[PATCH v2 1/1] Add field checking tests for perf stat JSON output.

Counts number of fields to make sure expected fields are present.

Signed-off-by: Claire Jensen <redacted>
---
 .../tests/shell/lib/perf_json_output_lint.py  |  48 ++++++++
 tools/perf/tests/shell/stat+json_output.sh    | 114 ++++++++++++++++++
 2 files changed, 162 insertions(+)
 create mode 100644 tools/perf/tests/shell/lib/perf_json_output_lint.py
 create mode 100644 tools/perf/tests/shell/stat+json_output.sh

diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py
new file mode 100644
index 000000000000..45d9163e7423
--- /dev/null
+++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py

@@ -0,0 +1,48 @@
+#!/usr/bin/python
+
+from __future__ import print_function
+import argparse
+import sys
+
+# Basic sanity check of perf JSON output as specified in the man page.
+# Currently just checks the number of fields per line in output.
+
+ap = argparse.ArgumentParser()
+ap.add_argument('--no-args', action='store_true')
+ap.add_argument('--interval', action='store_true')
+ap.add_argument('--all-cpus-no-aggr', action='store_true')
+ap.add_argument('--all-cpus', action='store_true')
+ap.add_argument('--event', action='store_true')
+ap.add_argument('--per-core', action='store_true')
+ap.add_argument('--per-thread', action='store_true')
+ap.add_argument('--per-die', action='store_true')
+ap.add_argument('--per-node', action='store_true')
+ap.add_argument('--per-socket', action='store_true')
+args = ap.parse_args()
+
+Lines = sys.stdin.readlines()
+ch = ','
+
+
+def check_json_output(exp):
+  for line in Lines:
+    if 'failed' not in line:
+      count = 0
+      count = line.count(ch)
+      if count != exp:
+        sys.stdout.write(''.join(Lines))
+        raise RuntimeError('wrong number of fields. counted {0}'
+                           ' expected {1} in {2}\n'.format(count, exp, line))
+
+
+try:
+  if args.no_args or args.all_cpus or args.event:
+    check_json_output(6)
+  if args.interval or args.per_thread:
+    check_json_output(7)
+  if args.per_core or args.per_socket or args.per_node or args.per_die:
+    check_json_output(8)
+
+except:
+  sys.stdout.write('Test failed for input:\n' + ''.join(Lines))
+  raise

diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
new file mode 100644
index 000000000000..8a772badae45
--- /dev/null
+++ b/tools/perf/tests/shell/stat+json_output.sh

@@ -0,0 +1,114 @@
+#!/bin/bash
+# perf stat JSON output linter
+# SPDX-License-Identifier: GPL-2.0
+# Checks various perf stat JSON output commands for the
+# correct number of fields.
+
+set -e
+set -x
+
+pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py
+file="/proc/sys/kernel/perf_event_paranoid"
+paranoia=$(cat "$file" | grep -o -E '[0-9]+')
+
+check_no_args()
+{
+	perf stat -j sleep 1 2>&1 | \
+	python $pythonchecker --no-args
+}
+
+if [ $paranoia -gt 0 ];
+then
+	echo check_all_cpus test skipped because of paranoia level.
+else
+	check_all_cpus()
+	{
+		perf stat -j -a 2>&1 sleep 1 | \
+		python $pythonchecker --all-cpus
+	}
+	check_all_cpus
+fi
+
+check_interval()
+{
+	perf stat -j -I 1000 2>&1 sleep 1 | \
+	python $pythonchecker --interval
+}
+
+check_all_cpus_no_aggr()
+{
+	perf stat -j -A -a --no-merge 2>&1 sleep 1 | \
+	python $pythonchecker --all-cpus-no-aggr
+}
+
+check_event()
+{
+	perf stat -j -e cpu-clock 2>&1 sleep 1 | \
+	python $pythonchecker --event
+}
+
+if [ $paranoia -gt 0 ];
+then
+	echo check_all_cpus test skipped because of paranoia level.
+else
+	check_per_core()
+	{
+		perf stat -j --per-core -a 2>&1 sleep 1 | \
+		python $pythonchecker --per-core
+	}
+	check_per_core
+fi
+
+if [ $paranoia -gt 0 ];
+then
+	echo check_all_cpus test skipped because of paranoia level.
+else
+	check_per_thread()
+	{
+		perf stat -j --per-thread -a 2>&1 sleep 1 | \
+		python $pythonchecker --per-thread
+	}
+	check_per_thread
+fi
+
+if [ $paranoia -gt 0 ];
+then
+	echo check_per_die test skipped because of paranoia level.
+else
+	check_per_die()
+	{
+		perf stat -j --per-die -a 2>&1 sleep 1 | \
+		python $pythonchecker --per-die
+	}
+	check_per_die
+fi
+
+if [ $paranoia -gt 0 ];
+then
+	echo check_per_node test skipped because of paranoia level.
+else
+	check_per_node()
+	{
+		perf stat -j --per-node -a 2>&1 sleep 1 | \
+		python $pythonchecker --per-node
+	}
+	check_per_node
+fi
+
+if [ $paranoia -gt 0 ];
+then
+	echo check_per_socket test skipped because of paranoia level.
+else
+	check_per_socket()
+	{
+		perf stat -j --per-socket -a 2>&1 sleep 1 | \
+		python $pythonchecker --per-socket
+	}
+	check_per_socket
+fi
+
+check_no_args
+check_interval
+check_all_cpus_no_aggr
+check_event
+exit 0

