scrape etcd in http mode
This commit is contained in:
kongfei
parent
001cc3e2d5
commit
6587f49e94
|
|
@ -0,0 +1,26 @@
|
|||
# monitoring kubernetes control plane with plugin prometheus
|
||||
|
||||
|
||||
## if your control plane is in pod, for example, you use kubeadm build k8s cluster. Then kube-controller-manager, kube-scheduler and etcd need some extrac work to be discovery.
|
||||
|
||||
### create service for kube-controller-manager
|
||||
1. `kubectl apply -f controller-service.yaml`
|
||||
2. edit `/etc/kubernetes/manifests/kube-controller-manager.yaml` , modify or add one line `- --bind-address=0.0.0.0`
|
||||
3. wait kube-controller-manager to restart
|
||||
|
||||
### create service for kube-scheduler
|
||||
3. `kubectl apply -f scheduler-service.yaml`
|
||||
4. edit `/etc/kubernetes/manifests/kube-scheduler.yaml` , modify or add one line `- --bind-address=0.0.0.0`
|
||||
5. wait kube-scheduler to restart
|
||||
|
||||
### create service for etcd
|
||||
6. `kubectl apply -f etcd-service-http.yaml`
|
||||
7. edit `/etc/kubernetes/manifests/etcd.yaml` , modify `- --listen-metrics-urls=http://127.0.0.1:2381` to `- --listen-metrics-urls=http://0.0.0.0:2381`
|
||||
8. wait etcd to restart
|
||||
|
||||
### create all other objects with deployment
|
||||
9. edit deployment.yaml and modify it with your own configure.
|
||||
i. replace ${CATEGRAF_NAMESPACE} which located in ClusterRoleBinding part
|
||||
ii. replace ${NSERVER_SERVICE_WITH_PORT} which located in ConfigMap part config.toml and in_cluster_scrape.yaml
|
||||
|
||||
10. `kubectl apply -f deplyment-etcd-http.yaml -n monitoring`
|
||||
|
|
@ -0,0 +1,279 @@
|
|||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
annotations: {}
|
||||
labels:
|
||||
app: n9e
|
||||
component: categraf
|
||||
name: categraf-role
|
||||
rules:
|
||||
- apiGroups: [""]
|
||||
resources:
|
||||
- nodes
|
||||
- nodes/metrics
|
||||
- services
|
||||
- endpoints
|
||||
- pods
|
||||
verbs: ["get", "list", "watch"]
|
||||
- apiGroups:
|
||||
- extensions
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs: ["get", "list", "watch"]
|
||||
- nonResourceURLs: ["/metrics", "/metrics/cadvisor"]
|
||||
verbs: ["get"]
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
annotations: {}
|
||||
labels:
|
||||
app: n9e
|
||||
component: categraf
|
||||
name: categraf-serviceaccount
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
annotations: {}
|
||||
labels:
|
||||
app: n9e
|
||||
component: categraf
|
||||
name: categraf-rolebinding
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: categraf-role
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: categraf-serviceaccount
|
||||
namespace: ${CATEGRAF_NAMESPACE}
|
||||
---
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: categraf-config
|
||||
apiVersion: v1
|
||||
data:
|
||||
config.toml: |
|
||||
[global]
|
||||
# whether print configs
|
||||
print_configs = true
|
||||
|
||||
# add label(agent_hostname) to series
|
||||
# "" -> auto detect hostname
|
||||
# "xx" -> use specified string xx
|
||||
# "$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]
|
||||
# region = "shanghai"
|
||||
# env = "localhost"
|
||||
|
||||
[writer_opt]
|
||||
# default: 2000
|
||||
batch = 2000
|
||||
# channel(as queue) size
|
||||
chan_size = 10000
|
||||
|
||||
[[writers]]
|
||||
url = "http://${NSERVER_SERVICE_WITH_PORT}/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
|
||||
prometheus.toml: |
|
||||
[prometheus]
|
||||
enable = true
|
||||
scrape_config_file="/opt/categraf/scrape/in_cluster_scrape.yaml"
|
||||
## log level, debug warn info error
|
||||
log_level="info"
|
||||
## wal reserve time duration, default value is 2 hour
|
||||
# wal_min_duration=2
|
||||
---
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: scrape-config
|
||||
apiVersion: v1
|
||||
data:
|
||||
in_cluster_scrape.yaml: |
|
||||
global:
|
||||
scrape_interval: 15s
|
||||
#external_labels:
|
||||
# cluster: test
|
||||
# replica: 0
|
||||
scrape_configs:
|
||||
- job_name: "apiserver"
|
||||
metrics_path: "/metrics"
|
||||
kubernetes_sd_configs:
|
||||
- role: endpoints
|
||||
scheme: https
|
||||
tls_config:
