From: Kan Liang <[email protected]>
Changes since V1:
- Remove EVSEL_EVENT_MASK and use the __evsel__match which is suggested
by Ian.
- Support TopdownL1 on both e-core and p-core of ADL in the default
mode. (Ian)
- Have separate patches for the modifications of metricgroup and output.
(Ian)
- Does 2nd sort for the Default metricgroup. Remove the logic of
changing the associated metric event. (Ian)
- Move all the metric related code to stat-shadow (Ian)
- Move the commong functions between stat+csv_output and stat+std_output
to the lib directory (Ian)
In the default mode, the current output of the metricgroup include both
events and metrics, which is not necessary and makes the output hard to
read. Also, different ARCHs (even different generations of the ARCH) may
have a different output format because of the different events in a
metrics.
The patch proposes a new output format which only outputting the value
of each metric and the metricgroup name. It can brings a clean and
consistent output format among ARCHs and generations.
The first patche is a bug fix for the current code.
The patches 2-5 introduce the new metricgroup output.
The patches 6-8 improve the tests to cover the default mode.
Here are some examples for the new output.
STD output:
On SPR
perf stat -a sleep 1
Performance counter stats for 'system wide':
226,054.13 msec cpu-clock # 224.588 CPUs utilized
932 context-switches # 4.123 /sec
224 cpu-migrations # 0.991 /sec
76 page-faults # 0.336 /sec
45,940,682 cycles # 0.000 GHz
36,676,047 instructions # 0.80 insn per cycle
7,044,516 branches # 31.163 K/sec
62,169 branch-misses # 0.88% of all branches
TopdownL1 # 68.7 % tma_backend_bound
# 3.1 % tma_bad_speculation
# 13.0 % tma_frontend_bound
# 15.2 % tma_retiring
TopdownL2 # 2.7 % tma_branch_mispredicts
# 19.6 % tma_core_bound
# 4.8 % tma_fetch_bandwidth
# 8.3 % tma_fetch_latency
# 2.9 % tma_heavy_operations
# 12.3 % tma_light_operations
# 0.4 % tma_machine_clears
# 49.1 % tma_memory_bound
1.006529767 seconds time elapsed
perf stat -a sleep 1
Performance counter stats for 'system wide':
32,127.99 msec cpu-clock # 31.992 CPUs utilized
240 context-switches # 7.470 /sec
32 cpu-migrations # 0.996 /sec
74 page-faults # 2.303 /sec
6,313,960 cpu_core/cycles/ # 0.000 GHz
257,711,907 cpu_atom/cycles/ # 0.008 GHz (54.18%)
4,477,162 cpu_core/instructions/ # 0.71 insn per cycle
37,721,481 cpu_atom/instructions/ # 5.97 insn per cycle (63.33%)
809,747 cpu_core/branches/ # 25.204 K/sec
6,621,226 cpu_atom/branches/ # 206.089 K/sec (63.32%)
39,667 cpu_core/branch-misses/ # 4.90% of all branches
1,032,146 cpu_atom/branch-misses/ # 127.47% of all branches (63.33%)
TopdownL1 (cpu_core) # nan % tma_backend_bound
# 0.0 % tma_bad_speculation
# nan % tma_frontend_bound
# nan % tma_retiring
TopdownL1 (cpu_atom) # 13.6 % tma_bad_speculation (63.36%)
# 41.1 % tma_frontend_bound (63.54%)
# 39.2 % tma_backend_bound
# 39.2 % tma_backend_bound_aux (63.93%)
# 5.4 % tma_retiring (64.15%)
1.004244114 seconds time elapsed
JSON output
on SPR
perf stat --json -a sleep 1
{"counter-value" : "225904.823297", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 225904323425, "pcnt-running" : 100.00, "metric-value" : "224.456872", "metric-unit" : "CPUs utilized"}
{"counter-value" : "986.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 225904108985, "pcnt-running" : 100.00, "metric-value" : "4.364670", "metric-unit" : "/sec"}
{"counter-value" : "224.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 225904016141, "pcnt-running" : 100.00, "metric-value" : "0.991568", "metric-unit" : "/sec"}
{"counter-value" : "76.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 225903913270, "pcnt-running" : 100.00, "metric-value" : "0.336425", "metric-unit" : "/sec"}
{"counter-value" : "48433482.000000", "unit" : "", "event" : "cycles", "event-runtime" : 225903792732, "pcnt-running" : 100.00, "metric-value" : "0.000214", "metric-unit" : "GHz"}
{"counter-value" : "38620409.000000", "unit" : "", "event" : "instructions", "event-runtime" : 225903657830, "pcnt-running" : 100.00, "metric-value" : "0.797391", "metric-unit" : "insn per cycle"}
{"counter-value" : "7369473.000000", "unit" : "", "event" : "branches", "event-runtime" : 225903464328, "pcnt-running" : 100.00, "metric-value" : "32.622026", "metric-unit" : "K/sec"}
{"counter-value" : "54747.000000", "unit" : "", "event" : "branch-misses", "event-runtime" : 225903234523, "pcnt-running" : 100.00, "metric-value" : "0.742889", "metric-unit" : "of all branches"}
{"event-runtime" : 225902840555, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1"}
{"metric-value" : "69.950631", "metric-unit" : "% tma_backend_bound"}
{"metric-value" : "2.771783", "metric-unit" : "% tma_bad_speculation"}
{"metric-value" : "12.026074", "metric-unit" : "% tma_frontend_bound"}
{"metric-value" : "15.251513", "metric-unit" : "% tma_retiring"}
{"event-runtime" : 225902840555, "pcnt-running" : 100.00, "metricgroup" : "TopdownL2"}
{"metric-value" : "2.351757", "metric-unit" : "% tma_branch_mispredicts"}
{"metric-value" : "19.729771", "metric-unit" : "% tma_core_bound"}
{"metric-value" : "4.555207", "metric-unit" : "% tma_fetch_bandwidth"}
{"metric-value" : "7.470867", "metric-unit" : "% tma_fetch_latency"}
{"metric-value" : "2.938808", "metric-unit" : "% tma_heavy_operations"}
{"metric-value" : "12.312705", "metric-unit" : "% tma_light_operations"}
{"metric-value" : "0.420026", "metric-unit" : "% tma_machine_clears"}
{"metric-value" : "50.220860", "metric-unit" : "% tma_memory_bound"}
On hybrid
perf stat --json -a sleep 1
{"counter-value" : "32131.530625", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 32131536951, "pcnt-running" : 100.00, "metric-value" : "31.992642", "metric-unit" : "CPUs utilized"}
{"counter-value" : "328.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 32131525778, "pcnt-running" : 100.00, "metric-value" : "10.208042", "metric-unit" : "/sec"}
{"counter-value" : "32.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 32131515104, "pcnt-running" : 100.00, "metric-value" : "0.995906", "metric-unit" : "/sec"}
{"counter-value" : "353.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 32131501396, "pcnt-running" : 100.00, "metric-value" : "10.986094", "metric-unit" : "/sec"}
{"counter-value" : "18685492.000000", "unit" : "", "event" : "cpu_core/cycles/", "event-runtime" : 16061585292, "pcnt-running" : 100.00, "metric-value" : "0.000582", "metric-unit" : "GHz"}
{"counter-value" : "255620352.000000", "unit" : "", "event" : "cpu_atom/cycles/", "event-runtime" : 8690268422, "pcnt-running" : 54.00, "metric-value" : "0.007955", "metric-unit" : "GHz"}
{"counter-value" : "15489913.000000", "unit" : "", "event" : "cpu_core/instructions/", "event-runtime" : 16061582200, "pcnt-running" : 100.00, "metric-value" : "0.828981", "metric-unit" : "insn per cycle"}
{"counter-value" : "38790161.000000", "unit" : "", "event" : "cpu_atom/instructions/", "event-runtime" : 10163133324, "pcnt-running" : 63.00, "metric-value" : "2.075951", "metric-unit" : "insn per cycle"}
{"counter-value" : "2908031.000000", "unit" : "", "event" : "cpu_core/branches/", "event-runtime" : 16061563416, "pcnt-running" : 100.00, "metric-value" : "90.503967", "metric-unit" : "K/sec"}
{"counter-value" : "6814948.000000", "unit" : "", "event" : "cpu_atom/branches/", "event-runtime" : 10161711336, "pcnt-running" : 63.00, "metric-value" : "212.095343", "metric-unit" : "K/sec"}
{"counter-value" : "97638.000000", "unit" : "", "event" : "cpu_core/branch-misses/", "event-runtime" : 16061535261, "pcnt-running" : 100.00, "metric-value" : "3.357530", "metric-unit" : "of all branches"}
{"counter-value" : "1017066.000000", "unit" : "", "event" : "cpu_atom/branch-misses/", "event-runtime" : 10159971797, "pcnt-running" : 63.00, "metric-value" : "34.974386", "metric-unit" : "of all branches"}
{"event-runtime" : 16061513607, "pcnt-running" : 100.00, "metricgroup" : "TopdownL1 (cpu_core)"}
{"metric-value" : "nan", "metric-unit" : "% tma_backend_bound"}
{"metric-value" : "0.000000", "metric-unit" : "% tma_bad_speculation"}
