DEFAULT ''::character varying,
+    rule_prod varchar(255) NOT NULL DEFAULT ''::character varying,
+    rule_algo varchar(255) NOT NULL DEFAULT ''::character varying,
+    CONSTRAINT alert_cur_event_pk PRIMARY KEY (id)
+);
+CREATE INDEX alert_cur_event_hash_idx ON alert_cur_event USING btree (hash);
+CREATE INDEX alert_cur_event_notify_repeat_next_idx ON alert_cur_event USING btree (notify_repeat_next);
+CREATE INDEX alert_cur_event_rule_id_idx ON alert_cur_event USING btree (rule_id);
+CREATE INDEX alert_cur_event_trigger_time_idx ON alert_cur_event USING btree (trigger_time, group_id);
+COMMENT ON COLUMN alert_cur_event.id IS 'use alert_his_event.id';
+COMMENT ON COLUMN alert_cur_event.group_id IS 'busi group id of rule';
+COMMENT ON COLUMN alert_cur_event.group_name IS 'busi group name';
+COMMENT ON COLUMN alert_cur_event.hash IS 'rule_id + vector_pk';
+COMMENT ON COLUMN alert_cur_event.rule_note IS 'alert rule note';
+COMMENT ON COLUMN alert_cur_event.severity IS '1:Emergency 2:Warning 3:Notice';
+COMMENT ON COLUMN alert_cur_event.prom_for_duration IS 'prometheus for, unit:s';
+COMMENT ON COLUMN alert_cur_event.prom_ql IS 'promql';
+COMMENT ON COLUMN alert_cur_event.prom_eval_interval IS 'evaluate interval';
+COMMENT ON COLUMN alert_cur_event.callbacks IS 'split by space: http://a.com/api/x http://a.com/api/y';
+COMMENT ON COLUMN alert_cur_event.notify_recovered IS 'whether notify when recovery';
+COMMENT ON COLUMN alert_cur_event.notify_channels IS 'split by space: sms voice email dingtalk wecom';
+COMMENT ON COLUMN alert_cur_event.notify_groups IS 'split by space: 233 43';
+COMMENT ON COLUMN alert_cur_event.notify_repeat_next IS 'next timestamp to notify, get repeat settings from rule';
+COMMENT ON COLUMN alert_cur_event.target_ident IS 'target ident, also in tags';
+COMMENT ON COLUMN alert_cur_event.target_note IS 'target note';
+COMMENT ON COLUMN alert_cur_event.tags IS 'merge data_tags rule_tags, split by ,,';
+
+CREATE TABLE alert_his_event (
+    id bigserial NOT NULL,
+    is_recovered int2 NOT NULL,
+    cate varchar(128) not null default '' ,
+    "cluster" varchar(128) NOT NULL,
+    group_id int8 NOT NULL,
+    group_name varchar(255) NOT NULL DEFAULT ''::character varying,
+    hash varchar(64) NOT NULL,
+    rule_id int8 NOT NULL,
+    rule_name varchar(255) NOT NULL,
+    rule_note varchar(2048) NOT NULL DEFAULT 'alert rule note'::character varying,
+    severity int2 NOT NULL,
+    prom_for_duration int4 NOT NULL,
+    prom_ql varchar(8192) NOT NULL,
+    prom_eval_interval int4 NOT NULL,
+    callbacks varchar(255) NOT NULL DEFAULT ''::character varying,
+    runbook_url varchar(255) NULL,
+    notify_recovered int2 NOT NULL,
+    notify_channels varchar(255) NOT NULL DEFAULT ''::character varying,
+    notify_groups varchar(255) NOT NULL DEFAULT ''::character varying,
+    notify_cur_number int4 not null default 0,
+    target_ident varchar(191) NOT NULL DEFAULT ''::character varying,
+    target_note varchar(191) NOT NULL DEFAULT ''::character varying,
+    first_trigger_time int8,
+    trigger_time int8 NOT NULL,
+    trigger_value varchar(255) NOT NULL,
+    recover_time int8 NOT NULL DEFAULT 0,
+    last_eval_time int8 NOT NULL DEFAULT 0,
+    tags varchar(1024) NOT NULL DEFAULT ''::character varying,
+    rule_prod varchar(255) NOT NULL DEFAULT ''::character varying,
+    rule_algo varchar(255) NOT NULL DEFAULT ''::character varying,
+    CONSTRAINT alert_his_event_pk PRIMARY KEY (id)
+);
+CREATE INDEX alert_his_event_hash_idx ON alert_his_event USING btree (hash);
+CREATE INDEX alert_his_event_rule_id_idx ON alert_his_event USING btree (rule_id);
+CREATE INDEX alert_his_event_trigger_time_idx ON alert_his_event USING btree (trigger_time, group_id);
+
+COMMENT ON COLUMN alert_his_event.group_id IS 'busi group id of rule';
+COMMENT ON COLUMN alert_his_event.group_name IS 'busi group name';
+COMMENT ON COLUMN alert_his_event.hash IS 'rule_id + vector_pk';
+COMMENT ON COLUMN alert_his_event.rule_note IS 'alert rule note';
+COMMENT ON COLUMN alert_his_event.severity IS '0:Emergency 1:Warning 2:Notice';
+COMMENT ON COLUMN alert_his_event.prom_for_duration IS 'prometheus for, unit:s';
+COMMENT ON COLUMN alert_his_event.prom_ql IS 'promql';
+COMMENT ON COLUMN alert_his_event.prom_eval_interval IS 'evaluate interval';
+COMMENT ON COLUMN alert_his_event.callbacks IS 'split by space: http://a.com/api/x http://a.com/api/y';
+COMMENT ON COLUMN alert_his_event.notify_recovered IS 'whether notify when recovery';
+COMMENT ON COLUMN alert_his_event.notify_channels IS 'split by space: sms voice email dingtalk wecom';
+COMMENT ON COLUMN alert_his_event.notify_groups IS 'split by space: 233 43';
+COMMENT ON COLUMN alert_his_event.target_ident IS 'target ident, also in tags';
+COMMENT ON COLUMN alert_his_event.target_note IS 'target note';
+COMMENT ON COLUMN alert_his_event.last_eval_time IS 'for time filter';
+COMMENT ON COLUMN alert_his_event.tags IS 'merge data_tags rule_tags, split by ,,';
+
+CREATE TABLE task_tpl
+(
+    id        serial,
+    group_id  int  not null ,
+    title     varchar(255) not null default '',
+    account   varchar(64)  not null,
+    batch     int  not null default 0,
+    tolerance int  not null default 0,
+    timeout   int  not null default 0,
+    pause     varchar(255) not null default '',
+    script    text         not null,
+    args      varchar(512) not null default '',
+    tags      varchar(255) not null default '' ,
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default '',
+    update_at bigint not null default 0,
+    update_by varchar(64) not null default ''
+) ;
+ALTER TABLE task_tpl ADD CONSTRAINT task_tpl_pk PRIMARY KEY (id);
+CREATE INDEX task_tpl_group_id_idx ON task_tpl (group_id);
+
+COMMENT ON COLUMN task_tpl.group_id IS 'busi group id';
+COMMENT ON COLUMN task_tpl.tags IS 'split by space';
+
+
+CREATE TABLE task_tpl_host
+(
+    ii   serial,
+    id   int  not null ,
+    host varchar(128)  not null 
+) ;
+ALTER TABLE task_tpl_host ADD CONSTRAINT task_tpl_host_pk PRIMARY KEY (id);
+CREATE INDEX task_tpl_host_id_idx ON task_tpl_host (id,host);
+
+COMMENT ON COLUMN task_tpl_host.id IS 'task tpl id';
+COMMENT ON COLUMN task_tpl_host.host IS 'ip or hostname';
+
+CREATE TABLE task_record
+(
+    id bigserial,
+    group_id bigint not null ,
+    ibex_address   varchar(128) not null,
+    ibex_auth_user varchar(128) not null default '',
+    ibex_auth_pass varchar(128) not null default '',
+    title     varchar(255)    not null default '',
+    account   varchar(64)     not null,
+    batch     int     not null default 0,
+    tolerance int     not null default 0,
+    timeout   int     not null default 0,
+    pause     varchar(255)    not null default '',
+    script    text            not null,
+    args      varchar(512)    not null default '',
+    create_at bigint not null default 0,
+    create_by varchar(64) not null default ''
+) ;
+ALTER TABLE task_record ADD CONSTRAINT task_record_pk PRIMARY KEY (id);
+CREATE INDEX task_record_create_at_idx ON task_record (create_at,group_id);
+CREATE INDEX task_record_create_by_idx ON task_record (create_by);
+
+COMMENT ON COLUMN task_record.id IS 'ibex task id';
+COMMENT ON COLUMN task_record.group_id IS 'busi group id';
+
+CREATE TABLE alerting_engines
+(
+    id bigserial NOT NULL,
+    instance varchar(128) not null default '',
+    cluster varchar(128) not null default '',
+    clock bigint not null
+) ;
+ALTER TABLE alerting_engines ADD CONSTRAINT alerting_engines_pk PRIMARY KEY (id);
+ALTER TABLE alerting_engines ADD CONSTRAINT alerting_engines_un UNIQUE (instance);
+COMMENT ON COLUMN alerting_engines.instance IS 'instance identification, e.g. 10.9.0.9:9090';
+COMMENT ON COLUMN alerting_engines.cluster IS 'target reader cluster';

docker/n9eetc/alerts/http_response_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "HTTP地址探测失败",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "http_response_result_code != 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

docker/n9eetc/alerts/linux_by_categraf.json

@@ -0,0 +1,243 @@
+[
+    {
+      "name": "监控对象失联",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "max_over_time(target_up[130s]) == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "机器负载-CPU较高，请关注",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "cpu_usage_idle{cpu=\"cpu-total\"} < 25",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "机器负载-内存较高，请关注",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "mem_available_percent < 25",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "硬盘-IO有点繁忙",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "rate(diskio_io_time[1m])/10 > 99",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "硬盘-预计再有4小时写满",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "predict_linear(disk_free[1h], 4*3600) < 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "网卡-入向有丢包",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "increase(net_drop_in[1m]) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "网卡-出向有丢包",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "increase(net_drop_out[1m]) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "网络连接-TME_WAIT数量超过2万",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "netstat_tcp_time_wait > 20000",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+]
+  

docker/n9eetc/alerts/mysql_by_categraf.json

@@ -0,0 +1,302 @@
+[
+    {
+      "name": "MysqlInnodbLogWaits",
+      "note": "MySQL innodb log writes stalling",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "rate(mysql_global_status_innodb_log_waits[15m]) > 10",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlInnodbLogWaits"
+      ]
+    },
+    {
+      "name": "MysqlSlaveIoThreadNotRunning",
+      "note": "MySQL Slave IO thread not running",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_io_running == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlaveIoThreadNotRunning"
+      ]
+    },
+    {
+      "name": "MysqlSlaveReplicationLag",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) (mysql_slave_status_seconds_behind_master - mysql_slave_status_sql_delay) > 30",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlaveReplicationLag"
+      ]
+    },
+    {
+      "name": "MysqlSlaveSqlThreadNotRunning",
+      "note": "MySQL Slave SQL thread not running",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_sql_running == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlaveSqlThreadNotRunning"
+      ]
+    },
+    {
+      "name": "Mysql刚刚有重启，请注意",
+      "note": "MySQL has just been restarted, less than one minute ago",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_global_status_uptime < 60",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlRestarted"
+      ]
+    },
+    {
+      "name": "Mysql实例挂了",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_up == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlDown"
+      ]
+    },
+    {
+      "name": "Mysql打开了很多文件句柄，请注意",
+      "note": "More than 80% of MySQL files open",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "avg by (instance) (mysql_global_status_open_files) / avg by (instance)(mysql_global_variables_open_files_limit) * 100 > 80",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlHighOpenFiles"
+      ]
+    },
+    {
+      "name": "Mysql最近一分钟有慢查询出现",
+      "note": "MySQL server mysql has some new slow query",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "increase(mysql_global_status_slow_queries[1m]) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlowQueries"
+      ]
+    },
+    {
+      "name": "Mysql有超过60%的连接是running状态",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "avg by (instance) (mysql_global_status_threads_running) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 60",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlHighThreadsRunning"
+      ]
+    },
+    {
+      "name": "Mysql连接数已超过80%",
+      "note": "More than 80% of MySQL connections are in use",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "avg by (instance) (mysql_global_status_threads_connected) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 80",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlTooManyConnections"
+      ]
+    }
+  ]

docker/n9eetc/alerts/net_response_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "网络地址探活失败",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "net_response_result_code != 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

docker/n9eetc/alerts/ntp_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "NTP时间偏移太大",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "ntp_offset_ms > 1000 or ntp_offset_ms < -1000",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

docker/n9eetc/alerts/ping_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "PING地址探测失败",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "ping_result_code != 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

docker/n9eetc/alerts/procstat_by_categraf.json

@@ -0,0 +1,62 @@
+[
+    {
+        "name": "进程监控-有进程数为0，某进程可能挂了",
+        "note": "",
+        "severity": 1,
+        "disabled": 0,
+        "prom_for_duration": 60,
+        "prom_ql": "procstat_lookup_count == 0",
+        "prom_eval_interval": 15,
+        "enable_stime": "00:00",
+        "enable_etime": "23:59",
+        "enable_days_of_week": [
+          "1",
+          "2",
+          "3",
+          "4",
+          "5",
+          "6",
+          "0"
+        ],
+        "notify_recovered": 1,
+        "notify_channels": [
+          "email",
+          "dingtalk",
+          "wecom"
+        ],
+        "notify_repeat_step": 60,
+        "callbacks": [],
+        "runbook_url": "",
+        "append_tags": []
+    },
+    {
+        "name": "进程监控-进程句柄限制过小",
+        "note": "",
+        "severity": 3,
+        "disabled": 0,
+        "prom_for_duration": 60,
+        "prom_ql": "procstat_rlimit_num_fds_soft < 2048",
+        "prom_eval_interval": 15,
+        "enable_stime": "00:00",
+        "enable_etime": "23:59",
+        "enable_days_of_week": [
+          "1",
+          "2",
+          "3",
+          "4",
+          "5",
+          "6",
+          "0"
+        ],
+        "notify_recovered": 1,
+        "notify_channels": [
+          "email",
+          "dingtalk",
+          "wecom"
+        ],
+        "notify_repeat_step": 60,
+        "callbacks": [],
+        "runbook_url": "",
+        "append_tags": []
+    }
+]

docker/n9eetc/alerts/redis_by_categraf.json

@@ -0,0 +1,182 @@
+[
+    {
+      "name": "Redis Ping 延迟高（大于100毫秒）",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "redis_ping_use_seconds > 0.1",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=HighPingLatency"
+      ]
+    },
+    {
+      "name": "Redis内存使用率较高",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "redis_maxmemory > 0 and (redis_used_memory / redis_maxmemory) > 0.85",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisHighMemoryUsage"
+      ]
+    },
+    {
+      "name": "Redis出现拒绝连接",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "(rate(redis_rejected_connections[5m])) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisRejectedConnHigh"
+      ]
+    },
+    {
+      "name": "Redis刚刚有重启，请注意",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "redis_uptime_in_seconds < 600",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisLowUptime"
+      ]
+    },
+    {
+      "name": "Redis较低的命中率",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "rate(redis_keyspace_hits[5m])\n/\n(rate(redis_keyspace_misses[5m]) + rate(redis_keyspace_hits[5m]))\n< 0.9",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisLowHitRatio"
+      ]
+    },
+    {
+      "name": "Redis驱逐率较高",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "(sum(rate(redis_evicted_keys[5m])) / sum(redis_keyspace_keys)) > 0.1",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisHighKeysEvictionRatio"
+      ]
+    }
+  ]

docker/n9eetc/dashboards/http_response_by_categraf.json

@@ -0,0 +1,19 @@
+[
+  {
+    "name": "HTTP探测",
+    "tags": "",
+    "configs": "",
+    "chart_groups": [
+      {
+        "name": "Default chart group",
+        "weight": 0,
+        "charts": [
+          {
+            "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(http_response_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(http_response_response_code) by (target)\",\"refId\":\"B\",\"legend\":\"status code\"},{\"expr\":\"max(http_response_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"},{\"expr\":\"max(http_response_cert_expire_timestamp) by (target) - time()\",\"refId\":\"D\",\"legend\":\"cert expire\"}],\"name\":\"URL Details\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}},{\"type\":\"special\",\"matcher\":{\"value\":\"D\"},\"properties\":{\"standardOptions\":{\"util\":\"humantimeSeconds\"}}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+            "weight": 0
+          }
+        ]
+      }
+    ]
+  }
+]

