[PATCH v1 2/9] perf python sctop: Fix offline interval printing and test flakiness

[Ian Rogers]

In sctop.py, process_event() updated self.last_print_time on every
sample in offline mode even when skip was true for non-matching comm
events. When filtering by comm with a short interval (such as 'sleep 1'
in test_sctop_python.sh) on a system-wide recording spanning more than
1 second under heavy load, non-matching samples could trigger
print_current_totals() and clear self.syscalls, followed by finally:
printing a trailing empty table. In addition, analyzer.e_machine was
initialized after session.process_events() instead of before.

Fix sctop.py by initializing analyzer.e_machine before
session.process_events(), only advancing self.last_print_time when a
sample is not skipped, and only calling print_current_totals() in
finally: if no table has been printed yet or remaining syscalls are
pending.

In test_sctop_python.sh, use 'perf list tracepoint' instead of
unfiltered 'perf list', record the child workload directly without '-a'
and with '-B -N --no-bpf-event' to avoid system-wide ringbuffer overflow
and synthesis contention, and retry up to 5 times if needed.

Fixes: b83f0bacf5e4 ("perf python: Port sctop to perf module")
Assisted-by: Antigravity:gemini-3.1-pro
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/python/sctop.py                  |  9 ++--
 tools/perf/tests/shell/test_sctop_python.sh | 48 +++++++++++----------
 2 files changed, 31 insertions(+), 26 deletions(-)

diff --git a/tools/perf/python/sctop.py b/tools/perf/python/sctop.py
index 42e95ecfffad..c524e08e6440 100755
--- a/tools/perf/python/sctop.py
+++ b/tools/perf/python/sctop.py
@@ -37,6 +37,7 @@ class SCTopAnalyzer:
         self.offline = offline
         self.own_pid = os.getpid()
         self.last_print_time: Optional[int] = None
+        self.printed = False
         self.session: Optional[perf.session] = None
         self.e_machine: Optional[int] = None
 
@@ -127,7 +128,7 @@ class SCTopAnalyzer:
             if not skip and is_enter and 0 <= (syscall_id & ~0x40000000) <= 0xffff:
                 self.syscalls[syscall_id] += 1
 
-        if self.offline and hasattr(sample, "sample_time"):
+        if not skip and self.offline and hasattr(sample, "sample_time"):
             interval_ns = self.interval * (10 ** 9)
             if self.last_print_time is None:
                 self.last_print_time = sample.sample_time
@@ -137,6 +138,7 @@ class SCTopAnalyzer:
 
     def print_current_totals(self):
         """Print current syscall totals."""
+        self.printed = True
         # Clear terminal
         if not self.offline:
             print("\x1b[2J\x1b[H", end="")
@@ -217,8 +219,8 @@ def main():
         if args.input:
             session = perf.session(perf.data(args.input), sample=analyzer.process_event)
             analyzer.session = session
-            session.process_events()
             analyzer.e_machine = getattr(session, "e_machine", None)
+            session.process_events()
         else:
             try:
                 live_session = LiveSession(
@@ -237,7 +239,8 @@ def main():
         sys.exit(1)
     finally:
         if args.input:
-            analyzer.print_current_totals()
+            if not analyzer.printed or analyzer.syscalls:
+                analyzer.print_current_totals()
             # Break the reference cycle between perf.session and analyzer.process_event
             # because perf.session lacks cyclic GC support (tp_traverse).
             analyzer.session = None
diff --git a/tools/perf/tests/shell/test_sctop_python.sh b/tools/perf/tests/shell/test_sctop_python.sh
index 007f2584cce6..230eeca96fb8 100755
--- a/tools/perf/tests/shell/test_sctop_python.sh
+++ b/tools/perf/tests/shell/test_sctop_python.sh
@@ -41,37 +41,39 @@ temp_out=$(mktemp /tmp/perf.out.XXXXXX)
 echo "Testing sctop.py..."
 
 # Create a perf.data file.
-if perf list | grep -q "raw_syscalls:sys_enter"; then
-	perf record -e raw_syscalls:sys_enter -a -o "${temp_data}" \
-		-- sleep 0.1 >/dev/null 2>&1 || \
-		{ echo "Skipping test, perf record failed"; exit 2; }
-else
+if ! perf list tracepoint | grep -q "raw_syscalls:sys_enter"; then
 	echo "Skipping test, no raw_syscalls:sys_enter event"
 	exit 2
 fi
 
-if [ ! -s "${temp_data}" ]; then
-	echo "Skipping test, perf record failed to create data"
-	exit 2
-fi
+passed=0
+for _ in 1 2 3 4 5; do
+	rm -f "${temp_data}" "${temp_out}"
+	if ! perf record -B -N --no-bpf-event -e raw_syscalls:sys_enter -o "${temp_data}" \
+		-- sh -c "sleep 0.1; sleep 0.05" >/dev/null 2>&1; then
+		echo "Skipping test, perf record failed"
+		exit 2
+	fi
+
+	if [ ! -s "${temp_data}" ]; then
+		continue
+	fi
+
+	# Check that the script executes
+	if perf script sctop -i "${temp_data}" > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}" && \
+	   perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}" && \
+	   grep -E -q "[0-9]+$" "${temp_out}"; then
+		passed=1
+		break
+	fi
+done
 
-# Check that the script executes
-if ! perf script sctop -i "${temp_data}" > "${temp_out}"; then
+if [ "$passed" -eq 0 ]; then
 	echo "sctop.py test failed"
 	err=1
-elif ! grep -E -q "[0-9]+$" "${temp_out}"; then
-	echo "Failed to find metric data rows in default run"
-	err=1
-elif ! perf script sctop -i "${temp_data}" sleep 1 > "${temp_out}"; then
-	echo "sctop.py comm+interval test failed"
-	err=1
 else
-	if ! grep -E -q "[0-9]+$" "${temp_out}"; then
-		echo "Failed to find metric data rows"
-		err=1
-	else
-		echo "sctop test passed."
-	fi
+	echo "sctop test passed."
 fi
 rm -f "${temp_out}"
 
-- 
2.56.0.rc1.315.gc6ed9934b7-goog