{"metric-value" : "nan", "metric-unit" : "% tma_frontend_bound"}
{"metric-value" : "nan", "metric-unit" : "% tma_retiring"}
{"event-runtime" : 10157398501, "pcnt-running" : 63.00, "metricgroup" : "TopdownL1 (cpu_atom)"}
{"metric-value" : "13.719821", "metric-unit" : "% tma_bad_speculation"}
{"event-runtime" : 10178698656, "pcnt-running" : 63.00, "metric-value" : "41.016738", "metric-unit" : "% tma_frontend_bound"}
{"event-runtime" : 10240582902, "pcnt-running" : 63.00, "metric-value" : "39.327764", "metric-unit" : "% tma_backend_bound"}
{"metric-value" : "39.327764", "metric-unit" : "% tma_backend_bound_aux"}
{"event-runtime" : 10284284920, "pcnt-running" : 64.00, "metric-value" : "5.374638", "metric-unit" : "% tma_retiring"}
CSV output
On SPR
perf stat -x, -a sleep 1
225851.20,msec,cpu-clock,225850700108,100.00,224.431,CPUs utilized
976,,context-switches,225850504803,100.00,4.321,/sec
224,,cpu-migrations,225850410336,100.00,0.992,/sec
76,,page-faults,225850304155,100.00,0.337,/sec
52288305,,cycles,225850188531,100.00,0.000,GHz
37977214,,instructions,225850071251,100.00,0.73,insn per cycle
7299859,,branches,225849890722,100.00,32.322,K/sec
51102,,branch-misses,225849672536,100.00,0.70,of all branches
,225849327050,100.00,,,,TopdownL1
,,,,,70.1,% tma_backend_bound
,,,,,2.7,% tma_bad_speculation
,,,,,12.5,% tma_frontend_bound
,,,,,14.6,% tma_retiring
,225849327050,100.00,,,,TopdownL2
,,,,,2.3,% tma_branch_mispredicts
,,,,,19.6,% tma_core_bound
,,,,,4.6,% tma_fetch_bandwidth
,,,,,7.9,% tma_fetch_latency
,,,,,2.9,% tma_heavy_operations
,,,,,11.7,% tma_light_operations
,,,,,0.5,% tma_machine_clears
,,,,,50.5,% tma_memory_bound
On Hybrid
perf stat -x, -a sleep 1
32139.34,msec,cpu-clock,32139351409,100.00,32.001,CPUs utilized
225,,context-switches,32139342672,100.00,7.001,/sec
32,,cpu-migrations,32139337772,100.00,0.996,/sec
72,,page-faults,32139328384,100.00,2.240,/sec
6766433,,cpu_core/cycles/,16067551558,100.00,0.000,GHz
256500230,,cpu_atom/cycles/,8695757391,54.00,0.008,GHz
4688595,,cpu_core/instructions/,16067558976,100.00,0.69,insn per cycle
37487490,,cpu_atom/instructions/,10165193856,63.00,5.54,insn per cycle
845211,,cpu_core/branches/,16067540225,100.00,26.298,K/sec
6571193,,cpu_atom/branches/,10155940853,63.00,204.459,K/sec
41359,,cpu_core/branch-misses/,16067516493,100.00,4.89,of all branches
1020231,,cpu_atom/branch-misses/,10159363620,63.00,120.71,of all branches
,16067494476,100.00,,,,TopdownL1 (cpu_core)
,,,,,,% tma_backend_bound
,,,,,0.0,% tma_bad_speculation
,,,,,,% tma_frontend_bound
,,,,,,% tma_retiring
,10160989992,63.00,,,,TopdownL1 (cpu_atom)
,,,,,13.8,% tma_bad_speculation
,10188319019,63.00,,,41.3,% tma_frontend_bound
,10258326591,63.00,,,38.6,% tma_backend_bound
,,,,,38.6,% tma_backend_bound_aux
,10282689488,64.00,,,5.4,% tma_retiring
Kan Liang (8):
perf evsel: Fix the annotation for hardware events on hybrid
perf metric: JSON flag to default metric group
perf stat,jevents: Introduce Default tags for the default mode
perf metrics: Sort the Default metricgroup
perf stat: New metricgroup output for the default mode
pert tests: Update metric-value for perf stat JSON output
perf test: Move all the check functions of stat csv output to lib
perf test: Add test case for the standard perf stat output
tools/perf/builtin-stat.c | 5 +-
.../arch/x86/alderlake/adl-metrics.json | 45 +++--
.../arch/x86/alderlaken/adln-metrics.json | 25 ++-
.../arch/x86/icelake/icl-metrics.json | 20 +-
.../arch/x86/icelakex/icx-metrics.json | 20 +-
.../arch/x86/sapphirerapids/spr-metrics.json | 60 +++---
.../arch/x86/tigerlake/tgl-metrics.json | 20 +-
tools/perf/pmu-events/jevents.py | 5 +-
tools/perf/pmu-events/pmu-events.h | 1 +
.../tests/shell/lib/perf_json_output_lint.py | 6 +-
tools/perf/tests/shell/lib/stat_output.sh | 169 ++++++++++++++++
tools/perf/tests/shell/stat+csv_output.sh | 188 ++----------------
tools/perf/tests/shell/stat+std_output.sh | 108 ++++++++++
tools/perf/util/evsel.h | 18 +-
tools/perf/util/metricgroup.c | 41 ++++
tools/perf/util/metricgroup.h | 3 +
tools/perf/util/stat-display.c | 108 +++++++++-
tools/perf/util/stat-shadow.c | 108 ++++++++--
tools/perf/util/stat.h | 15 ++
19 files changed, 684 insertions(+), 281 deletions(-)
create mode 100755 tools/perf/tests/shell/lib/stat_output.sh
create mode 100755 tools/perf/tests/shell/stat+std_output.sh
--
2.35.1
From: Kan Liang <[email protected]>
Add a new test case to verify the standard perf stat output with
different options.
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/tests/shell/stat+std_output.sh | 108 ++++++++++++++++++++++
1 file changed, 108 insertions(+)
create mode 100755 tools/perf/tests/shell/stat+std_output.sh
diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh
new file mode 100755
index 000000000000..98cc3356a04a
--- /dev/null
+++ b/tools/perf/tests/shell/stat+std_output.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# perf stat STD output linter
+# SPDX-License-Identifier: GPL-2.0
+# Tests various perf stat STD output commands for
+# default event and metricgroup
+
+set -e
+
+. $(dirname $0)/lib/stat_output.sh
+
+stat_output=$(mktemp /tmp/__perf_test.stat_output.std.XXXXX)
+
+event_name=(cpu-clock task-clock context-switches cpu-migrations page-faults cycles instructions branches branch-misses stalled-cycles-frontend stalled-cycles-backend)
+event_metric=("CPUs utilized" "CPUs utilized" "/sec" "/sec" "/sec" "GHz" "insn per cycle" "/sec" "of all branches" "frontend cycles idle" "backend cycles idle")
+
+metricgroup_name=(TopdownL1 TopdownL2)
+
+cleanup() {
+ rm -f "${stat_output}"
+
+ trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+ cleanup
+ exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+function commachecker()
+{
+ local -i cnt=0
+ local prefix=1
+
+ case "$1"
+ in "--interval") prefix=2
+ ;; "--per-thread") prefix=2
+ ;; "--system-wide-no-aggr") prefix=2
+ ;; "--per-core") prefix=3
+ ;; "--per-socket") prefix=3
+ ;; "--per-node") prefix=3
+ ;; "--per-die") prefix=3
+ ;; "--per-cache") prefix=3
+ esac
+
+ while read line
+ do
+ # Ignore initial "started on" comment.
+ x=${line:0:1}
+ [ "$x" = "#" ] && continue
+ # Ignore initial blank line.
+ [ "$line" = "" ] && continue
+ # Ignore "Performance counter stats"
+ x=${line:0:25}
+ [ "$x" = "Performance counter stats" ] && continue
+ # Ignore "seconds time elapsed" and break
+ [[ "$line" == *"time elapsed"* ]] && break
+
+ main_body=$(echo $line | cut -d' ' -f$prefix-)
+ x=${main_body%#*}
+ # Check default metricgroup
+ y=$(echo $x | tr -d ' ')
+ [ "$y" = "" ] && continue
+ for i in "${!metricgroup_name[@]}"; do
+ [[ "$y" == *"${metricgroup_name[$i]}"* ]] && break
+ done
+ [[ "$y" == *"${metricgroup_name[$i]}"* ]] && continue
+
+ # Check default event
+ for i in "${!event_name[@]}"; do
+ [[ "$x" == *"${event_name[$i]}"* ]] && break
+ done
+
+ [[ ! "$x" == *"${event_name[$i]}"* ]] && {
+ echo "Unknown event name in $line" 1>&2
+ exit 1;
+ }
+
+ # Check event metric if it exists
+ [[ ! "$main_body" == *"#"* ]] && continue
+ [[ ! "$main_body" == *"${event_metric[$i]}"* ]] && {
+ echo "wrong event metric. expected ${event_metric[$i]} in $line" 1>&2
+ exit 1;
+ }
+ done < "${stat_output}"
+ return 0
+}
+
+perf_cmd="-o ${stat_output}"
+
+skip_test=$(check_for_topology)
+check_no_args "STD" "$perf_cmd"
+check_system_wide "STD" "$perf_cmd"
+check_interval "STD" "$perf_cmd"
+check_per_thread "STD" "$perf_cmd"
+check_per_node "STD" "$perf_cmd"
+if [ $skip_test -ne 1 ]
+then
+ check_system_wide_no_aggr "STD" "$perf_cmd"
+ check_per_core "STD" "$perf_cmd"
+ check_per_cache_instance "STD" "$perf_cmd"
+ check_per_die "STD" "$perf_cmd"
+ check_per_socket "STD" "$perf_cmd"
+else
+ echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
+fi
+cleanup
+exit 0
--
2.35.1
From: Kan Liang <[email protected]>
In the default mode, the current output of the metricgroup include both
events and metrics, which is not necessary and just makes the output
hard to read. Since different ARCHs (even different generations in the
same ARCH) may use different events. The output also vary on different
platforms.