docker/n9eetc/dashboards/mysql_by_categraf.json

@@ -0,0 +1,119 @@
+[
+    {
+      "name": "MySQL Overview - 模板",
+      "tags": "Prometheus MySQL",
+      "configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(mysql_global_status_uptime, instance)\"}]}",
+      "chart_groups": [
+        {
+          "name": "Basic Info",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"min(mysql_global_status_uptime{instance=~\\\"$instance\\\"})\"}],\"name\":\"MySQL Uptime\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":1800},\"result\":{\"color\":\"#ec7718\"}},{\"type\":\"range\",\"match\":{\"from\":1800},\"result\":{\"color\":\"#369603\"}}],\"standardOptions\":{\"util\":\"humantimeSeconds\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_queries{instance=~\\\"$instance\\\"}[5m])\"}],\"name\":\"Current QPS\",\"description\":\"mysql_global_status_queries\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":100},\"result\":{\"color\":\"#05a31f\"}},{\"type\":\"range\",\"match\":{\"from\":100},\"result\":{\"color\":\"#ea3939\"}}],\"standardOptions\":{\"decimals\":2}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"avg(mysql_global_variables_innodb_buffer_pool_size{instance=~\\\"$instance\\\"})\"}],\"name\":\"InnoDB Buffer Pool\",\"description\":\"**InnoDB Buffer Pool Size**\\n\\nInnoDB maintains a storage area called the buffer pool for caching data and indexes in memory.  Knowing how the InnoDB buffer pool works, and taking advantage of it to keep frequently accessed data in memory, is one of the most important aspects of MySQL tuning. The goal is to keep the working set in memory. In most cases, this should be between 60%-90% of available memory on a dedicated database host, but depends on many factors.\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"bytesIEC\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(increase(mysql_global_status_table_locks_waited{instance=~\\\"$instance\\\"}[5m]))\"}],\"name\":\"Table Locks Waited(5min)\",\"description\":\"**Table Locks**\\n\\nMySQL takes a number of different locks for varying reasons. In this graph we see how many Table level locks MySQL has requested from the storage engine. In the case of InnoDB, many times the locks could actually be row locks as it only takes table level locks in a few specific cases.\\n\\nIt is most useful to compare Locks Immediate and Locks Waited. If Locks waited is rising, it means you have lock contention. Otherwise, Locks Immediate rising and falling is normal activity.\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":1},\"result\":{\"color\":\"#e70d0d\"}},{\"type\":\"range\",\"match\":{\"to\":1},\"result\":{\"color\":\"#53b503\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Connections",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(mysql_global_status_threads_connected{instance=~\\\"$instance\\\"})\",\"legend\":\"Connections\"},{\"expr\":\"sum(mysql_global_status_max_used_connections{instance=~\\\"$instance\\\"})\",\"legend\":\"Max Used Connections\"},{\"expr\":\"sum(mysql_global_variables_max_connections{instance=~\\\"$instance\\\"})\",\"legend\":\"Max Connections\"},{\"expr\":\"sum(rate(mysql_global_status_aborted_connects{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Aborted Connections\"}],\"name\":\"MySQL Connections\",\"description\":\"**Max Connections** \\n\\nMax Connections is the maximum permitted number of simultaneous client connections. By default, this is 151. Increasing this value increases the number of file descriptors that mysqld requires. If the required number of descriptors are not available, the server reduces the value of Max Connections.\\n\\nmysqld actually permits Max Connections + 1 clients to connect. The extra connection is reserved for use by accounts that have the SUPER privilege, such as root.\\n\\nMax Used Connections is the maximum number of connections that have been in use simultaneously since the server started.\\n\\nConnections is the number of connection attempts (successful or not) to the MySQL server.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(mysql_global_status_threads_connected{instance=~\\\"$instance\\\"})\",\"legend\":\"Threads Connected\"},{\"expr\":\"sum(mysql_global_status_threads_running{instance=~\\\"$instance\\\"})\",\"legend\":\"Threads Running\"}],\"name\":\"MySQL Client Thread Activity\",\"description\":\"Threads Connected is the number of open connections, while Threads Running is the number of threads not sleeping.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Query Performance",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_created_tmp_tables{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Tables\"},{\"expr\":\"sum(rate(mysql_global_status_created_tmp_disk_tables{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Disk Tables\"},{\"expr\":\"sum(rate(mysql_global_status_created_tmp_files{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Files\"}],\"name\":\"MySQL Temporary Objects\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.64,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_select_full_join{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Full Join\"},{\"expr\":\"sum(rate(mysql_global_status_select_full_range_join{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Full Range Join\"},{\"expr\":\"sum(rate(mysql_global_status_select_range{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Range\"},{\"expr\":\"sum(rate(mysql_global_status_select_range_check{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Range Check\"},{\"expr\":\"sum(rate(mysql_global_status_select_scan{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Scan\"}],\"name\":\"MySQL Select Types\",\"description\":\"**MySQL Select Types**\\n\\nAs with most relational databases, selecting based on indexes is more efficient than scanning an entire table's data. Here we see the counters for selects not done with indexes.\\n\\n* ***Select Scan*** is how many queries caused full table scans, in which all the data in the table had to be read and either discarded or returned.\\n* ***Select Range*** is how many queries used a range scan, which means MySQL scanned all rows in a given range.\\n* ***Select Full Join*** is the number of joins that are not joined on an index, this is usually a huge performance hit.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"stack\":\"off\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.41},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_sort_rows{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Rows\"},{\"expr\":\"sum(rate(mysql_global_status_sort_range{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Range\"},{\"expr\":\"sum(rate(mysql_global_status_sort_merge_passes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Merge Passes\"},{\"expr\":\"sum(rate(mysql_global_status_sort_scan{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Scan\"}],\"name\":\"MySQL Sorts\",\"description\":\"**MySQL Sorts**\\n\\nDue to a query's structure, order, or other requirements, MySQL sorts the rows before returning them. For example, if a table is ordered 1 to 10 but you want the results reversed, MySQL then has to sort the rows to return 10 to 1.\\n\\nThis graph also shows when sorts had to scan a whole table or a given range of a table in order to return the results and which could not have been sorted via an index.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_slow_queries{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Slow Queries\"}],\"name\":\"MySQL Slow Queries\",\"description\":\"**MySQL Slow Queries**\\n\\nSlow queries are defined as queries being slower than the long_query_time setting. For example, if you have long_query_time set to 3, all queries that take longer than 3 seconds to complete will show on this graph.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"bars\",\"stack\":\"off\",\"fillOpacity\":0.81},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Network",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_bytes_received{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Inbound\"},{\"expr\":\"sum(rate(mysql_global_status_bytes_sent{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Outbound\"}],\"name\":\"MySQL Network Traffic\",\"description\":\"**MySQL Network Traffic**\\n\\nHere we can see how much network traffic is generated by MySQL. Outbound is network traffic sent from MySQL and Inbound is network traffic MySQL has received.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesSI\",\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Commands, Handlers",
+          "weight": 4,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"topk(10, rate(mysql_global_status_commands_total{instance=~\\\"$instance\\\"}[5m])>0)\",\"legend\":\"Com_{{command}}\"}],\"name\":\"Top Command Counters\",\"description\":\"**Top Command Counters**\\n\\nThe Com_{{xxx}} statement counter variables indicate the number of times each xxx statement has been executed. There is one status variable for each type of statement. For example, Com_delete and Com_update count [``DELETE``](https://dev.mysql.com/doc/refman/5.7/en/delete.html) and [``UPDATE``](https://dev.mysql.com/doc/refman/5.7/en/update.html) statements, respectively. Com_delete_multi and Com_update_multi are similar but apply to [``DELETE``](https://dev.mysql.com/doc/refman/5.7/en/delete.html) and [``UPDATE``](https://dev.mysql.com/doc/refman/5.7/en/update.html) statements that use multiple-table syntax.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.2,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_handlers_total{instance=~\\\"$instance\\\", handler!~\\\"commit|rollback|savepoint.*|prepare\\\"}[5m])\",\"legend\":\"{{handler}}\"}],\"name\":\"MySQL Handlers\",\"description\":\"**MySQL Handlers**\\n\\nHandler statistics are internal statistics on how MySQL is selecting, updating, inserting, and modifying rows, tables, and indexes.\\n\\nThis is in fact the layer between the Storage Engine and MySQL.\\n\\n* `read_rnd_next` is incremented when the server performs a full table scan and this is a counter you don't really want to see with a high value.\\n* `read_key` is incremented when a read is done with an index.\\n* `read_next` is incremented when the storage engine is asked to 'read the next index entry'. A high value means a lot of index scans are being done.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":3},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_handlers_total{instance=~\\\"$instance\\\", handler=~\\\"commit|rollback|savepoint.*|prepare\\\"}[5m])\",\"legend\":\"{{handler}}\"}],\"name\":\"MySQL Transaction Handlers\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Open Files",
+          "weight": 5,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"mysql_global_variables_open_files_limit{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Files Limit\"},{\"expr\":\"mysql_global_status_open_files{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Files\"}],\"name\":\"MySQL Open Files\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Table Openings",
+          "weight": 6,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_table_open_cache_hits{instance=~\\\"$instance\\\"}[5m])\\n/\\n(\\nrate(mysql_global_status_table_open_cache_hits{instance=~\\\"$instance\\\"}[5m])\\n+\\nrate(mysql_global_status_table_open_cache_misses{instance=~\\\"$instance\\\"}[5m])\\n)\",\"legend\":\"Table Open Cache Hit Ratio\"}],\"name\":\"Table Open Cache Hit Ratio  Mysql 5.6.6+\",\"description\":\"**MySQL Table Open Cache Status**\\n\\nThe recommendation is to set the `table_open_cache_instances` to a loose correlation to virtual CPUs, keeping in mind that more instances means the cache is split more times. If you have a cache set to 500 but it has 10 instances, each cache will only have 50 cached.\\n\\nThe `table_definition_cache` and `table_open_cache` can be left as default as they are auto-sized MySQL 5.6 and above (ie: do not set them to any value).\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"percentUnit\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"mysql_global_status_open_tables{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Tables\"},{\"expr\":\"mysql_global_variables_table_open_cache{instance=~\\\"$instance\\\"}\",\"legend\":\"Table Open Cache\"}],\"name\":\"MySQL Open Tables\",\"description\":\"**MySQL Open Tables**\\n\\nThe recommendation is to set the `table_open_cache_instances` to a loose correlation to virtual CPUs, keeping in mind that more instances means the cache is split more times. If you have a cache set to 500 but it has 10 instances, each cache will only have 50 cached.\\n\\nThe `table_definition_cache` and `table_open_cache` can be left as default as they are auto-sized MySQL 5.6 and above (ie: do not set them to any value).\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

docker/n9eetc/dashboards/net_response_by_categraf.json

@@ -0,0 +1,19 @@
+[
+    {
+      "name": "TCP探测",
+      "tags": "",
+      "configs": "",
+      "chart_groups": [
+        {
+          "name": "Default chart group",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(net_response_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(net_response_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"}],\"name\":\"Targets\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

docker/n9eetc/dashboards/oracle_by_categraf.json

@@ -0,0 +1,127 @@
+[
+    {
+      "name": "Oracle - 模板",
+      "tags": "Telegraf",
+      "configs": "{\"var\":[{\"name\":\"ident\",\"definition\":\"label_values(oracle_up,ident)\",\"options\":[\"tt-fc-log00.nj\"]},{\"name\":\"instance\",\"definition\":\"label_values(oracle_up{ident=\\\"$ident\\\"},instance)\"}]}",
+      "chart_groups": [
+        {
+          "name": "Activities",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_execute_count_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"execute count / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"decimals\":1}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_user_commits_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"user commits / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_user_rollbacks_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"user rollbacks / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_up{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"status\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":1},\"result\":{\"text\":\"UP\",\"color\":\"#5ea70f\"}},{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"DOWN\",\"color\":\"#f60f0f\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Waits",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_wait_time_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{wait_class}}\"}],\"name\":\"Time waited\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Tablespace",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_tablespace_bytes{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}/oracle_tablespace_max_bytes{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{tablespace}}\"}],\"name\":\"Used Percent\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"percentUnit\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_tablespace_free{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{tablespace}}\"}],\"name\":\"Free space\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "IO and TPS",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_io_requests_per_second_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_user_transaction_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"TPS\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_io_megabytes_per_second_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}*1024*1024\"}],\"name\":\"IO Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Connections",
+          "weight": 4,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sessions_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\",status=\\\"ACTIVE\\\"}\",\"legend\":\"\"}],\"name\":\"Sessions\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Hit Ratio",
+          "weight": 5,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_buffer_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Buffer Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_redo_allocation_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Redo Allocation Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_row_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Row Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_library_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Library Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Physical Read Write",
+          "weight": 6,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_bytes_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Bytes_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical Read Write Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_total_bytes_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Total_Bytes_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical Read Write Total Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_io_requests_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_IO_Requests_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical RW IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_total_io_requests_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Total_IO_Requests_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical RW Total IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

docker/n9eetc/dashboards/ping_by_categraf.json

@@ -0,0 +1,19 @@
+[
+    {
+      "name": "PING探测",
+      "tags": "",
+      "configs": "",
+      "chart_groups": [
+        {
+          "name": "Default chart group",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(ping_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(ping_percent_packet_loss) by (target)\",\"refId\":\"B\",\"legend\":\"Packet Loss %\"},{\"expr\":\"max(httpresponse_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"}],\"name\":\"Ping\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

docker/n9eetc/dashboards/rabbitmq_by_categraf.json

@@ -0,0 +1,221 @@
+[
+    {
+      "name": "RabbitMQ 3.8+",
+      "tags": "",
+      "configs": "{\"var\":[{\"definition\":\"label_values(rabbitmq_identity_info, rabbitmq_cluster)\",\"name\":\"rabbitmq_cluster\"}]}",
+      "chart_groups": [
+        {
+          "name": "Overview",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_ready * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Ready messages\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10000},\"result\":{\"color\":\"#4a90e2\"}},{\"type\":\"range\",\"match\":{\"from\":100000},\"result\":{\"color\":\"#f50a0a\"}},{\"type\":\"range\",\"match\":{\"to\":9999},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":7,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Incoming messages / s\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":50},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":5,\"x\":7,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channels * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) - sum(rabbitmq_channel_consumers * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Publishers\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_connections * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Connections\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queues * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Queues\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":0,\"i\":\"4\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_unacked * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Unacknowledged messages\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":99},\"result\":{\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"from\":100},\"result\":{\"color\":\"#4a90e2\"}},{\"type\":\"range\",\"match\":{\"from\":500},\"result\":{\"color\":\"#d0021b\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":7,\"x\":0,\"y\":1,\"i\":\"5\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_redelivered_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_get_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_get_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Outgoing messages / s\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":50},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":5,\"x\":7,\"y\":1,\"i\":\"6\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channel_consumers * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Consumers\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":1,\"i\":\"7\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channels * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Channels\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":1,\"i\":\"8\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_build_info * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Nodes\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":null,\"from\":3},\"result\":{\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"from\":8},\"result\":{\"color\":\"#e70909\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":1,\"i\":\"9\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Nodes",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_build_info * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"nodes\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelsOfSeriesToRows\",\"columns\":[\"rabbitmq_cluster\",\"rabbitmq_node\",\"rabbitmq_version\",\"erlang_version\"]},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":1,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_resident_memory_limit_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_resident_memory_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Memory available before publishers blocked\",\"description\":\"If the value is zero or less, the memory alarm will be triggered and all publishing connections across all cluster nodes will be blocked.\\n\\nThis value can temporarily go negative because the memory alarm is triggered with a slight delay.\\n\\nThe kernel's view of the amount of memory used by the node can differ from what the node itself can observe. This means that this value can be negative for a sustained period of time.\\n\\nBy default nodes use resident set size (RSS) to compute how much memory they use. This strategy can be changed (see the guides below).\\n\\n* [Alarms](https://www.rabbitmq.com/alarms.html)\\n* [Memory Alarms](https://www.rabbitmq.com/memory.html)\\n* [Reasoning About Memory Use](https://www.rabbitmq.com/memory-use.html)\\n* [Blocked Connection Notifications](https://www.rabbitmq.com/connection-blocked.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":1,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_disk_space_available_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Disk space available before publishers blocked\",\"description\":\"This metric is reported for the partition where the RabbitMQ data directory is stored.\\n\\nIf the value is zero or less, the disk alarm will be triggered and all publishing connections across all cluster nodes will be blocked.\\n\\nThis value can temporarily go negative because the free disk space alarm is triggered with a slight delay.\\n\\n* [Alarms](https://www.rabbitmq.com/alarms.html)\\n* [Disk Space Alarms](https://www.rabbitmq.com/disk-alarms.html)\\n* [Disk Space](https://www.rabbitmq.com/production-checklist.html#resource-limits-disk-space)\\n* [Persistence Configuration](https://www.rabbitmq.com/persistence-conf.html)\\n* [Blocked Connection Notifications](https://www.rabbitmq.com/connection-blocked.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":1,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_process_max_fds * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_open_fds * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"File descriptors available\",\"description\":\"When this value reaches zero, new connections will not be accepted and disk write operations may fail.\\n\\nClient libraries, peer nodes and CLI tools will not be able to connect when the node runs out of available file descriptors.\\n\\n* [Open File Handles Limit](https://www.rabbitmq.com/production-checklist.html#resource-limits-file-handle-limit)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":1,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_process_max_tcp_sockets * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_open_tcp_sockets * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"TCP sockets available\",\"description\":\"When this value reaches zero, new connections will not be accepted.\\n\\nClient libraries, peer nodes and CLI tools will not be able to connect when the node runs out of available file descriptors.\\n\\n* [Networking and RabbitMQ](https://www.rabbitmq.com/networking.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":2,\"i\":\"4\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "QUEUED MESSAGES",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_ready * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages ready to be delivered to consumers\",\"description\":\"Total number of ready messages ready to be delivered to consumers.\\n\\nAim to keep this value as low as possible. RabbitMQ behaves best when messages are flowing through it. It's OK for publishers to occasionally outpace consumers, but the expectation is that consumers will eventually process all ready messages.\\n\\nIf this metric keeps increasing, your system will eventually run out of memory and/or disk space. Consider using TTL or Queue Length Limit to prevent unbounded message growth.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\\n* [Queue Length Limit](https://www.rabbitmq.com/maxlength.html)\\n* [Time-To-Live and Expiration](https://www.rabbitmq.com/ttl.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_unacked * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages pending consumer acknowledgement\",\"description\":\"The total number of messages that are either in-flight to consumers, currently being processed by consumers or simply waiting for the consumer acknowledgements to be processed by the queue. Until the queue processes the message acknowledgement, the message will remain unacknowledged.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Confirms and Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "INCOMING MESSAGES",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages published / s\",\"description\":\"The incoming message rate before any routing rules are applied.\\n\\nIf this value is lower than the number of messages published to queues, it may indicate that some messages are delivered to more than one queue.\\n\\nIf this value is higher than the number of messages published to queues, messages cannot be routed and will either be dropped or returned to publishers.\\n\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_confirmed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages confirmed to publishers / s\",\"description\":\"The rate of messages confirmed by the broker to publishers. Publishers must opt-in to receive message confirmations.\\n\\nIf this metric is consistently at zero it may suggest that publisher confirms are not used by clients. The safety of published messages is likely to be at risk.\\n\\n* [Publisher Confirms](https://www.rabbitmq.com/confirms.html#publisher-confirms)\\n* [Publisher Confirms and Data Safety](https://www.rabbitmq.com/publishers.html#data-safety)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queue_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages routed to queues / s\",\"description\":\"The rate of messages received from publishers and successfully routed to the master queue replicas.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":1,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unconfirmed[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages unconfirmed to publishers / s\",\"description\":\"The rate of messages received from publishers that have publisher confirms enabled and the broker has not confirmed yet.\\n\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\\n* [Confirms and Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":1,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unroutable_dropped_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Unroutable messages dropped / s\",\"description\":\"The rate of messages that cannot be routed and are dropped. \\n\\nAny value above zero means message loss and likely suggests a routing problem on the publisher end.\\n\\n* [Unroutable Message Handling](https://www.rabbitmq.com/publishers.html#unroutable)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":2,\"i\":\"4\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unroutable_returned_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Unroutable messages returned to publishers / s\",\"description\":\"The rate of messages that cannot be routed and are returned back to publishers.\\n\\nSustained values above zero may indicate a routing problem on the publisher end.\\n\\n* [Unroutable Message Handling](https://www.rabbitmq.com/publishers.html#unroutable)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":2,\"i\":\"5\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "OUTGOING MESSAGES",
+          "weight": 4,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(\\n  (rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\n  (rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\\n) by(rabbitmq_node)\"}],\"name\":\"Messages delivered / s\",\"description\":\"The rate of messages delivered to consumers. It includes messages that have been redelivered.\\n\\nThis metric does not include messages that have been fetched by consumers using `basic.get` (consumed by polling).\\n\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_redelivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages redelivered / s\",\"description\":\"The rate of messages that have been redelivered to consumers. It includes messages that have been requeued automatically and redelivered due to channel exceptions or connection closures.\\n\\nHaving some redeliveries is expected, but if this metric is consistently non-zero, it is worth investigating why.\\n\\n* [Negative Acknowledgement and Requeuing of Deliveries](https://www.rabbitmq.com/confirms.html#consumer-nacks-requeue)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages delivered with manual ack / s\",\"description\":\"The rate of message deliveries to consumers that use manual acknowledgement mode.\\n\\nWhen this mode is used, RabbitMQ waits for consumers to acknowledge messages before more messages can be delivered.\\n\\nThis is the safest way of consuming messages.\\n\\n* [Consumer Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":1,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages delivered auto ack / s\",\"description\":\"The rate of message deliveries to consumers that use automatic acknowledgement mode.\\n\\nWhen this mode is used, RabbitMQ does not wait for consumers to acknowledge message deliveries.\\n\\nThis mode is fire-and-forget and does not offer any delivery safety guarantees. It tends to provide higher throughput and it may lead to consumer overload  and higher consumer memory usage.\\n\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":1,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_acked_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages acknowledged / s\",\"description\":\"The rate of message acknowledgements coming from consumers that use manual acknowledgement mode.\\n\\n* [Consumer Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":2,\"i\":\"4\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations with auto ack / s\",\"description\":\"The rate of messages delivered to polling consumers that use automatic acknowledgement mode.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":2,\"i\":\"5\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_empty_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations that yield no result / s\",\"description\":\"The rate of polling consumer operations that yield no result.\\n\\nAny value above zero means that RabbitMQ resources are wasted by polling consumers.\\n\\nCompare this metric to the other polling consumer metrics to see the inefficiency rate.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":3,\"i\":\"6\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations with manual ack / s\",\"description\":\"The rate of messages delivered to polling consumers that use manual acknowledgement mode.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":3,\"i\":\"7\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "QUEUES",
+          "weight": 5,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_queues * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total queues\",\"description\":\"Total number of queue masters  per node. \\n\\nThis metric makes it easy to see sub-optimal queue distribution in a cluster.\\n\\n* [Queue Masters, Data Locality](https://www.rabbitmq.com/ha.html#master-migration-data-locality)\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_declared_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues declared / s\",\"description\":\"The rate of queue declarations performed by clients.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_created_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues created / s\",\"description\":\"The rate of new queues created (as opposed to redeclarations).\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_deleted_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues deleted / s\",\"description\":\"The rate of queues deleted.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "CHANNELS",
+          "weight": 6,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_channels * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total channels\",\"description\":\"Total number of channels on all currently opened connections.\\n\\nIf this metric grows monotonically it is highly likely a channel leak in one of the applications. Confirm channel leaks by using the _Channels opened_ and _Channels closed_ metrics.\\n\\n* [Channel Leak](https://www.rabbitmq.com/channels.html#channel-leaks)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channels_opened_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Channels opened / s\",\"description\":\"The rate of new channels opened by applications across all connections. Channels are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of channel churn or mass connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [High Channel Churn](https://www.rabbitmq.com/channels.html#high-channel-churn)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channels_closed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Channels closed / s\",\"description\":\"The rate of channels closed by applications across all connections. Channels are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of channel churn or mass connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [High Channel Churn](https://www.rabbitmq.com/channels.html#high-channel-churn)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "CONNECTIONS",
+          "weight": 7,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_connections_closed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Connections closed / s\",\"description\":\"The rate of connections closed. Connections are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of connection churn or mass connection recovery.\\n\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_connections * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total connections\",\"description\":\"Total number of client connections.\\n\\nIf this metric grows monotonically it is highly likely a connection leak in one of the applications. Confirm connection leaks by using the _Connections opened_ and _Connections closed_ metrics.\\n\\n* [Connection Leak](https://www.rabbitmq.com/connections.html#monitoring)\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_connections_opened_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Connections opened / s\",\"description\":\"The rate of new connections opened by clients. Connections are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of connection churn or mass connection recovery.\\n\\n* [Connection Leak](https://www.rabbitmq.com/connections.html#monitoring)\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

docker/n9eetc/dashboards/redis_by_categraf.json

@@ -0,0 +1,77 @@
+[
+    {
+      "name": "Redis Overview - 模板",
+      "tags": "Redis Prometheus",
+      "configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(redis_uptime_in_seconds,instance)\",\"selected\":\"10.206.0.16:6379\"}]}",
+      "chart_groups": [
+        {
+          "name": "Basic Info",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"min(redis_uptime_in_seconds{instance=~\\\"$instance\\\"})\"}],\"name\":\"Redis Uptime\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"humantimeSeconds\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(redis_connected_clients{instance=~\\\"$instance\\\"})\"}],\"name\":\"Connected Clients\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"redis_used_memory{instance=~\\\"$instance\\\"}\"}],\"name\":\"Memory Used\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":128000000},\"result\":{\"color\":\"#079e05\"}},{\"type\":\"range\",\"match\":{\"from\":128000000},\"result\":{\"color\":\"#f10909\"}}],\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":0}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"redis_maxmemory{instance=~\\\"$instance\\\"}\"}],\"name\":\"Max Memory Limit\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"bytesIEC\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Commands",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(redis_total_commands_processed{instance=~\\\"$instance\\\"}[5m])\"}],\"name\":\"Commands Executed / sec\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"irate(redis_keyspace_hits{instance=~\\\"$instance\\\"}[5m])\",\"legend\":\"hits\"},{\"expr\":\"irate(redis_keyspace_misses{instance=~\\\"$instance\\\"}[5m])\",\"legend\":\"misses\"}],\"name\":\"Hits / Misses per Sec\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"noraml\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"topk(5, irate(redis_cmdstat_calls{instance=~\\\"$instance\\\"} [1m]))\",\"legend\":\"{{command}}\"}],\"name\":\"Top Commands\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Keys",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum (redis_keyspace_keys{instance=~\\\"$instance\\\"}) by (db)\",\"legend\":\"{{db}}\"}],\"name\":\"Total Items per DB\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(redis_expired_keys{instance=~\\\"$instance\\\"}[5m])) by (instance)\",\"legend\":\"expired\"},{\"expr\":\"sum(rate(redis_evicted_keys{instance=~\\\"$instance\\\"}[5m])) by (instance)\",\"legend\":\"evicted\"}],\"name\":\"Expired / Evicted\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(redis_keyspace_keys{instance=~\\\"$instance\\\"}) - sum(redis_keyspace_expires{instance=~\\\"$instance\\\"}) \",\"legend\":\"not expiring\"},{\"expr\":\"sum(redis_keyspace_expires{instance=~\\\"$instance\\\"}) \",\"legend\":\"expiring\"}],\"name\":\"Expiring vs Not-Expiring Keys\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"noraml\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Network",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(redis_total_net_input_bytes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"input\"},{\"expr\":\"sum(rate(redis_total_net_output_bytes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"output\"}],\"name\":\"Network I/O\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

docker/n9eetc/dashboards/tomcat_by_categraf.json

@@ -0,0 +1,63 @@
+[
+    {
+      "name": "Tomcat - 模板",
+      "tags": "Categraf",
+      "configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(tomcat_up, instance)\"}],\"links\":[{\"title\":\"n9e\",\"url\":\"https://n9e.gitee.io/\",\"targetBlank\":true}]}",
+      "chart_groups": [
+        {
+          "name": "connector",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_bytes_sent{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"sent\"},{\"expr\":\"rate(tomcat_connector_bytes_received{instance=\\\"$instance\\\"}[1m])\",\"refId\":\"B\",\"legend\":\"received\"}],\"name\":\"Traffic Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_request_count{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"tomcat_connector_request_count\"},{\"expr\":\"rate(tomcat_connector_error_count{instance=\\\"$instance\\\"}[1m])\",\"refId\":\"B\",\"legend\":\"tomcat_connector_error_count\"}],\"name\":\"Request count / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_connector_max_threads{instance=\\\"$instance\\\"}\",\"legend\":\"max_threads\"},{\"expr\":\"tomcat_connector_current_thread_count{instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"current_thread_count\"},{\"expr\":\"tomcat_connector_current_threads_busy{instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"current_threads_busy\"}],\"name\":\"Tread\",\"description\":\"max_threads: The maximum number of allowed worker threads.\\ncurrent_thread_count: The number of threads managed by the thread pool\\ncurrent_threads_busy: The number of threads that are in use\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_processing_time{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"{{name}}-processing_time\"}],\"name\":\"Processing time\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "mem used",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memory_max{instance=\\\"$instance\\\"}\",\"legend\":\"max\"},{\"expr\":\"tomcat_jvm_memory_total{instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"used\"},{\"expr\":\"tomcat_jvm_memory_free{instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"free\"}],\"name\":\"Mem Used\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "memorypool",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_used{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Used\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_max{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Max\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_committed{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Committed\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_init{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Init\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

docker/n9eetc/script/notify.py

@@ -23,6 +23,11 @@ class Sender(object):
     def send_feishu(cls, payload):
         # already done in go code
         pass
+    
+    @classmethod
+    def send_mm(cls, payload):
+        # already done in go code
+        pass
 
