Skip to contentSkip to conversation

perf/test: fix perf ftrace test on s390

PATCH Superseded Thomas Richter 2 participants 3 messages Nov 14, 2024 perf events

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 perf/test: fix perf ftrace test on s390

On s390 the perf test case ftrace sometimes fails as follows:

  # ./perf test ftrace
  79: perf ftrace tests    : FAILED!
  #

The failure depends on the kernel .config file. Some configurarions always work fine, some do not. The ftrace profile test mostly fails, because the ring buffer was not large enough, and some lines (especially the interesting ones with nanosleep in it) where dropped.

To achieve success for all our tested kernel configurations, enlarge the buffer to store the traces complete without wrapping. The default buffer size is too small for all kernel configurations. Set the buffer size of /sys/kernel/tracing/buffer_size_kb to 16 MB

Output after:

  # ./perf test ftrace
  79: perf ftrace tests     : Ok
  #
---
 tools/perf/tests/shell/ftrace.sh | 11 +++++++++++
 1 file changed, 11 insertions(+)
tools/perf/tests/shell/ftrace.sh +11 -0
index a6ee740f0d7e..742d6b8f34d3 100755
@@ -80,10 +80,21 @@ test_ftrace_profile() {
     echo "perf ftrace profile test  [Success]"
 }
 
+if [ "$(uname -m)" = "s390x" ]
+then
+	ftrace_size=$(cat /sys/kernel/tracing/buffer_size_kb)
+	echo 16384 > /sys/kernel/tracing/buffer_size_kb
+fi
+
 test_ftrace_list
 test_ftrace_trace
 test_ftrace_latency
 test_ftrace_profile
 
+if [ "$(uname -m)" = "s390x" ]
+then
+	echo $ftrace_size > /sys/kernel/tracing/buffer_size_kb
+fi
+
 cleanup
 exit 0
Signature · 1 line
2.47.0
reviewer Reviewed-by on v1 1/1
#1 lore raw
Quoted 33 lines · Thomas Richter

On s390 the perf test case ftrace sometimes fails as follows:

   # ./perf test ftrace
   79: perf ftrace tests    : FAILED!
   #

The failure depends on the kernel .config file. Some configurarions always work fine, some do not. The ftrace profile test mostly fails, because the ring buffer was not large enough, and some lines (especially the interesting ones with nanosleep in it) where dropped.

To achieve success for all our tested kernel configurations, enlarge the buffer to store the traces complete without wrapping. The default buffer size is too small for all kernel configurations. Set the buffer size of /sys/kernel/tracing/buffer_size_kb to 16 MB

Output after:

   # ./perf test ftrace
   79: perf ftrace tests     : Ok
   #
---
  tools/perf/tests/shell/ftrace.sh | 11 +++++++++++
  1 file changed, 11 insertions(+)
tools/perf/tests/shell/ftrace.sh +0 -0
index a6ee740f0d7e..742d6b8f34d3 100755

tools/perf/tests/shell/ftrace.sh test_ftrace_profile() { · line 88

Quoted 9 lines
tools/perf/tests/shell/ftrace.sh +6 -0
@@ -80,10 +80,21 @@ test_ftrace_profile() {
      echo "perf ftrace profile test  [Success]"
  }
 
+if [ "$(uname -m)" = "s390x" ]
+then
+	ftrace_size=$(cat /sys/kernel/tracing/buffer_size_kb)
+	echo 16384 > /sys/kernel/tracing/buffer_size_kb
+fi
+

It probably wouldn't be terrible to do this for all platforms to reduce fragmentation. It doesn't do any harm and it only added a few seconds to the test time even on a small Arm box, maybe it will prevent flakes everywhere else in the future. But I don't feel too strongly about this one.

tools/perf/tests/shell/ftrace.sh test_ftrace_profile() { · line 98

Quoted 10 lines
tools/perf/tests/shell/ftrace.sh +5 -0
  test_ftrace_list
  test_ftrace_trace
  test_ftrace_latency
  test_ftrace_profile
 
+if [ "$(uname -m)" = "s390x" ]
+then
+	echo $ftrace_size > /sys/kernel/tracing/buffer_size_kb
+fi
+

Restoring the value should be in cleanup() so it works on interrupt too.

With that:

Quoted 2 lines
tools/perf/tests/shell/ftrace.sh +0 -0
  cleanup
  exit 0
#2 lore raw
Quoted 59 lines · James Clark
Quoted 36 lines · Thomas Richter

On s390 the perf test case ftrace sometimes fails as follows:

   # ./perf test ftrace
   79: perf ftrace tests    : FAILED!
   #

The failure depends on the kernel .config file. Some configurarions always work fine, some do not.  The ftrace profile test mostly fails, because the ring buffer was not large enough, and some lines (especially the interesting ones with nanosleep in it) where dropped.

To achieve success for all our tested kernel configurations, enlarge the buffer to store the traces complete without wrapping. The default buffer size is too small  for all kernel configurations. Set the buffer size of /sys/kernel/tracing/buffer_size_kb to 16 MB

Output after:

   # ./perf test ftrace
   79: perf ftrace tests     : Ok
   #

---
  tools/perf/tests/shell/ftrace.sh | 11 +++++++++++

  1 file changed, 11 insertions(+)
tools/perf/tests/shell/ftrace.sh +0 -0
index a6ee740f0d7e..742d6b8f34d3 100755
@@ -80,10 +80,21 @@ test_ftrace_profile() {

      echo "perf ftrace profile test  [Success]"
  }
  +if [ "$(uname -m)" = "s390x" ]

tools/perf/tests/shell/ftrace.sh test_ftrace_profile() { · line 88

Quoted 5 lines
tools/perf/tests/shell/ftrace.sh +5 -0
+then
+    ftrace_size=$(cat /sys/kernel/tracing/buffer_size_kb)
+    echo 16384 > /sys/kernel/tracing/buffer_size_kb
+fi
+

It probably wouldn't be terrible to do this for all platforms to reduce fragmentation. It doesn't do any harm and it only added a few seconds to the test time even on a small Arm box, maybe it will prevent flakes everywhere else in the future. But I don't feel too strongly about this one.

tools/perf/tests/shell/ftrace.sh test_ftrace_profile() { · line 98

Quoted 9 lines

  test_ftrace_list
  test_ftrace_trace
  test_ftrace_latency
  test_ftrace_profile
  +if [ "$(uname -m)" = "s390x" ]

tools/perf/tests/shell/ftrace.sh +4 -0
+then
+    echo $ftrace_size > /sys/kernel/tracing/buffer_size_kb
+fi
+

Restoring the value should be in cleanup() so it works on interrupt too.

Quoted 4 lines

With that:

Thanks for your feedback. Will do it and post v2

Signature · 9 lines
Thomas Richter, Dept 3303, IBM s390 Linux Development, Boeblingen, Germany
--
IBM Deutschland Research & Development GmbH

Vorsitzender des Aufsichtsrats: Wolfgang Wendt

Geschäftsführung: David Faller

Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB 243294