[PATCH v3 07/13] perf tests: Fix flakiness in trace record and replay test

[Ian Rogers]

The `perf trace record and replay` test fails intermittently on slow or
virtualized hosts because the default recording workload (`sleep 1`)
occasionally completes without scheduling the target `nanosleep` or
`clock_nanosleep` system calls inside the recorded sample window,
resulting in the error: `Failed: cannot find *nanosleep syscall`.

Generalize the `perf_record_with_retry` helper in
`tests/shell/lib/perf_record.sh` to support a custom record command prefix
via the `PERF_RECORD_CMD` environment variable (defaulting to "perf
record").

Update `trace_record_replay.sh` to use this robust retry loop running with
`PERF_RECORD_CMD="perf trace record"` and a base workload of `sleep`. The
test will automatically retry with scaled sleep durations (from 0.01s up
to 2.0s) until the required `nanosleep` event is successfully captured.

Fixes: 15bcfb96d0dd ("perf test: Add trace record and replay test")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/tests/shell/lib/perf_record.sh     |  7 ++++++-
 tools/perf/tests/shell/trace_record_replay.sh | 18 ++++++++++++++----
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/tools/perf/tests/shell/lib/perf_record.sh b/tools/perf/tests/shell/lib/perf_record.sh
index e137fa75370d..2b9e11b66dc7 100644
--- a/tools/perf/tests/shell/lib/perf_record.sh
+++ b/tools/perf/tests/shell/lib/perf_record.sh
@@ -24,9 +24,14 @@ perf_record_with_retry() {
   local duration
   local first_run=true
   local ret=1
+  local cmd_prefix="perf record"
+  if [ -n "${PERF_RECORD_CMD}" ]; then
+    cmd_prefix="${PERF_RECORD_CMD}"
+  fi
+
   for duration in 0.01 0.1 0.3 1.0 2.0; do
     rm -f "${perfdata}".old
-    perf record "$@" -o "${perfdata}" ${testprog_base} ${duration} > "$logfile" 2>&1
+    ${cmd_prefix} "$@" -o "${perfdata}" ${testprog_base} ${duration} > "$logfile" 2>&1
     local record_exit=$?
 
     if [ "$first_run" = true ] && [ $record_exit -ne 0 ]; then
diff --git a/tools/perf/tests/shell/trace_record_replay.sh b/tools/perf/tests/shell/trace_record_replay.sh
index 88d30a03dcec..f27e32b18697 100755
--- a/tools/perf/tests/shell/trace_record_replay.sh
+++ b/tools/perf/tests/shell/trace_record_replay.sh
@@ -6,16 +6,26 @@
 
 # shellcheck source=lib/probe.sh
 . "$(dirname $0)"/lib/probe.sh
+# shellcheck source=lib/perf_record.sh
+. "$(dirname $0)"/lib/perf_record.sh
 
 skip_if_no_perf_trace || exit 2
 [ "$(id -u)" = 0 ] || exit 2
 
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
-perf trace record -o ${file} sleep 1 || exit 1
-if ! perf trace -i ${file} 2>&1 | grep nanosleep; then
+check_nanosleep() {
+  perf trace -i "${file}" 2>&1 | grep -q nanosleep
+}
+
+PERF_RECORD_CMD="perf trace record" perf_record_with_retry "${file}" "check_nanosleep" "sleep"
+err=$?
+
+perf_record_cleanup
+rm -f ${file}
+
+if [ $err -ne 0 ]; then
 	echo "Failed: cannot find *nanosleep syscall"
 	exit 1
 fi
-
-rm -f ${file}
+exit 0
-- 
2.54.0.1189.g8c84645362-goog