Skip to content

Optimize perf ring-buffer

Peter Zijlstra lkml 1 version In review

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest5 patches 16 repliesIn review

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/5perf: Disallow mmap() on per-task inherited eventskernel/perf_event.c+8 -03 replies
2/5perf: Remove IRQ-disable from the perf_output pathinclude/linux/perf_event.h kernel/perf_event.c+30 -690 replies
3/5perf: Convert the perf output buffer to local_tinclude/linux/perf_event.h kernel/perf_event.c+22 -230 replies
4/5perf: Avoid local_xchginclude/linux/perf_event.h kernel/perf_event.c+3 -10 replies
5/5perf: Implement perf_output_addr()arch/x86/kernel/cpu/perf_event_intel_ds.c include/linux/perf_event.h kernel/perf_event.c+74 -2012 replies

Reviews trailers per patch

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

Read the v1 thread

Cover letter [PATCH 0/5] Optimize perf ring-buffer

This patch-set optimizes the perf ring-buffer by removing IRQ disable and all LOCK ops from the fast paths.

There's also an RFC patch that adds perf_output_addr() which will allow you to write directly to the buffer, however I'm not sure how to go about using it for the trace events since we need to multiplex event -- there is no single copy of the actual event.