From mboxrd@z Thu Jan 1 00:00:00 1970 From: Glauber Costa Subject: [PATCH v3 0/6] per cgroup /proc/stat statistics Date: Wed, 30 May 2012 13:48:31 +0400 Message-ID: <1338371317-5980-1-git-send-email-glommer@parallels.com> Return-path: Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org Cc: cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, devel-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org, Paul Turner , Peter Zijlstra , Tejun Heo , "Eric W. Biederman" , handai.szj-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org, Andrew.Phillips-xheW4WVAX9Y@public.gmane.org, Serge Hallyn Hi This is a rework of my v2 series taking into account Paul Turner's comments. All the series is the same except for the patch that collets nr_switches that is now completely reworked. It is out of schedule(), relegated to a scheduler hook. Only difference from Paul's suggestion is that I added a new one, instead of messing with put_prev_task + pick_next_task pairs. In the patchset that adds it, I'll try to argue for my solution. Hope this is acceptable, and please let me know of any other concerns. v2: * completely reworked nr_switches gathering * separated per-se sleep_start to be more clear about it Glauber Costa (6): measure exec_clock for rt sched entities account guest time per-cgroup as well. expose fine-grained per-cpu data for cpuacct stats add a new scheduler hook for context switch Also record sleep start for a task group expose per-taskgroup schedstats in cgroup include/linux/sched.h | 1 + kernel/sched/core.c | 166 +++++++++++++++++++++++++++++++++++++++++++++++-- kernel/sched/fair.c | 42 ++++++++++++- kernel/sched/rt.c | 20 ++++++ kernel/sched/sched.h | 6 ++ 5 files changed, 228 insertions(+), 7 deletions(-) -- 1.7.10.2