perf test: Use sqrtloop workload to test bperf event

Replace `brstack` workload with `sqrtloop` workload, because `sqrtloop`
workload contains fork(), which is suitable for testing the bperf event
i

perf test: Use sqrtloop workload to test bperf event

Replace `brstack` workload with `sqrtloop` workload, because `sqrtloop`
workload contains fork(), which is suitable for testing the bperf event
inheritance feature.

Signed-off-by: Tengda Wu <[email protected]>
Cc: [email protected]
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Namhyung Kim <[email protected]>

show more ...

perf test: Tag parallel failing shell tests with "(exclusive)"

Some shell tests compete for resources and so can't run with other
tests, tag such tests. The "(exclusive)" stems from shared/exclusiv

perf test: Tag parallel failing shell tests with "(exclusive)"

Some shell tests compete for resources and so can't run with other
tests, tag such tests. The "(exclusive)" stems from shared/exclusive
to describe how the tests run as if holding a lock.

For ARM/coresight tests:
Suggested-by: James Clark <[email protected]>

Additional failing tests:
Suggested-by: Namhyung Kim <[email protected]>

Tested-by: James Clark <[email protected]>
Signed-off-by: Ian Rogers <[email protected]>
Cc: Colin Ian King <[email protected]>
Cc: Howard Chu <[email protected]>
Cc: Weilin Wang <[email protected]>
Cc: Ilya Leoshkevich <[email protected]>
Cc: Thomas Richter <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Dapeng Mi <[email protected]>
Cc: Athira Jajeev <[email protected]>
Cc: Michael Petlan <[email protected]>
Cc: Veronika Molnarova <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Namhyung Kim <[email protected]>

show more ...

perf test stat_bpf_counter.sh: Stabilize the test results

The test has been failing for some time when two separate runs of
perf benchmarks are recorded for cycles events and their counts are
compar

perf test stat_bpf_counter.sh: Stabilize the test results

The test has been failing for some time when two separate runs of
perf benchmarks are recorded for cycles events and their counts are
compared, while once the recording was done with option --bpf-counters
and once without it. It is expected that the count of the samples
should be within a certain range, firstly the difference was set to be
within 10%, which was then later raised to 20%. However, the test case
keeps failing on certain architectures as recording the provided
benchmark can produce completely different counts based on the
current load of the system.

Sampling two separate runs on intel-eaglestream-spr-13 of "perf stat
--no-big-num -e cycles -- perf bench sched messaging -g 1 -l 100 -t":

Performance counter stats for 'perf bench sched messaging -g 1 -l 100 -t':

396782898 cycles

0.010051983 seconds time elapsed

0.008664000 seconds user
0.097058000 seconds sys

Performance counter stats for 'perf bench sched messaging -g 1 -l 100 -t':

1431133032 cycles

0.021803714 seconds time elapsed

0.023377000 seconds user
0.349918000 seconds sys

, which is ranging from 400mil to 1400mil samples.

Instead of recording the cycles use instructions event, which provides
more stable values. At the same time change the tested workload to one
of the provided testing workloads by perf that is not based on a
scheduler, which can provide another dependency on the current load.

Sampling instructions event with the new workload provide much more
stable results on intel-eaglestream-spr-13 of "perf stat --no-big-num
-e instructions -- perf test -w brstack":

Performance counter stats for 'perf test -w brstack':

64584494 instructions

0.009173945 seconds time elapsed

0.007262000 seconds user
0.002071000 seconds sys

Performance counter stats for 'perf test -w brstack':

64672669 instructions

0.008888135 seconds time elapsed

0.005018000 seconds user
0.004018000 seconds sys

Signed-off-by: Veronika Molnarova <[email protected]>
Acked-by: Namhyung Kim <[email protected]>
Cc: [email protected]
Signed-off-by: Namhyung Kim <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

perf test bpf-counters: Add test for BPF event modifier

Refactor test to better enable sharing of logic, to give an idea of
progress and introduce test functions. Add test of measuring both
cycles a

perf test bpf-counters: Add test for BPF event modifier

Refactor test to better enable sharing of logic, to give an idea of
progress and introduce test functions. Add test of measuring both
cycles and cycles:b simultaneously.

Signed-off-by: Ian Rogers <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Athira Rajeev <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Thomas Richter <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...

perf test: raise limit to 20 percent for perf_stat_--bpf-counters_test

This test case often fails on s390 (about 2 out of 10) because the
10% percent limit on the difference between --bpf-counters e

perf test: raise limit to 20 percent for perf_stat_--bpf-counters_test

This test case often fails on s390 (about 2 out of 10) because the
10% percent limit on the difference between --bpf-counters event counting
and s390 hardware counting is more than 10% in all failure cases.
Raise the limit to 20% on s390 and the test case succeeds.

Signed-off-by: Thomas Richter <[email protected]>
Acked-by: Namhyung Kim <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Namhyung Kim <[email protected]>

show more ...

perf test shell stat_bpf_counters: Fix test on Intel

As of now, bpf counters (bperf) don't support event groups. But the
default perf stat includes topdown metrics if supported (on recent Intel
mac

perf test shell stat_bpf_counters: Fix test on Intel

As of now, bpf counters (bperf) don't support event groups. But the
default perf stat includes topdown metrics if supported (on recent Intel
machines) which require groups. That makes perf stat exiting.