     @classmethod
     def send_sms(cls, payload):

docker/n9eetc/server.conf

@@ -9,7 +9,14 @@ ClusterName = "Default"
 BusiGroupLabelKey = "busigroup"
 
 # sleep x seconds, then start judge engine
-EngineDelay = 120
+EngineDelay = 60
+
+DisableUsageReport = false
+
+# config | database
+ReaderFrom = "config"
+
+ForceUseServerTS = true
 
 [Log]
 # log write dir
@@ -68,10 +75,12 @@ InsecureSkipVerify = true
 Batch = 5
 
 [Alerting]
+# timeout settings, unit: ms, default: 30000ms
+Timeout=30000
 TemplatesDir = "./etc/template"
 NotifyConcurrency = 10
 # use builtin go code notify
-NotifyBuiltinChannels = ["email", "dingtalk", "wecom", "feishu"]
+NotifyBuiltinChannels = ["email", "dingtalk", "wecom", "feishu", "mm"]
 
 [Alerting.CallScript]
 # built in sending capability in go code
@@ -83,7 +92,8 @@ ScriptPath = "./etc/script/notify.py"
 Enable = false
 # use a plugin via `go build -buildmode=plugin -o notify.so`
 PluginPath = "./etc/script/notify.so"
-Caller = "n9eCaller"
+# The first letter must be capitalized to be exported
+Caller = "N9eCaller"
 
 [Alerting.RedisPub]
 Enable = false
@@ -101,7 +111,7 @@ Headers = ["Content-Type", "application/json", "X-From", "N9E"]
 [NoData]
 Metric = "target_up"
 # unit: second
-Interval = 15
+Interval = 120
 
 [Ibex]
 # callback: ${ibex}/${tplid}/${host}
@@ -136,7 +146,7 @@ MaxIdleConns = 50
 # table prefix
 TablePrefix = ""
 # enable auto migrate or not
-EnableAutoMigrate = false
+# EnableAutoMigrate = false
 
 [Reader]
 # prometheus base url
@@ -147,23 +157,16 @@ BasicAuthUser = ""
 BasicAuthPass = ""
 # timeout settings, unit: ms
 Timeout = 30000
-DialTimeout = 10000
-TLSHandshakeTimeout = 30000
-ExpectContinueTimeout = 1000
-IdleConnTimeout = 90000
-# time duration, unit: ms
-KeepAlive = 30000
-MaxConnsPerHost = 0
-MaxIdleConns = 100
-MaxIdleConnsPerHost = 10
+DialTimeout = 3000
+MaxIdleConnsPerHost = 100
 
 [WriterOpt]
+# queue channel count
+QueueCount = 100
 # queue max size
-QueueMaxSize = 10000000
+QueueMaxSize = 200000
 # once pop samples number from queue
 QueuePopSize = 2000
-# unit: ms
-SleepInterval = 50
 
 [[Writers]]
 Url = "http://prometheus:9090/api/v1/write"
@@ -172,8 +175,8 @@ BasicAuthUser = ""
 # Basic auth password
 BasicAuthPass = ""
 # timeout settings, unit: ms
-Timeout = 30000
-DialTimeout = 10000
+Timeout = 10000
+DialTimeout = 3000
 TLSHandshakeTimeout = 30000
 ExpectContinueTimeout = 1000
 IdleConnTimeout = 90000
@@ -182,6 +185,12 @@ KeepAlive = 30000
 MaxConnsPerHost = 0
 MaxIdleConns = 100
 MaxIdleConnsPerHost = 100
+# [[Writers.WriteRelabels]]
+# Action = "replace"
+# SourceLabels = ["__address__"]
+# Regex = "([^:]+)(?::\\d+)?"
+# Replacement = "$1:80"
+# TargetLabel = "__address__"
 
 # [[Writers]]
 # Url = "http://m3db:7201/api/v1/prom/remote/write"

docker/n9eetc/webapi.conf

@@ -4,12 +4,21 @@ RunMode = "release"
 # # custom i18n dict config
 # I18N = "./etc/i18n.json"
 
+# # custom i18n request header key
+# I18NHeaderKey = "X-Language"
+
 # metrics descriptions
 MetricsYamlFile = "./etc/metrics.yaml"
 
 BuiltinAlertsDir = "./etc/alerts"
 BuiltinDashboardsDir = "./etc/dashboards"
 
+# config | api
+ClustersFrom = "config"
+
+# using when ClustersFrom = "api"
+ClustersFromAPIs = []
+
 [[NotifyChannels]]
 Label = "邮箱"
 # do not change Key
@@ -30,6 +39,11 @@ Label = "飞书机器人"
 # do not change Key
 Key = "feishu"
 
+[[NotifyChannels]]
+Label = "mm bot"
+# do not change Key
+Key = "mm"
+
 [[ContactKeys]]
 Label = "Wecom Robot Token"
 # do not change Key
@@ -45,6 +59,11 @@ Label = "Feishu Robot Token"
 # do not change Key
 Key = "feishu_robot_token"
 
+[[ContactKeys]]
+Label = "MatterMost Webhook URL"
+# do not change Key
+Key = "mm_webhook_url"
+
 [Log]
 # log write dir
 Dir = "logs"
@@ -92,6 +111,13 @@ AccessExpired = 1500
 RefreshExpired = 10080
 RedisKeyPrefix = "/jwt/"
 
+[ProxyAuth]
+# if proxy auth enabled, jwt auth is disabled
+Enable = false
+# username key in http proxy header
+HeaderUserNameKey = "X-User-Name"
+DefaultRoles = ["Standard"]
+
 [BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
@@ -121,6 +147,20 @@ Nickname = "cn"
 Phone = "mobile"
 Email = "mail"
 
+[OIDC]
+Enable = false
+RedirectURL = "http://n9e.com/callback"
+SsoAddr = "http://sso.example.org"
+ClientId = ""
+ClientSecret = ""
+CoverAttributes = true
+DefaultRoles = ["Standard"]
+
+[OIDC.Attributes]
+Nickname = "nickname"
+Phone = "phone_number"
+Email = "email"
+
 [Redis]
 # address, ip:port
 Address = "redis:6379"
@@ -145,7 +185,7 @@ MaxIdleConns = 50
 # table prefix
 TablePrefix = ""
 # enable auto migrate or not
-EnableAutoMigrate = false
+# EnableAutoMigrate = false
 
 [[Clusters]]
 # Prometheus cluster name
@@ -158,14 +198,7 @@ BasicAuthUser = ""
 BasicAuthPass = ""
 # timeout settings, unit: ms
 Timeout = 30000
-DialTimeout = 10000
-TLSHandshakeTimeout = 30000
-ExpectContinueTimeout = 1000
-IdleConnTimeout = 90000
-# time duration, unit: ms
-KeepAlive = 30000
-MaxConnsPerHost = 0
-MaxIdleConns = 100
+DialTimeout = 3000
 MaxIdleConnsPerHost = 100
 
 [Ibex]
@@ -174,4 +207,10 @@ Address = "http://ibex:10090"
 BasicAuthUser = "ibex"
 BasicAuthPass = "ibex"
 # unit: ms
-Timeout = 3000
+Timeout = 3000
+
+[TargetMetrics]
+TargetUp = '''max(max_over_time(target_up{ident=~"(%s)"}[%dm])) by (ident)'''
+LoadPerCore = '''max(max_over_time(system_load_norm_1{ident=~"(%s)"}[%dm])) by (ident)'''
+MemUtil = '''100-max(max_over_time(mem_available_percent{ident=~"(%s)"}[%dm])) by (ident)'''
+DiskUtil = '''max(max_over_time(disk_used_percent{ident=~"(%s)", path="/"}[%dm])) by (ident)'''

etc/alerts/http_response_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "HTTP地址探测失败",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "http_response_result_code != 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

etc/alerts/kafka_by_exporter.json

@@ -1,58 +1,72 @@
 [
-    {
-      "name": "数据有丢失风险-同步副本数小于3",
-      "note": "",
-      "severity": 2,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
-        "1",
-        "2",
-        "3",
-        "4",
-        "5",
-        "6",
-        "0"
-      ],
-      "enable_in_bg": 0,
-      "notify_recovered": 1,
-      "notify_channels": [],
-      "notify_repeat_step": 60,
-      "recover_duration": 0,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
-    },
-    {
-      "name": "消费能力不足-积压消息数超过50条",
-      "note": "",
-      "severity": 2,
-      "disabled": 0,
-      "prom_for_duration": 60,
-      "prom_ql": "sum(kafka_topic_partition_current_offset{instance=\"$instance\"}) by (topic) - sum(kafka_consumergroup_current_offset{instance=\"$instance\"}) by (topic) ",
-      "prom_eval_interval": 15,
-      "enable_stime": "00:00",
-      "enable_etime": "23:59",
-      "enable_days_of_week": [
-        "1",
-        "2",
-        "3",
-        "4",
-        "5",
-        "6",
-        "0"
-      ],
-      "enable_in_bg": 0,
-      "notify_recovered": 1,
-      "notify_channels": [],
-      "notify_repeat_step": 60,
-      "recover_duration": 0,
-      "callbacks": [],
-      "runbook_url": "",
-      "append_tags": []
-    }
-  ]
+  {
+    "name": "数据有丢失风险-副本数小于3",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_etime": "23:59",
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "service=kafka"
+    ]
+  },
+  {
+    "name": "消费能力不足-延迟超过5分钟",
+    "note": "",
+    "prod": "",
+    "algorithm": "",
+    "algo_params": null,
+    "delay": 0,
+    "severity": 2,
+    "disabled": 1,
+    "prom_for_duration": 60,
+    "prom_ql": "kafka_consumer_lag_millis / 1000 > 300",
+    "prom_eval_interval": 15,
+    "enable_stime": "00:00",
+    "enable_etime": "23:59",
+    "enable_days_of_week": [
+      "1",
+      "2",
+      "3",
+      "4",
+      "5",
+      "6",
+      "0"
+    ],
+    "enable_in_bg": 0,
+    "notify_recovered": 1,
+    "notify_channels": [],
+    "notify_repeat_step": 60,
+    "notify_max_number": 0,
+    "recover_duration": 0,
+    "callbacks": [],
+    "runbook_url": "",
+    "append_tags": [
+      "service=kafka"
+    ]
+  }
+]

etc/alerts/linux_by_categraf.json

@@ -0,0 +1,243 @@
+[
+    {
+      "name": "监控对象失联",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "max_over_time(target_up[130s]) == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "机器负载-CPU较高，请关注",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "cpu_usage_idle{cpu=\"cpu-total\"} < 25",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "机器负载-内存较高，请关注",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "mem_available_percent < 25",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "硬盘-IO有点繁忙",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "rate(diskio_io_time[1m])/10 > 99",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "硬盘-预计再有4小时写满",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "predict_linear(disk_free[1h], 4*3600) < 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "网卡-入向有丢包",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "increase(net_drop_in[1m]) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "网卡-出向有丢包",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "increase(net_drop_out[1m]) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    },
+    {
+      "name": "网络连接-TME_WAIT数量超过2万",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "netstat_tcp_time_wait > 20000",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "notify_recovered": 1,
+      "notify_channels": [
+        "email",
+        "dingtalk",
+        "wecom"
+      ],
+      "notify_repeat_step": 60,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+]
+  

etc/alerts/mysql_by_categraf.json

@@ -0,0 +1,302 @@
+[
+    {
+      "name": "MysqlInnodbLogWaits",
+      "note": "MySQL innodb log writes stalling",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "rate(mysql_global_status_innodb_log_waits[15m]) > 10",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlInnodbLogWaits"
+      ]
+    },
+    {
+      "name": "MysqlSlaveIoThreadNotRunning",
+      "note": "MySQL Slave IO thread not running",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_io_running == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlaveIoThreadNotRunning"
+      ]
+    },
+    {
+      "name": "MysqlSlaveReplicationLag",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) (mysql_slave_status_seconds_behind_master - mysql_slave_status_sql_delay) > 30",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlaveReplicationLag"
+      ]
+    },
+    {
+      "name": "MysqlSlaveSqlThreadNotRunning",
+      "note": "MySQL Slave SQL thread not running",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_sql_running == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlaveSqlThreadNotRunning"
+      ]
+    },
+    {
+      "name": "Mysql刚刚有重启，请注意",
+      "note": "MySQL has just been restarted, less than one minute ago",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_global_status_uptime < 60",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlRestarted"
+      ]
+    },
+    {
+      "name": "Mysql实例挂了",
+      "note": "",
+      "severity": 1,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "mysql_up == 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlDown"
+      ]
+    },
+    {
+      "name": "Mysql打开了很多文件句柄，请注意",
+      "note": "More than 80% of MySQL files open",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "avg by (instance) (mysql_global_status_open_files) / avg by (instance)(mysql_global_variables_open_files_limit) * 100 > 80",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlHighOpenFiles"
+      ]
+    },
+    {
+      "name": "Mysql最近一分钟有慢查询出现",
+      "note": "MySQL server mysql has some new slow query",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "increase(mysql_global_status_slow_queries[1m]) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlSlowQueries"
+      ]
+    },
+    {
+      "name": "Mysql有超过60%的连接是running状态",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "avg by (instance) (mysql_global_status_threads_running) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 60",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlHighThreadsRunning"
+      ]
+    },
+    {
+      "name": "Mysql连接数已超过80%",
+      "note": "More than 80% of MySQL connections are in use",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 120,
+      "prom_ql": "avg by (instance) (mysql_global_status_threads_connected) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 80",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=MysqlTooManyConnections"
+      ]
+    }
+  ]

etc/alerts/net_response_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "网络地址探活失败",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "net_response_result_code != 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

etc/alerts/ntp_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "NTP时间偏移太大",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "ntp_offset_ms > 1000 or ntp_offset_ms < -1000",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

etc/alerts/ping_by_categraf.json

@@ -0,0 +1,30 @@
+[
+    {
+      "name": "PING地址探测失败",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "ping_result_code != 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": []
+    }
+  ]

etc/alerts/procstat_by_categraf.json

@@ -0,0 +1,62 @@
+[
+    {
+        "name": "进程监控-有进程数为0，某进程可能挂了",
+        "note": "",
+        "severity": 1,
+        "disabled": 0,
+        "prom_for_duration": 60,
+        "prom_ql": "procstat_lookup_count == 0",
+        "prom_eval_interval": 15,
+        "enable_stime": "00:00",
+        "enable_etime": "23:59",
+        "enable_days_of_week": [
+          "1",
+          "2",
+          "3",
+          "4",
+          "5",
+          "6",
+          "0"
+        ],
+        "notify_recovered": 1,
+        "notify_channels": [
+          "email",
+          "dingtalk",
+          "wecom"
+        ],
+        "notify_repeat_step": 60,
+        "callbacks": [],
+        "runbook_url": "",
+        "append_tags": []
+    },
+    {
+        "name": "进程监控-进程句柄限制过小",
+        "note": "",
+        "severity": 3,
+        "disabled": 0,
+        "prom_for_duration": 60,
+        "prom_ql": "procstat_rlimit_num_fds_soft < 2048",
+        "prom_eval_interval": 15,
+        "enable_stime": "00:00",
+        "enable_etime": "23:59",
+        "enable_days_of_week": [
+          "1",
+          "2",
+          "3",
+          "4",
+          "5",
+          "6",
+          "0"
+        ],
+        "notify_recovered": 1,
+        "notify_channels": [
+          "email",
+          "dingtalk",
+          "wecom"
+        ],
+        "notify_repeat_step": 60,
+        "callbacks": [],
+        "runbook_url": "",
+        "append_tags": []
+    }
+]

etc/alerts/redis_by_categraf.json

@@ -0,0 +1,182 @@
+[
+    {
+      "name": "Redis Ping 延迟高（大于100毫秒）",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "redis_ping_use_seconds > 0.1",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=HighPingLatency"
+      ]
+    },
+    {
+      "name": "Redis内存使用率较高",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "redis_maxmemory > 0 and (redis_used_memory / redis_maxmemory) > 0.85",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisHighMemoryUsage"
+      ]
+    },
+    {
+      "name": "Redis出现拒绝连接",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "(rate(redis_rejected_connections[5m])) > 0",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisRejectedConnHigh"
+      ]
+    },
+    {
+      "name": "Redis刚刚有重启，请注意",
+      "note": "",
+      "severity": 3,
+      "disabled": 0,
+      "prom_for_duration": 0,
+      "prom_ql": "redis_uptime_in_seconds < 600",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisLowUptime"
+      ]
+    },
+    {
+      "name": "Redis较低的命中率",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "rate(redis_keyspace_hits[5m])\n/\n(rate(redis_keyspace_misses[5m]) + rate(redis_keyspace_hits[5m]))\n< 0.9",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisLowHitRatio"
+      ]
+    },
+    {
+      "name": "Redis驱逐率较高",
+      "note": "",
+      "severity": 2,
+      "disabled": 0,
+      "prom_for_duration": 60,
+      "prom_ql": "(sum(rate(redis_evicted_keys[5m])) / sum(redis_keyspace_keys)) > 0.1",
+      "prom_eval_interval": 15,
+      "enable_stime": "00:00",
+      "enable_etime": "23:59",
+      "enable_days_of_week": [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "0"
+      ],
+      "enable_in_bg": 0,
+      "notify_recovered": 1,
+      "notify_channels": [],
+      "notify_repeat_step": 60,
+      "recover_duration": 0,
+      "callbacks": [],
+      "runbook_url": "",
+      "append_tags": [
+        "alertname=RedisHighKeysEvictionRatio"
+      ]
+    }
+  ]

etc/dashboards/http_response_by_categraf.json

@@ -0,0 +1,19 @@
+[
+  {
+    "name": "HTTP探测",
+    "tags": "",
+    "configs": "",
+    "chart_groups": [
+      {
+        "name": "Default chart group",
+        "weight": 0,
+        "charts": [
+          {
+            "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(http_response_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(http_response_response_code) by (target)\",\"refId\":\"B\",\"legend\":\"status code\"},{\"expr\":\"max(http_response_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"},{\"expr\":\"max(http_response_cert_expire_timestamp) by (target) - time()\",\"refId\":\"D\",\"legend\":\"cert expire\"}],\"name\":\"URL Details\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}},{\"type\":\"special\",\"matcher\":{\"value\":\"D\"},\"properties\":{\"standardOptions\":{\"util\":\"humantimeSeconds\"}}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+            "weight": 0
+          }
+        ]
+      }
+    ]
+  }
+]