-- 
2.33.0.rc1.237.g0d66db33f3-goog

On Fri, Aug 13, 2021 at 10:09:37PM +0000, Claire Jensen wrote:

Counts number of fields to make sure expected fields are present.

Signed-off-by: Claire Jensen <redacted>
---
 .../tests/shell/lib/perf_json_output_lint.py  |  48 ++++++++
 tools/perf/tests/shell/stat+json_output.sh    | 114 ++++++++++++++++++
 2 files changed, 162 insertions(+)
 create mode 100644 tools/perf/tests/shell/lib/perf_json_output_lint.py
 create mode 100644 tools/perf/tests/shell/stat+json_output.sh

this one needs to have exec priv, right?

SNIP

hum, is this based on some other change? I don't see -j option in perf stat

jirka

+	python $pythonchecker --no-args
+}
+
+if [ $paranoia -gt 0 ];
+then
+	echo check_all_cpus test skipped because of paranoia level.
+else
+	check_all_cpus()
+	{
+		perf stat -j -a 2>&1 sleep 1 | \
+		python $pythonchecker --all-cpus
+	}

SNIP

Em Tue, Aug 31, 2021 at 09:46:10PM +0200, Jiri Olsa escreveu:

On Fri, Aug 13, 2021 at 10:09:37PM +0000, Claire Jensen wrote:

quoted

Counts number of fields to make sure expected fields are present.

Signed-off-by: Claire Jensen <redacted>
---
 .../tests/shell/lib/perf_json_output_lint.py  |  48 ++++++++
 tools/perf/tests/shell/stat+json_output.sh    | 114 ++++++++++++++++++
 2 files changed, 162 insertions(+)
 create mode 100644 tools/perf/tests/shell/lib/perf_json_output_lint.py
 create mode 100644 tools/perf/tests/shell/stat+json_output.sh

this one needs to have exec priv, right?

quoted

diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py
new file mode 100644
index 000000000000..45d9163e7423
--- /dev/null

SNIP

quoted

diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
new file mode 100644
index 000000000000..8a772badae45
--- /dev/null
+++ b/tools/perf/tests/shell/stat+json_output.sh

@@ -0,0 +1,114 @@
+#!/bin/bash
+# perf stat JSON output linter
+# SPDX-License-Identifier: GPL-2.0
+# Checks various perf stat JSON output commands for the
+# correct number of fields.
+
+set -e
+set -x
+
+pythonchecker=$(dirname $0)/lib/perf_json_output_lint.py
+file="/proc/sys/kernel/perf_event_paranoid"
+paranoia=$(cat "$file" | grep -o -E '[0-9]+')
+
+check_no_args()
+{
+	perf stat -j sleep 1 2>&1 | \

hum, is this based on some other change? I don't see -j option in perf stat

Yeah, testing it I stumbled in both problems as reported by Jiri:

⬢[acme@toolbox perf]$ perf test -v linter
Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc
87: perf stat JSON output linter                                    :

--- start ---

test child forked, pid 1826327
sh: line 1: ./tools/perf/tests/shell/stat+json_output.sh: Permission denied
test child finished with -1
---- end ----
perf stat JSON output linter: FAILED!
⬢[acme@toolbox perf]$
⬢[acme@toolbox perf]$ ls -la tools/perf/tests/shell/stat+json_output.sh
-rw-r--r--. 1 acme acme 2113 Jan  3 11:51 tools/perf/tests/shell/stat+json_output.sh
⬢[acme@toolbox perf]$ chmod +x tools/perf/tests/shell/stat+json_output.sh
⬢[acme@toolbox perf]$ perf test -v linter
Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc
87: perf stat JSON output linter                                    :