For a metricgroup, only outputting the value of each metric is good
enough.
Add a new field default_metricgroup in evsel to indicate an event of
the default metricgroup. For those events, printout() should print
the metricgroup name rather than each event.
Add perf_stat__skip_metric_event() to skip the evsel in the Default
metricgroup, if it's not running or not the metric event.
Add print_metricgroup_header_t to pass the functions which print the
display name of each metricgroup in the Default metricgroup. Support
all three output methods.
Factor out perf_stat__print_shadow_stats_metricgroup() to print out
each metrics.
On SPR
Before:
./perf_old stat sleep 1
Performance counter stats for 'sleep 1':
0.54 msec task-clock:u # 0.001 CPUs utilized
0 context-switches:u # 0.000 /sec
0 cpu-migrations:u # 0.000 /sec
68 page-faults:u # 125.445 K/sec
540,970 cycles:u # 0.998 GHz
556,325 instructions:u # 1.03 insn per cycle
123,602 branches:u # 228.018 M/sec
6,889 branch-misses:u # 5.57% of all branches
3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound
# 17.2 % tma_retiring
# 23.1 % tma_bad_speculation
# 41.4 % tma_frontend_bound
564,859 topdown-retiring:u
1,370,999 topdown-fe-bound:u
603,271 topdown-be-bound:u
744,874 topdown-bad-spec:u
12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec
1.001798215 seconds time elapsed
0.000193000 seconds user
0.001700000 seconds sys
After:
$ ./perf stat sleep 1
Performance counter stats for 'sleep 1':
0.51 msec task-clock:u # 0.001 CPUs utilized
0 context-switches:u # 0.000 /sec
0 cpu-migrations:u # 0.000 /sec
68 page-faults:u # 132.683 K/sec
545,228 cycles:u # 1.064 GHz
555,509 instructions:u # 1.02 insn per cycle
123,574 branches:u # 241.120 M/sec
6,957 branch-misses:u # 5.63% of all branches
TopdownL1 # 17.5 % tma_backend_bound
# 22.6 % tma_bad_speculation
# 42.7 % tma_frontend_bound
# 17.1 % tma_retiring
TopdownL2 # 21.8 % tma_branch_mispredicts
# 11.5 % tma_core_bound
# 13.4 % tma_fetch_bandwidth
# 29.3 % tma_fetch_latency
# 2.7 % tma_heavy_operations
# 14.5 % tma_light_operations
# 0.8 % tma_machine_clears
# 6.1 % tma_memory_bound
1.001712086 seconds time elapsed
0.000151000 seconds user
0.001618000 seconds sys
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/builtin-stat.c | 1 +
tools/perf/util/evsel.h | 1 +
tools/perf/util/stat-display.c | 108 ++++++++++++++++++++++++++++++---
tools/perf/util/stat-shadow.c | 108 +++++++++++++++++++++++++++++----
tools/perf/util/stat.h | 15 +++++
5 files changed, 211 insertions(+), 22 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 55601b4b5c34..3f4e76f76f94 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2172,6 +2172,7 @@ static int add_default_attributes(void)
evlist__for_each_entry(metric_evlist, metric_evsel) {
metric_evsel->skippable = true;
+ metric_evsel->default_metricgroup = true;
}
evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries);
evlist__delete(metric_evlist);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index cc6fb3049b99..9f06d6cd5379 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -131,6 +131,7 @@ struct evsel {
bool reset_group;
bool errored;
bool needs_auxtrace_mmap;
+ bool default_metricgroup; /* A member of the Default metricgroup */
struct hashmap *per_pkg_mask;
int err;
struct {
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index a2bbdc25d979..7329b3340f88 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -25,6 +25,7 @@
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
+#define MGROUP_LEN 50
#define METRIC_LEN 38
#define EVNAME_LEN 32
#define COUNTS_LEN 18
@@ -364,16 +365,27 @@ static void new_line_std(struct perf_stat_config *config __maybe_unused,
os->newline = true;
}
-static void do_new_line_std(struct perf_stat_config *config,
- struct outstate *os)
+static inline void __new_line_std_csv(struct perf_stat_config *config,
+ struct outstate *os)
{
fputc('\n', os->fh);
if (os->prefix)
fputs(os->prefix, os->fh);
aggr_printout(config, os->evsel, os->id, os->aggr_nr);
+}
+
+static inline void __new_line_std(struct outstate *os)
+{
+ fprintf(os->fh, " ");
+}
+
+static void do_new_line_std(struct perf_stat_config *config,
+ struct outstate *os)
+{
+ __new_line_std_csv(config, os);
if (config->aggr_mode == AGGR_NONE)
fprintf(os->fh, " ");
- fprintf(os->fh, " ");
+ __new_line_std(os);
}
static void print_metric_std(struct perf_stat_config *config,
@@ -408,10 +420,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx)
struct outstate *os = ctx;
int i;
- fputc('\n', os->fh);
- if (os->prefix)
- fprintf(os->fh, "%s", os->prefix);
- aggr_printout(config, os->evsel, os->id, os->aggr_nr);
+ __new_line_std_csv(config, os);
for (i = 0; i < os->nfields; i++)
fputs(config->csv_sep, os->fh);
}
@@ -462,6 +471,54 @@ static void new_line_json(struct perf_stat_config *config, void *ctx)
aggr_printout(config, os->evsel, os->id, os->aggr_nr);
}
+static void print_metricgroup_header_json(struct perf_stat_config *config,
+ void *ctx,
+ const char *metricgroup_name)
+{
+ if (!metricgroup_name)
+ return;
+
+ fprintf(config->output, "\"metricgroup\" : \"%s\"}", metricgroup_name);
+ new_line_json(config, ctx);
+}
+
+static void print_metricgroup_header_csv(struct perf_stat_config *config,
+ void *ctx,
+ const char *metricgroup_name)
+{
+ struct outstate *os = ctx;
+ int i;
+
+ if (!metricgroup_name) {
+ /* Leave space for running and enabling */
+ for (i = 0; i < os->nfields - 2; i++)
+ fputs(config->csv_sep, os->fh);
+ return;
+ }
+
+ for (i = 0; i < os->nfields; i++)
+ fputs(config->csv_sep, os->fh);
+ fprintf(config->output, "%s", metricgroup_name);
+ new_line_csv(config, ctx);
+}
+
+static void print_metricgroup_header_std(struct perf_stat_config *config,
+ void *ctx,
+ const char *metricgroup_name)
+{
+ struct outstate *os = ctx;
+ int n;
+
+ if (!metricgroup_name) {
+ __new_line_std(os);
+ return;
+ }
+
+ n = fprintf(config->output, " %*s", EVNAME_LEN, metricgroup_name);
+
+ fprintf(config->output, "%*s", MGROUP_LEN - n - 1, "");
+}
+
/* Filter out some columns that don't work well in metrics only mode */
static bool valid_only_metric(const char *unit)
@@ -713,19 +770,23 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
struct perf_stat_output_ctx out;
print_metric_t pm;
new_line_t nl;
+ print_metricgroup_header_t pmh;
bool ok = true;
struct evsel *counter = os->evsel;
if (config->csv_output) {
pm = config->metric_only ? print_metric_only_csv : print_metric_csv;
nl = config->metric_only ? new_line_metric : new_line_csv;
+ pmh = print_metricgroup_header_csv;
os->nfields = 4 + (counter->cgrp ? 1 : 0);
} else if (config->json_output) {
pm = config->metric_only ? print_metric_only_json : print_metric_json;
nl = config->metric_only ? new_line_metric : new_line_json;
+ pmh = print_metricgroup_header_json;
} else {
pm = config->metric_only ? print_metric_only : print_metric_std;
nl = config->metric_only ? new_line_metric : new_line_std;
+ pmh = print_metricgroup_header_std;
}
if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
@@ -747,10 +808,11 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
out.print_metric = pm;
out.new_line = nl;
+ out.print_metricgroup_header = pmh;
out.ctx = os;
out.force_header = false;
- if (!config->metric_only) {
+ if (!config->metric_only && !counter->default_metricgroup) {
abs_printout(config, os->id, os->aggr_nr, counter, uval, ok);
print_noise(config, counter, noise, /*before_metric=*/true);
@@ -758,8 +820,31 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
}
if (ok) {
- perf_stat__print_shadow_stats(config, counter, uval, aggr_idx,
- &out, &config->metric_events);
+ if (!config->metric_only && counter->default_metricgroup) {
+ void *from = NULL;
+
+ aggr_printout(config, os->evsel, os->id, os->aggr_nr);
+ /* Print out all the metricgroup with the same metric event. */
+ do {
+ int num = 0;
+
+ /* Print out the new line for the next new metricgroup. */
+ if (from) {
+ if (config->json_output)
+ new_line_json(config, (void *)os);
+ else
+ __new_line_std_csv(config, os);
+ }
+
+ print_noise(config, counter, noise, /*before_metric=*/true);
+ print_running(config, run, ena, /*before_metric=*/true);
+ from = perf_stat__print_shadow_stats_metricgroup(config, counter, aggr_idx,
+ &num, from, &out,
+ &config->metric_events);
+ } while (from != NULL);
+ } else
+ perf_stat__print_shadow_stats(config, counter, uval, aggr_idx,
+ &out, &config->metric_events);
} else {
pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0);
}
@@ -889,6 +974,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
ena = aggr->counts.ena;
run = aggr->counts.run;
+ if (perf_stat__skip_metric_event(counter, &config->metric_events, ena, run))
+ return;
+
if (val == 0 && should_skip_zero_counter(config, counter, &id))
return;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 1566a206ba42..b25974670d30 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -539,6 +539,83 @@ double test_generic_metric(struct metric_expr *mexp, int aggr_idx)
return ratio;
}
+/**
+ * perf_stat__print_shadow_stats_metricgroup - Print out metrics associated with the evsel
+ * For the non-default, all metrics associated
+ * with the evsel are printed.
