perf test: Add direct off-cpu tests

Since we added --off-cpu-thresh, add tests for when a sample's off-cpu
time is above the threshold, and when it's below the threshold.

Note that the basic test performed in test_offcpu_basic() collects a
direct sample now, since sleep 1 has duration of 1000ms, higher than the
default value of --off-cpu-thresh of 500ms, resulting in a direct
sample.

An example:

  $ sudo perf test offcpu
  124: perf record offcpu profiling tests                              : Ok
  $

Committer testing:

  root@number:~# perf test offcpu
  126: perf record offcpu profiling tests                              : Ok
  root@number:~# perf test -v offcpu
  126: perf record offcpu profiling tests                              : Ok
  root@number:~# perf test -vv offcpu
  126: perf record offcpu profiling tests:
  --- start ---
  test child forked, pid 1410791
  Checking off-cpu privilege
  Basic off-cpu test
  Basic off-cpu test [Success]
  Child task off-cpu test
  Child task off-cpu test [Success]
  Threshold test (above threshold)
  Threshold test (above threshold) [Success]
  Threshold test (below threshold)
  Threshold test (below threshold) [Success]
  ---- end(0) ----
  126: perf record offcpu profiling tests                              : Ok
  root@number:~#

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Howard Chu <howardchu95@gmail.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Gautam Menghani <gautam@linux.ibm.com>
Tested-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250501022809.449767-11-howardchu95@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh
index 678947fe69eed2e85bac1d9e85f744e04c0c2810..21a22efe08f5acfbd657063cc77c4200995f1799 100755 (executable)
--- a/tools/perf/tests/shell/record_offcpu.sh
+++ b/tools/perf/tests/shell/record_offcpu.sh
@@ -7,6 +7,9 @@ set -e
 err=0
 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
 
+ts=$(printf "%u" $((~0 << 32))) # OFF_CPU_TIMESTAMP
+dummy_timestamp=${ts%???} # remove the last 3 digits to match perf script
+
 cleanup() {
   rm -f ${perfdata}
   rm -f ${perfdata}.old
@@ -19,6 +22,9 @@ trap_cleanup() {
 }
 trap trap_cleanup EXIT TERM INT
 
+test_above_thresh="Threshold test (above threshold)"
+test_below_thresh="Threshold test (below threshold)"
+
 test_offcpu_priv() {
   echo "Checking off-cpu privilege"
 
@@ -88,6 +94,63 @@ test_offcpu_child() {
   echo "Child task off-cpu test [Success]"
 }
 
+# task blocks longer than the --off-cpu-thresh, perf should collect a direct sample
+test_offcpu_above_thresh() {
+  echo "${test_above_thresh}"
+
+  # collect direct off-cpu samples for tasks blocked for more than 999ms
+  if ! perf record -e dummy --off-cpu --off-cpu-thresh 999 -o ${perfdata} -- sleep 1 2> /dev/null
+  then
+    echo "${test_above_thresh} [Failed record]"
+    err=1
+    return
+  fi
+  # direct sample's timestamp should be lower than the dummy_timestamp of the at-the-end sample
+  # check if a direct sample exists
+  if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q "offcpu-time"
+  then
+    echo "${test_above_thresh} [Failed missing direct samples]"
+    err=1
+    return
+  fi
+  # there should only be one direct sample, and its period should be higher than off-cpu-thresh
+  if ! perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F period | \
+       awk '{ if (int($1) > 999000000) exit 0; else exit 1; }'
+  then
+    echo "${test_above_thresh} [Failed off-cpu time too short]"
+    err=1
+    return
+  fi
+  echo "${test_above_thresh} [Success]"
+}
+
+# task blocks shorter than the --off-cpu-thresh, perf should collect an at-the-end sample
+test_offcpu_below_thresh() {
+  echo "${test_below_thresh}"
+
+  # collect direct off-cpu samples for tasks blocked for more than 1.2s
+  if ! perf record -e dummy --off-cpu --off-cpu-thresh 1200 -o ${perfdata} -- sleep 1 2> /dev/null
+  then
+    echo "${test_below_thresh} [Failed record]"
+    err=1
+    return
+  fi
+  # see if there's an at-the-end sample
+  if ! perf script --time "${dummy_timestamp}," -i ${perfdata} -F event | grep -q 'offcpu-time'
+  then
+    echo "${test_below_thresh} [Failed at-the-end samples cannot be found]"
+    err=1
+    return
+  fi
+  # plus there shouldn't be any direct samples
+  if perf script --time "0, ${dummy_timestamp}" -i ${perfdata} -F event | grep -q 'offcpu-time'
+  then
+    echo "${test_below_thresh} [Failed direct samples are found when they shouldn't be]"
+    err=1
+    return
+  fi
+  echo "${test_below_thresh} [Success]"
+}
 
 test_offcpu_priv
 
@@ -99,5 +162,13 @@ if [ $err = 0 ]; then
   test_offcpu_child
 fi
 
+if [ $err = 0 ]; then
+  test_offcpu_above_thresh
+fi
+
+if [ $err = 0 ]; then
+  test_offcpu_below_thresh
+fi
+
 cleanup
 exit $err