linux/tools
Namhyung Kim c587e77e10 perf stat: Do not delay the workload with --delay
The -D/--delay option is to delay the measure after the program starts.
But the current code goes to sleep before starting the program so the
program is delayed too.  This is not the intention, let's fix it.

Before:

  $ time sudo ./perf stat -a -e cycles -D 3000 sleep 4
  Events disabled
  Events enabled

   Performance counter stats for 'system wide':

       4,326,949,337      cycles

         4.007494118 seconds time elapsed

  real	0m7.474s
  user	0m0.356s
  sys	0m0.120s

It ran the workload for 4 seconds and gave the 3 second delay.  So it
should skip the first 3 second and measure the last 1 second only.  But
as you can see, it delays 3 seconds and ran the workload after that for
4 seconds.  So the total time (real) was 7 seconds.

After:

  $ time sudo ./perf stat -a -e cycles -D 3000 sleep 4
  Events disabled
  Events enabled

   Performance counter stats for 'system wide':

       1,063,551,013      cycles

         1.002769510 seconds time elapsed

  real	0m4.484s
  user	0m0.385s
  sys	0m0.086s

The bug was introduced when it changed enablement of system-wide events
with a command line workload.  But it should've considered the initial
delay case.  The code was reworked since then (in bb8bc52e75) so I'm
afraid it won't be applied cleanly.

Fixes: d0a0a51149 ("perf stat: Fix forked applications enablement of counters")
Reported-by: Kevin Nomura <nomurak@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Link: https://lore.kernel.org/r/20221212230820.901382-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-12-14 15:28:19 -03:00
..
accounting
arch x86/cpu: Restore AMD's DE_CFG MSR after resume 2022-11-15 10:15:58 -08:00
bootconfig
bpf bpftool: Fix NULL pointer dereference when pin {PROG, MAP, LINK} without FILE 2022-11-02 12:05:42 +01:00
build perf bpf: Fix build with libbpf 0.7.0 by checking if bpf_program__set_insns() is available 2022-10-25 17:40:48 -03:00
certs
cgroup iocost_monitor: reorder BlkgIterator 2022-09-23 16:57:10 -10:00
counter
debugging tools: Add new "test" taint to kernel-chktaint 2022-09-07 14:51:12 -06:00
edid
firewire
firmware
gpio
hv
iio tools: iio: iio_generic_buffer: Fix read size 2022-11-01 08:48:13 +00:00
include bpf-for-netdev 2022-11-03 19:51:02 -07:00
io_uring
kvm/kvm_stat tools/kvm_stat: update exit reasons for vmx/svm/aarch64/userspace 2022-11-09 12:26:52 -05:00
laptop
leds
lib tools lib traceevent: Remove libtraceevent 2022-12-14 11:16:12 -03:00
memory-model
objtool - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in 2022-10-10 17:53:04 -07:00
pci
pcmcia
perf perf stat: Do not delay the workload with --delay 2022-12-14 15:28:19 -03:00
power pm-graph v5.10 2022-10-25 17:46:15 +02:00
rcu
scripts
spi
testing Networking fixes for 6.1-rc6, including fixes from bpf 2022-11-17 08:58:36 -08:00
thermal
time
tracing
usb
verification rv/dot2c: Make automaton definition static 2022-10-20 16:02:45 -04:00
virtio virtio_test: fixup for vq reset 2022-09-27 18:30:49 -04:00
vm tools/vm/page_owner_sort: fix -f option 2022-09-11 20:25:51 -07:00
wmi
Makefile