+ * For the default mode, only the metrics from
+ * the same metricgroup and the name of the
+ * metricgroup are printed. To print the metrics
+ * from the next metricgroup (if available),
+ * invoke the function with correspoinding
+ * metric_expr.
+ */
+void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
+ struct evsel *evsel,
+ int aggr_idx,
+ int *num,
+ void *from,
+ struct perf_stat_output_ctx *out,
+ struct rblist *metric_events)
+{
+ struct metric_event *me;
+ struct metric_expr *mexp = from;
+ void *ctxp = out->ctx;
+ bool header_printed = false;
+ const char *name = NULL;
+ static const char *last_name;
+
+ me = metricgroup__lookup(metric_events, evsel, false);
+ if (me == NULL)
+ return NULL;
+
+ if (!mexp)
+ mexp = list_first_entry(&me->head, typeof(*mexp), nd);
+
+ list_for_each_entry_from(mexp, &me->head, nd) {
+ /* Print the display name of the Default metricgroup */
+ if (me->is_default) {
+ if (!name)
+ name = mexp->default_metricgroup_name;
+ /*
+ * Two or more metricgroup may share the same metric
+ * event, e.g., TopdownL1 and TopdownL2 on SPR.
+ * Return and print the prefix, e.g., noise, running
+ * for the next metricgroup.
+ */
+ if (strcmp(name, mexp->default_metricgroup_name))
+ return (void *)mexp;
+ /* Only print the name of the metricgroup once */
+ if (!header_printed) {
+ header_printed = true;
+ if (!last_name || strcmp(last_name, name)) {
+ /* Print out the name for the new metricgroup. */
+ out->print_metricgroup_header(config, ctxp, name);
+ last_name = name;
+ } else if (!strcmp(last_name, name)) {
+ /*
+ * A metricgroup may have several metric events,
+ * e.g.,TopdownL1 on e-core of ADL.
+ * The name has been output by the first metric
+ * event. Only align with other metics from
+ * different metric events.
+ */
+ out->print_metricgroup_header(config, ctxp, NULL);
+ }
+ }
+ }
+
+ if ((*num)++ > 0)
+ out->new_line(config, ctxp);
+ generic_metric(config, mexp->metric_expr, mexp->metric_threshold,
+ mexp->metric_events, mexp->metric_refs, evsel->name,
+ mexp->metric_name, mexp->metric_unit, mexp->runtime,
+ aggr_idx, out);
+ }
+
+ return NULL;
+}
+
void perf_stat__print_shadow_stats(struct perf_stat_config *config,
struct evsel *evsel,
double avg, int aggr_idx,
@@ -565,7 +642,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
};
print_metric_t print_metric = out->print_metric;
void *ctxp = out->ctx;
- struct metric_event *me;
int num = 1;
if (config->iostat_run) {
@@ -592,18 +668,26 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
}
}
- if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
- struct metric_expr *mexp;
+ perf_stat__print_shadow_stats_metricgroup(config, evsel, aggr_idx,
+ &num, NULL, out, metric_events);
- list_for_each_entry (mexp, &me->head, nd) {
- if (num++ > 0)
- out->new_line(config, ctxp);
- generic_metric(config, mexp->metric_expr, mexp->metric_threshold,
- mexp->metric_events, mexp->metric_refs, evsel->name,
- mexp->metric_name, mexp->metric_unit, mexp->runtime,
- aggr_idx, out);
- }
- }
if (num == 0)
print_metric(config, ctxp, NULL, NULL, NULL, 0);
}
+
+/**
+ * perf_stat__skip_metric_event - Skip the evsel in the Default metricgroup,
+ * if it's not running or not the metric event.
+ */
+bool perf_stat__skip_metric_event(struct evsel *evsel,
+ struct rblist *metric_events,
+ u64 ena, u64 run)
+{
+ if (!evsel->default_metricgroup)
+ return false;
+
+ if (!ena || !run)
+ return true;
+
+ return !metricgroup__lookup(metric_events, evsel, false);
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 7abff7cbb5a1..934f79778cea 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -158,11 +158,16 @@ typedef void (*print_metric_t)(struct perf_stat_config *config,
const char *fmt, double val);
typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
+/* Used to print the display name of the Default metricgroup for now. */
+typedef void (*print_metricgroup_header_t)(struct perf_stat_config *config,
+ void *ctx, const char *metricgroup_name);
+
void perf_stat__reset_shadow_stats(void);
struct perf_stat_output_ctx {
void *ctx;
print_metric_t print_metric;
new_line_t new_line;
+ print_metricgroup_header_t print_metricgroup_header;
bool force_header;
};
@@ -171,6 +176,16 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
double avg, int aggr_idx,
struct perf_stat_output_ctx *out,
struct rblist *metric_events);
+bool perf_stat__skip_metric_event(struct evsel *evsel,
+ struct rblist *metric_events,
+ u64 ena, u64 run);
+void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
+ struct evsel *evsel,
+ int aggr_idx,
+ int *num,
+ void *from,
+ struct perf_stat_output_ctx *out,
+ struct rblist *metric_events);
int evlist__alloc_stats(struct perf_stat_config *config,
struct evlist *evlist, bool alloc_raw);
--
2.35.1
From: Kan Liang <[email protected]>
These functions can be shared with the stat std output test.
There is no functional change.
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/tests/shell/lib/stat_output.sh | 169 +++++++++++++++++++
tools/perf/tests/shell/stat+csv_output.sh | 188 ++--------------------
2 files changed, 184 insertions(+), 173 deletions(-)
create mode 100755 tools/perf/tests/shell/lib/stat_output.sh
diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh
new file mode 100755
index 000000000000..363979b1123d
--- /dev/null
+++ b/tools/perf/tests/shell/lib/stat_output.sh
@@ -0,0 +1,169 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Return true if perf_event_paranoid is > $1 and not running as root.
+function ParanoidAndNotRoot()
+{
+ [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
+}
+
+# $1 name $2 extra_opt
+check_no_args()
+{
+ echo -n "Checking $1 output: no args"
+ perf stat $2 true
+ commachecker --no-args
+ echo "[Success]"
+}
+
+check_system_wide()
+{
+ echo -n "Checking $1 output: system wide "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat -a $2 true
+ commachecker --system-wide
+ echo "[Success]"
+}
+
+check_system_wide_no_aggr()
+{
+ echo -n "Checking $1 output: system wide no aggregation "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat -A -a --no-merge $2 true
+ commachecker --system-wide-no-aggr
+ echo "[Success]"
+}
+
+check_interval()
+{
+ echo -n "Checking $1 output: interval "
+ perf stat -I 1000 $2 true
+ commachecker --interval
+ echo "[Success]"
+}
+
+check_event()
+{
+ echo -n "Checking $1 output: event "
+ perf stat -e cpu-clock $2 true
+ commachecker --event
+ echo "[Success]"
+}
+
+check_per_core()
+{
+ echo -n "Checking $1 output: per core "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat --per-core -a $2 true
+ commachecker --per-core
+ echo "[Success]"
+}
+
+check_per_thread()
+{
+ echo -n "Checking $1 output: per thread "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat --per-thread -a $2 true
+ commachecker --per-thread
+ echo "[Success]"
+}
+
+check_per_cache_instance()
+{
+ echo -n "Checking $1 output: per cache instance "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat --per-cache -a $2 true
+ commachecker --per-cache
+ echo "[Success]"
+}
+
+check_per_die()
+{
+ echo -n "Checking $1 output: per die "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat --per-die -a $2 true
+ commachecker --per-die
+ echo "[Success]"
+}
+
+check_per_node()
+{
+ echo -n "Checking $1 output: per node "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat --per-node -a $2 true
+ commachecker --per-node
+ echo "[Success]"
+}
+
+check_per_socket()
+{
+ echo -n "Checking $1 output: per socket "
+ if ParanoidAndNotRoot 0
+ then
+ echo "[Skip] paranoid and not root"
+ return
+ fi
+ perf stat --per-socket -a $2 true
+ commachecker --per-socket
+ echo "[Success]"
+}
+
+# The perf stat options for per-socket, per-core, per-die
+# and -A ( no_aggr mode ) uses the info fetched from this
+# directory: "/sys/devices/system/cpu/cpu*/topology". For
+# example, socket value is fetched from "physical_package_id"
+# file in topology directory.