$ sudo perf stat --bpf-counter true
bpf managed perf events do not yet support groups.

Actually the test explicitly uses cycles event only, but it missed to
pass the option when it checks the availability of the command.

Fixes: 2c0cb9f56020d2ea ("perf test: Add a shell test for 'perf stat --bpf-counters' new option")
Reviewed-by: Song Liu <[email protected]>
Signed-off-by: Namhyung Kim <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Ian Rogers <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...

perf tests stat_bpf_counters: Fix usage of '==' to address shellcheck warning

Running shellcheck on stat_bpf_counter.sh generates below
warning:

In tests/shell/stat_bpf_counters.sh line 34:
i

perf tests stat_bpf_counters: Fix usage of '==' to address shellcheck warning

Running shellcheck on stat_bpf_counter.sh generates below
warning:

In tests/shell/stat_bpf_counters.sh line 34:
if [ "$base_cycles" == "<not" ]; then
^-- SC3014 (warning): In POSIX sh, == in place of = is undefined.

In tests/shell/stat_bpf_counters.sh line 39:
if [ "$bpf_cycles" == "<not" ]; then
^-- SC3014 (warning): In POSIX sh, == in place of = is undefined.

Fix this by using "=" instead of "==" to work for
all shells.

Signed-off-by: Athira Rajeev <[email protected]>
Acked-by: Ian Rogers <[email protected]>
Cc: Disha Goel <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Kajol Jain <[email protected]>
Cc: Madhavan Srinivasan <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...

perf test: Remove bash construct from stat_bpf_counters.sh test

Currently the test skips with an error because == only works in bash:

$ ./perf test 91 -v
Couldn't bump rlimit(MEMLOCK), failures

perf test: Remove bash construct from stat_bpf_counters.sh test

Currently the test skips with an error because == only works in bash:

$ ./perf test 91 -v
Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc
91: perf stat --bpf-counters test :
--- start ---
test child forked, pid 44586
./tests/shell/stat_bpf_counters.sh: 26: [: -v: unexpected operator
test child finished with -2
---- end ----
perf stat --bpf-counters test: Skip

Changing == to = does the same thing, but doesn't result in an error:

./perf test 91 -v
Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc
91: perf stat --bpf-counters test :
--- start ---
test child forked, pid 45833
Skipping: --bpf-counters not supported
Error: unknown option `bpf-counters'
[...]
test child finished with -2
---- end ----
perf stat --bpf-counters test: Skip

Signed-off-by: James Clark <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Florian Fainelli <[email protected]>
Cc: Ian Rogers <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: John Fastabend <[email protected]>
Cc: KP Singh <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Martin KaFai Lau <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Sumanth Korikkar <[email protected]>
Cc: Thomas Richter <[email protected]>
Cc: Yonghong Song <[email protected]>
Cc: [email protected]
Cc: [email protected]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...

perf test: Fix non-bash issue with stat bpf counters

$(( .. )) is a bash feature but the test's interpreter is !/bin/sh,
switch the code to use expr.

Signed-off-by: Ian Rogers <[email protected]>

perf test: Fix non-bash issue with stat bpf counters

$(( .. )) is a bash feature but the test's interpreter is !/bin/sh,
switch the code to use expr.

Signed-off-by: Ian Rogers <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Song Liu <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...

perf test: Make stat bpf counters test more robust

If the test is run on a hypervisor then the cycles event may not be
counted, skip the test in this situation. Fail the test if cycles are
not count

perf test: Make stat bpf counters test more robust

If the test is run on a hypervisor then the cycles event may not be
counted, skip the test in this situation. Fail the test if cycles are
not counted in the subsequent bpf counter run.

Signed-off-by: Ian Rogers <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Song Liu <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...

perf test: Add verbose skip output for bpf counters

Provide additional context for when the stat bpf counters test skips.

Signed-off-by: Ian Rogers <[email protected]>
Cc: Alexander Shishkin <alex

perf test: Add verbose skip output for bpf counters

Provide additional context for when the stat bpf counters test skips.

Signed-off-by: Ian Rogers <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Song Liu <[email protected]>
Cc: [email protected]
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...

perf test: Add a shell test for 'perf stat --bpf-counters' new option

Add a test to compare the output of perf-stat with and without option
--bpf-counters. If the difference is more than 10%, the te

perf test: Add a shell test for 'perf stat --bpf-counters' new option

Add a test to compare the output of perf-stat with and without option
--bpf-counters. If the difference is more than 10%, the test is considered
as failed.

Committer testing:

# perf test bpf-counters
86: perf stat --bpf-counters test : Ok
# perf test -v bpf-counters
86: perf stat --bpf-counters test :
--- start ---
test child forked, pid 2433339
test child finished with 0
---- end ----
perf stat --bpf-counters test: Ok
#

Signed-off-by: Song Liu <[email protected]>
Requested-by: Arnaldo Carvalho de Melo <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Acked-by: Namhyung Kim <[email protected]>
Cc: Jiri Olsa <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

show more ...