etc/dashboards/kafka_by_exporter.json

@@ -1,63 +1,362 @@
-[
-    {
-      "name": "Kafka - 模板",
-      "tags": "Kafka Prometheus ",
-      "configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(kafka_brokers,  instance)\"},{\"name\":\"job\",\"definition\":\"label_values(kafka_brokers,  job)\"}]}",
-      "chart_groups": [
-        {
-          "name": "overview",
-          "weight": 0,
-          "charts": [
+{
+    "name": "Kafka - 模板",
+    "tags": "Kafka Prometheus",
+    "configs": {
+        "var": [
             {
-              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"count(count by (topic) (kafka_topic_partitions))\"}],\"name\":\"topics\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":8,\"y\":0,\"i\":\"0\"}}",
-              "weight": 0
-            },
-            {
-              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_brokers\"}],\"name\":\"brokers\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":0,\"y\":0,\"i\":\"1\"}}",
-              "weight": 0
-            },
-            {
-              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(kafka_topic_partitions)\"}],\"name\":\"partitions\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
-              "weight": 0
+                "name": "cluster",
+                "definition": "label_values(kafka_brokers,  cluster)",
+                "type": "query"
             }
-          ]
-        },
-        {
-          "name": "throughput",
-          "weight": 1,
-          "charts": [
+        ],
+        "version": "2.0.0",
+        "panels": [
             {
-              "configs": "{\"targets\":[{\"expr\":\"sum(rate(kafka_topic_partition_current_offset{instance=\\\"$instance\\\"}[1m])) by (topic)\"}],\"name\":\"Message in per second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-              "weight": 0
+                "id": "51502c3a-dd6f-41c7-b8f1-87b88826c96e",
+                "type": "row",
+                "name": "overview",
+                "layout": {
+                    "h": 1,
+                    "w": 24,
+                    "x": 0,
+                    "y": 0,
+                    "i": "51502c3a-dd6f-41c7-b8f1-87b88826c96e",
+                    "isResizable": false
+                },
+                "collapsed": true
             },
             {
-              "configs": "{\"targets\":[{\"expr\":\"sum(kafka_consumer_lag_millis{instance=\\\"$instance\\\"}) by (consumergroup, topic) \",\"legend\":\"{{consumergroup}} (topic: {{topic}})\"}],\"name\":\"Latency by Consumer Group\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"humantimeMilliseconds\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"1\"}}",
-              "weight": 0
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "kafka_brokers{cluster=\"$cluster\"}"
+                    }
+                ],
+                "name": "brokers",
+                "custom": {
+                    "textMode": "value",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "colSpan": 1,
+                    "textSize": {
+                        "value": 50
+                    }
+                },
+                "options": {
+                    "standardOptions": {}
+                },
+                "version": "2.0.0",
+                "type": "stat",
+                "layout": {
+                    "h": 3,
+                    "w": 6,
+                    "x": 0,
+                    "y": 1,
+                    "i": "e2c1d271-ec43-4821-aa19-451e856af755",
+                    "isResizable": true
+                },
+                "id": "e2c1d271-ec43-4821-aa19-451e856af755"
             },
             {
-              "configs": "{\"targets\":[{\"expr\":\"sum(rate(kafka_consumergroup_current_offset{instance=\\\"$instance\\\"}[1m])) by (topic)\"}],\"name\":\"Message consume per second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"2\"}}",
-              "weight": 0
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "count(count by (topic) (kafka_topic_partitions{cluster=\"$cluster\"}))"
+                    }
+                ],
+                "name": "topics",
+                "custom": {
+                    "textMode": "value",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "colSpan": 1,
+                    "textSize": {
+                        "value": 50
+                    }
+                },
+                "options": {
+                    "standardOptions": {}
+                },
+                "version": "2.0.0",
+                "type": "stat",
+                "layout": {
+                    "h": 3,
+                    "w": 6,
+                    "x": 6,
+                    "y": 1,
+                    "i": "fd3a0b9f-fd67-4360-a94c-869fee7b5b98",
+                    "isResizable": true
+                },
+                "id": "fd3a0b9f-fd67-4360-a94c-869fee7b5b98"
             },
             {
-              "configs": "{\"targets\":[{\"expr\":\"sum(kafka_topic_partition_current_offset{instance=\\\"$instance\\\"}) by (topic) - sum(kafka_consumergroup_current_offset{instance=\\\"$instance\\\"}) by (topic) \",\"legend\":\"{{consumergroup}} (topic: {{topic}})\"}],\"name\":\"Lag by Consumer Group\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
-              "weight": 0
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "sum(kafka_topic_partitions{cluster=\"$cluster\"})"
+                    }
+                ],
+                "name": "partitions",
+                "custom": {
+                    "textMode": "value",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "colSpan": 1,
+                    "textSize": {
+                        "value": 50
+                    }
+                },
+                "options": {
+                    "standardOptions": {}
+                },
+                "version": "2.0.0",
+                "type": "stat",
+                "layout": {
+                    "h": 3,
+                    "w": 6,
+                    "x": 12,
+                    "y": 1,
+                    "i": "e228d857-746b-41b6-8d2d-0152453c46f4",
+                    "isResizable": true
+                },
+                "id": "e228d857-746b-41b6-8d2d-0152453c46f4"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "sum(kafka_topic_partition_replicas{cluster=\"$cluster\"})"
+                    }
+                ],
+                "name": "Replicas",
+                "custom": {
+                    "textMode": "valueAndName",
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "colSpan": 1,
+                    "textSize": {}
+                },
+                "options": {
+                    "standardOptions": {}
+                },
+                "version": "2.0.0",
+                "type": "stat",
+                "layout": {
+                    "h": 3,
+                    "w": 6,
+                    "x": 18,
+                    "y": 1,
+                    "i": "85438099-8d6b-4817-b9b9-1d0ed36029cd",
+                    "isResizable": true
+                },
+                "id": "85438099-8d6b-4817-b9b9-1d0ed36029cd"
+            },
+            {
+                "id": "0db4aac4-86cf-44cd-950e-6c6a99be8ff4",
+                "type": "row",
+                "name": "throughput",
+                "layout": {
+                    "h": 1,
+                    "w": 24,
+                    "x": 0,
+                    "y": 4,
+                    "i": "0db4aac4-86cf-44cd-950e-6c6a99be8ff4",
+                    "isResizable": false
+                },
+                "collapsed": true
+            },
+            {
+                "targets": [
+                    {
+                        "expr": "sum(rate(kafka_topic_partition_current_offset{cluster=\"$cluster\"}[1m])) by (topic)"
+                    }
+                ],
+                "name": "Messages produced per second",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 7,
+                    "w": 8,
+                    "x": 0,
+                    "y": 5,
+                    "i": "c2ec4036-3081-45cc-b672-024c6df93833",
+                    "isResizable": true
+                },
+                "id": "c2ec4036-3081-45cc-b672-024c6df93833"
+            },
+            {
+                "targets": [
+                    {
+                        "expr": "sum(rate(kafka_consumergroup_current_offset{cluster=\"$cluster\"}[1m])) by (topic)"
+                    }
+                ],
+                "name": "Messages consumed per second",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 7,
+                    "w": 8,
+                    "x": 8,
+                    "y": 5,
+                    "i": "7ad651a6-c12c-4d46-8d01-749fa776faef",
+                    "isResizable": true
+                },
+                "id": "7ad651a6-c12c-4d46-8d01-749fa776faef"
+            },
+            {
+                "targets": [
+                    {
+                        "expr": "sum(kafka_consumer_lag_millis{cluster=\"$cluster\"}) by (consumergroup, topic)",
+                        "legend": "{{consumergroup}} (topic: {{topic}})"
+                    }
+                ],
+                "name": "Latency by Consumer Group",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {
+                        "util": "humantimeMilliseconds"
+                    },
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 7,
+                    "w": 8,
+                    "x": 16,
+                    "y": 5,
+                    "i": "855aa8f5-0c51-42d4-b9a4-5460b7cd0f5a",
+                    "isResizable": true
+                },
+                "id": "855aa8f5-0c51-42d4-b9a4-5460b7cd0f5a"
+            },
+            {
+                "id": "20166830-7f85-4665-8f39-bf904267af29",
+                "type": "row",
+                "name": "patition/replicate",
+                "layout": {
+                    "h": 1,
+                    "w": 24,
+                    "x": 0,
+                    "y": 12,
+                    "i": "20166830-7f85-4665-8f39-bf904267af29",
+                    "isResizable": false
+                },
+                "collapsed": true
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "kafka_topic_partitions{cluster=\"$cluster\"}",
+                        "legend": "{{topic}}"
+                    }
+                ],
+                "name": "Partitions per Topic",
+                "custom": {
+                    "showHeader": true,
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "displayMode": "seriesToRows"
+                },
+                "options": {
+                    "standardOptions": {}
+                },
+                "overrides": [
+                    {}
+                ],
+                "version": "2.0.0",
+                "type": "table",
+                "layout": {
+                    "h": 7,
+                    "w": 12,
+                    "x": 0,
+                    "y": 13,
+                    "i": "8837a52e-c9eb-4afa-acc1-c3a5dac72d3b",
+                    "isResizable": true
+                },
+                "id": "8837a52e-c9eb-4afa-acc1-c3a5dac72d3b"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "kafka_topic_partition_under_replicated_partition{cluster=\"$cluster\"}",
+                        "legend": "{{topic}}-{{partition}}"
+                    }
+                ],
+                "name": "Partitions Under Replicated",
+                "description": "副本不同步预案\n1. Restart the Zookeeper leader.\n2. Restart the broker\\brokers that are not replicating some of the partitions.",
+                "custom": {
+                    "showHeader": true,
+                    "colorMode": "value",
+                    "calc": "lastNotNull",
+                    "displayMode": "seriesToRows"
+                },
+                "options": {
+                    "standardOptions": {}
+                },
+                "overrides": [
+                    {}
+                ],
+                "version": "2.0.0",
+                "type": "table",
+                "layout": {
+                    "h": 7,
+                    "w": 12,
+                    "x": 12,
+                    "y": 13,
+                    "i": "dd615767-dda7-4da6-b37f-0d484553aac6",
+                    "isResizable": true
+                },
+                "id": "dd615767-dda7-4da6-b37f-0d484553aac6"
             }
-          ]
-        },
-        {
-          "name": "patition/replicate",
-          "weight": 2,
-          "charts": [
-            {
-              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_topic_partitions{instance=\\\"$instance\\\"}\",\"legend\":\"{{topic}}\"}],\"name\":\"Partitions per Topic\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"seriesToRows\"},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
-              "weight": 0
-            },
-            {
-              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_topic_partition_under_replicated_partition\",\"legend\":\"{{topic}}-{{partition}}\"}],\"name\":\"Under Replicated\",\"description\":\"副本不同步预案\\n1. Restart the Zookeeper leader.\\n2. Restart the broker\\\\brokers that are not replicating some of the partitions.\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"seriesToRows\"},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
-              "weight": 0
-            }
-          ]
-        }
-      ]
+        ]
     }
-  ]
+}

etc/dashboards/mysql_by_categraf.json

@@ -0,0 +1,119 @@
+[
+    {
+      "name": "MySQL Overview - 模板",
+      "tags": "Prometheus MySQL",
+      "configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(mysql_global_status_uptime, instance)\"}]}",
+      "chart_groups": [
+        {
+          "name": "Basic Info",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"min(mysql_global_status_uptime{instance=~\\\"$instance\\\"})\"}],\"name\":\"MySQL Uptime\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":1800},\"result\":{\"color\":\"#ec7718\"}},{\"type\":\"range\",\"match\":{\"from\":1800},\"result\":{\"color\":\"#369603\"}}],\"standardOptions\":{\"util\":\"humantimeSeconds\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_queries{instance=~\\\"$instance\\\"}[5m])\"}],\"name\":\"Current QPS\",\"description\":\"mysql_global_status_queries\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":100},\"result\":{\"color\":\"#05a31f\"}},{\"type\":\"range\",\"match\":{\"from\":100},\"result\":{\"color\":\"#ea3939\"}}],\"standardOptions\":{\"decimals\":2}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"avg(mysql_global_variables_innodb_buffer_pool_size{instance=~\\\"$instance\\\"})\"}],\"name\":\"InnoDB Buffer Pool\",\"description\":\"**InnoDB Buffer Pool Size**\\n\\nInnoDB maintains a storage area called the buffer pool for caching data and indexes in memory.  Knowing how the InnoDB buffer pool works, and taking advantage of it to keep frequently accessed data in memory, is one of the most important aspects of MySQL tuning. The goal is to keep the working set in memory. In most cases, this should be between 60%-90% of available memory on a dedicated database host, but depends on many factors.\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"bytesIEC\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(increase(mysql_global_status_table_locks_waited{instance=~\\\"$instance\\\"}[5m]))\"}],\"name\":\"Table Locks Waited(5min)\",\"description\":\"**Table Locks**\\n\\nMySQL takes a number of different locks for varying reasons. In this graph we see how many Table level locks MySQL has requested from the storage engine. In the case of InnoDB, many times the locks could actually be row locks as it only takes table level locks in a few specific cases.\\n\\nIt is most useful to compare Locks Immediate and Locks Waited. If Locks waited is rising, it means you have lock contention. Otherwise, Locks Immediate rising and falling is normal activity.\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":1},\"result\":{\"color\":\"#e70d0d\"}},{\"type\":\"range\",\"match\":{\"to\":1},\"result\":{\"color\":\"#53b503\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Connections",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(mysql_global_status_threads_connected{instance=~\\\"$instance\\\"})\",\"legend\":\"Connections\"},{\"expr\":\"sum(mysql_global_status_max_used_connections{instance=~\\\"$instance\\\"})\",\"legend\":\"Max Used Connections\"},{\"expr\":\"sum(mysql_global_variables_max_connections{instance=~\\\"$instance\\\"})\",\"legend\":\"Max Connections\"},{\"expr\":\"sum(rate(mysql_global_status_aborted_connects{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Aborted Connections\"}],\"name\":\"MySQL Connections\",\"description\":\"**Max Connections** \\n\\nMax Connections is the maximum permitted number of simultaneous client connections. By default, this is 151. Increasing this value increases the number of file descriptors that mysqld requires. If the required number of descriptors are not available, the server reduces the value of Max Connections.\\n\\nmysqld actually permits Max Connections + 1 clients to connect. The extra connection is reserved for use by accounts that have the SUPER privilege, such as root.\\n\\nMax Used Connections is the maximum number of connections that have been in use simultaneously since the server started.\\n\\nConnections is the number of connection attempts (successful or not) to the MySQL server.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(mysql_global_status_threads_connected{instance=~\\\"$instance\\\"})\",\"legend\":\"Threads Connected\"},{\"expr\":\"sum(mysql_global_status_threads_running{instance=~\\\"$instance\\\"})\",\"legend\":\"Threads Running\"}],\"name\":\"MySQL Client Thread Activity\",\"description\":\"Threads Connected is the number of open connections, while Threads Running is the number of threads not sleeping.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Query Performance",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_created_tmp_tables{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Tables\"},{\"expr\":\"sum(rate(mysql_global_status_created_tmp_disk_tables{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Disk Tables\"},{\"expr\":\"sum(rate(mysql_global_status_created_tmp_files{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Files\"}],\"name\":\"MySQL Temporary Objects\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.64,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_select_full_join{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Full Join\"},{\"expr\":\"sum(rate(mysql_global_status_select_full_range_join{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Full Range Join\"},{\"expr\":\"sum(rate(mysql_global_status_select_range{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Range\"},{\"expr\":\"sum(rate(mysql_global_status_select_range_check{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Range Check\"},{\"expr\":\"sum(rate(mysql_global_status_select_scan{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Scan\"}],\"name\":\"MySQL Select Types\",\"description\":\"**MySQL Select Types**\\n\\nAs with most relational databases, selecting based on indexes is more efficient than scanning an entire table's data. Here we see the counters for selects not done with indexes.\\n\\n* ***Select Scan*** is how many queries caused full table scans, in which all the data in the table had to be read and either discarded or returned.\\n* ***Select Range*** is how many queries used a range scan, which means MySQL scanned all rows in a given range.\\n* ***Select Full Join*** is the number of joins that are not joined on an index, this is usually a huge performance hit.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"stack\":\"off\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.41},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_sort_rows{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Rows\"},{\"expr\":\"sum(rate(mysql_global_status_sort_range{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Range\"},{\"expr\":\"sum(rate(mysql_global_status_sort_merge_passes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Merge Passes\"},{\"expr\":\"sum(rate(mysql_global_status_sort_scan{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Scan\"}],\"name\":\"MySQL Sorts\",\"description\":\"**MySQL Sorts**\\n\\nDue to a query's structure, order, or other requirements, MySQL sorts the rows before returning them. For example, if a table is ordered 1 to 10 but you want the results reversed, MySQL then has to sort the rows to return 10 to 1.\\n\\nThis graph also shows when sorts had to scan a whole table or a given range of a table in order to return the results and which could not have been sorted via an index.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_slow_queries{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Slow Queries\"}],\"name\":\"MySQL Slow Queries\",\"description\":\"**MySQL Slow Queries**\\n\\nSlow queries are defined as queries being slower than the long_query_time setting. For example, if you have long_query_time set to 3, all queries that take longer than 3 seconds to complete will show on this graph.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"bars\",\"stack\":\"off\",\"fillOpacity\":0.81},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Network",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_bytes_received{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Inbound\"},{\"expr\":\"sum(rate(mysql_global_status_bytes_sent{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Outbound\"}],\"name\":\"MySQL Network Traffic\",\"description\":\"**MySQL Network Traffic**\\n\\nHere we can see how much network traffic is generated by MySQL. Outbound is network traffic sent from MySQL and Inbound is network traffic MySQL has received.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesSI\",\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Commands, Handlers",
+          "weight": 4,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"topk(10, rate(mysql_global_status_commands_total{instance=~\\\"$instance\\\"}[5m])>0)\",\"legend\":\"Com_{{command}}\"}],\"name\":\"Top Command Counters\",\"description\":\"**Top Command Counters**\\n\\nThe Com_{{xxx}} statement counter variables indicate the number of times each xxx statement has been executed. There is one status variable for each type of statement. For example, Com_delete and Com_update count [``DELETE``](https://dev.mysql.com/doc/refman/5.7/en/delete.html) and [``UPDATE``](https://dev.mysql.com/doc/refman/5.7/en/update.html) statements, respectively. Com_delete_multi and Com_update_multi are similar but apply to [``DELETE``](https://dev.mysql.com/doc/refman/5.7/en/delete.html) and [``UPDATE``](https://dev.mysql.com/doc/refman/5.7/en/update.html) statements that use multiple-table syntax.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.2,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_handlers_total{instance=~\\\"$instance\\\", handler!~\\\"commit|rollback|savepoint.*|prepare\\\"}[5m])\",\"legend\":\"{{handler}}\"}],\"name\":\"MySQL Handlers\",\"description\":\"**MySQL Handlers**\\n\\nHandler statistics are internal statistics on how MySQL is selecting, updating, inserting, and modifying rows, tables, and indexes.\\n\\nThis is in fact the layer between the Storage Engine and MySQL.\\n\\n* `read_rnd_next` is incremented when the server performs a full table scan and this is a counter you don't really want to see with a high value.\\n* `read_key` is incremented when a read is done with an index.\\n* `read_next` is incremented when the storage engine is asked to 'read the next index entry'. A high value means a lot of index scans are being done.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":3},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_handlers_total{instance=~\\\"$instance\\\", handler=~\\\"commit|rollback|savepoint.*|prepare\\\"}[5m])\",\"legend\":\"{{handler}}\"}],\"name\":\"MySQL Transaction Handlers\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Open Files",
+          "weight": 5,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"mysql_global_variables_open_files_limit{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Files Limit\"},{\"expr\":\"mysql_global_status_open_files{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Files\"}],\"name\":\"MySQL Open Files\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Table Openings",
+          "weight": 6,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_table_open_cache_hits{instance=~\\\"$instance\\\"}[5m])\\n/\\n(\\nrate(mysql_global_status_table_open_cache_hits{instance=~\\\"$instance\\\"}[5m])\\n+\\nrate(mysql_global_status_table_open_cache_misses{instance=~\\\"$instance\\\"}[5m])\\n)\",\"legend\":\"Table Open Cache Hit Ratio\"}],\"name\":\"Table Open Cache Hit Ratio  Mysql 5.6.6+\",\"description\":\"**MySQL Table Open Cache Status**\\n\\nThe recommendation is to set the `table_open_cache_instances` to a loose correlation to virtual CPUs, keeping in mind that more instances means the cache is split more times. If you have a cache set to 500 but it has 10 instances, each cache will only have 50 cached.\\n\\nThe `table_definition_cache` and `table_open_cache` can be left as default as they are auto-sized MySQL 5.6 and above (ie: do not set them to any value).\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"percentUnit\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"mysql_global_status_open_tables{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Tables\"},{\"expr\":\"mysql_global_variables_table_open_cache{instance=~\\\"$instance\\\"}\",\"legend\":\"Table Open Cache\"}],\"name\":\"MySQL Open Tables\",\"description\":\"**MySQL Open Tables**\\n\\nThe recommendation is to set the `table_open_cache_instances` to a loose correlation to virtual CPUs, keeping in mind that more instances means the cache is split more times. If you have a cache set to 500 but it has 10 instances, each cache will only have 50 cached.\\n\\nThe `table_definition_cache` and `table_open_cache` can be left as default as they are auto-sized MySQL 5.6 and above (ie: do not set them to any value).\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