+# Reference: cpu__get_topology_int in util/cpumap.c
+# If the platform doesn't expose topology information, values
+# will be set to -1. For example, incase of pSeries platform
+# of powerpc, value for "physical_package_id" is restricted
+# and set to -1. Check here validates the socket-id read from
+# topology file before proceeding further
+
+FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
+FILE_NAME="physical_package_id"
+
+function check_for_topology()
+{
+ if ! ParanoidAndNotRoot 0
+ then
+ socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
+ [ -z $socket_file ] && {
+ echo 0
+ return
+ }
+ socket_id=`cat $socket_file`
+ [ $socket_id == -1 ] && {
+ echo 1
+ return
+ }
+ fi
+ echo 0
+}
diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
index ed082daf839c..34a0701fee05 100755
--- a/tools/perf/tests/shell/stat+csv_output.sh
+++ b/tools/perf/tests/shell/stat+csv_output.sh
@@ -6,7 +6,8 @@
set -e
-skip_test=0
+. $(dirname $0)/lib/stat_output.sh
+
csv_sep=@
stat_output=$(mktemp /tmp/__perf_test.stat_output.csv.XXXXX)
@@ -63,181 +64,22 @@ function commachecker()
return 0
}
-# Return true if perf_event_paranoid is > $1 and not running as root.
-function ParanoidAndNotRoot()
-{
- [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
-}
-
-check_no_args()
-{
- echo -n "Checking CSV output: no args "
- perf stat -x$csv_sep -o "${stat_output}" true
- commachecker --no-args
- echo "[Success]"
-}
-
-check_system_wide()
-{
- echo -n "Checking CSV output: system wide "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep -a -o "${stat_output}" true
- commachecker --system-wide
- echo "[Success]"
-}
-
-check_system_wide_no_aggr()
-{
- echo -n "Checking CSV output: system wide no aggregation "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep -A -a --no-merge -o "${stat_output}" true
- commachecker --system-wide-no-aggr
- echo "[Success]"
-}
-
-check_interval()
-{
- echo -n "Checking CSV output: interval "
- perf stat -x$csv_sep -I 1000 -o "${stat_output}" true
- commachecker --interval
- echo "[Success]"
-}
-
-
-check_event()
-{
- echo -n "Checking CSV output: event "
- perf stat -x$csv_sep -e cpu-clock -o "${stat_output}" true
- commachecker --event
- echo "[Success]"
-}
-
-check_per_core()
-{
- echo -n "Checking CSV output: per core "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep --per-core -a -o "${stat_output}" true
- commachecker --per-core
- echo "[Success]"
-}
-
-check_per_thread()
-{
- echo -n "Checking CSV output: per thread "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep --per-thread -a -o "${stat_output}" true
- commachecker --per-thread
- echo "[Success]"
-}
-
-check_per_cache_instance()
-{
- echo -n "Checking CSV output: per cache instance "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep --per-cache -a true 2>&1 | commachecker --per-cache
- echo "[Success]"
-}
-
-check_per_die()
-{
- echo -n "Checking CSV output: per die "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep --per-die -a -o "${stat_output}" true
- commachecker --per-die
- echo "[Success]"
-}
-
-check_per_node()
-{
- echo -n "Checking CSV output: per node "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep --per-node -a -o "${stat_output}" true
- commachecker --per-node
- echo "[Success]"
-}
-
-check_per_socket()
-{
- echo -n "Checking CSV output: per socket "
- if ParanoidAndNotRoot 0
- then
- echo "[Skip] paranoid and not root"
- return
- fi
- perf stat -x$csv_sep --per-socket -a -o "${stat_output}" true
- commachecker --per-socket
- echo "[Success]"
-}
-
-# The perf stat options for per-socket, per-core, per-die
-# and -A ( no_aggr mode ) uses the info fetched from this
-# directory: "/sys/devices/system/cpu/cpu*/topology". For
-# example, socket value is fetched from "physical_package_id"
-# file in topology directory.
-# Reference: cpu__get_topology_int in util/cpumap.c
-# If the platform doesn't expose topology information, values
-# will be set to -1. For example, incase of pSeries platform
-# of powerpc, value for "physical_package_id" is restricted
-# and set to -1. Check here validates the socket-id read from
-# topology file before proceeding further
-
-FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
-FILE_NAME="physical_package_id"
-
-check_for_topology()
-{
- if ! ParanoidAndNotRoot 0
- then
- socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
- [ -z $socket_file ] && return 0
- socket_id=`cat $socket_file`
- [ $socket_id == -1 ] && skip_test=1
- return 0
- fi
-}
+perf_cmd="-x$csv_sep -o ${stat_output}"
-check_for_topology
-check_no_args
-check_system_wide
-check_interval
-check_event
-check_per_thread
-check_per_node
+skip_test=$(check_for_topology)
+check_no_args "CSV" "$perf_cmd"
+check_system_wide "CSV" "$perf_cmd"
+check_interval "CSV" "$perf_cmd"
+check_event "CSV" "$perf_cmd"
+check_per_thread "CSV" "$perf_cmd"
+check_per_node "CSV" "$perf_cmd"
if [ $skip_test -ne 1 ]
then
- check_system_wide_no_aggr
- check_per_core
- check_per_cache_instance
- check_per_die
- check_per_socket
+ check_system_wide_no_aggr "CSV" "$perf_cmd"
+ check_per_core "CSV" "$perf_cmd"
+ check_per_cache_instance "CSV" "$perf_cmd"
+ check_per_die "CSV" "$perf_cmd"
+ check_per_socket "CSV" "$perf_cmd"
else
echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
fi
--
2.35.1
On Wed, Jun 14, 2023 at 5:18 PM <[email protected]> wrote:
>
> From: Kan Liang <[email protected]>
>
> In the default mode, the current output of the metricgroup include both
> events and metrics, which is not necessary and just makes the output
> hard to read. Since different ARCHs (even different generations in the
> same ARCH) may use different events. The output also vary on different
> platforms.
>
> For a metricgroup, only outputting the value of each metric is good
> enough.
>
> Add a new field default_metricgroup in evsel to indicate an event of
> the default metricgroup. For those events, printout() should print
> the metricgroup name rather than each event.
>
> Add perf_stat__skip_metric_event() to skip the evsel in the Default
> metricgroup, if it's not running or not the metric event.
>
> Add print_metricgroup_header_t to pass the functions which print the
> display name of each metricgroup in the Default metricgroup. Support
> all three output methods.
>
> Factor out perf_stat__print_shadow_stats_metricgroup() to print out
> each metrics.