--- start ---

test child forked, pid 1826350
++ dirname ./tools/perf/tests/shell/stat+json_output.sh
+ pythonchecker=./tools/perf/tests/shell/lib/perf_json_output_lint.py
+ file=/proc/sys/kernel/perf_event_paranoid
++ cat /proc/sys/kernel/perf_event_paranoid
++ grep -o -E '[0-9]+'
+ paranoia=2
+ '[' 2 -gt 0 ']'
+ echo check_all_cpus test skipped because of paranoia level.
check_all_cpus test skipped because of paranoia level.
+ '[' 2 -gt 0 ']'
+ echo check_all_cpus test skipped because of paranoia level.
check_all_cpus test skipped because of paranoia level.
+ '[' 2 -gt 0 ']'
+ echo check_all_cpus test skipped because of paranoia level.
check_all_cpus test skipped because of paranoia level.
+ '[' 2 -gt 0 ']'
+ echo check_per_die test skipped because of paranoia level.
check_per_die test skipped because of paranoia level.
+ '[' 2 -gt 0 ']'
+ echo check_per_node test skipped because of paranoia level.
check_per_node test skipped because of paranoia level.
+ '[' 2 -gt 0 ']'
+ echo check_per_socket test skipped because of paranoia level.
check_per_socket test skipped because of paranoia level.
+ check_no_args
+ perf stat -j sleep 1
+ python ./tools/perf/tests/shell/lib/perf_json_output_lint.py --no-args
  Error: unknown switch `j'

 Usage: perf stat [<options>] [<command>]

    -a, --all-cpus        system-wide collection from all CPUs
    -A, --no-aggr         disable CPU count aggregation
    -B, --big-num         print large numbers with thousands' separators
    -b, --bpf-prog <bpf-prog-id>
                          stat events on existing bpf program id
    -C, --cpu <cpu>       list of cpus to monitor in system-wide
    -D, --delay <n>       ms to wait before starting measurement after program start (-1: start with events disabled)
    -d, --detailed        detailed run - start a lot of events
    -e, --event <event>   event selector. use 'perf list' to list available events
    -G, --cgroup <name>   monitor event in cgroup name only
    -g, --group           put the counters into a counter group
    -I, --interval-print <n>
                          print counts at regular interval in ms (overhead is possible for values <= 100ms)
    -i, --no-inherit      child tasks do not inherit counters
    -M, --metrics <metric/metric group list>
                          monitor specified metrics or metric groups (separated by ,)
    -n, --null            null run - dont start any counters
    -o, --output <file>   output file name
    -p, --pid <pid>       stat events on existing process id
    -r, --repeat <n>      repeat command and print average + stddev (max: 100, forever: 0)
    -S, --sync            call sync() before starting a run
    -t, --tid <tid>       stat events on existing thread id
    -T, --transaction     hardware transaction statistics
    -v, --verbose         be more verbose (show counter open errors, etc)
    -x, --field-separator <separator>
                          print counts with custom separator
        --all-kernel      Configure all used events to run in kernel space.
        --all-user        Configure all used events to run in user space.
        --append          append to the output file
        --bpf-attr-map <attr-map-path>
                          path to perf_event_attr map
        --bpf-counters    use bpf program to count events
        --control <fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]>
                          Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).
			  Optionally send control command completion ('ack\n') to ack-fd descriptor.
			  Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.
        --filter <filter>
                          event filter
        --for-each-cgroup <name>
                          expand events for each cgroup
        --interval-clear  clear screen in between new interval
        --interval-count <n>
                          print counts for fixed number of times
        --iostat[=<default>]
                          measure I/O performance metrics provided by arch/platform
        --log-fd <n>      log output to fd, instead of stderr
        --metric-no-group
                          don't group metric events, impacts multiplexing
        --metric-no-merge
                          don't try to share events between metrics in a group
        --metric-only     Only print computed metrics. No raw values
        --no-csv-summary  don't print 'summary' for CSV summary output
        --no-merge        Do not merge identical named events
        --per-core        aggregate counts per physical processor core
        --per-die         aggregate counts per processor die
        --per-node        aggregate counts per numa node
        --per-socket      aggregate counts per processor socket
        --per-thread      aggregate counts per thread
        --percore-show-thread
                          Use with 'percore' event qualifier to show the event counts of one hardware thread by sum up total hardware threads of same physical core
        --post <command>  command to run after to the measured command
        --pre <command>   command to run prior to the measured command
        --quiet           don't print output (useful with record)
        --scale           Use --no-scale to disable counter scaling for multiplexing
        --smi-cost        measure SMI cost
        --summary         print summary for interval mode
        --table           display details about each run (only with -r option)
        --td-level <n>    Set the metrics level for the top-down statistics (0: max level)
        --timeout <n>     stop workload and print counts after a timeout period in ms (>= 10ms)
        --topdown         measure top-down statistics

