[PATCH v3] perf test: perftool-testsuite-report fails on s390

[PATCH v3] perf test: perftool-testsuite-report fails on s390

[Thomas Richter]

V2 --> V3: Add finding from sashiko
   Initialize shell variable perf_config_tmp to null string on
   other plattforms. This avoids removing any file specified on
   command line as in 'perf_config_tmp=XXXX ./perf test '
V1 --> V2: Add finding from sashiko
   Add check for non-zero string length to avoid 'rm -f'
   command without file name.

Test case perftool-testsuite-report.sh always fails on s390.
Root cause is a default timeout for addr2line command which is too
short for s390. Function cmd_addr2line() invokes addr2line command
and reads via pipe the function name on stdout, after writing
an address to stdin. There is a default timeout for the expected
reply, but very often this timeout is too short and nothing is
returned. This leads to the error message listed in
util/addr2line.c:

   switch (read_addr2line_record(&io, cmd_a2l_style, dso_name, ..) {
   case -1:
          if (!symbol_conf.addr2line_disable_warn)
                 pr_warning("%s %s: could not read first record\n",
				   ...)
          goto out;
   ...

As the test case emits warnings, it is reported as failed.
Fix this for s390 and create a temporary perf configuration file to
suppress these warnings. (An alternative would be to increase
the default timeout to a larger value).

Output before:
 # bash perftool-testsuite_report.sh
 -- [ PASS ] -- perf_report :: setup :: prepare the perf.data file
 ==================
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.087 MB (402 samples) ]
 ==================
 -- [ PASS ] -- perf_report :: setup :: prepare the perf.data.1 file
 ## [ PASS ] ## perf_report :: setup SUMMARY
 -- [ SKIP ] -- perf_report :: test_basic :: help message :: \
 		testcase skipped
 Line did not match any pattern: "cmd__addr2line <file> could not \
	read first record"
 -- [ FAIL ] -- perf_report :: test_basic :: basic execution \
	 (output regexp parsing)
 Line did not match any pattern: "cmd__addr2line <file> could not \
	read first record"
 ...
 ## [ FAIL ] ## perf_report :: test_basic SUMMARY :: 6 failures found

All six tests fail for the same reason, addr2line did not respond in
time.

Output after:
 # bash perftool-testsuite_report.sh
 -- [ PASS ] -- perf_report :: setup :: prepare the perf.data file
 ==================
 [ perf record: Woken up 1 times to write data ]
 [ perf record: Captured and wrote 0.086 MB .... (380 samples) ]
 ==================
 -- [ PASS ] -- perf_report :: setup :: prepare the perf.data.1 file
 ## [ PASS ] ## perf_report :: setup SUMMARY
 -- [ SKIP ] -- perf_report :: test_basic :: help message :: \
 				testcase skipped
 -- [ PASS ] -- perf_report :: test_basic :: basic execution
 -- [ PASS ] -- perf_report :: test_basic :: number of samples
 -- [ PASS ] -- perf_report :: test_basic :: header
 -- [ PASS ] -- perf_report :: test_basic :: header timestamp
 -- [ PASS ] -- perf_report :: test_basic :: show CPU utilization
 -- [ PASS ] -- perf_report :: test_basic :: pid
 -- [ PASS ] -- perf_report :: test_basic :: non-existing symbol
 -- [ PASS ] -- perf_report :: test_basic :: symbol filter
 -- [ PASS ] -- perf_report :: test_basic :: latency header
 -- [ PASS ] -- perf_report :: test_basic :: default report for \
						 latency profile
 -- [ PASS ] -- perf_report :: test_basic :: latency report for \
 						latency profile
 -- [ PASS ] -- perf_report :: test_basic :: parallelism histogram
 ## [ PASS ] ## perf_report :: test_basic SUMMARY
 #

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Jan Polensky <japo@linux.ibm.com>
---
 tools/perf/tests/shell/perftool-testsuite_report.sh | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/perf/tests/shell/perftool-testsuite_report.sh b/tools/perf/tests/shell/perftool-testsuite_report.sh
index a8cf75b4e77e..01116f8d71ce 100755
--- a/tools/perf/tests/shell/perftool-testsuite_report.sh
+++ b/tools/perf/tests/shell/perftool-testsuite_report.sh
@@ -6,6 +6,16 @@ test -d "$(dirname "$0")/base_report" || exit 2
 cd "$(dirname "$0")/base_report" || exit 2
 status=0
 
+# On s390 the default timeout for addr2line is too short, disable warnings
+if [ $(uname -m) = s390x ]
+then
+	perf_config_tmp=$(mktemp /tmp/.perfconfig_XXXXX)
+	export PERF_CONFIG="${perf_config_tmp}"
+	perf config 'core.addr2line-disable-warn = true'
+else
+	perf_config_tmp=""
+fi
+
 PERFSUITE_RUN_DIR=$(mktemp -d /tmp/"$(basename "$0" .sh)".XXX)
 export PERFSUITE_RUN_DIR
 
@@ -19,5 +29,6 @@ if ! [ "$PERFTEST_KEEP_LOGS" = "y" ]; then
 	rm -rf "$PERFSUITE_RUN_DIR"
 fi
 
+[ -n "${perf_config_tmp}" ] && rm -f "${perf_config_tmp}"
 test $status -ne 0 && exit 1
 exit 0
-- 
2.55.0

Re: [PATCH v3] perf test: perftool-testsuite-report fails on s390

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] The patch introduces a divergent configuration state where user/system configurations are strictly ignored on s390x but loaded on all other architectures.
--

--- Patch [1]: [PATCH v3] perf test: perftool-testsuite-report fails on s390 ---
commit 01af4a3a83b9a4ed0f3f18651c07cbbbdda377c8
Author: Thomas Richter <tmricht@linux.ibm.com>

perf test: perftool-testsuite-report fails on s390

This commit modifies the perftool-testsuite-report test script to address
failures on s390 caused by addr2line timeouts. It creates a temporary
perf configuration file to disable addr2line warnings specifically on the
s390x architecture.

> diff --git a/tools/perf/tests/shell/perftool-testsuite_report.sh b/tools/perf/tests/shell/perftool-testsuite_report.sh
> index a8cf75b4e77ec..01116f8d71ce6 100755
> --- a/tools/perf/tests/shell/perftool-testsuite_report.sh
> +++ b/tools/perf/tests/shell/perftool-testsuite_report.sh
> @@ -6,6 +6,16 @@ test -d "$(dirname "$0")/base_report" || exit 2
>  cd "$(dirname "$0")/base_report" || exit 2
>  status=0
>  
> +# On s390 the default timeout for addr2line is too short, disable warnings
> +if [ $(uname -m) = s390x ]
> +then
> +	perf_config_tmp=$(mktemp /tmp/.perfconfig_XXXXX)
> +	export PERF_CONFIG="${perf_config_tmp}"

[Severity: Medium]
Does this introduce a divergent configuration state between architectures?

By exporting PERF_CONFIG to a temporary file on s390x, perf is instructed
to read only that file, ignoring the user's ~/.perfconfig and system
/etc/perfconfig.

On other architectures, PERF_CONFIG is left unmodified, meaning user and
system configurations are still applied. This architectural divergence
isolates the test environment on s390x but leaves it exposed to arbitrary
user settings on other platforms.

> +	perf config 'core.addr2line-disable-warn = true'
> +else
> +	perf_config_tmp=""
> +fi

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260709090136.1031645-1-tmricht@linux.ibm.com?part=1