>
> On SPR
> Before:
>
> ./perf_old stat sleep 1
>
> Performance counter stats for 'sleep 1':
>
> 0.54 msec task-clock:u # 0.001 CPUs utilized
> 0 context-switches:u # 0.000 /sec
> 0 cpu-migrations:u # 0.000 /sec
> 68 page-faults:u # 125.445 K/sec
> 540,970 cycles:u # 0.998 GHz
> 556,325 instructions:u # 1.03 insn per cycle
> 123,602 branches:u # 228.018 M/sec
> 6,889 branch-misses:u # 5.57% of all branches
> 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound
> # 17.2 % tma_retiring
> # 23.1 % tma_bad_speculation
> # 41.4 % tma_frontend_bound
> 564,859 topdown-retiring:u
> 1,370,999 topdown-fe-bound:u
> 603,271 topdown-be-bound:u
> 744,874 topdown-bad-spec:u
> 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec
>
> 1.001798215 seconds time elapsed
>
> 0.000193000 seconds user
> 0.001700000 seconds sys
>
> After:
>
> $ ./perf stat sleep 1
>
> Performance counter stats for 'sleep 1':
>
> 0.51 msec task-clock:u # 0.001 CPUs utilized
> 0 context-switches:u # 0.000 /sec
> 0 cpu-migrations:u # 0.000 /sec
> 68 page-faults:u # 132.683 K/sec
> 545,228 cycles:u # 1.064 GHz
> 555,509 instructions:u # 1.02 insn per cycle
> 123,574 branches:u # 241.120 M/sec
> 6,957 branch-misses:u # 5.63% of all branches
> TopdownL1 # 17.5 % tma_backend_bound
> # 22.6 % tma_bad_speculation
> # 42.7 % tma_frontend_bound
> # 17.1 % tma_retiring
> TopdownL2 # 21.8 % tma_branch_mispredicts
> # 11.5 % tma_core_bound
> # 13.4 % tma_fetch_bandwidth
> # 29.3 % tma_fetch_latency
> # 2.7 % tma_heavy_operations
> # 14.5 % tma_light_operations
> # 0.8 % tma_machine_clears
> # 6.1 % tma_memory_bound
>
> 1.001712086 seconds time elapsed
>
> 0.000151000 seconds user
> 0.001618000 seconds sys
>
> Signed-off-by: Kan Liang <[email protected]>
Reviewed-by: Ian Rogers <[email protected]>
Thanks,
Ian
> ---
> tools/perf/builtin-stat.c | 1 +
> tools/perf/util/evsel.h | 1 +
> tools/perf/util/stat-display.c | 108 ++++++++++++++++++++++++++++++---
> tools/perf/util/stat-shadow.c | 108 +++++++++++++++++++++++++++++----
> tools/perf/util/stat.h | 15 +++++
> 5 files changed, 211 insertions(+), 22 deletions(-)
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 55601b4b5c34..3f4e76f76f94 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -2172,6 +2172,7 @@ static int add_default_attributes(void)
>
> evlist__for_each_entry(metric_evlist, metric_evsel) {
> metric_evsel->skippable = true;
> + metric_evsel->default_metricgroup = true;
> }
> evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries);
> evlist__delete(metric_evlist);
> diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
> index cc6fb3049b99..9f06d6cd5379 100644
> --- a/tools/perf/util/evsel.h
> +++ b/tools/perf/util/evsel.h
> @@ -131,6 +131,7 @@ struct evsel {
> bool reset_group;
> bool errored;
> bool needs_auxtrace_mmap;
> + bool default_metricgroup; /* A member of the Default metricgroup */
> struct hashmap *per_pkg_mask;
> int err;
> struct {
> diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
> index a2bbdc25d979..7329b3340f88 100644
> --- a/tools/perf/util/stat-display.c
> +++ b/tools/perf/util/stat-display.c
> @@ -25,6 +25,7 @@
> #define CNTR_NOT_SUPPORTED "<not supported>"
> #define CNTR_NOT_COUNTED "<not counted>"
>
> +#define MGROUP_LEN 50
> #define METRIC_LEN 38
> #define EVNAME_LEN 32
> #define COUNTS_LEN 18
> @@ -364,16 +365,27 @@ static void new_line_std(struct perf_stat_config *config __maybe_unused,
> os->newline = true;
> }
>
> -static void do_new_line_std(struct perf_stat_config *config,
> - struct outstate *os)
> +static inline void __new_line_std_csv(struct perf_stat_config *config,
> + struct outstate *os)
> {
> fputc('\n', os->fh);
> if (os->prefix)
> fputs(os->prefix, os->fh);
> aggr_printout(config, os->evsel, os->id, os->aggr_nr);
> +}
> +
> +static inline void __new_line_std(struct outstate *os)
> +{
> + fprintf(os->fh, " ");
> +}
> +
> +static void do_new_line_std(struct perf_stat_config *config,
> + struct outstate *os)
> +{
> + __new_line_std_csv(config, os);
> if (config->aggr_mode == AGGR_NONE)
> fprintf(os->fh, " ");
> - fprintf(os->fh, " ");
> + __new_line_std(os);
> }
>
> static void print_metric_std(struct perf_stat_config *config,
> @@ -408,10 +420,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx)
> struct outstate *os = ctx;
> int i;
>
> - fputc('\n', os->fh);
> - if (os->prefix)
> - fprintf(os->fh, "%s", os->prefix);
> - aggr_printout(config, os->evsel, os->id, os->aggr_nr);
> + __new_line_std_csv(config, os);
> for (i = 0; i < os->nfields; i++)
> fputs(config->csv_sep, os->fh);
> }
> @@ -462,6 +471,54 @@ static void new_line_json(struct perf_stat_config *config, void *ctx)
> aggr_printout(config, os->evsel, os->id, os->aggr_nr);
> }
>
> +static void print_metricgroup_header_json(struct perf_stat_config *config,
> + void *ctx,
> + const char *metricgroup_name)
> +{
> + if (!metricgroup_name)
> + return;
> +
> + fprintf(config->output, "\"metricgroup\" : \"%s\"}", metricgroup_name);
> + new_line_json(config, ctx);
> +}
> +
> +static void print_metricgroup_header_csv(struct perf_stat_config *config,
> + void *ctx,
> + const char *metricgroup_name)
> +{
> + struct outstate *os = ctx;
> + int i;
> +
> + if (!metricgroup_name) {
> + /* Leave space for running and enabling */
> + for (i = 0; i < os->nfields - 2; i++)
> + fputs(config->csv_sep, os->fh);
> + return;
> + }
> +
> + for (i = 0; i < os->nfields; i++)
> + fputs(config->csv_sep, os->fh);
> + fprintf(config->output, "%s", metricgroup_name);
> + new_line_csv(config, ctx);
> +}
> +
> +static void print_metricgroup_header_std(struct perf_stat_config *config,
> + void *ctx,
> + const char *metricgroup_name)
> +{
> + struct outstate *os = ctx;
> + int n;
> +
> + if (!metricgroup_name) {
> + __new_line_std(os);
> + return;
> + }
> +
> + n = fprintf(config->output, " %*s", EVNAME_LEN, metricgroup_name);
> +
> + fprintf(config->output, "%*s", MGROUP_LEN - n - 1, "");
> +}
> +
> /* Filter out some columns that don't work well in metrics only mode */
>
> static bool valid_only_metric(const char *unit)
> @@ -713,19 +770,23 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
> struct perf_stat_output_ctx out;
> print_metric_t pm;
> new_line_t nl;
> + print_metricgroup_header_t pmh;
> bool ok = true;
> struct evsel *counter = os->evsel;
>
> if (config->csv_output) {
> pm = config->metric_only ? print_metric_only_csv : print_metric_csv;
> nl = config->metric_only ? new_line_metric : new_line_csv;
> + pmh = print_metricgroup_header_csv;
> os->nfields = 4 + (counter->cgrp ? 1 : 0);
> } else if (config->json_output) {
> pm = config->metric_only ? print_metric_only_json : print_metric_json;
> nl = config->metric_only ? new_line_metric : new_line_json;
> + pmh = print_metricgroup_header_json;
> } else {
> pm = config->metric_only ? print_metric_only : print_metric_std;
> nl = config->metric_only ? new_line_metric : new_line_std;
> + pmh = print_metricgroup_header_std;
> }
>
> if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
> @@ -747,10 +808,11 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
>
> out.print_metric = pm;
> out.new_line = nl;
> + out.print_metricgroup_header = pmh;
> out.ctx = os;
> out.force_header = false;
>
> - if (!config->metric_only) {
> + if (!config->metric_only && !counter->default_metricgroup) {
> abs_printout(config, os->id, os->aggr_nr, counter, uval, ok);
>
> print_noise(config, counter, noise, /*before_metric=*/true);
> @@ -758,8 +820,31 @@ static void printout(struct perf_stat_config *config, struct outstate *os,
> }
>
> if (ok) {
> - perf_stat__print_shadow_stats(config, counter, uval, aggr_idx,
> - &out, &config->metric_events);
> + if (!config->metric_only && counter->default_metricgroup) {
> + void *from = NULL;
> +
> + aggr_printout(config, os->evsel, os->id, os->aggr_nr);
> + /* Print out all the metricgroup with the same metric event. */
> + do {
> + int num = 0;
> +
> + /* Print out the new line for the next new metricgroup. */
> + if (from) {
> + if (config->json_output)
> + new_line_json(config, (void *)os);
> + else
> + __new_line_std_csv(config, os);
> + }
> +
> + print_noise(config, counter, noise, /*before_metric=*/true);
> + print_running(config, run, ena, /*before_metric=*/true);
> + from = perf_stat__print_shadow_stats_metricgroup(config, counter, aggr_idx,
> + &num, from, &out,
> + &config->metric_events);
> + } while (from != NULL);
> + } else
> + perf_stat__print_shadow_stats(config, counter, uval, aggr_idx,
> + &out, &config->metric_events);
> } else {
> pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0);
> }
> @@ -889,6 +974,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
> ena = aggr->counts.ena;
> run = aggr->counts.run;
>
> + if (perf_stat__skip_metric_event(counter, &config->metric_events, ena, run))
> + return;
> +
> if (val == 0 && should_skip_zero_counter(config, counter, &id))
> return;
>
> diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
> index 1566a206ba42..b25974670d30 100644
> --- a/tools/perf/util/stat-shadow.c
> +++ b/tools/perf/util/stat-shadow.c
> @@ -539,6 +539,83 @@ double test_generic_metric(struct metric_expr *mexp, int aggr_idx)
> return ratio;
> }
>
> +/**
> + * perf_stat__print_shadow_stats_metricgroup - Print out metrics associated with the evsel
> + * For the non-default, all metrics associated
> + * with the evsel are printed.
> + * For the default mode, only the metrics from
> + * the same metricgroup and the name of the
> + * metricgroup are printed. To print the metrics
> + * from the next metricgroup (if available),
> + * invoke the function with correspoinding
> + * metric_expr.
> + */
> +void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
> + struct evsel *evsel,
> + int aggr_idx,
> + int *num,
> + void *from,
> + struct perf_stat_output_ctx *out,
> + struct rblist *metric_events)
> +{
> + struct metric_event *me;
> + struct metric_expr *mexp = from;
> + void *ctxp = out->ctx;
> + bool header_printed = false;
> + const char *name = NULL;
> + static const char *last_name;
> +
> + me = metricgroup__lookup(metric_events, evsel, false);
> + if (me == NULL)
> + return NULL;
> +
> + if (!mexp)
> + mexp = list_first_entry(&me->head, typeof(*mexp), nd);
> +
> + list_for_each_entry_from(mexp, &me->head, nd) {
> + /* Print the display name of the Default metricgroup */
> + if (me->is_default) {
> + if (!name)
> + name = mexp->default_metricgroup_name;
> + /*
> + * Two or more metricgroup may share the same metric
> + * event, e.g., TopdownL1 and TopdownL2 on SPR.
> + * Return and print the prefix, e.g., noise, running
> + * for the next metricgroup.
