Re: [PATCH v3 0/5] Dump off-cpu samples directly

[Ian Rogers]

On Fri, Jul 26, 2024 at 3:28 AM Howard Chu <howardchu95@xxxxxxxxx> wrote:
>
> As mentioned in: https://bugzilla.kernel.org/show_bug.cgi?id=207323
>
> Currently, off-cpu samples are dumped when perf record is exiting. This
> results in off-cpu samples being after the regular samples. This patch
> series makes possible dumping off-cpu samples on-the-fly, directly into
> perf ring buffer. And it dispatches those samples to the correct format
> for perf.data consumers.
>
> Changes in v3:
>  - Add off-cpu-thresh argument
>  - Process direct off-cpu samples in post
>
> Changes in v2:
>  - Remove unnecessary comments.
>  - Rename function off_cpu_change_type to off_cpu_prepare_parse
>
> Before:
> ```
>      migration/0      21 [000] 27981.041319: 2944637851    cycles:P:  ffffffff90d2e8aa record_times+0xa ([kernel.kallsyms])
>             perf  770116 [001] 27981.041375:          1    cycles:P:  ffffffff90ee4960 event_function+0xf0 ([kernel.kallsyms])
>             perf  770116 [001] 27981.041377:          1    cycles:P:  ffffffff90c184b1 intel_bts_enable_local+0x31 ([kernel.kallsyms])
>             perf  770116 [001] 27981.041379:      51611    cycles:P:  ffffffff91a160b0 native_sched_clock+0x30 ([kernel.kallsyms])
>      migration/1      26 [001] 27981.041400: 4227682775    cycles:P:  ffffffff90d06a74 wakeup_preempt+0x44 ([kernel.kallsyms])
>      migration/2      32 [002] 27981.041477: 4159401534    cycles:P:  ffffffff90d11993 update_load_avg+0x63 ([kernel.kallsyms])
>
> sshd  708098 [000] 18446744069.414584:     286392 offcpu-time:
>             79a864f1c8bb ppoll+0x4b (/usr/lib/libc.so.6)
>             585690935cca [unknown] (/usr/bin/sshd)
> ```
>
> After:
> ```
>             perf  774767 [003] 28178.033444:        497           cycles:P:  ffffffff91a160c3 native_sched_clock+0x43 ([kernel.kallsyms])
>             perf  774767 [003] 28178.033445:     399440           cycles:P:  ffffffff91c01f8d nmi_restore+0x25 ([kernel.kallsyms])
>          swapper       0 [001] 28178.036639:  376650973           cycles:P:  ffffffff91a1ae99 intel_idle+0x59 ([kernel.kallsyms])
>          swapper       0 [003] 28178.182921:  348779378           cycles:P:  ffffffff91a1ae99 intel_idle+0x59 ([kernel.kallsyms])
>     blueman-tray    1355 [000] 28178.627906:  100184571 offcpu-time-direct:
>             7528eef1c39d __poll+0x4d (/usr/lib/libc.so.6)
>             7528edf7d8fd [unknown] (/usr/lib/libglib-2.0.so.0.8000.2)
>             7528edf1af95 g_main_context_iteration+0x35 (/usr/lib/libglib-2.0.so.0.8000.2)
>             7528eda4ab86 g_application_run+0x1f6 (/usr/lib/libgio-2.0.so.0.8000.2)
>             7528ee6aa596 [unknown] (/usr/lib/libffi.so.8.1.4)
>             7fff24e862d8 [unknown] ([unknown])
>
>
>     blueman-tray    1355 [000] 28178.728137:  100187539 offcpu-time-direct:
>             7528eef1c39d __poll+0x4d (/usr/lib/libc.so.6)
>             7528edf7d8fd [unknown] (/usr/lib/libglib-2.0.so.0.8000.2)
>             7528edf1af95 g_main_context_iteration+0x35 (/usr/lib/libglib-2.0.so.0.8000.2)
>             7528eda4ab86 g_application_run+0x1f6 (/usr/lib/libgio-2.0.so.0.8000.2)
>             7528ee6aa596 [unknown] (/usr/lib/libffi.so.8.1.4)
>             7fff24e862d8 [unknown] ([unknown])
>
>
>          swapper       0 [000] 28178.463253:  195945410           cycles:P:  ffffffff91a1ae99 intel_idle+0x59 ([kernel.kallsyms])
>      dbus-broker     412 [002] 28178.464855:  376737008           cycles:P:  ffffffff91c000a0 entry_SYSCALL_64+0x20 ([kernel.kallsyms])
> ```
>
> Howard Chu (5):
>   perf record off-cpu: Add direct off-cpu event
>   perf record off-cpu: Dumping samples in BPF
>   perf record off-cpu: processing of embedded sample
>   perf record off-cpu: save embedded sample type
>   perf record off-cpu: Add direct off-cpu test

This worked nicely on some tests with me. I'm not sure about
separating offcpu-time and offcpu-time-direct rather than the just 1
event. I also immediately set --off-cpu-thresh=1 so maybe milliseconds
should be microseconds, and the default shouldn't be to not use the
direct samples.

Thanks,
Ian

>  tools/perf/builtin-record.c             |   2 +
>  tools/perf/builtin-script.c             |   2 +-
>  tools/perf/tests/builtin-test.c         |   1 +
>  tools/perf/tests/shell/record_offcpu.sh |  29 +++++
>  tools/perf/tests/tests.h                |   1 +
>  tools/perf/tests/workloads/Build        |   1 +
>  tools/perf/tests/workloads/offcpu.c     |  16 +++
>  tools/perf/util/bpf_off_cpu.c           |  53 ++++++++-
>  tools/perf/util/bpf_skel/off_cpu.bpf.c  | 143 ++++++++++++++++++++++++
>  tools/perf/util/evsel.c                 |  16 ++-
>  tools/perf/util/evsel.h                 |  13 +++
>  tools/perf/util/header.c                |  12 ++
>  tools/perf/util/off_cpu.h               |   1 +
>  tools/perf/util/record.h                |   1 +
>  tools/perf/util/session.c               |  23 +++-
>  15 files changed, 309 insertions(+), 5 deletions(-)
>  create mode 100644 tools/perf/tests/workloads/offcpu.c
>
> --
> 2.45.2
>