mirror of
https://github.com/torvalds/linux.git
synced 2024-12-24 11:51:27 +00:00
0997a2662f
Peter suggested that using the exclusive mode in perf could avoid some
problems with bad scheduling of groups. Exclusive is implemented in the
kernel, but wasn't exposed by the perf tool, so hard to use without
custom low level API users.
Add support for marking groups or events with :e for exclusive in the
perf tool. The implementation is basically the same as the existing
pinned attribute.
Committer testing:
# perf test "parse event"
6: Parse event definition strings : Ok
# perf test -v "parse event" |& grep :u*e
running test 56 'instructions:uep'
running test 57 '{cycles,cache-misses,branch-misses}:e'
#
#
# grep "model name" -m1 /proc/cpuinfo
model name : AMD Ryzen 9 3900X 12-Core Processor
#
# perf stat -a -e '{cycles,cache-misses,branch-misses}:e' sleep 1
Performance counter stats for 'system wide':
<not counted> cycles (0.00%)
<not counted> cache-misses (0.00%)
<not counted> branch-misses (0.00%)
1.001269893 seconds time elapsed
Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog
# echo 0 > /proc/sys/kernel/nmi_watchdog
# perf stat -a -e '{cycles,cache-misses,branch-misses}:e' sleep 1
Performance counter stats for 'system wide':
1,298,663,141 cycles
30,962,215 cache-misses
5,325,150 branch-misses
1.001474934 seconds time elapsed
#
# The output for asking for precise events on AMD needs to improve, it
# supposedly works only for system wide or per CPU
#
# perf stat -a -e '{cycles,cache-misses,branch-misses}:uep' sleep 1
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles).
/bin/dmesg | grep -i perf may provide additional information.
# perf stat -a -e '{cycles,cache-misses,branch-misses}:ue' sleep 1
Performance counter stats for 'system wide':
746,363,126 cycles
16,881,611 cache-misses
2,871,259 branch-misses
1.001636066 seconds time elapsed
#
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20201014144255.22699-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|
||
|---|---|---|
| .. | ||
| attr | ||
| shell | ||
| .gitignore | ||
| api-io.c | ||
| attr.c | ||
| attr.py | ||
| backward-ring-buffer.c | ||
| bitmap.c | ||
| bp_account.c | ||
| bp_signal_overflow.c | ||
| bp_signal.c | ||
| bpf-script-example.c | ||
| bpf-script-test-kbuild.c | ||
| bpf-script-test-prologue.c | ||
| bpf-script-test-relocation.c | ||
| bpf.c | ||
| Build | ||
| builtin-test.c | ||
| clang.c | ||
| code-reading.c | ||
| cpumap.c | ||
| demangle-java-test.c | ||
| dso-data.c | ||
| dwarf-unwind.c | ||
| event_update.c | ||
| event-times.c | ||
| evsel-roundtrip-name.c | ||
| evsel-tp-sched.c | ||
| expand-cgroup.c | ||
| expr.c | ||
| fdarray.c | ||
| genelf.c | ||
| hists_common.c | ||
| hists_common.h | ||
| hists_cumulate.c | ||
| hists_filter.c | ||
| hists_link.c | ||
| hists_output.c | ||
| is_printable_array.c | ||
| keep-tracking.c | ||
| kmod-path.c | ||
| llvm.c | ||
| llvm.h | ||
| make | ||
| maps.c | ||
| mem2node.c | ||
| mem.c | ||
| mmap-basic.c | ||
| mmap-thread-lookup.c | ||
| openat-syscall-all-cpus.c | ||
| openat-syscall-tp-fields.c | ||
| openat-syscall.c | ||
| parse-events.c | ||
| parse-metric.c | ||
| parse-no-sample-id-all.c | ||
| pe-file-parsing.c | ||
| pe-file.c | ||
| pe-file.exe | ||
| pe-file.exe.debug | ||
| perf-hooks.c | ||
| perf-record.c | ||
| perf-targz-src-pkg | ||
| pfm.c | ||
| pmu-events.c | ||
| pmu.c | ||
| python-use.c | ||
| sample-parsing.c | ||
| sdt.c | ||
| stat.c | ||
| sw-clock.c | ||
| switch-tracking.c | ||
| task-exit.c | ||
| tests.h | ||
| thread-map.c | ||
| thread-maps-share.c | ||
| time-utils-test.c | ||
| topology.c | ||
| unit_number__scnprintf.c | ||
| vmlinux-kallsyms.c | ||
| wp.c | ||