etc/dashboards/n9e_server.json

@@ -0,0 +1,232 @@
+{
+    "name": "夜莺大盘",
+    "tags": "",
+    "configs": {
+        "var": [],
+        "panels": [
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "rate(n9e_server_samples_received_total[1m])"
+                    }
+                ],
+                "name": "每秒接收的数据点个数",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 0,
+                    "i": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4",
+                    "isResizable": true
+                },
+                "id": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "rate(n9e_server_alerts_total[10m])"
+                    }
+                ],
+                "name": "每秒产生的告警事件个数",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 0,
+                    "i": "47fc6252-9cc8-4b53-8e27-0c5c59a47269",
+                    "isResizable": true
+                },
+                "id": "f70dcb8b-b58b-4ef9-9e48-f230d9e17140"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_alert_queue_size"
+                    }
+                ],
+                "name": "告警事件内存队列长度",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "none"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 4,
+                    "i": "ad1af16c-de0c-45f4-8875-cea4e85d51d0",
+                    "isResizable": true
+                },
+                "id": "caf23e58-d907-42b0-9ed6-722c8c6f3c5f"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_http_request_duration_seconds_sum/n9e_server_http_request_duration_seconds_count"
+                    }
+                ],
+                "name": "数据接收接口平均响应时间（单位：秒）",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "noraml"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 4,
+                    "i": "64c3abc2-404c-4462-a82f-c109a21dac91",
+                    "isResizable": true
+                },
+                "id": "6b8d2db1-efca-4b9e-b429-57a9d2272bc5"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "n9e_server_sample_queue_size"
+                    }
+                ],
+                "name": "内存数据队列长度",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "off"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 0,
+                    "y": 8,
+                    "i": "1c7da942-58c2-40dc-b42f-983e4a35b89b",
+                    "isResizable": true
+                },
+                "id": "bd41677d-40d3-482e-bb6e-fbd25df46d87"
+            },
+            {
+                "targets": [
+                    {
+                        "refId": "A",
+                        "expr": "avg(n9e_server_forward_duration_seconds_sum/n9e_server_forward_duration_seconds_count)"
+                    }
+                ],
+                "name": "数据发往TSDB平均耗时（单位：秒）",
+                "options": {
+                    "tooltip": {
+                        "mode": "all",
+                        "sort": "desc"
+                    },
+                    "legend": {
+                        "displayMode": "hidden"
+                    },
+                    "standardOptions": {},
+                    "thresholds": {}
+                },
+                "custom": {
+                    "drawStyle": "lines",
+                    "lineInterpolation": "smooth",
+                    "fillOpacity": 0.5,
+                    "stack": "noraml"
+                },
+                "version": "2.0.0",
+                "type": "timeseries",
+                "layout": {
+                    "h": 4,
+                    "w": 12,
+                    "x": 12,
+                    "y": 8,
+                    "i": "eed94a0b-954f-48ac-82e5-a2eada1c8a3d",
+                    "isResizable": true
+                },
+                "id": "c8642e72-f384-46a5-8410-1e6be2953c3c"
+            }
+        ],
+        "version": "2.0.0"
+    }
+}

etc/dashboards/net_response_by_categraf.json

@@ -0,0 +1,19 @@
+[
+    {
+      "name": "TCP探测",
+      "tags": "",
+      "configs": "",
+      "chart_groups": [
+        {
+          "name": "Default chart group",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(net_response_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(net_response_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"}],\"name\":\"Targets\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

etc/dashboards/oracle_by_categraf.json

@@ -0,0 +1,127 @@
+[
+    {
+      "name": "Oracle - 模板",
+      "tags": "Telegraf",
+      "configs": "{\"var\":[{\"name\":\"ident\",\"definition\":\"label_values(oracle_up,ident)\",\"options\":[\"tt-fc-log00.nj\"]},{\"name\":\"instance\",\"definition\":\"label_values(oracle_up{ident=\\\"$ident\\\"},instance)\"}]}",
+      "chart_groups": [
+        {
+          "name": "Activities",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_execute_count_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"execute count / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"decimals\":1}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_user_commits_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"user commits / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_user_rollbacks_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"user rollbacks / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_up{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"status\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":1},\"result\":{\"text\":\"UP\",\"color\":\"#5ea70f\"}},{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"DOWN\",\"color\":\"#f60f0f\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Waits",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_wait_time_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{wait_class}}\"}],\"name\":\"Time waited\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Tablespace",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_tablespace_bytes{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}/oracle_tablespace_max_bytes{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{tablespace}}\"}],\"name\":\"Used Percent\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"percentUnit\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_tablespace_free{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{tablespace}}\"}],\"name\":\"Free space\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "IO and TPS",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_io_requests_per_second_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_user_transaction_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"TPS\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_io_megabytes_per_second_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}*1024*1024\"}],\"name\":\"IO Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Connections",
+          "weight": 4,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sessions_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\",status=\\\"ACTIVE\\\"}\",\"legend\":\"\"}],\"name\":\"Sessions\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Hit Ratio",
+          "weight": 5,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_buffer_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Buffer Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_redo_allocation_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Redo Allocation Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_row_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Row Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_library_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Library Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Physical Read Write",
+          "weight": 6,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_bytes_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Bytes_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical Read Write Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_total_bytes_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Total_Bytes_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical Read Write Total Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_io_requests_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_IO_Requests_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical RW IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_total_io_requests_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Total_IO_Requests_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical RW Total IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

etc/dashboards/ping_by_categraf.json

@@ -0,0 +1,19 @@
+[
+    {
+      "name": "PING探测",
+      "tags": "",
+      "configs": "",
+      "chart_groups": [
+        {
+          "name": "Default chart group",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(ping_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(ping_percent_packet_loss) by (target)\",\"refId\":\"B\",\"legend\":\"Packet Loss %\"},{\"expr\":\"max(httpresponse_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"}],\"name\":\"Ping\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

etc/dashboards/rabbitmq_by_categraf.json

@@ -0,0 +1,221 @@
+[
+    {
+      "name": "RabbitMQ 3.8+",
+      "tags": "",
+      "configs": "{\"var\":[{\"definition\":\"label_values(rabbitmq_identity_info, rabbitmq_cluster)\",\"name\":\"rabbitmq_cluster\"}]}",
+      "chart_groups": [
+        {
+          "name": "Overview",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_ready * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Ready messages\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10000},\"result\":{\"color\":\"#4a90e2\"}},{\"type\":\"range\",\"match\":{\"from\":100000},\"result\":{\"color\":\"#f50a0a\"}},{\"type\":\"range\",\"match\":{\"to\":9999},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":7,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Incoming messages / s\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":50},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":5,\"x\":7,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channels * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) - sum(rabbitmq_channel_consumers * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Publishers\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_connections * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Connections\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queues * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Queues\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":0,\"i\":\"4\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_unacked * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Unacknowledged messages\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":99},\"result\":{\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"from\":100},\"result\":{\"color\":\"#4a90e2\"}},{\"type\":\"range\",\"match\":{\"from\":500},\"result\":{\"color\":\"#d0021b\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":7,\"x\":0,\"y\":1,\"i\":\"5\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_redelivered_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_get_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_get_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Outgoing messages / s\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":50},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":5,\"x\":7,\"y\":1,\"i\":\"6\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channel_consumers * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Consumers\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":1,\"i\":\"7\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channels * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Channels\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":1,\"i\":\"8\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_build_info * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Nodes\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":null,\"from\":3},\"result\":{\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"from\":8},\"result\":{\"color\":\"#e70909\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":1,\"i\":\"9\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Nodes",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_build_info * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"nodes\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelsOfSeriesToRows\",\"columns\":[\"rabbitmq_cluster\",\"rabbitmq_node\",\"rabbitmq_version\",\"erlang_version\"]},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":1,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_resident_memory_limit_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_resident_memory_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Memory available before publishers blocked\",\"description\":\"If the value is zero or less, the memory alarm will be triggered and all publishing connections across all cluster nodes will be blocked.\\n\\nThis value can temporarily go negative because the memory alarm is triggered with a slight delay.\\n\\nThe kernel's view of the amount of memory used by the node can differ from what the node itself can observe. This means that this value can be negative for a sustained period of time.\\n\\nBy default nodes use resident set size (RSS) to compute how much memory they use. This strategy can be changed (see the guides below).\\n\\n* [Alarms](https://www.rabbitmq.com/alarms.html)\\n* [Memory Alarms](https://www.rabbitmq.com/memory.html)\\n* [Reasoning About Memory Use](https://www.rabbitmq.com/memory-use.html)\\n* [Blocked Connection Notifications](https://www.rabbitmq.com/connection-blocked.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":1,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_disk_space_available_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Disk space available before publishers blocked\",\"description\":\"This metric is reported for the partition where the RabbitMQ data directory is stored.\\n\\nIf the value is zero or less, the disk alarm will be triggered and all publishing connections across all cluster nodes will be blocked.\\n\\nThis value can temporarily go negative because the free disk space alarm is triggered with a slight delay.\\n\\n* [Alarms](https://www.rabbitmq.com/alarms.html)\\n* [Disk Space Alarms](https://www.rabbitmq.com/disk-alarms.html)\\n* [Disk Space](https://www.rabbitmq.com/production-checklist.html#resource-limits-disk-space)\\n* [Persistence Configuration](https://www.rabbitmq.com/persistence-conf.html)\\n* [Blocked Connection Notifications](https://www.rabbitmq.com/connection-blocked.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":1,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_process_max_fds * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_open_fds * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"File descriptors available\",\"description\":\"When this value reaches zero, new connections will not be accepted and disk write operations may fail.\\n\\nClient libraries, peer nodes and CLI tools will not be able to connect when the node runs out of available file descriptors.\\n\\n* [Open File Handles Limit](https://www.rabbitmq.com/production-checklist.html#resource-limits-file-handle-limit)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":1,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_process_max_tcp_sockets * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_open_tcp_sockets * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"TCP sockets available\",\"description\":\"When this value reaches zero, new connections will not be accepted.\\n\\nClient libraries, peer nodes and CLI tools will not be able to connect when the node runs out of available file descriptors.\\n\\n* [Networking and RabbitMQ](https://www.rabbitmq.com/networking.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":2,\"i\":\"4\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "QUEUED MESSAGES",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_ready * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages ready to be delivered to consumers\",\"description\":\"Total number of ready messages ready to be delivered to consumers.\\n\\nAim to keep this value as low as possible. RabbitMQ behaves best when messages are flowing through it. It's OK for publishers to occasionally outpace consumers, but the expectation is that consumers will eventually process all ready messages.\\n\\nIf this metric keeps increasing, your system will eventually run out of memory and/or disk space. Consider using TTL or Queue Length Limit to prevent unbounded message growth.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\\n* [Queue Length Limit](https://www.rabbitmq.com/maxlength.html)\\n* [Time-To-Live and Expiration](https://www.rabbitmq.com/ttl.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_unacked * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages pending consumer acknowledgement\",\"description\":\"The total number of messages that are either in-flight to consumers, currently being processed by consumers or simply waiting for the consumer acknowledgements to be processed by the queue. Until the queue processes the message acknowledgement, the message will remain unacknowledged.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Confirms and Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "INCOMING MESSAGES",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages published / s\",\"description\":\"The incoming message rate before any routing rules are applied.\\n\\nIf this value is lower than the number of messages published to queues, it may indicate that some messages are delivered to more than one queue.\\n\\nIf this value is higher than the number of messages published to queues, messages cannot be routed and will either be dropped or returned to publishers.\\n\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_confirmed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages confirmed to publishers / s\",\"description\":\"The rate of messages confirmed by the broker to publishers. Publishers must opt-in to receive message confirmations.\\n\\nIf this metric is consistently at zero it may suggest that publisher confirms are not used by clients. The safety of published messages is likely to be at risk.\\n\\n* [Publisher Confirms](https://www.rabbitmq.com/confirms.html#publisher-confirms)\\n* [Publisher Confirms and Data Safety](https://www.rabbitmq.com/publishers.html#data-safety)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queue_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages routed to queues / s\",\"description\":\"The rate of messages received from publishers and successfully routed to the master queue replicas.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":1,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unconfirmed[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages unconfirmed to publishers / s\",\"description\":\"The rate of messages received from publishers that have publisher confirms enabled and the broker has not confirmed yet.\\n\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\\n* [Confirms and Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":1,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unroutable_dropped_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Unroutable messages dropped / s\",\"description\":\"The rate of messages that cannot be routed and are dropped. \\n\\nAny value above zero means message loss and likely suggests a routing problem on the publisher end.\\n\\n* [Unroutable Message Handling](https://www.rabbitmq.com/publishers.html#unroutable)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":2,\"i\":\"4\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unroutable_returned_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Unroutable messages returned to publishers / s\",\"description\":\"The rate of messages that cannot be routed and are returned back to publishers.\\n\\nSustained values above zero may indicate a routing problem on the publisher end.\\n\\n* [Unroutable Message Handling](https://www.rabbitmq.com/publishers.html#unroutable)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":2,\"i\":\"5\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "OUTGOING MESSAGES",
+          "weight": 4,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(\\n  (rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\n  (rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\\n) by(rabbitmq_node)\"}],\"name\":\"Messages delivered / s\",\"description\":\"The rate of messages delivered to consumers. It includes messages that have been redelivered.\\n\\nThis metric does not include messages that have been fetched by consumers using `basic.get` (consumed by polling).\\n\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_redelivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages redelivered / s\",\"description\":\"The rate of messages that have been redelivered to consumers. It includes messages that have been requeued automatically and redelivered due to channel exceptions or connection closures.\\n\\nHaving some redeliveries is expected, but if this metric is consistently non-zero, it is worth investigating why.\\n\\n* [Negative Acknowledgement and Requeuing of Deliveries](https://www.rabbitmq.com/confirms.html#consumer-nacks-requeue)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages delivered with manual ack / s\",\"description\":\"The rate of message deliveries to consumers that use manual acknowledgement mode.\\n\\nWhen this mode is used, RabbitMQ waits for consumers to acknowledge messages before more messages can be delivered.\\n\\nThis is the safest way of consuming messages.\\n\\n* [Consumer Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":1,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages delivered auto ack / s\",\"description\":\"The rate of message deliveries to consumers that use automatic acknowledgement mode.\\n\\nWhen this mode is used, RabbitMQ does not wait for consumers to acknowledge message deliveries.\\n\\nThis mode is fire-and-forget and does not offer any delivery safety guarantees. It tends to provide higher throughput and it may lead to consumer overload  and higher consumer memory usage.\\n\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":1,\"i\":\"3\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_acked_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages acknowledged / s\",\"description\":\"The rate of message acknowledgements coming from consumers that use manual acknowledgement mode.\\n\\n* [Consumer Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":2,\"i\":\"4\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations with auto ack / s\",\"description\":\"The rate of messages delivered to polling consumers that use automatic acknowledgement mode.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":2,\"i\":\"5\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_empty_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations that yield no result / s\",\"description\":\"The rate of polling consumer operations that yield no result.\\n\\nAny value above zero means that RabbitMQ resources are wasted by polling consumers.\\n\\nCompare this metric to the other polling consumer metrics to see the inefficiency rate.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":3,\"i\":\"6\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations with manual ack / s\",\"description\":\"The rate of messages delivered to polling consumers that use manual acknowledgement mode.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":3,\"i\":\"7\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "QUEUES",
+          "weight": 5,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_queues * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total queues\",\"description\":\"Total number of queue masters  per node. \\n\\nThis metric makes it easy to see sub-optimal queue distribution in a cluster.\\n\\n* [Queue Masters, Data Locality](https://www.rabbitmq.com/ha.html#master-migration-data-locality)\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_declared_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues declared / s\",\"description\":\"The rate of queue declarations performed by clients.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_created_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues created / s\",\"description\":\"The rate of new queues created (as opposed to redeclarations).\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_deleted_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues deleted / s\",\"description\":\"The rate of queues deleted.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "CHANNELS",
+          "weight": 6,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_channels * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total channels\",\"description\":\"Total number of channels on all currently opened connections.\\n\\nIf this metric grows monotonically it is highly likely a channel leak in one of the applications. Confirm channel leaks by using the _Channels opened_ and _Channels closed_ metrics.\\n\\n* [Channel Leak](https://www.rabbitmq.com/channels.html#channel-leaks)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channels_opened_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Channels opened / s\",\"description\":\"The rate of new channels opened by applications across all connections. Channels are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of channel churn or mass connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [High Channel Churn](https://www.rabbitmq.com/channels.html#high-channel-churn)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channels_closed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Channels closed / s\",\"description\":\"The rate of channels closed by applications across all connections. Channels are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of channel churn or mass connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [High Channel Churn](https://www.rabbitmq.com/channels.html#high-channel-churn)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "CONNECTIONS",
+          "weight": 7,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_connections_closed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Connections closed / s\",\"description\":\"The rate of connections closed. Connections are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of connection churn or mass connection recovery.\\n\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_connections * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total connections\",\"description\":\"Total number of client connections.\\n\\nIf this metric grows monotonically it is highly likely a connection leak in one of the applications. Confirm connection leaks by using the _Connections opened_ and _Connections closed_ metrics.\\n\\n* [Connection Leak](https://www.rabbitmq.com/connections.html#monitoring)\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_connections_opened_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Connections opened / s\",\"description\":\"The rate of new connections opened by clients. Connections are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of connection churn or mass connection recovery.\\n\\n* [Connection Leak](https://www.rabbitmq.com/connections.html#monitoring)\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

etc/dashboards/redis_by_categraf.json

@@ -0,0 +1,77 @@
+[
+    {
+      "name": "Redis Overview - 模板",
+      "tags": "Redis Prometheus",
+      "configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(redis_uptime_in_seconds,instance)\",\"selected\":\"10.206.0.16:6379\"}]}",
+      "chart_groups": [
+        {
+          "name": "Basic Info",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"min(redis_uptime_in_seconds{instance=~\\\"$instance\\\"})\"}],\"name\":\"Redis Uptime\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"humantimeSeconds\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(redis_connected_clients{instance=~\\\"$instance\\\"})\"}],\"name\":\"Connected Clients\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"redis_used_memory{instance=~\\\"$instance\\\"}\"}],\"name\":\"Memory Used\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":128000000},\"result\":{\"color\":\"#079e05\"}},{\"type\":\"range\",\"match\":{\"from\":128000000},\"result\":{\"color\":\"#f10909\"}}],\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":0}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"redis_maxmemory{instance=~\\\"$instance\\\"}\"}],\"name\":\"Max Memory Limit\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"bytesIEC\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Commands",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"rate(redis_total_commands_processed{instance=~\\\"$instance\\\"}[5m])\"}],\"name\":\"Commands Executed / sec\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"irate(redis_keyspace_hits{instance=~\\\"$instance\\\"}[5m])\",\"legend\":\"hits\"},{\"expr\":\"irate(redis_keyspace_misses{instance=~\\\"$instance\\\"}[5m])\",\"legend\":\"misses\"}],\"name\":\"Hits / Misses per Sec\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"noraml\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"topk(5, irate(redis_cmdstat_calls{instance=~\\\"$instance\\\"} [1m]))\",\"legend\":\"{{command}}\"}],\"name\":\"Top Commands\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Keys",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum (redis_keyspace_keys{instance=~\\\"$instance\\\"}) by (db)\",\"legend\":\"{{db}}\"}],\"name\":\"Total Items per DB\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(redis_expired_keys{instance=~\\\"$instance\\\"}[5m])) by (instance)\",\"legend\":\"expired\"},{\"expr\":\"sum(rate(redis_evicted_keys{instance=~\\\"$instance\\\"}[5m])) by (instance)\",\"legend\":\"evicted\"}],\"name\":\"Expired / Evicted\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(redis_keyspace_keys{instance=~\\\"$instance\\\"}) - sum(redis_keyspace_expires{instance=~\\\"$instance\\\"}) \",\"legend\":\"not expiring\"},{\"expr\":\"sum(redis_keyspace_expires{instance=~\\\"$instance\\\"}) \",\"legend\":\"expiring\"}],\"name\":\"Expiring vs Not-Expiring Keys\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"noraml\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "Network",
+          "weight": 3,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"expr\":\"sum(rate(redis_total_net_input_bytes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"input\"},{\"expr\":\"sum(rate(redis_total_net_output_bytes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"output\"}],\"name\":\"Network I/O\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

etc/dashboards/tomcat_by_categraf.json

@@ -0,0 +1,63 @@
+[
+    {
+      "name": "Tomcat - 模板",
+      "tags": "Categraf",
+      "configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(tomcat_up, instance)\"}],\"links\":[{\"title\":\"n9e\",\"url\":\"https://n9e.gitee.io/\",\"targetBlank\":true}]}",
+      "chart_groups": [
+        {
+          "name": "connector",
+          "weight": 0,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_bytes_sent{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"sent\"},{\"expr\":\"rate(tomcat_connector_bytes_received{instance=\\\"$instance\\\"}[1m])\",\"refId\":\"B\",\"legend\":\"received\"}],\"name\":\"Traffic Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_request_count{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"tomcat_connector_request_count\"},{\"expr\":\"rate(tomcat_connector_error_count{instance=\\\"$instance\\\"}[1m])\",\"refId\":\"B\",\"legend\":\"tomcat_connector_error_count\"}],\"name\":\"Request count / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_connector_max_threads{instance=\\\"$instance\\\"}\",\"legend\":\"max_threads\"},{\"expr\":\"tomcat_connector_current_thread_count{instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"current_thread_count\"},{\"expr\":\"tomcat_connector_current_threads_busy{instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"current_threads_busy\"}],\"name\":\"Tread\",\"description\":\"max_threads: The maximum number of allowed worker threads.\\ncurrent_thread_count: The number of threads managed by the thread pool\\ncurrent_threads_busy: The number of threads that are in use\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_processing_time{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"{{name}}-processing_time\"}],\"name\":\"Processing time\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "mem used",
+          "weight": 1,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memory_max{instance=\\\"$instance\\\"}\",\"legend\":\"max\"},{\"expr\":\"tomcat_jvm_memory_total{instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"used\"},{\"expr\":\"tomcat_jvm_memory_free{instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"free\"}],\"name\":\"Mem Used\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            }
+          ]
+        },
+        {
+          "name": "memorypool",
+          "weight": 2,
+          "charts": [
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_used{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Used\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_max{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Max\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_committed{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Committed\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
+              "weight": 0
+            },
+            {
+              "configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_init{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Init\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
+              "weight": 0
+            }
+          ]
+        }
+      ]
+    }
+  ]

etc/metrics.yaml

@@ -1,131 +1,383 @@
-cpu_usage_idle: CPU空闲率（单位：%）
-cpu_usage_active: CPU使用率（单位：%）
-cpu_usage_system: CPU内核态时间占比（单位：%）
-cpu_usage_user: CPU用户态时间占比（单位：%）
-cpu_usage_nice: 低优先级用户态CPU时间占比，也就是进程nice值被调整为1-19之间的CPU时间。这里注意，nice可取值范围是-20到19，数值越大，优先级反而越低（单位：%）
-cpu_usage_iowait: CPU等待I/O的时间占比（单位：%）
-cpu_usage_irq: CPU处理硬中断的时间占比（单位：%）
-cpu_usage_softirq: CPU处理软中断的时间占比（单位：%）
-cpu_usage_steal: 在虚拟机环境下有该指标，表示CPU被其他虚拟机争用的时间占比，超过20就表示争抢严重（单位：%）
-cpu_usage_guest: 通过虚拟化运行其他操作系统的时间，也就是运行虚拟机的CPU时间占比（单位：%）
-cpu_usage_guest_nice: 以低优先级运行虚拟机的时间占比（单位：%）
+zh:
+  cpu_usage_idle: CPU空闲率（单位：%）
+  cpu_usage_active: CPU使用率（单位：%）
+  cpu_usage_system: CPU内核态时间占比（单位：%）
+  cpu_usage_user: CPU用户态时间占比（单位：%）
+  cpu_usage_nice: 低优先级用户态CPU时间占比，也就是进程nice值被调整为1-19之间的CPU时间。这里注意，nice可取值范围是-20到19，数值越大，优先级反而越低（单位：%）
+  cpu_usage_iowait: CPU等待I/O的时间占比（单位：%）
+  cpu_usage_irq: CPU处理硬中断的时间占比（单位：%）
+  cpu_usage_softirq: CPU处理软中断的时间占比（单位：%）
+  cpu_usage_steal: 在虚拟机环境下有该指标，表示CPU被其他虚拟机争用的时间占比，超过20就表示争抢严重（单位：%）
+  cpu_usage_guest: 通过虚拟化运行其他操作系统的时间，也就是运行虚拟机的CPU时间占比（单位：%）
+  cpu_usage_guest_nice: 以低优先级运行虚拟机的时间占比（单位：%）
 