Test failed for input:
  Error: unknown switch `j'

 Usage: perf stat [<options>] [<command>]

    -a, --all-cpus        system-wide collection from all CPUs
    -A, --no-aggr         disable CPU count aggregation
    -B, --big-num         print large numbers with thousands' separators
    -b, --bpf-prog <bpf-prog-id>
                          stat events on existing bpf program id
    -C, --cpu <cpu>       list of cpus to monitor in system-wide
    -D, --delay <n>       ms to wait before starting measurement after program start (-1: start with events disabled)
    -d, --detailed        detailed run - start a lot of events
    -e, --event <event>   event selector. use 'perf list' to list available events
    -G, --cgroup <name>   monitor event in cgroup name only
    -g, --group           put the counters into a counter group
    -I, --interval-print <n>
                          print counts at regular interval in ms (overhead is possible for values <= 100ms)
    -i, --no-inherit      child tasks do not inherit counters
    -M, --metrics <metric/metric group list>
                          monitor specified metrics or metric groups (separated by ,)
    -n, --null            null run - dont start any counters
    -o, --output <file>   output file name
    -p, --pid <pid>       stat events on existing process id
    -r, --repeat <n>      repeat command and print average + stddev (max: 100, forever: 0)
    -S, --sync            call sync() before starting a run
    -t, --tid <tid>       stat events on existing thread id
    -T, --transaction     hardware transaction statistics
    -v, --verbose         be more verbose (show counter open errors, etc)
    -x, --field-separator <separator>
                          print counts with custom separator
        --all-kernel      Configure all used events to run in kernel space.
        --all-user        Configure all used events to run in user space.
        --append          append to the output file
        --bpf-attr-map <attr-map-path>
                          path to perf_event_attr map
        --bpf-counters    use bpf program to count events
        --control <fd:ctl-fd[,ack-fd] or fifo:ctl-fifo[,ack-fifo]>
                          Listen on ctl-fd descriptor for command to control measurement ('enable': enable events, 'disable': disable events).
			  Optionally send control command completion ('ack\n') to ack-fd descriptor.
			  Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.
        --filter <filter>
                          event filter
        --for-each-cgroup <name>
                          expand events for each cgroup
        --interval-clear  clear screen in between new interval
        --interval-count <n>
                          print counts for fixed number of times
        --iostat[=<default>]
                          measure I/O performance metrics provided by arch/platform
        --log-fd <n>      log output to fd, instead of stderr
        --metric-no-group
                          don't group metric events, impacts multiplexing
        --metric-no-merge
                          don't try to share events between metrics in a group
        --metric-only     Only print computed metrics. No raw values
        --no-csv-summary  don't print 'summary' for CSV summary output
        --no-merge        Do not merge identical named events
        --per-core        aggregate counts per physical processor core
        --per-die         aggregate counts per processor die
        --per-node        aggregate counts per numa node
        --per-socket      aggregate counts per processor socket
        --per-thread      aggregate counts per thread
        --percore-show-thread
                          Use with 'percore' event qualifier to show the event counts of one hardware thread by sum up total hardware threads of same physical core
        --post <command>  command to run after to the measured command
        --pre <command>   command to run prior to the measured command
        --quiet           don't print output (useful with record)
        --scale           Use --no-scale to disable counter scaling for multiplexing
        --smi-cost        measure SMI cost
        --summary         print summary for interval mode
        --table           display details about each run (only with -r option)
        --td-level <n>    Set the metrics level for the top-down statistics (0: max level)
        --timeout <n>     stop workload and print counts after a timeout period in ms (>= 10ms)
        --topdown         measure top-down statistics

Traceback (most recent call last):
  File "/var/home/acme/git/perf/./tools/perf/tests/shell/lib/perf_json_output_lint.py", line 40, in <module>
    check_json_output(6)
  File "/var/home/acme/git/perf/./tools/perf/tests/shell/lib/perf_json_output_lint.py", line 34, in check_json_output
    raise RuntimeError('wrong number of fields. counted {0}'
RuntimeError: wrong number of fields. counted 0 expected 6 in   Error: unknown switch `j'


test child finished with -1
---- end ----
perf stat JSON output linter: FAILED!
⬢[acme@toolbox perf]$