Re: [PATCH] perf: update perf_cgroup time for ancestor cgroup(s)

2018-03-12 Thread Song Liu
> On Mar 12, 2018, at 5:38 AM, Peter Zijlstra wrote: > > On Sun, Mar 11, 2018 at 10:32:44PM -0700, Song Liu wrote: >> When a perf_event is attached to parent cgroup, it should count events >> for all children cgroups: >> >> parent_group < perf_event >> \ >>- child_group < proc

Re: [PATCH] perf: update perf_cgroup time for ancestor cgroup(s)

2018-03-12 Thread Peter Zijlstra
On Sun, Mar 11, 2018 at 10:32:44PM -0700, Song Liu wrote: > When a perf_event is attached to parent cgroup, it should count events > for all children cgroups: > > parent_group < perf_event >\ > - child_group < process(es) > > However, in our tests, we found this perf_event can

[PATCH] perf: update perf_cgroup time for ancestor cgroup(s)

2018-03-11 Thread Song Liu
When a perf_event is attached to parent cgroup, it should count events for all children cgroups: parent_group < perf_event \ - child_group < process(es) However, in our tests, we found this perf_event cannot report reliable results. This is because perf_event->cgrp and cpuctx->