-disk_free: 硬盘分区剩余量（单位：byte）
-disk_used: 硬盘分区使用量（单位：byte）
-disk_used_percent: 硬盘分区使用率（单位：%）
-disk_total: 硬盘分区总量（单位：byte）
-disk_inodes_free: 硬盘分区inode剩余量 
-disk_inodes_used: 硬盘分区inode使用量
-disk_inodes_total: 硬盘分区inode总量
+  disk_free: 硬盘分区剩余量（单位：byte）
+  disk_used: 硬盘分区使用量（单位：byte）
+  disk_used_percent: 硬盘分区使用率（单位：%）
+  disk_total: 硬盘分区总量（单位：byte）
+  disk_inodes_free: 硬盘分区inode剩余量
+  disk_inodes_used: 硬盘分区inode使用量
+  disk_inodes_total: 硬盘分区inode总量
 
-diskio_io_time: 从设备视角来看I/O请求总时间，队列中有I/O请求就计数（单位：毫秒），counter类型，需要用函数求rate才有使用价值
-diskio_iops_in_progress: 已经分配给设备驱动且尚未完成的IO请求，不包含在队列中但尚未分配给设备驱动的IO请求，gauge类型
-diskio_merged_reads: 相邻读请求merge读的次数，counter类型
-diskio_merged_writes: 相邻写请求merge写的次数，counter类型
-diskio_read_bytes: 读取的byte数量，counter类型，需要用函数求rate才有使用价值
-diskio_read_time: 读请求总时间（单位：毫秒），counter类型，需要用函数求rate才有使用价值
-diskio_reads: 读请求次数，counter类型，需要用函数求rate才有使用价值
-diskio_weighted_io_time: 从I/O请求视角来看I/O等待总时间，如果同时有多个I/O请求，时间会叠加（单位：毫秒）
-diskio_write_bytes: 写入的byte数量，counter类型，需要用函数求rate才有使用价值
-diskio_write_time: 写请求总时间（单位：毫秒），counter类型，需要用函数求rate才有使用价值
-diskio_writes: 写请求次数，counter类型，需要用函数求rate才有使用价值
+  diskio_io_time: 从设备视角来看I/O请求总时间，队列中有I/O请求就计数（单位：毫秒），counter类型，需要用函数求rate才有使用价值
+  diskio_iops_in_progress: 已经分配给设备驱动且尚未完成的IO请求，不包含在队列中但尚未分配给设备驱动的IO请求，gauge类型
+  diskio_merged_reads: 相邻读请求merge读的次数，counter类型
+  diskio_merged_writes: 相邻写请求merge写的次数，counter类型
+  diskio_read_bytes: 读取的byte数量，counter类型，需要用函数求rate才有使用价值
+  diskio_read_time: 读请求总时间（单位：毫秒），counter类型，需要用函数求rate才有使用价值
+  diskio_reads: 读请求次数，counter类型，需要用函数求rate才有使用价值
+  diskio_weighted_io_time: 从I/O请求视角来看I/O等待总时间，如果同时有多个I/O请求，时间会叠加（单位：毫秒）
+  diskio_write_bytes: 写入的byte数量，counter类型，需要用函数求rate才有使用价值
+  diskio_write_time: 写请求总时间（单位：毫秒），counter类型，需要用函数求rate才有使用价值
+  diskio_writes: 写请求次数，counter类型，需要用函数求rate才有使用价值
 
-kernel_boot_time: 内核启动时间
-kernel_context_switches: 内核上下文切换次数
-kernel_entropy_avail: linux系统内部的熵池
-kernel_interrupts: 内核中断次数
-kernel_processes_forked: fork的进程数
+  kernel_boot_time: 内核启动时间
+  kernel_context_switches: 内核上下文切换次数
+  kernel_entropy_avail: linux系统内部的熵池
+  kernel_interrupts: 内核中断次数
+  kernel_processes_forked: fork的进程数
 
-mem_active: 活跃使用的内存总数(包括cache和buffer内存)
-mem_available: 应用程序可用内存数
-mem_available_percent: 内存剩余百分比(0~100)
-mem_buffered: 用来给文件做缓冲大小
-mem_cached: 被高速缓冲存储器（cache memory）用的内存的大小（等于 diskcache minus SwapCache ）
-mem_commit_limit: 根据超额分配比率（'vm.overcommit_ratio'），这是当前在系统上分配可用的内存总量，这个限制只是在模式2('vm.overcommit_memory')时启用
-mem_committed_as: 目前在系统上分配的内存量。是所有进程申请的内存的总和
-mem_dirty: 等待被写回到磁盘的内存大小
-mem_free: 空闲内存数
-mem_high_free: 未被使用的高位内存大小
-mem_high_total: 高位内存总大小（Highmem是指所有内存高于860MB的物理内存,Highmem区域供用户程序使用，或用于页面缓存。该区域不是直接映射到内核空间。内核必须使用不同的手法使用该段内存）
-mem_huge_page_size: 每个大页的大小
-mem_huge_pages_free: 池中尚未分配的 HugePages 数量
-mem_huge_pages_total: 预留HugePages的总个数
-mem_inactive: 空闲的内存数(包括free和avalible的内存)
-mem_low_free: 未被使用的低位大小
-mem_low_total: 低位内存总大小,低位可以达到高位内存一样的作用，而且它还能够被内核用来记录一些自己的数据结构
-mem_mapped: 设备和文件等映射的大小
-mem_page_tables: 管理内存分页页面的索引表的大小
-mem_shared: 多个进程共享的内存总额
-mem_slab: 内核数据结构缓存的大小，可以减少申请和释放内存带来的消耗
-mem_sreclaimable: 可收回Slab的大小
-mem_sunreclaim: 不可收回Slab的大小（SUnreclaim+SReclaimable＝Slab）
-mem_swap_cached: 被高速缓冲存储器（cache memory）用的交换空间的大小，已经被交换出来的内存，但仍然被存放在swapfile中。用来在需要的时候很快的被替换而不需要再次打开I/O端口
-mem_swap_free: 未被使用交换空间的大小
-mem_swap_total: 交换空间的总大小
-mem_total: 内存总数
-mem_used: 已用内存数
-mem_used_percent: 已用内存数百分比(0~100)
-mem_vmalloc_chunk: 最大的连续未被使用的vmalloc区域
-mem_vmalloc_totalL: 可以vmalloc虚拟内存大小
-mem_vmalloc_used: vmalloc已使用的虚拟内存大小
-mem_write_back: 正在被写回到磁盘的内存大小
-mem_write_back_tmp: FUSE用于临时写回缓冲区的内存
+  mem_active: 活跃使用的内存总数(包括cache和buffer内存)
+  mem_available: 应用程序可用内存数
+  mem_available_percent: 内存剩余百分比(0~100)
+  mem_buffered: 用来给文件做缓冲大小
+  mem_cached: 被高速缓冲存储器（cache memory）用的内存的大小（等于 diskcache minus SwapCache ）
+  mem_commit_limit: 根据超额分配比率（'vm.overcommit_ratio'），这是当前在系统上分配可用的内存总量，这个限制只是在模式2('vm.overcommit_memory')时启用
+  mem_committed_as: 目前在系统上分配的内存量。是所有进程申请的内存的总和
+  mem_dirty: 等待被写回到磁盘的内存大小
+  mem_free: 空闲内存数
+  mem_high_free: 未被使用的高位内存大小
+  mem_high_total: 高位内存总大小（Highmem是指所有内存高于860MB的物理内存,Highmem区域供用户程序使用，或用于页面缓存。该区域不是直接映射到内核空间。内核必须使用不同的手法使用该段内存）
+  mem_huge_page_size: 每个大页的大小
+  mem_huge_pages_free: 池中尚未分配的 HugePages 数量
+  mem_huge_pages_total: 预留HugePages的总个数
+  mem_inactive: 空闲的内存数(包括free和avalible的内存)
+  mem_low_free: 未被使用的低位大小
+  mem_low_total: 低位内存总大小,低位可以达到高位内存一样的作用，而且它还能够被内核用来记录一些自己的数据结构
+  mem_mapped: 设备和文件等映射的大小
+  mem_page_tables: 管理内存分页页面的索引表的大小
+  mem_shared: 多个进程共享的内存总额
+  mem_slab: 内核数据结构缓存的大小，可以减少申请和释放内存带来的消耗
+  mem_sreclaimable: 可收回Slab的大小
+  mem_sunreclaim: 不可收回Slab的大小（SUnreclaim+SReclaimable＝Slab）
+  mem_swap_cached: 被高速缓冲存储器（cache memory）用的交换空间的大小，已经被交换出来的内存，但仍然被存放在swapfile中。用来在需要的时候很快的被替换而不需要再次打开I/O端口
+  mem_swap_free: 未被使用交换空间的大小
+  mem_swap_total: 交换空间的总大小
+  mem_total: 内存总数
+  mem_used: 已用内存数
+  mem_used_percent: 已用内存数百分比(0~100)
+  mem_vmalloc_chunk: 最大的连续未被使用的vmalloc区域
+  mem_vmalloc_totalL: 可以vmalloc虚拟内存大小
+  mem_vmalloc_used: vmalloc已使用的虚拟内存大小
+  mem_write_back: 正在被写回到磁盘的内存大小
+  mem_write_back_tmp: FUSE用于临时写回缓冲区的内存
 
-net_bytes_recv: 网卡收包总数(bytes)
-net_bytes_sent: 网卡发包总数(bytes)
-net_drop_in: 网卡收丢包数量
-net_drop_out: 网卡发丢包数量
-net_err_in: 网卡收包错误数量
-net_err_out: 网卡发包错误数量
-net_packets_recv: 网卡收包数量
-net_packets_sent: 网卡发包数量
+  net_bytes_recv: 网卡收包总数(bytes)
+  net_bytes_sent: 网卡发包总数(bytes)
+  net_drop_in: 网卡收丢包数量
+  net_drop_out: 网卡发丢包数量
+  net_err_in: 网卡收包错误数量
+  net_err_out: 网卡发包错误数量
+  net_packets_recv: 网卡收包数量
+  net_packets_sent: 网卡发包数量
 
-netstat_tcp_established: ESTABLISHED状态的网络链接数
-netstat_tcp_fin_wait1: FIN_WAIT1状态的网络链接数
-netstat_tcp_fin_wait2: FIN_WAIT2状态的网络链接数
-netstat_tcp_last_ack: LAST_ACK状态的网络链接数
-netstat_tcp_listen: LISTEN状态的网络链接数
-netstat_tcp_syn_recv: SYN_RECV状态的网络链接数
-netstat_tcp_syn_sent: SYN_SENT状态的网络链接数
-netstat_tcp_time_wait: TIME_WAIT状态的网络链接数
-netstat_udp_socket: UDP状态的网络链接数
+  netstat_tcp_established: ESTABLISHED状态的网络链接数
+  netstat_tcp_fin_wait1: FIN_WAIT1状态的网络链接数
+  netstat_tcp_fin_wait2: FIN_WAIT2状态的网络链接数
+  netstat_tcp_last_ack: LAST_ACK状态的网络链接数
+  netstat_tcp_listen: LISTEN状态的网络链接数
+  netstat_tcp_syn_recv: SYN_RECV状态的网络链接数
+  netstat_tcp_syn_sent: SYN_SENT状态的网络链接数
+  netstat_tcp_time_wait: TIME_WAIT状态的网络链接数
+  netstat_udp_socket: UDP状态的网络链接数
 
-processes_blocked: 不可中断的睡眠状态下的进程数('U','D','L')
-processes_dead: 回收中的进程数('X')
-processes_idle: 挂起的空闲进程数('I')
-processes_paging: 分页进程数('P')
-processes_running: 运行中的进程数('R')
-processes_sleeping: 可中断进程数('S')
-processes_stopped: 暂停状态进程数('T')
-processes_total: 总进程数
-processes_total_threads: 总线程数
-processes_unknown: 未知状态进程数
-processes_zombies: 僵尸态进程数('Z')
+  #[ping]
+  ping_percent_packet_loss: ping数据包丢失百分比(%)
+  ping_result_code: ping返回码('0','1')
 
-swap_used_percent: Swap空间换出数据量
+  processes_blocked: 不可中断的睡眠状态下的进程数('U','D','L')
+  processes_dead: 回收中的进程数('X')
+  processes_idle: 挂起的空闲进程数('I')
+  processes_paging: 分页进程数('P')
+  processes_running: 运行中的进程数('R')
+  processes_sleeping: 可中断进程数('S')
+  processes_stopped: 暂停状态进程数('T')
+  processes_total: 总进程数
+  processes_total_threads: 总线程数
+  processes_unknown: 未知状态进程数
+  processes_zombies: 僵尸态进程数('Z')
 
-system_load1: 1分钟平均load值
-system_load5: 5分钟平均load值
-system_load15: 15分钟平均load值
-system_n_users: 用户数
-system_n_cpus: CPU核数
-system_uptime: 系统启动时间
+  swap_used_percent: Swap空间换出数据量
 
-nginx_accepts: 自nginx启动起,与客户端建立过得连接总数
-nginx_active: 当前nginx正在处理的活动连接数,等于Reading/Writing/Waiting总和
-nginx_handled: 自nginx启动起,处理过的客户端连接总数
-nginx_reading: 正在读取HTTP请求头部的连接总数
-nginx_requests: 自nginx启动起,处理过的客户端请求总数,由于存在HTTP Krrp-Alive请求,该值会大于handled值
-nginx_upstream_check_fall: upstream_check模块检测到后端失败的次数
-nginx_upstream_check_rise: upstream_check模块对后端的检测次数
-nginx_upstream_check_status_code: 后端upstream的状态,up为1,down为0
-nginx_waiting: 开启 keep-alive 的情况下,这个值等于 active – (reading+writing), 意思就是 Nginx 已经处理完正在等候下一次请求指令的驻留连接
-nginx_writing: 正在向客户端发送响应的连接总数
+  system_load1: 1分钟平均load值
+  system_load5: 5分钟平均load值
+  system_load15: 15分钟平均load值
+  system_n_users: 用户数
+  system_n_cpus: CPU核数
+  system_uptime: 系统启动时间
 
