Skip to content

tracing/workqueue fixes

Anton Blanchard lkml 1 version In review

Get series with b4
b4 am 20090922023920.GA31801@kryten

Versions newest first

  1. v1 Latest2 patches 4 repliesIn review

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/2tracing/workqueue: Use %pf in workqueue trace eventsinclude/trace/events/workqueue.h+2 -22 replies
2/2tracing/workqueue: Rename workqueue_execute to worklet_entry and add worklet_exitinclude/trace/events/workqueue.h kernel/trace/trace_workqueue.c kernel/workqueue.c+29 -72 replies

Reviews trailers per patch

No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.

Read the v1 thread

Cover letter [PATCH 0/2] tracing/workqueue fixes

Hi,

The workqueue tracepoint patchset looks to have stalled for a bit. While we discuss how much functionality we want in kernel, I think we have a solid case for tracing the latency caused by workqueue events.

For an example we can look at the rt_worker_func work. As memory grew its duration would also grow, and I measured 14ms spikes on one box. Once found we placed a cap on it:

http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=c9503e0fe052020e0294cd07d0ecd982eb7c9177

The following patches add entry and exit tracepoints so we can find these things easily.

Anton