> + */
> + if (strcmp(name, mexp->default_metricgroup_name))
> + return (void *)mexp;
> + /* Only print the name of the metricgroup once */
> + if (!header_printed) {
> + header_printed = true;
> + if (!last_name || strcmp(last_name, name)) {
> + /* Print out the name for the new metricgroup. */
> + out->print_metricgroup_header(config, ctxp, name);
> + last_name = name;
> + } else if (!strcmp(last_name, name)) {
> + /*
> + * A metricgroup may have several metric events,
> + * e.g.,TopdownL1 on e-core of ADL.
> + * The name has been output by the first metric
> + * event. Only align with other metics from
> + * different metric events.
> + */
> + out->print_metricgroup_header(config, ctxp, NULL);
> + }
> + }
> + }
> +
> + if ((*num)++ > 0)
> + out->new_line(config, ctxp);
> + generic_metric(config, mexp->metric_expr, mexp->metric_threshold,
> + mexp->metric_events, mexp->metric_refs, evsel->name,
> + mexp->metric_name, mexp->metric_unit, mexp->runtime,
> + aggr_idx, out);
> + }
> +
> + return NULL;
> +}
> +
> void perf_stat__print_shadow_stats(struct perf_stat_config *config,
> struct evsel *evsel,
> double avg, int aggr_idx,
> @@ -565,7 +642,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
> };
> print_metric_t print_metric = out->print_metric;
> void *ctxp = out->ctx;
> - struct metric_event *me;
> int num = 1;
>
> if (config->iostat_run) {
> @@ -592,18 +668,26 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
> }
> }
>
> - if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
> - struct metric_expr *mexp;
> + perf_stat__print_shadow_stats_metricgroup(config, evsel, aggr_idx,
> + &num, NULL, out, metric_events);
>
> - list_for_each_entry (mexp, &me->head, nd) {
> - if (num++ > 0)
> - out->new_line(config, ctxp);
> - generic_metric(config, mexp->metric_expr, mexp->metric_threshold,
> - mexp->metric_events, mexp->metric_refs, evsel->name,
> - mexp->metric_name, mexp->metric_unit, mexp->runtime,
> - aggr_idx, out);
> - }
> - }
> if (num == 0)
> print_metric(config, ctxp, NULL, NULL, NULL, 0);
> }
> +
> +/**
> + * perf_stat__skip_metric_event - Skip the evsel in the Default metricgroup,
> + * if it's not running or not the metric event.
> + */
> +bool perf_stat__skip_metric_event(struct evsel *evsel,
> + struct rblist *metric_events,
> + u64 ena, u64 run)
> +{
> + if (!evsel->default_metricgroup)
> + return false;
> +
> + if (!ena || !run)
> + return true;
> +
> + return !metricgroup__lookup(metric_events, evsel, false);
> +}
> diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
> index 7abff7cbb5a1..934f79778cea 100644
> --- a/tools/perf/util/stat.h
> +++ b/tools/perf/util/stat.h
> @@ -158,11 +158,16 @@ typedef void (*print_metric_t)(struct perf_stat_config *config,
> const char *fmt, double val);
> typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
>
> +/* Used to print the display name of the Default metricgroup for now. */
> +typedef void (*print_metricgroup_header_t)(struct perf_stat_config *config,
> + void *ctx, const char *metricgroup_name);
> +
> void perf_stat__reset_shadow_stats(void);
> struct perf_stat_output_ctx {
> void *ctx;
> print_metric_t print_metric;
> new_line_t new_line;
> + print_metricgroup_header_t print_metricgroup_header;
> bool force_header;
> };
>
> @@ -171,6 +176,16 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
> double avg, int aggr_idx,
> struct perf_stat_output_ctx *out,
> struct rblist *metric_events);
> +bool perf_stat__skip_metric_event(struct evsel *evsel,
> + struct rblist *metric_events,
> + u64 ena, u64 run);
> +void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
> + struct evsel *evsel,
> + int aggr_idx,
> + int *num,
> + void *from,
> + struct perf_stat_output_ctx *out,
> + struct rblist *metric_events);
>
> int evlist__alloc_stats(struct perf_stat_config *config,
> struct evlist *evlist, bool alloc_raw);
> --
> 2.35.1
>
On Wed, Jun 14, 2023 at 5:18 PM <[email protected]> wrote:
>
> From: Kan Liang <[email protected]>
>
> These functions can be shared with the stat std output test.
>
> There is no functional change.
>
> Signed-off-by: Kan Liang <[email protected]>
Reviewed-by: Ian Rogers <[email protected]>
Thanks,
Ian
> ---
> tools/perf/tests/shell/lib/stat_output.sh | 169 +++++++++++++++++++
> tools/perf/tests/shell/stat+csv_output.sh | 188 ++--------------------
> 2 files changed, 184 insertions(+), 173 deletions(-)
> create mode 100755 tools/perf/tests/shell/lib/stat_output.sh
>
> diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh
> new file mode 100755
> index 000000000000..363979b1123d
> --- /dev/null
> +++ b/tools/perf/tests/shell/lib/stat_output.sh
> @@ -0,0 +1,169 @@
> +# SPDX-License-Identifier: GPL-2.0
> +
> +# Return true if perf_event_paranoid is > $1 and not running as root.
> +function ParanoidAndNotRoot()
> +{
> + [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
> +}
> +
> +# $1 name $2 extra_opt
> +check_no_args()
> +{
> + echo -n "Checking $1 output: no args"
> + perf stat $2 true
> + commachecker --no-args
> + echo "[Success]"
> +}
> +
> +check_system_wide()
> +{
> + echo -n "Checking $1 output: system wide "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat -a $2 true
> + commachecker --system-wide
> + echo "[Success]"
> +}
> +
> +check_system_wide_no_aggr()
> +{
> + echo -n "Checking $1 output: system wide no aggregation "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat -A -a --no-merge $2 true
> + commachecker --system-wide-no-aggr
> + echo "[Success]"
> +}
> +
> +check_interval()
> +{
> + echo -n "Checking $1 output: interval "
> + perf stat -I 1000 $2 true
> + commachecker --interval
> + echo "[Success]"
> +}
> +
> +check_event()
> +{
> + echo -n "Checking $1 output: event "
> + perf stat -e cpu-clock $2 true
> + commachecker --event
> + echo "[Success]"
> +}
> +
> +check_per_core()
> +{
> + echo -n "Checking $1 output: per core "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat --per-core -a $2 true
> + commachecker --per-core
> + echo "[Success]"
> +}
> +
> +check_per_thread()
> +{
> + echo -n "Checking $1 output: per thread "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat --per-thread -a $2 true
> + commachecker --per-thread
> + echo "[Success]"
> +}
> +
> +check_per_cache_instance()
> +{
> + echo -n "Checking $1 output: per cache instance "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat --per-cache -a $2 true
> + commachecker --per-cache
> + echo "[Success]"
> +}
> +
> +check_per_die()
> +{
> + echo -n "Checking $1 output: per die "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat --per-die -a $2 true
> + commachecker --per-die
> + echo "[Success]"
> +}
> +
> +check_per_node()
> +{
> + echo -n "Checking $1 output: per node "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat --per-node -a $2 true
> + commachecker --per-node
> + echo "[Success]"
> +}
> +
> +check_per_socket()
> +{
> + echo -n "Checking $1 output: per socket "
> + if ParanoidAndNotRoot 0
> + then
> + echo "[Skip] paranoid and not root"
> + return
> + fi
> + perf stat --per-socket -a $2 true
> + commachecker --per-socket
> + echo "[Success]"
> +}
> +
> +# The perf stat options for per-socket, per-core, per-die
> +# and -A ( no_aggr mode ) uses the info fetched from this
> +# directory: "/sys/devices/system/cpu/cpu*/topology". For
> +# example, socket value is fetched from "physical_package_id"
> +# file in topology directory.
> +# Reference: cpu__get_topology_int in util/cpumap.c
> +# If the platform doesn't expose topology information, values
> +# will be set to -1. For example, incase of pSeries platform
> +# of powerpc, value for "physical_package_id" is restricted
> +# and set to -1. Check here validates the socket-id read from
> +# topology file before proceeding further
> +
> +FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
> +FILE_NAME="physical_package_id"
> +
> +function check_for_topology()
> +{
> + if ! ParanoidAndNotRoot 0
> + then
> + socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
> + [ -z $socket_file ] && {
> + echo 0
> + return
> + }
> + socket_id=`cat $socket_file`
> + [ $socket_id == -1 ] && {
> + echo 1
> + return
> + }
> + fi
> + echo 0
> +}
> diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh
> index ed082daf839c..34a0701fee05 100755
> --- a/tools/perf/tests/shell/stat+csv_output.sh
> +++ b/tools/perf/tests/shell/stat+csv_output.sh
> @@ -6,7 +6,8 @@
>
> set -e
>
> -skip_test=0
> +. $(dirname $0)/lib/stat_output.sh
> +
> csv_sep=@
>
> stat_output=$(mktemp /tmp/__perf_test.stat_output.csv.XXXXX)
> @@ -63,181 +64,22 @@ function commachecker()
> return 0
> }
>
> -# Return true if perf_event_paranoid is > $1 and not running as root.