-http_response_content_length: HTTP消息实体的传输长度
-http_response_http_response_code: http响应状态码
-http_response_response_time: http响应用时
-http_response_result_code: url探测结果0为正常否则url无法访问
+  nginx_accepts: 自nginx启动起,与客户端建立过得连接总数
+  nginx_active: 当前nginx正在处理的活动连接数,等于Reading/Writing/Waiting总和
+  nginx_handled: 自nginx启动起,处理过的客户端连接总数
+  nginx_reading: 正在读取HTTP请求头部的连接总数
+  nginx_requests: 自nginx启动起,处理过的客户端请求总数,由于存在HTTP Krrp-Alive请求,该值会大于handled值
+  nginx_upstream_check_fall: upstream_check模块检测到后端失败的次数
+  nginx_upstream_check_rise: upstream_check模块对后端的检测次数
+  nginx_upstream_check_status_code: 后端upstream的状态,up为1,down为0
+  nginx_waiting: 开启 keep-alive 的情况下,这个值等于 active – (reading+writing), 意思就是 Nginx 已经处理完正在等候下一次请求指令的驻留连接
+  nginx_writing: 正在向客户端发送响应的连接总数
+
+  http_response_content_length: HTTP消息实体的传输长度
+  http_response_http_response_code: http响应状态码
+  http_response_response_time: http响应用时
+  http_response_result_code: url探测结果0为正常否则url无法访问
+
+  # [aws cloudwatch rds]
+  cloudwatch_aws_rds_bin_log_disk_usage_average: rds 磁盘使用平均值
+  cloudwatch_aws_rds_bin_log_disk_usage_maximum: rds 磁盘使用量最大值
+  cloudwatch_aws_rds_bin_log_disk_usage_minimum: rds binlog 磁盘使用量最低
+  cloudwatch_aws_rds_bin_log_disk_usage_sample_count: rds binlog 磁盘使用情况样本计数
+  cloudwatch_aws_rds_bin_log_disk_usage_sum: rds binlog 磁盘使用总和
+  cloudwatch_aws_rds_burst_balance_average: rds 突发余额平均值
+  cloudwatch_aws_rds_burst_balance_maximum: rds 突发余额最大值
+  cloudwatch_aws_rds_burst_balance_minimum: rds 突发余额最低
+  cloudwatch_aws_rds_burst_balance_sample_count: rds 突发平衡样本计数
+  cloudwatch_aws_rds_burst_balance_sum: rds 突发余额总和
+  cloudwatch_aws_rds_cpu_utilization_average: rds cpu 利用率平均值
+  cloudwatch_aws_rds_cpu_utilization_maximum: rds cpu 利用率最大值
+  cloudwatch_aws_rds_cpu_utilization_minimum: rds cpu 利用率最低
+  cloudwatch_aws_rds_cpu_utilization_sample_count: rds cpu 利用率样本计数
+  cloudwatch_aws_rds_cpu_utilization_sum: rds cpu 利用率总和
+  cloudwatch_aws_rds_database_connections_average: rds 数据库连接平均值
+  cloudwatch_aws_rds_database_connections_maximum: rds 数据库连接数最大值
+  cloudwatch_aws_rds_database_connections_minimum: rds 数据库连接最小
+  cloudwatch_aws_rds_database_connections_sample_count: rds 数据库连接样本数
+  cloudwatch_aws_rds_database_connections_sum: rds 数据库连接总和
+  cloudwatch_aws_rds_db_load_average: rds db 平均负载
+  cloudwatch_aws_rds_db_load_cpu_average: rds db 负载 cpu 平均值
+  cloudwatch_aws_rds_db_load_cpu_maximum: rds db 负载 cpu 最大值
+  cloudwatch_aws_rds_db_load_cpu_minimum: rds db 负载 cpu 最小值
+  cloudwatch_aws_rds_db_load_cpu_sample_count: rds db 加载 CPU 样本数
+  cloudwatch_aws_rds_db_load_cpu_sum: rds db 加载cpu总和
+  cloudwatch_aws_rds_db_load_maximum: rds 数据库负载最大值
+  cloudwatch_aws_rds_db_load_minimum: rds 数据库负载最小值
+  cloudwatch_aws_rds_db_load_non_cpu_average: rds 加载非 CPU 平均值
+  cloudwatch_aws_rds_db_load_non_cpu_maximum: rds 加载非 cpu 最大值
+  cloudwatch_aws_rds_db_load_non_cpu_minimum: rds 加载非 cpu 最小值
+  cloudwatch_aws_rds_db_load_non_cpu_sample_count: rds 加载非 cpu 样本计数
+  cloudwatch_aws_rds_db_load_non_cpu_sum: rds 加载非cpu总和
+  cloudwatch_aws_rds_db_load_sample_count: rds db 加载样本计数
+  cloudwatch_aws_rds_db_load_sum: rds db 负载总和
+  cloudwatch_aws_rds_disk_queue_depth_average: rds 磁盘队列深度平均值
+  cloudwatch_aws_rds_disk_queue_depth_maximum: rds 磁盘队列深度最大值
+  cloudwatch_aws_rds_disk_queue_depth_minimum: rds 磁盘队列深度最小值
+  cloudwatch_aws_rds_disk_queue_depth_sample_count: rds 磁盘队列深度样本计数
+  cloudwatch_aws_rds_disk_queue_depth_sum: rds 磁盘队列深度总和
+  cloudwatch_aws_rds_ebs_byte_balance__average: rds ebs 字节余额平均值
+  cloudwatch_aws_rds_ebs_byte_balance__maximum: rds ebs 字节余额最大值
+  cloudwatch_aws_rds_ebs_byte_balance__minimum: rds ebs 字节余额最低
+  cloudwatch_aws_rds_ebs_byte_balance__sample_count: rds ebs 字节余额样本数
+  cloudwatch_aws_rds_ebs_byte_balance__sum: rds ebs 字节余额总和
+  cloudwatch_aws_rds_ebsio_balance__average: rds ebsio 余额平均值
+  cloudwatch_aws_rds_ebsio_balance__maximum: rds ebsio 余额最大值
+  cloudwatch_aws_rds_ebsio_balance__minimum: rds ebsio 余额最低
+  cloudwatch_aws_rds_ebsio_balance__sample_count: rds ebsio 平衡样本计数
+  cloudwatch_aws_rds_ebsio_balance__sum: rds ebsio 余额总和
+  cloudwatch_aws_rds_free_storage_space_average: rds 免费存储空间平均
+  cloudwatch_aws_rds_free_storage_space_maximum: rds 最大可用存储空间
+  cloudwatch_aws_rds_free_storage_space_minimum: rds 最低可用存储空间
+  cloudwatch_aws_rds_free_storage_space_sample_count: rds 可用存储空间样本数
+  cloudwatch_aws_rds_free_storage_space_sum: rds 免费存储空间总和
+  cloudwatch_aws_rds_freeable_memory_average: rds 可用内存平均值
+  cloudwatch_aws_rds_freeable_memory_maximum: rds 最大可用内存
+  cloudwatch_aws_rds_freeable_memory_minimum: rds 最小可用内存
+  cloudwatch_aws_rds_freeable_memory_sample_count: rds 可释放内存样本数
+  cloudwatch_aws_rds_freeable_memory_sum: rds 可释放内存总和
+  cloudwatch_aws_rds_lvm_read_iops_average: rds lvm 读取 iops 平均值
+  cloudwatch_aws_rds_lvm_read_iops_maximum: rds lvm 读取 iops 最大值
+  cloudwatch_aws_rds_lvm_read_iops_minimum: rds lvm 读取 iops 最低
+  cloudwatch_aws_rds_lvm_read_iops_sample_count: rds lvm 读取 iops 样本计数
+  cloudwatch_aws_rds_lvm_read_iops_sum: rds lvm 读取 iops 总和
+  cloudwatch_aws_rds_lvm_write_iops_average: rds lvm 写入 iops 平均值
+  cloudwatch_aws_rds_lvm_write_iops_maximum: rds lvm 写入 iops 最大值
+  cloudwatch_aws_rds_lvm_write_iops_minimum: rds lvm 写入 iops 最低
+  cloudwatch_aws_rds_lvm_write_iops_sample_count: rds lvm 写入 iops 样本计数
+  cloudwatch_aws_rds_lvm_write_iops_sum: rds lvm 写入 iops 总和
+  cloudwatch_aws_rds_network_receive_throughput_average: rds 网络接收吞吐量平均
+  cloudwatch_aws_rds_network_receive_throughput_maximum: rds 网络接收吞吐量最大值
+  cloudwatch_aws_rds_network_receive_throughput_minimum: rds 网络接收吞吐量最小值
+  cloudwatch_aws_rds_network_receive_throughput_sample_count: rds 网络接收吞吐量样本计数
+  cloudwatch_aws_rds_network_receive_throughput_sum: rds 网络接收吞吐量总和
+  cloudwatch_aws_rds_network_transmit_throughput_average: rds 网络传输吞吐量平均值
+  cloudwatch_aws_rds_network_transmit_throughput_maximum: rds 网络传输吞吐量最大
+  cloudwatch_aws_rds_network_transmit_throughput_minimum: rds 网络传输吞吐量最小值
+  cloudwatch_aws_rds_network_transmit_throughput_sample_count: rds 网络传输吞吐量样本计数
+  cloudwatch_aws_rds_network_transmit_throughput_sum: rds 网络传输吞吐量总和
+  cloudwatch_aws_rds_read_iops_average: rds 读取 iops 平均值
+  cloudwatch_aws_rds_read_iops_maximum: rds 最大读取 iops
+  cloudwatch_aws_rds_read_iops_minimum: rds 读取 iops 最低
+  cloudwatch_aws_rds_read_iops_sample_count: rds 读取 iops 样本计数
+  cloudwatch_aws_rds_read_iops_sum: rds 读取 iops 总和
+  cloudwatch_aws_rds_read_latency_average: rds 读取延迟平均值
+  cloudwatch_aws_rds_read_latency_maximum: rds 读取延迟最大值
+  cloudwatch_aws_rds_read_latency_minimum: rds 最小读取延迟
+  cloudwatch_aws_rds_read_latency_sample_count: rds 读取延迟样本计数
+  cloudwatch_aws_rds_read_latency_sum: rds 读取延迟总和
+  cloudwatch_aws_rds_read_throughput_average: rds 读取吞吐量平均值
+  cloudwatch_aws_rds_read_throughput_maximum: rds 最大读取吞吐量
+  cloudwatch_aws_rds_read_throughput_minimum: rds 最小读取吞吐量
+  cloudwatch_aws_rds_read_throughput_sample_count: rds 读取吞吐量样本计数
+  cloudwatch_aws_rds_read_throughput_sum: rds 读取吞吐量总和
+  cloudwatch_aws_rds_swap_usage_average: rds 交换使用平均值
+  cloudwatch_aws_rds_swap_usage_maximum: rds 交换使用最大值
+  cloudwatch_aws_rds_swap_usage_minimum: rds 交换使用量最低
+  cloudwatch_aws_rds_swap_usage_sample_count: rds 交换使用示例计数
+  cloudwatch_aws_rds_swap_usage_sum: rds 交换使用总和
+  cloudwatch_aws_rds_write_iops_average: rds 写入 iops 平均值
+  cloudwatch_aws_rds_write_iops_maximum: rds 写入 iops 最大值
+  cloudwatch_aws_rds_write_iops_minimum: rds 写入 iops 最低
+  cloudwatch_aws_rds_write_iops_sample_count: rds 写入 iops 样本计数
+  cloudwatch_aws_rds_write_iops_sum: rds 写入 iops 总和
+  cloudwatch_aws_rds_write_latency_average: rds 写入延迟平均值
+  cloudwatch_aws_rds_write_latency_maximum: rds 最大写入延迟
+  cloudwatch_aws_rds_write_latency_minimum: rds 写入延迟最小值
+  cloudwatch_aws_rds_write_latency_sample_count: rds 写入延迟样本计数
+  cloudwatch_aws_rds_write_latency_sum: rds 写入延迟总和
+  cloudwatch_aws_rds_write_throughput_average: rds 写入吞吐量平均值
+  cloudwatch_aws_rds_write_throughput_maximum: rds 最大写入吞吐量
+  cloudwatch_aws_rds_write_throughput_minimum: rds 写入吞吐量最小值
+  cloudwatch_aws_rds_write_throughput_sample_count: rds 写入吞吐量样本计数
+  cloudwatch_aws_rds_write_throughput_sum: rds 写入吞吐量总和
+
+en:
+  cpu_usage_idle: "CPU idle rate(unit：%)"
+  cpu_usage_active: "CPU usage rate(unit：%)"
+  cpu_usage_system: "CPU kernel state time proportion(unit：%)"
+  cpu_usage_user: "CPU user attitude time proportion(unit：%)"
+  cpu_usage_nice: "The proportion of low priority CPU time, that is, the process NICE value is adjusted to the CPU time between 1-19. Note here that the value range of NICE is -20 to 19, the larger the value, the lower the priority, the lower the priority(unit：%)"
+  cpu_usage_iowait: "CPU waiting for I/O time proportion(unit：%)"
+  cpu_usage_irq: "CPU processing hard interrupt time proportion(unit：%)"
+  cpu_usage_softirq: "CPU processing soft interrupt time proportion(unit：%)"
+  cpu_usage_steal: "In the virtual machine environment, there is this indicator, which means that the CPU is used by other virtual machines for the proportion of time.(unit：%)"
+  cpu_usage_guest: "The time to run other operating systems by virtualization, that is, the proportion of CPU time running the virtual machine(unit：%)"
+  cpu_usage_guest_nice: "The proportion of time to run the virtual machine at low priority(unit：%)"
+
+  disk_free: "The remaining amount of the hard disk partition (unit: byte)"
+  disk_used: "Hard disk partitional use (unit: byte)"
+  disk_used_percent: "Hard disk partitional use rate (unit:%)"
+  disk_total: "Total amount of hard disk partition (unit: byte)"
+  disk_inodes_free: "Hard disk partition INODE remaining amount"
+  disk_inodes_used: "Hard disk partition INODE usage amount"
+  disk_inodes_total: "The total amount of hard disk partition INODE"
+
+  diskio_io_time: "From the perspective of the device perspective, the total time of I/O request, the I/O request in the queue is count (unit: millisecond), the counter type, you need to use the function to find the value"
+  diskio_iops_in_progress: "IO requests that have been assigned to device -driven and have not yet been completed, not included in the queue but not yet assigned to the device -driven IO request, Gauge type"
+  diskio_merged_reads: "The number of times of adjacent reading request Merge, the counter type"
+  diskio_merged_writes: "The number of times the request Merge writes, the counter type"
+  diskio_read_bytes: "The number of byte reads, the counter type, you need to use the function to find the Rate to use the value"
+  diskio_read_time: "The total time of reading request (unit: millisecond), the counter type, you need to use the function to find the Rate to have the value of use"
+  diskio_reads: "Read the number of requests, the counter type, you need to use the function to find the Rate to use the value"
+  diskio_weighted_io_time: "From the perspective of the I/O request perspective, I/O wait for the total time. If there are multiple I/O requests at the same time, the time will be superimposed (unit: millisecond)"
+  diskio_write_bytes: "The number of bytes written, the counter type, you need to use the function to find the Rate to use the value"
+  diskio_write_time: "The total time of the request (unit: millisecond), the counter type, you need to use the function to find the rate to have the value of use"
+  diskio_writes: "Write the number of requests, the counter type, you need to use the function to find the rate to use value"
+
+  kernel_boot_time: "Kernel startup time"
+  kernel_context_switches: "Number of kernel context switching times"
+  kernel_entropy_avail: "Entropy pool inside the Linux system"
+  kernel_interrupts: "Number of kernel interruption"
+  kernel_processes_forked: "ForK's process number"
+
+  mem_active: "The total number of memory (including Cache and BUFFER memory)"
+  mem_available: "Application can use memory numbers"
+  mem_available_percent: "Memory remaining percentage (0 ~ 100)"
+  mem_buffered: "Used to make buffer size for the file"
+  mem_cached: "The size of the memory used by the cache memory (equal to diskcache minus Swap Cache )"
+  mem_commit_limit: "According to the over allocation ratio ('vm.overCommit _ Ratio'), this is the current total memory that can be allocated on the system."
+  mem_committed_as: "Currently allocated on the system. It is the sum of the memory of all process applications"
+  mem_dirty: "Waiting to be written back to the memory size of the disk"
+  mem_free: "Senior memory number"
+  mem_high_free: "Unused high memory size"
+  mem_high_total: "The total memory size of the high memory (Highmem refers to all the physical memory that is higher than 860 MB of memory, the HighMem area is used for user programs, or for page cache. This area is not directly mapped to the kernel space. The kernels must use different methods to use this section of memory. )"
+  mem_huge_page_size: "The size of each big page"
+  mem_huge_pages_free: "The number of Huge Pages in the pool that have not been allocated"
+  mem_huge_pages_total: "Reserve the total number of Huge Pages"
+  mem_inactive: "Free memory (including the memory of free and avalible)"
+  mem_low_free: "Unused low size"
+  mem_low_total: "The total size of the low memory memory can achieve the same role of high memory, and it can be used by the kernel to record some of its own data structure"
+  mem_mapped: "The size of the mapping of equipment and files"
+  mem_page_tables: "The size of the index table of the management of the memory paging page"
+  mem_shared: "The total memory shared by multiple processes"
+  mem_slab: "The size of the kernel data structure cache can reduce the consumption of application and release memory"
+  mem_sreclaimable: "The size of the SLAB can be recovered"
+  mem_sunreclaim: "The size of the SLAB cannot be recovered(SUnreclaim+SReclaimable＝Slab)"
+  mem_swap_cached: "The size of the swap space used by the cache memory (cache memory), the memory that has been swapped out, but is still stored in the swapfile. Used to be quickly replaced when needed without opening the I/O port again"
+  mem_swap_free: "The size of the switching space is not used"
+  mem_swap_total: "The total size of the exchange space"
+  mem_total: "Total memory"
+  mem_used: "Memory number"
+  mem_used_percent: "The memory has been used by several percentage (0 ~ 100)"
+  mem_vmalloc_chunk: "The largest continuous unused vmalloc area"
+  mem_vmalloc_totalL: "You can vmalloc virtual memory size"
+  mem_vmalloc_used: "Vmalloc's virtual memory size"
+  mem_write_back: "The memory size of the disk is being written back to the disk"
+  mem_write_back_tmp: "Fuse is used to temporarily write back the memory of the buffer area"
+
+  net_bytes_recv: "The total number of packaging of the network card (bytes)"
+  net_bytes_sent: "Total number of network cards (bytes)"
+  net_drop_in: "The number of packets for network cards"
+  net_drop_out: "The number of packets issued by the network card"
+  net_err_in: "The number of incorrect packets of the network card"
+  net_err_out: "Number of incorrect number of network cards"
+  net_packets_recv: "Net card collection quantity"
+  net_packets_sent: "Number of network card issuance"
+
+  netstat_tcp_established: "ESTABLISHED status network link number"
+  netstat_tcp_fin_wait1: "FIN _ WAIT1 status network link number"
+  netstat_tcp_fin_wait2: "FIN _ WAIT2 status number of network links"
+  netstat_tcp_last_ack: "LAST_ ACK status number of network links"
+  netstat_tcp_listen: "Number of network links in Listen status"
+  netstat_tcp_syn_recv: "SYN _ RECV status number of network links"
+  netstat_tcp_syn_sent: "SYN _ SENT status number of network links"
+  netstat_tcp_time_wait: "Time _ WAIT status network link number"
+  netstat_udp_socket: "Number of network links in UDP status"
+
+  processes_blocked: "The number of processes in the unreprudible sleep state('U','D','L')"
+  processes_dead: "Number of processes in recycling('X')"
+  processes_idle: "Number of idle processes hanging('I')"
+  processes_paging: "Number of paging processes('P')"
+  processes_running: "Number of processes during operation('R')"
+  processes_sleeping: "Can interrupt the number of processes('S')"
+  processes_stopped: "Pushing status process number('T')"
+  processes_total: "Total process number"
+  processes_total_threads: "Number of threads"
+  processes_unknown: "Unknown status process number"
+  processes_zombies: "Number of zombies('Z')"
+
+  swap_used_percent: "SWAP space replace the data volume"
+
+  system_load1: "1 minute average load value"
+  system_load5: "5 minutes average load value"
+  system_load15: "15 minutes average load value"
+  system_n_users: "User number"
+  system_n_cpus: "CPU nuclear number"
+  system_uptime: "System startup time"
+
+  nginx_accepts: "Since Nginx started, the total number of connections has been established with the client"
+  nginx_active: "The current number of activity connections that Nginx is being processed is equal to Reading/Writing/Waiting"
+  nginx_handled: "Starting from Nginx, the total number of client connections that have been processed"
+  nginx_reading: "Reading the total number of connections on the http request header"
+  nginx_requests: "Since nginx is started, the total number of client requests processed, due to the existence of HTTP Krrp - Alive requests, this value will be greater than the handled value"
+  nginx_upstream_check_fall: "UPStream_CHECK module detects the number of back -end failures"
+  nginx_upstream_check_rise: "UPSTREAM _ Check module to detect the number of back -end"
+  nginx_upstream_check_status_code: "The state of the backstream is 1, and the down is 0"
+  nginx_waiting: "When keep-alive is enabled, this value is equal to active – (reading+writing), which means that Nginx has processed the resident connection that is waiting for the next request command"
+  nginx_writing: "The total number of connections to send a response to the client"
+
+  http_response_content_length: "HTTP message entity transmission length"
+  http_response_http_response_code: "http response status code"
+  http_response_response_time: "When http ring application"
+  http_response_result_code: "URL detection result 0 is normal, otherwise the URL cannot be accessed"
 
 # [mysqld_exporter]
 mysql_global_status_uptime: The number of seconds that the server has been up.(Gauge)
@@ -237,7 +489,7 @@ redis_last_key_groups_scrape_duration_milliseconds: Duration of the last key gro
 redis_last_slow_execution_duration_seconds: The amount of time needed for last slow execution, in seconds.
 redis_latest_fork_seconds: The amount of time needed for last fork, in seconds.
 redis_lazyfree_pending_objects: The number of objects waiting to be freed (as a result of calling UNLINK, or FLUSHDB and FLUSHALL with the ASYNC option).
-redis_master_repl_offset: The server's current replication offset. 
+redis_master_repl_offset: The server's current replication offset.
 redis_mem_clients_normal: Memory used by normal clients.(Gauge)
 redis_mem_clients_slaves: Memory used by replica clients - Starting Redis 7.0, replica buffers share memory with the replication backlog, so this field can show 0 when replicas don't trigger an increase of memory usage.
 redis_mem_fragmentation_bytes: Delta between used_memory_rss and used_memory. Note that when the total fragmentation bytes is low (few megabytes), a high ratio (e.g. 1.5 and above) is not an indication of an issue.
@@ -370,8 +622,6 @@ node_load15: cpu load 15m
 
 # MEM
 # 内核态
-# 用户追踪已从交换区获取但尚未修改的页面的内存
-node_memory_SwapCached_bytes: Memory that keeps track of pages that have been fetched from swap but not yet been modified
 # 内核用于缓存数据结构供自己使用的内存
 node_memory_Slab_bytes: Memory used by the kernel to cache data structures for its own use
 # slab中可回收的部分
@@ -433,7 +683,7 @@ node_memory_SwapTotal_bytes: Memory information field SwapTotal_bytes
 node_memory_SwapFree_bytes: Memory information field SwapFree_bytes
 
 # DISK
-node_filesystem_files_free: Filesystem space available to non-root users in byte
+node_filesystem_avail_bytes: Filesystem space available to non-root users in byte
 node_filesystem_free_bytes: Filesystem free space in bytes
 node_filesystem_size_bytes: Filesystem size in bytes
 node_filesystem_files_free: Filesystem total free file nodes
@@ -479,7 +729,7 @@ kafka_consumer_lag_millis: Current approximation of consumer lag for a ConsumerG
 kafka_topic_partition_under_replicated_partition: 1 if Topic/Partition is under Replicated
 
 # [zookeeper_exporter]
-zk_znode_count: The total count of znodes stored 
+zk_znode_count: The total count of znodes stored
 zk_ephemerals_count: The number of Ephemerals nodes
 zk_watch_count: The number of watchers setup over Zookeeper nodes.
 zk_approximate_data_size: Size of data in bytes that a zookeeper server has in its data tree
@@ -491,4 +741,4 @@ zk_open_file_descriptor_count: Number of file descriptors that a zookeeper serve
 zk_max_file_descriptor_count: Maximum number of file descriptors that a zookeeper server can open
 zk_avg_latency: Average time in milliseconds for requests to be processed
 zk_min_latency: Maximum time in milliseconds for a request to be processed
-zk_max_latency: Minimum time in milliseconds for a request to be processed
+zk_max_latency: Minimum time in milliseconds for a request to be processed

etc/script/notify.py

@@ -24,6 +24,11 @@ class Sender(object):
         # already done in go code
         pass
 
+    @classmethod
+    def send_mm(cls, payload):
+        # already done in go code
+        pass
+
     @classmethod
     def send_sms(cls, payload):
         users = payload.get('event').get("notify_users_obj")

etc/script/notify/notify.go

@@ -7,12 +7,6 @@ import (
 	"github.com/tidwall/gjson"
 )
 
-// the caller can be called for alerting notify by complete this interface
-type inter interface {
-	Descript() string
-	Notify([]byte)
-}
-
 // N9E complete
 type N9EPlugin struct {
 	Name        string
@@ -37,9 +31,16 @@ func (n *N9EPlugin) Notify(bs []byte) {
 	}
 }
 
