[PATCH 4/4] perf test: Don't starve per-process tests with system-wide events

[James Clark]

Some tests intermittently fail when run in parallel, for example "Check
branch stack sampling" fails with no branches recorded at all.

The default event is cycles:P which there may only be 1 or 2 HW counters
for on Intel because it's precise. System wide or per-core precise
events hog the HW counter leaving other per-process tests with no
samples. Rather than make all the tests that use default record commands
run serially, just make the system wide ones use a non-precise event.
They don't need precise sampling anyway, so use plain cycles which can
go on any counter. The per-process tests can be left alone as their
events/processes never run concurrently on any one core.

The LBR filter is another resource shared by all events on a CPU, and
the system-wide LBR test uses different filters to the per-process
branch stack test, so mark the LBR test as exclusive.

This fixes the "Check branch stack sampling" test and other flakes when
a system-wide record from another test runs at the same time, for
example:

  $ sudo perf record -a -o /dev/null -- sleep 30 &
  $ sudo perf test -vvv "Check branch stack sampling"
  ...
  Testing user branch stack sampling
  ERROR: Branches missing ^brstack_bench\+[^ ]*/brstack_foo\+[^ ]*/IND_CALL/.*$
  ...
  Testing user branch stack sampling [Failed]
  ...
  Testing branch stack filtering permutation (call,CALL|SYSCALL)
  Testing branch stack filtering [Failed empty script output]
  ...
  ---- end(-1) ----
  138: Check branch stack sampling : FAILED!

Signed-off-by: James Clark <james.clark@xxxxxxxxxx>
---
 tools/perf/tests/shell/record.sh          | 6 +++---
 tools/perf/tests/shell/record_lbr.sh      | 2 +-
 tools/perf/tests/shell/record_sideband.sh | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh
index 01dc3e22fa73..5292eff78a70 100755
--- a/tools/perf/tests/shell/record.sh
+++ b/tools/perf/tests/shell/record.sh
@@ -388,7 +388,7 @@ test_system_wide() {
   echo "Basic --system-wide mode test"
   local ret=0
   perf_record_with_retry "${perfdata}" "check_system_wide" "perf test -w thloop" \
-    -aB --synth=no || ret=$?
+    -aB --synth=no -e cycles || ret=$?
   if [ $ret -eq 2 ]; then
     echo "System-wide record [Skipped not supported]"
     return
@@ -471,7 +471,7 @@ test_cgroup() {
   echo "Cgroup sampling test"
   local ret=0
   perf_record_with_retry "${perfdata}" "check_cgroup" "perf test -w thloop" \
-    -aB --synth=cgroup --all-cgroups || ret=$?
+    -aB --synth=cgroup --all-cgroups -e cycles || ret=$?
   if [ $ret -eq 2 ]; then
     echo "Cgroup sampling [Skipped not supported]"
     return
@@ -491,7 +491,7 @@ test_uid() {
   echo "Uid sampling test"
   local ret=0
   perf_record_with_retry "${perfdata}" "check_uid" "perf test -w thloop" \
-    -aB --synth=no --uid "$(id -u)" || ret=$?
+    -aB --synth=no --uid "$(id -u)" -e cycles || ret=$?
   if [ $ret -eq 2 ]; then
     local logfile="${PERF_RECORD_LOGS[${#PERF_RECORD_LOGS[@]}-1]}"
     if grep -q -E "libbpf.*EPERM|Access to performance monitoring" "$logfile" || \
diff --git a/tools/perf/tests/shell/record_lbr.sh b/tools/perf/tests/shell/record_lbr.sh
index 8d51afeb437b..6b6af59db871 100755
--- a/tools/perf/tests/shell/record_lbr.sh
+++ b/tools/perf/tests/shell/record_lbr.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
-# perf record LBR tests
+# perf record LBR tests (exclusive)
 
 set -e
 
diff --git a/tools/perf/tests/shell/record_sideband.sh b/tools/perf/tests/shell/record_sideband.sh
index 2182551873be..31ec2f5cde69 100755
--- a/tools/perf/tests/shell/record_sideband.sh
+++ b/tools/perf/tests/shell/record_sideband.sh
@@ -22,7 +22,7 @@ trap trap_cleanup EXIT TERM INT
 
 can_cpu_wide()
 {
-    if ! perf record -o ${perfdata} -BN --no-bpf-event -C $1 true > /dev/null 2>&1
+    if ! perf record -o ${perfdata} -BN --no-bpf-event -e cycles -C $1 true > /dev/null 2>&1
     then
         echo "record sideband test [Skipped cannot record cpu$1]"
         err=2
@@ -39,7 +39,7 @@ test_system_wide_tracking()
     can_cpu_wide 1 || return 0
 
     # Record on CPU 0 a task running on CPU 1
-    perf record -BN --no-bpf-event -o ${perfdata} -C 0 -- taskset --cpu-list 1 true
+    perf record -BN --no-bpf-event -e cycles -o ${perfdata} -C 0 -- taskset --cpu-list 1 true
 
     # Should get MMAP events from CPU 1
     mmap_cnt=`perf script -i ${perfdata} --show-mmap-events -C 1 2>/dev/null | grep MMAP | wc -l`

-- 
2.43.0