> -function ParanoidAndNotRoot()
> -{
> - [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ]
> -}
> -
> -check_no_args()
> -{
> - echo -n "Checking CSV output: no args "
> - perf stat -x$csv_sep -o "${stat_output}" true
> - commachecker --no-args
> - echo "[Success]"
> -}
> -
> -check_system_wide()
> -{
> - echo -n "Checking CSV output: system wide "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep -a -o "${stat_output}" true
> - commachecker --system-wide
> - echo "[Success]"
> -}
> -
> -check_system_wide_no_aggr()
> -{
> - echo -n "Checking CSV output: system wide no aggregation "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep -A -a --no-merge -o "${stat_output}" true
> - commachecker --system-wide-no-aggr
> - echo "[Success]"
> -}
> -
> -check_interval()
> -{
> - echo -n "Checking CSV output: interval "
> - perf stat -x$csv_sep -I 1000 -o "${stat_output}" true
> - commachecker --interval
> - echo "[Success]"
> -}
> -
> -
> -check_event()
> -{
> - echo -n "Checking CSV output: event "
> - perf stat -x$csv_sep -e cpu-clock -o "${stat_output}" true
> - commachecker --event
> - echo "[Success]"
> -}
> -
> -check_per_core()
> -{
> - echo -n "Checking CSV output: per core "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep --per-core -a -o "${stat_output}" true
> - commachecker --per-core
> - echo "[Success]"
> -}
> -
> -check_per_thread()
> -{
> - echo -n "Checking CSV output: per thread "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep --per-thread -a -o "${stat_output}" true
> - commachecker --per-thread
> - echo "[Success]"
> -}
> -
> -check_per_cache_instance()
> -{
> - echo -n "Checking CSV output: per cache instance "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep --per-cache -a true 2>&1 | commachecker --per-cache
> - echo "[Success]"
> -}
> -
> -check_per_die()
> -{
> - echo -n "Checking CSV output: per die "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep --per-die -a -o "${stat_output}" true
> - commachecker --per-die
> - echo "[Success]"
> -}
> -
> -check_per_node()
> -{
> - echo -n "Checking CSV output: per node "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep --per-node -a -o "${stat_output}" true
> - commachecker --per-node
> - echo "[Success]"
> -}
> -
> -check_per_socket()
> -{
> - echo -n "Checking CSV output: per socket "
> - if ParanoidAndNotRoot 0
> - then
> - echo "[Skip] paranoid and not root"
> - return
> - fi
> - perf stat -x$csv_sep --per-socket -a -o "${stat_output}" true
> - commachecker --per-socket
> - echo "[Success]"
> -}
> -
> -# The perf stat options for per-socket, per-core, per-die
> -# and -A ( no_aggr mode ) uses the info fetched from this
> -# directory: "/sys/devices/system/cpu/cpu*/topology". For
> -# example, socket value is fetched from "physical_package_id"
> -# file in topology directory.
> -# Reference: cpu__get_topology_int in util/cpumap.c
> -# If the platform doesn't expose topology information, values
> -# will be set to -1. For example, incase of pSeries platform
> -# of powerpc, value for "physical_package_id" is restricted
> -# and set to -1. Check here validates the socket-id read from
> -# topology file before proceeding further
> -
> -FILE_LOC="/sys/devices/system/cpu/cpu*/topology/"
> -FILE_NAME="physical_package_id"
> -
> -check_for_topology()
> -{
> - if ! ParanoidAndNotRoot 0
> - then
> - socket_file=`ls $FILE_LOC/$FILE_NAME | head -n 1`
> - [ -z $socket_file ] && return 0
> - socket_id=`cat $socket_file`
> - [ $socket_id == -1 ] && skip_test=1
> - return 0
> - fi
> -}
> +perf_cmd="-x$csv_sep -o ${stat_output}"
>
> -check_for_topology
> -check_no_args
> -check_system_wide
> -check_interval
> -check_event
> -check_per_thread
> -check_per_node
> +skip_test=$(check_for_topology)
> +check_no_args "CSV" "$perf_cmd"
> +check_system_wide "CSV" "$perf_cmd"
> +check_interval "CSV" "$perf_cmd"
> +check_event "CSV" "$perf_cmd"
> +check_per_thread "CSV" "$perf_cmd"
> +check_per_node "CSV" "$perf_cmd"
> if [ $skip_test -ne 1 ]
> then
> - check_system_wide_no_aggr
> - check_per_core
> - check_per_cache_instance
> - check_per_die
> - check_per_socket
> + check_system_wide_no_aggr "CSV" "$perf_cmd"
> + check_per_core "CSV" "$perf_cmd"
> + check_per_cache_instance "CSV" "$perf_cmd"
> + check_per_die "CSV" "$perf_cmd"
> + check_per_socket "CSV" "$perf_cmd"
> else
> echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
> fi
> --
> 2.35.1
>
On Wed, Jun 14, 2023 at 5:18 PM <[email protected]> wrote:
>
> From: Kan Liang <[email protected]>
>
> Add a new test case to verify the standard perf stat output with
> different options.
>
> Signed-off-by: Kan Liang <[email protected]>
Reviewed-by: Ian Rogers <[email protected]>
Thanks,
Ian
> ---
> tools/perf/tests/shell/stat+std_output.sh | 108 ++++++++++++++++++++++
> 1 file changed, 108 insertions(+)
> create mode 100755 tools/perf/tests/shell/stat+std_output.sh
>
> diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh
> new file mode 100755
> index 000000000000..98cc3356a04a
> --- /dev/null
> +++ b/tools/perf/tests/shell/stat+std_output.sh
> @@ -0,0 +1,108 @@
> +#!/bin/bash
> +# perf stat STD output linter
> +# SPDX-License-Identifier: GPL-2.0
> +# Tests various perf stat STD output commands for
> +# default event and metricgroup
> +
> +set -e
> +
> +. $(dirname $0)/lib/stat_output.sh
> +
> +stat_output=$(mktemp /tmp/__perf_test.stat_output.std.XXXXX)
> +
> +event_name=(cpu-clock task-clock context-switches cpu-migrations page-faults cycles instructions branches branch-misses stalled-cycles-frontend stalled-cycles-backend)
> +event_metric=("CPUs utilized" "CPUs utilized" "/sec" "/sec" "/sec" "GHz" "insn per cycle" "/sec" "of all branches" "frontend cycles idle" "backend cycles idle")
> +
> +metricgroup_name=(TopdownL1 TopdownL2)
> +
> +cleanup() {
> + rm -f "${stat_output}"
> +
> + trap - EXIT TERM INT
> +}
> +
> +trap_cleanup() {
> + cleanup
> + exit 1
> +}
> +trap trap_cleanup EXIT TERM INT
> +
> +function commachecker()
> +{
> + local -i cnt=0
> + local prefix=1
> +
> + case "$1"
> + in "--interval") prefix=2
> + ;; "--per-thread") prefix=2
> + ;; "--system-wide-no-aggr") prefix=2
> + ;; "--per-core") prefix=3
> + ;; "--per-socket") prefix=3
> + ;; "--per-node") prefix=3
> + ;; "--per-die") prefix=3
> + ;; "--per-cache") prefix=3
> + esac
> +
> + while read line
> + do
> + # Ignore initial "started on" comment.
> + x=${line:0:1}
> + [ "$x" = "#" ] && continue
> + # Ignore initial blank line.
> + [ "$line" = "" ] && continue
> + # Ignore "Performance counter stats"
> + x=${line:0:25}
> + [ "$x" = "Performance counter stats" ] && continue
> + # Ignore "seconds time elapsed" and break
> + [[ "$line" == *"time elapsed"* ]] && break
> +
> + main_body=$(echo $line | cut -d' ' -f$prefix-)
> + x=${main_body%#*}
> + # Check default metricgroup
> + y=$(echo $x | tr -d ' ')
> + [ "$y" = "" ] && continue
> + for i in "${!metricgroup_name[@]}"; do
> + [[ "$y" == *"${metricgroup_name[$i]}"* ]] && break
> + done
> + [[ "$y" == *"${metricgroup_name[$i]}"* ]] && continue
> +
> + # Check default event
> + for i in "${!event_name[@]}"; do
> + [[ "$x" == *"${event_name[$i]}"* ]] && break
> + done
> +
> + [[ ! "$x" == *"${event_name[$i]}"* ]] && {
> + echo "Unknown event name in $line" 1>&2
> + exit 1;
> + }
> +
> + # Check event metric if it exists
> + [[ ! "$main_body" == *"#"* ]] && continue
> + [[ ! "$main_body" == *"${event_metric[$i]}"* ]] && {
> + echo "wrong event metric. expected ${event_metric[$i]} in $line" 1>&2
> + exit 1;
> + }
> + done < "${stat_output}"
> + return 0
> +}
> +
> +perf_cmd="-o ${stat_output}"
> +
> +skip_test=$(check_for_topology)
> +check_no_args "STD" "$perf_cmd"
> +check_system_wide "STD" "$perf_cmd"
> +check_interval "STD" "$perf_cmd"
> +check_per_thread "STD" "$perf_cmd"
> +check_per_node "STD" "$perf_cmd"
> +if [ $skip_test -ne 1 ]
> +then
> + check_system_wide_no_aggr "STD" "$perf_cmd"
> + check_per_core "STD" "$perf_cmd"
> + check_per_cache_instance "STD" "$perf_cmd"
> + check_per_die "STD" "$perf_cmd"
> + check_per_socket "STD" "$perf_cmd"
> +else
> + echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid"
> +fi
> +cleanup
> +exit 0
> --
> 2.35.1
>