+func (n *N9EPlugin) NotifyMaintainer(bs []byte) {
+	fmt.Println("do something... begin")
+	result := string(bs)
+	fmt.Println(result)
+	fmt.Println("do something... end")
+}
+
 // will be loaded for alertingCall , The first letter must be capitalized to be exported
 var N9eCaller = N9EPlugin{
-	Name:        "n9e",
-	Description: "演示告警通过动态链接库方式通知",
+	Name:        "N9EPlugin",
+	Description: "Notify by lib",
 	BuildAt:     time.Now().Local().Format("2006/01/02 15:04:05"),
 }

etc/script/rule_converter.py

@@ -0,0 +1,193 @@
+import json
+import yaml
+
+'''
+将promtheus/vmalert的rule转换为n9e中的rule
+支持k8s的rule configmap
+'''
+
+rule_file = 'rules.yaml'
+
+
+def convert_interval(interval):
+    if interval.endswith('s') or interval.endswith('S'):
+        return int(interval[:-1])
+    if interval.endswith('m') or interval.endswith('M'):
+        return int(interval[:-1]) * 60
+    if interval.endswith('h') or interval.endswith('H'):
+        return int(interval[:-1]) * 60 * 60
+    if interval.endswith('d') or interval.endswith('D'):
+        return int(interval[:-1]) * 60 * 60 * 24
+    return int(interval)
+
+
+def convert_alert(rule, interval):
+    name = rule['alert']
+    prom_ql = rule['expr']
+    if 'for' in rule:
+        prom_for_duration = convert_interval(rule['for'])
+    else:
+        prom_for_duration = 0
+
+    prom_eval_interval = convert_interval(interval)
+    note = ''
+    if 'annotations' in rule:
+        for v in rule['annotations'].values():
+            note = v
+            break
+
+    append_tags = []
+    severity = 2
+    if 'labels' in rule:
+        for k, v in rule['labels'].items():
+            if k != 'severity':
+                append_tags.append('{}={}'.format(k, v))
+                continue
+            if v == 'critical':
+                severity = 1
+            elif v == 'info':
+                severity = 3
+            # elif v == 'warning':
+            #     severity = 2
+
+
+    n9e_alert_rule = {
+        "name": name,
+        "note": note,
+        "severity": severity,
+        "disabled": 0,
+        "prom_for_duration": prom_for_duration,
+        "prom_ql": prom_ql,
+        "prom_eval_interval": prom_eval_interval,
+        "enable_stime": "00:00",
+        "enable_etime": "23:59",
+        "enable_days_of_week": [
+            "1",
+            "2",
+            "3",
+            "4",
+            "5",
+            "6",
+            "0"
+        ],
+        "enable_in_bg": 0,
+        "notify_recovered": 1,
+        "notify_channels": [],
+        "notify_repeat_step": 60,
+        "recover_duration": 0,
+        "callbacks": [],
+        "runbook_url": "",
+        "append_tags": append_tags
+    }
+    return n9e_alert_rule
+
+
+def convert_record(rule, interval):
+    name = rule['record']
+    prom_ql = rule['expr']
+    prom_eval_interval = convert_interval(interval)
+    note = ''
+    append_tags = []
+    if 'labels' in rule:
+        for k, v in rule['labels'].items():
+            append_tags.append('{}={}'.format(k, v))
+
+    n9e_record_rule = {
+        "name": name,
+        "note": note,
+        "disabled": 0,
+        "prom_ql": prom_ql,
+        "prom_eval_interval": prom_eval_interval,
+        "append_tags": append_tags
+    }
+    return n9e_record_rule
+
+
+'''
+example of rule group file
+---
+groups:
+- name: example
+  rules:
+  - alert: HighRequestLatency
+    expr: job:request_latency_seconds:mean5m{job="myjob"} > 0.5
+    for: 10m
+    labels:
+      severity: page
+    annotations:
+      summary: High request latency
+'''
+def deal_group(group):
+    """
+    parse single prometheus/vmalert rule group
+    """
+    alert_rules = []
+    record_rules = []
+
+    for rule_segment in group['groups']:
+        if 'interval' in rule_segment:
+            interval = rule_segment['interval']
+        else:
+            interval = '15s'
+        for rule in rule_segment['rules']:
+            if 'alert' in rule:
+                alert_rules.append(convert_alert(rule, interval))
+            else:
+                record_rules.append(convert_record(rule, interval))
+
+    return alert_rules, record_rules
+
+
+'''
+example of k8s rule configmap
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: rulefiles-0
+data:
+  etcdrules.yaml: |
+    groups:
+    - name: etcd
+      rules:
+      - alert: etcdInsufficientMembers
+        annotations:
+          message: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value}}).'
+        expr: sum(up{job=~".*etcd.*"} == bool 1) by (job) < ((count(up{job=~".*etcd.*"})
+          by (job) + 1) / 2)
+        for: 3m
+        labels:
+          severity: critical
+'''
+def deal_configmap(rule_configmap):
+    """
+    parse rule configmap from k8s
+    """
+    all_record_rules = []
+    all_alert_rules = []
+    for _, rule_group_str in rule_configmap['data'].items():
+        rule_group = yaml.load(rule_group_str, Loader=yaml.FullLoader)
+        alert_rules, record_rules = deal_group(rule_group)
+        all_alert_rules.extend(alert_rules)
+        all_record_rules.extend(record_rules)
+
+    return all_alert_rules, all_record_rules
+
+
+def main():
+    with open(rule_file, 'r') as f:
+        rule_config = yaml.load(f, Loader=yaml.FullLoader)
+        
+        # 如果文件是k8s中的configmap,使用下面的方法
+        # alert_rules, record_rules = deal_configmap(rule_config)
+        alert_rules, record_rules = deal_group(rule_config)
+
+        with open("alert-rules.json", 'w') as fw:
+            json.dump(alert_rules, fw, indent=2, ensure_ascii=False)
+
+        with open("record-rules.json", 'w') as fw:
+            json.dump(record_rules, fw, indent=2, ensure_ascii=False)
+
+
+if __name__ == '__main__':
+    main()

etc/server.conf

@@ -9,10 +9,15 @@ ClusterName = "Default"
 BusiGroupLabelKey = "busigroup"
 
 # sleep x seconds, then start judge engine
-EngineDelay = 120
+EngineDelay = 60
 
 DisableUsageReport = false
 
+# config | database
+ReaderFrom = "config"
+
+ForceUseServerTS = true
+
 [Log]
 # log write dir
 Dir = "logs"
@@ -70,10 +75,12 @@ InsecureSkipVerify = true
 Batch = 5
 
 [Alerting]
+# timeout settings, unit: ms, default: 30000ms
+Timeout=30000
 TemplatesDir = "./etc/template"
 NotifyConcurrency = 10
 # use builtin go code notify
-NotifyBuiltinChannels = ["email", "dingtalk", "wecom", "feishu"]
+NotifyBuiltinChannels = ["email", "dingtalk", "wecom", "feishu", "mm"]
 
 [Alerting.CallScript]
 # built in sending capability in go code
@@ -104,7 +111,7 @@ Headers = ["Content-Type", "application/json", "X-From", "N9E"]
 [NoData]
 Metric = "target_up"
 # unit: second
-Interval = 15
+Interval = 120
 
 [Ibex]
 # callback: ${ibex}/${tplid}/${host}
@@ -155,15 +162,8 @@ BasicAuthUser = ""
 BasicAuthPass = ""
 # timeout settings, unit: ms
 Timeout = 30000
-DialTimeout = 10000
-TLSHandshakeTimeout = 30000
-ExpectContinueTimeout = 1000
-IdleConnTimeout = 90000
-# time duration, unit: ms
-KeepAlive = 30000
-MaxConnsPerHost = 0
-MaxIdleConns = 100
-MaxIdleConnsPerHost = 10
+DialTimeout = 3000
+MaxIdleConnsPerHost = 100
 
 [WriterOpt]
 # queue channel count
@@ -180,8 +180,9 @@ BasicAuthUser = ""
 # Basic auth password
 BasicAuthPass = ""
 # timeout settings, unit: ms
-Timeout = 30000
-DialTimeout = 10000
+Headers = ["X-From", "n9e"]
+Timeout = 10000
+DialTimeout = 3000
 TLSHandshakeTimeout = 30000
 ExpectContinueTimeout = 1000
 IdleConnTimeout = 90000
@@ -190,6 +191,12 @@ KeepAlive = 30000
 MaxConnsPerHost = 0
 MaxIdleConns = 100
 MaxIdleConnsPerHost = 100
+# [[Writers.WriteRelabels]]
+# Action = "replace"
+# SourceLabels = ["__address__"]
+# Regex = "([^:]+)(?::\\d+)?"
+# Replacement = "$1:80"
+# TargetLabel = "__address__"
 
 # [[Writers]]
 # Url = "http://127.0.0.1:7201/api/v1/prom/remote/write"

etc/template/README.md

@@ -0,0 +1,26 @@
+# 告警消息模版文件
+
+模版中可以使用的变量参考`AlertCurEvent`对象
+模版语法如何使用可以参考[html/template](https://pkg.go.dev/html/template)
+
+## 如何在告警模版中添加监控详情url
+
+假设web的地址是http://127.0.0.1:18000/, 实际使用时用web地址替换该地址
+
+在监控模版中添加以下行:
+
+* dingtalk / wecom / feishu
+```markdown
+[监控详情](http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }})
+```
+
+* mailbody
+
+```html
+<tr>
+  <th>监控详情：</th>
+  <td>
+    <a href="http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }}" target="_blank">点击查看</a>
+  </td>
+</tr>
+```

etc/template/mm.tpl

@@ -0,0 +1,7 @@
+级别状态: S{{.Severity}} {{if .IsRecovered}}Recovered{{else}}Triggered{{end}}
+规则名称: {{.RuleName}}{{if .RuleNote}}
+规则备注: {{.RuleNote}}{{end}}
+监控指标: {{.TagsJSON}}
+{{if .IsRecovered}}恢复时间：{{timeformat .LastEvalTime}}{{else}}触发时间: {{timeformat .TriggerTime}}
+触发时值: {{.TriggerValue}}{{end}}
+发送时间: {{timestamp}}

etc/template/wecom.tpl

@@ -1,7 +1,9 @@
 **级别状态**: {{if .IsRecovered}}<font color="info">S{{.Severity}} Recovered</font>{{else}}<font color="warning">S{{.Severity}} Triggered</font>{{end}}
 **规则标题**: {{.RuleName}}{{if .RuleNote}}
-**规则备注**: {{.RuleNote}}{{end}}
-**监控指标**: {{.TagsJSON}}
-{{if .IsRecovered}}**恢复时间**：{{timeformat .LastEvalTime}}{{else}}**触发时间**: {{timeformat .TriggerTime}}
+**规则备注**: {{.RuleNote}}{{end}}{{if .TargetIdent}}
+**监控对象**: {{.TargetIdent}}{{end}}
+**监控指标**: {{.TagsJSON}}{{if not .IsRecovered}}
 **触发时值**: {{.TriggerValue}}{{end}}
+{{if .IsRecovered}}**恢复时间**: {{timeformat .LastEvalTime}}{{else}}**首次触发时间**: {{timeformat .FirstTriggerTime}}{{end}}
+{{$time_duration := sub now.Unix .FirstTriggerTime }}{{if .IsRecovered}}{{$time_duration = sub .LastEvalTime .FirstTriggerTime }}{{end}}**持续时长**: {{humanizeDurationInterface $time_duration}}
 **发送时间**: {{timestamp}}

etc/webapi.conf

@@ -4,6 +4,9 @@ RunMode = "release"
 # # custom i18n dict config
 # I18N = "./etc/i18n.json"
 
+# # custom i18n request header key
+# I18NHeaderKey = "X-Language"
+
 # metrics descriptions
 MetricsYamlFile = "./etc/metrics.yaml"
 
@@ -36,6 +39,11 @@ Label = "飞书机器人"
 # do not change Key
 Key = "feishu"
 
+[[NotifyChannels]]
+Label = "mm bot"
+# do not change Key
+Key = "mm"
+
 [[ContactKeys]]
 Label = "Wecom Robot Token"
 # do not change Key
@@ -51,6 +59,11 @@ Label = "Feishu Robot Token"
 # do not change Key
 Key = "feishu_robot_token"
 
+[[ContactKeys]]
+Label = "MatterMost Webhook URL"
+# do not change Key
+Key = "mm_webhook_url"
+
 [Log]
 # log write dir
 Dir = "logs"
@@ -98,6 +111,13 @@ AccessExpired = 1500
 RefreshExpired = 10080
 RedisKeyPrefix = "/jwt/"
 
+[ProxyAuth]
+# if proxy auth enabled, jwt auth is disabled
+Enable = false
+# username key in http proxy header
+HeaderUserNameKey = "X-User-Name"
+DefaultRoles = ["Standard"]
+
 [BasicAuth]
 user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
 
@@ -129,6 +149,7 @@ Email = "mail"
 
 [OIDC]
 Enable = false
+DiaplayName = "OIDC登录"
 RedirectURL = "http://n9e.com/callback"
 SsoAddr = "http://sso.example.org"
 ClientId = ""
@@ -141,6 +162,52 @@ Nickname = "nickname"
 Phone = "phone_number"
 Email = "email"
 
+[CAS]
+Enable = false
+DiaplayName = "CAS登录"
+SsoAddr = "https://cas.example.com/cas/"
+RedirectURL = "http://127.0.0.1:18000/callback/cas"
+CoverAttributes = false
+# cas user default roles
+DefaultRoles = ["Standard"]
+
+[CAS.Attributes]
+Nickname = "nickname"
+Phone = "phone_number"
+Email = "email"
+
+[OAuth]
+Enable = false
+DisplayName = "OAuth2登录"
+RedirectURL = "http://127.0.0.1:18000/callback/oauth"
+SsoAddr = "https://sso.example.com/oauth2/authorize"
+TokenAddr = "https://sso.example.com/oauth2/token"
+UserInfoAddr = "https://api.example.com/api/v1/user/info"
+ClientId = ""
+ClientSecret = ""
+CoverAttributes = true
+DefaultRoles = ["Standard"]
+UserinfoIsArray = false
+UserinfoPrefix = "data"
+Scopes = ["profile", "email", "phone"]
+
+[OAuth.Attributes]
+# Username must be defined
+Username = "username"
+Nickname = "nickname"
+Phone = "phone_number"
+Email = "email"
+
+# example
+# # nested : UserinfoIsArray=false, UserinfoPrefix="data"
+# # {"data":{"username":"123456","nickname":"姓名"},"code":0,"message":"ok"}
+# # nested and array : UserinfoIsArray=true, UserinfoPrefix="data"
+# # {"data":[{"username":"123456","nickname":"姓名"}],"code":0,"message":"ok"}
+# # flat : UserinfoIsArray=false, UserinfoPrefix=""
+# # {"username":"123456","nickname":"姓名"}
+# # flat and array : UserinfoIsArray=true, UserinfoPrefix=""
+# # [{"username":"123456","nickname":"姓名"}]
+
 [Redis]
 # address, ip:port or ip1:port,ip2:port for cluster and sentinel(SentinelAddrs)
 Address = "127.0.0.1:6379"
@@ -184,6 +251,7 @@ BasicAuthPass = ""
 Timeout = 30000
 DialTimeout = 3000
 MaxIdleConnsPerHost = 100
+Headers = ["X-From", "n9e"]
 
 [Ibex]
 Address = "http://127.0.0.1:10090"
@@ -191,4 +259,10 @@ Address = "http://127.0.0.1:10090"
 BasicAuthUser = "ibex"
 BasicAuthPass = "ibex"
 # unit: ms
-Timeout = 3000
+Timeout = 3000
+
+[TargetMetrics]
+TargetUp = '''max(max_over_time(target_up{ident=~"(%s)"}[%dm])) by (ident)'''
+LoadPerCore = '''max(max_over_time(system_load_norm_1{ident=~"(%s)"}[%dm])) by (ident)'''
+MemUtil = '''100-max(max_over_time(mem_available_percent{ident=~"(%s)"}[%dm])) by (ident)'''
+DiskUtil = '''max(max_over_time(disk_used_percent{ident=~"(%s)", path="/"}[%dm])) by (ident)'''

fe.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+TAG=$(curl -sX GET https://api.github.com/repos/n9e/fe-v5/releases/latest   | awk '/tag_name/{print $4;exit}' FS='[""]')
+VERSION=$(echo $TAG | sed 's/v//g')
+
+curl -o n9e-fe-${VERSION}.tar.gz -L https://github.com/n9e/fe-v5/releases/download/${TAG}/n9e-fe-${VERSION}.tar.gz  
+
+tar zxvf n9e-fe-${VERSION}.tar.gz

go.mod

@@ -1,16 +1,14 @@
 module github.com/didi/nightingale/v5
 
-go 1.14
+go 1.18
 
 require (
 	github.com/coreos/go-oidc v2.2.1+incompatible
 	github.com/dgrijalva/jwt-go v3.2.0+incompatible
-	github.com/fatih/camelcase v1.0.0 // indirect
-	github.com/fatih/structs v1.1.0 // indirect
 	github.com/gin-contrib/pprof v1.3.0
 	github.com/gin-gonic/gin v1.7.4
 	github.com/go-ldap/ldap/v3 v3.4.1
-	github.com/go-redis/redis/v8 v8.11.3
+	github.com/go-redis/redis/v9 v9.0.0-rc.1
 	github.com/gogo/protobuf v1.3.2
 	github.com/golang-jwt/jwt v3.2.2+incompatible
 	github.com/golang/protobuf v1.5.2
@@ -18,25 +16,73 @@ require (
 	github.com/google/uuid v1.3.0
 	github.com/json-iterator/go v1.1.12
 	github.com/koding/multiconfig v0.0.0-20171124222453-69c27309b2d7
+	github.com/mailru/easyjson v0.7.7
 	github.com/mattn/go-isatty v0.0.12
 	github.com/orcaman/concurrent-map v0.0.0-20210501183033-44dafcb38ecc
 	github.com/pkg/errors v0.9.1
-	github.com/pquerna/cachecontrol v0.1.0 // indirect
-	github.com/prometheus/client_golang v1.11.0
-	github.com/prometheus/common v0.26.0
+	github.com/prometheus/client_golang v1.12.2
+	github.com/prometheus/common v0.32.1
 	github.com/prometheus/prometheus v2.5.0+incompatible
 	github.com/tidwall/gjson v1.14.0
-	github.com/toolkits/pkg v1.2.9
+	github.com/toolkits/pkg v1.3.1-0.20220824084030-9f9f830a05d5
 	github.com/urfave/cli/v2 v2.3.0
-	golang.org/x/net v0.0.0-20210805182204-aaa1db679c0d // indirect
-	golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d
-	golang.org/x/sys v0.0.0-20210809222454-d867a43fc93e // indirect
-	google.golang.org/genproto v0.0.0-20211007155348-82e027067bd4 // indirect
-	google.golang.org/grpc v1.41.0 // indirect
-	gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc // indirect
+	golang.org/x/oauth2 v0.0.0-20210514164344-f6687ab2804c
 	gopkg.in/gomail.v2 v2.0.0-20160411212932-81ebce5c23df
-	gopkg.in/square/go-jose.v2 v2.6.0 // indirect
 	gorm.io/driver/mysql v1.1.2
 	gorm.io/driver/postgres v1.1.1
 	gorm.io/gorm v1.21.15
 )
+
+require (
+	github.com/Azure/go-ntlmssp v0.0.0-20200615164410-66371956d46c // indirect
+	github.com/BurntSushi/toml v0.3.1 // indirect
+	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/cespare/xxhash/v2 v2.1.2 // indirect
+	github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d // indirect
+	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
+	github.com/fatih/camelcase v1.0.0 // indirect
+	github.com/fatih/structs v1.1.0 // indirect
+	github.com/gin-contrib/sse v0.1.0 // indirect
+	github.com/go-asn1-ber/asn1-ber v1.5.1 // indirect
+	github.com/go-playground/locales v0.13.0 // indirect
+	github.com/go-playground/universal-translator v0.17.0 // indirect
+	github.com/go-playground/validator/v10 v10.4.1 // indirect
+	github.com/go-sql-driver/mysql v1.6.0 // indirect
+	github.com/grpc-ecosystem/grpc-gateway v1.16.0 // indirect
+	github.com/jackc/chunkreader/v2 v2.0.1 // indirect
+	github.com/jackc/pgconn v1.10.0 // indirect
+	github.com/jackc/pgio v1.0.0 // indirect
+	github.com/jackc/pgpassfile v1.0.0 // indirect
+	github.com/jackc/pgproto3/v2 v2.1.1 // indirect
+	github.com/jackc/pgservicefile v0.0.0-20200714003250-2b9c44734f2b // indirect
+	github.com/jackc/pgtype v1.8.1 // indirect
+	github.com/jackc/pgx/v4 v4.13.0 // indirect
+	github.com/jinzhu/inflection v1.0.0 // indirect
+	github.com/jinzhu/now v1.1.2 // indirect
+	github.com/josharian/intern v1.0.0 // indirect
+	github.com/leodido/go-urn v1.2.0 // indirect
+	github.com/matttproud/golang_protobuf_extensions v1.0.1 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
+	github.com/pquerna/cachecontrol v0.1.0 // indirect
+	github.com/prometheus/client_model v0.2.0 // indirect
+	github.com/prometheus/procfs v0.7.3 // indirect
+	github.com/russross/blackfriday/v2 v2.0.1 // indirect
+	github.com/shurcooL/sanitized_anchor_name v1.0.0 // indirect
+	github.com/spaolacci/murmur3 v1.1.0 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.0 // indirect
+	github.com/ugorji/go/codec v1.1.7 // indirect
+	go.uber.org/automaxprocs v1.4.0 // indirect
+	golang.org/x/crypto v0.0.0-20210817164053-32db794688a5 // indirect
+	golang.org/x/net v0.0.0-20220722155237-a158d28d115b // indirect
+	golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f // indirect
+	golang.org/x/text v0.3.7 // indirect
+	google.golang.org/appengine v1.6.6 // indirect
+	google.golang.org/genproto v0.0.0-20211007155348-82e027067bd4 // indirect
+	google.golang.org/grpc v1.41.0 // indirect
+	google.golang.org/protobuf v1.27.1 // indirect
+	gopkg.in/alexcesaro/quotedprintable.v3 v3.0.0-20150716171945-2caba252f4dc // indirect
+	gopkg.in/square/go-jose.v2 v2.6.0 // indirect
+	gopkg.in/yaml.v2 v2.4.0 // indirect
+)