We want to add this to libcontainer so that we can change docker so that
when you volume mount into a labeled container, we want to allow the
administrator/user the ability to tell docker to fix the labels on the mount.
Docker-DCO-1.1-Signed-off-by: Dan Walsh <dwalsh@redhat.com> (github: rhatdan)
Although it has some overlap with nsinit utility, it is useful to test
cgroup functinality directly and try out new or internal features not
exposed through nsinit.
It still needs some work as I haven't added enough systemd support yet.
I also need to expose an enter method.
Docker-DCO-1.1-Signed-off-by: Rohit Jnagal <jnagal@google.com> (github: rjnagal)
standalone cgroup test util. systemd does auto cleanup on empty, so
doesn't need an extra interface.
Docker-DCO-1.1-Signed-off-by: Rohit Jnagal <jnagal@google.com> (github: rjnagal)
Move concepts into specific files for easy management
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@docker.com> (github: crosbymichael)
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@docker.com> (github: vmarmol)
This version has mostly the behavior available today and the
functionality agreed upon in other PRs. Further changes will be sent as
smaller PRs for discussion.
Docker-DCO-1.1-Signed-off-by: Victor Marmol <vmarmol@google.com> (github: vmarmol)
Ensure that the command is killed if we receive an error from the child
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@docker.com> (github: crosbymichael)
We use a unix domain socketpair instead of a pipe for the sync pipe,
which allows us to use two-way shutdown. After sending the
context we shut down the write side which lets the child know
it finished reading.
We then block on a read in the parent for the child closing the file
(ensuring we close our version of it too) to sync for when the child
is finished initializing. If the read is non-empty we assume this
is an error report and fail with an error. Otherwise we continue as
before.
This also means we're now calling back the start callback later,
meaning at that point its more likely to have succeeded, as well as
having consumed all the container resources (like volume mounts,
making it safe to e.g. unmount them when the start callback is
called).
Docker-DCO-1.1-Signed-off-by: Alexander Larsson <alexl@redhat.com> (github: alexlarsson)
nsinit must be run as root.
Tidy up the README somewhat to clarify the distinction between
libcontainer and the nsinit CLI.
Fix some typos in other files.
Docker-DCO-1.1-Signed-off-by: Glyn Normington <gnormington@gopivotal.com> (github: glyn)
2. Introducing a new checkpoint file 'network.stats' which will contain the network runtime information (veth interface names for now).
3. Adding network stats to 'nsinit stats'.
4. Added a libcontainer Stats API to get both network and cgroup stats
Docker-DCO-1.1-Signed-off-by: Vishnu Kannan <vishnuk@google.com> (github: vishh)
Victor Marmol
Dan Walsh
Rohit Jnagal
Michael Crosby
Lee Treveil
Rohit Jnagal
Vishnu Kannan
Tianon Gravi
maebashi
Alexander Larsson
Glyn Normington