Introduce own perf buffer for important events #237
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There is now a second perf buffer for so called "control plane" events.
This means that the chances of them being dropped should be
significantly lower. The reason for this change is, that events such as
cgroup rmdir
will trigger the cleanup of cgroup related caches.Additionally we now leverage the path found in the
cgroup mkdir
eventto prepopulate a cache in the cgroup client, which means that the costly
filesystem scan to figure out the path of a cgroup should be triggered
far less often.
With the handling of
cgroup rmdir
event out of sync with the rest ofthe events from ebpf, the cgroup related cleanup logic has also been
changed. Instead of performing the cleanup straight away, it is delayed
by a minute. This should give the rest of the system enough time to
handle any events still targeted at the removed cgroup.