|
||||
insecure_skip_verify: true
|
||||
authorization:
|
||||
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[
|
||||
__meta_kubernetes_namespace,
|
||||
__meta_kubernetes_service_name,
|
||||
__meta_kubernetes_endpoint_port_name,
|
||||
]
|
||||
action: keep
|
||||
regex: default;kubernetes;https
|
||||
|
||||
- job_name: "controller-manager"
|
||||
metrics_path: "/metrics"
|
||||
kubernetes_sd_configs:
|
||||
- role: endpoints
|
||||
scheme: https
|
||||
tls_config:
|
||||
insecure_skip_verify: true
|
||||
authorization:
|
||||
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[
|
||||
__meta_kubernetes_namespace,
|
||||
__meta_kubernetes_service_name,
|
||||
__meta_kubernetes_endpoint_port_name,
|
||||
]
|
||||
action: keep
|
||||
regex: kube-system;kube-controller-manager;https
|
||||
|
||||
- job_name: "scheduler"
|
||||
metrics_path: "/metrics"
|
||||
kubernetes_sd_configs:
|
||||
- role: endpoints
|
||||
scheme: https
|
||||
tls_config:
|
||||
insecure_skip_verify: true
|
||||
authorization:
|
||||
credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[
|
||||
__meta_kubernetes_namespace,
|
||||
__meta_kubernetes_service_name,
|
||||
__meta_kubernetes_endpoint_port_name,
|
||||
]
|
||||
action: keep
|
||||
regex: kube-system;kube-scheduler;https
|
||||
|
||||
- job_name: "etcd"
|
||||
metrics_path: "/metrics"
|
||||
kubernetes_sd_configs:
|
||||
- role: endpoints
|
||||
scheme: http
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[
|
||||
__meta_kubernetes_namespace,
|
||||
__meta_kubernetes_service_name,
|
||||
__meta_kubernetes_endpoint_port_name,
|
||||
]
|
||||
action: keep
|
||||
regex: kube-system;etcd;http
|
||||
|
||||
- job_name: "coredns"
|
||||
metrics_path: "/metrics"
|
||||
kubernetes_sd_configs:
|
||||
- role: endpoints
|
||||
scheme: http
|
||||
relabel_configs:
|
||||
- source_labels:
|
||||
[
|
||||
__meta_kubernetes_namespace,
|
||||
__meta_kubernetes_service_name,
|
||||
__meta_kubernetes_endpoint_port_name,
|
||||
]
|
||||
action: keep
|
||||
regex: kube-system;kube-dns;metrics
|
||||
|
||||
remote_write:
|
||||
- url: 'http://${NSERVER_SERVICE_WITH_PORT}/prometheus/v1/write'
|
||||
---
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app: n9e
|
||||
component: categraf
|
||||
name: nightingale-categraf
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: n9e
|
||||
component: categraf
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: n9e
|
||||
component: categraf
|
||||
spec:
|
||||
containers:
|
||||
- env:
|
||||
- name: TZ
|
||||
value: Asia/Shanghai
|
||||
- name: HOSTNAME
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
apiVersion: v1
|
||||
fieldPath: spec.nodeName
|
||||
- name: HOSTIP
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
apiVersion: v1
|
||||
fieldPath: status.hostIP
|
||||
image: flashcatcloud/categraf:latest
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: categraf
|
||||
command: ["/usr/bin/categraf"]
|
||||
args: ["-configs", "/opt/categraf/conf"]
|
||||
resources: {}
|
||||
terminationMessagePath: /dev/termination-log
|
||||
terminationMessagePolicy: File
|
||||
volumeMounts:
|
||||
- mountPath: /opt/categraf/conf
|
||||
name: categraf-config
|
||||
- mountPath: /opt/categraf/scrape
|
||||
name: scrape-config
|
||||
dnsPolicy: ClusterFirst
|
||||
hostNetwork: false
|
||||
restartPolicy: Always
|
||||
schedulerName: default-scheduler
|
||||
securityContext: {}
|
||||
serviceAccountName: categraf-serviceaccount
|
||||
terminationGracePeriodSeconds: 30
|
||||
tolerations:
|
||||
- effect: NoSchedule
|
||||
operator: Exists
|
||||
volumes:
|
||||
- configMap:
|
||||
defaultMode: 420
|
||||
name: categraf-config
|
||||
name: categraf-config
|
||||
- configMap:
|
||||
defaultMode: 420
|
||||
name: scrape-config
|
||||
name: scrape-config
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
namespace: kube-system
|
||||
name: etcd
|
||||
labels:
|
||||
k8s-app: etcd
|
||||
spec:
|
||||
selector:
|
||||
component: etcd
|
||||
type: ClusterIP
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: http
|
||||
port: 2381
|
||||
targetPort: 2381
|
||||
protocol: TCP
|
||||
Loading…
Reference in New Issue