Skip to contentSkip to conversation

perf, tools: Fall weak group back even for EBADF

PATCH In review Andi Kleen 3 participants 3 messages Sep 5, 2017 – Sep 22, 2017 perf events

lore
Share & tools
lore

Andi Kleen

author
#0 lore raw

PATCH 1/1 perf, tools: Fall weak group back even for EBADF

From: Andi Kleen <[email protected]>

It's not possible to run a package event and a per cpu event in the same group. This is used by some of the power metrics. They work correctly when not using a group.

Normally weak groups should handle that, but in this case EBADF is returned instead of the normal EINVAL.

strace -e perf_event_open ./perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
Using CPUID GenuineIntel-6-3E
perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, PERF_FLAG_FD_CLOEXEC) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = 3 perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, 3, 0) = 4 perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 1, 0, 0) = -1 EBADF (Bad file descriptor)

and perf errors out.

Make weak groups trigger a fall back for EBADF too. Then this case works correctly:

$ ./perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
Using CPUID GenuineIntel-6-3E
Weak group for cstate_pkg/c2-residency//2 failed
cstate_pkg/c2-residency/: 476709882 1000598460 1000598460
msr/tsc/: 39625837911 12007369110 12007369110

Performance counter stats for 'system wide':

       476,709,882      cstate_pkg/c2-residency/
    39,625,837,911      msr/tsc/

       1.000697588 seconds time elapsed

This fixes perf stat -M Power ...

$ ./perf stat -M Power --metric-only -a sleep 1

Performance counter stats for 'system wide':

Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.0 0.7 30.0 0.0 0.9 0.1 0.4 0.0

1.001240740 seconds time elapsed

---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-stat.c +1 -1
index 60206a1e03aa..1929f92c824b 100644
@@ -656,7 +656,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		if (create_perf_stat_counter(counter) < 0) {
 
 			/* Weak group failed. Reset the group. */
-			if (errno == EINVAL &&
+			if ((errno == EINVAL || errno == EBADF) &&
 			    counter->leader != counter &&
 			    counter->weak_group) {
 				counter = reset_weak_group(counter);
Signature · 1 line
2.9.5
Acked-by on v1 1/1
#1 lore raw
Quoted 40 lines · Andi Kleen

From: Andi Kleen <[email protected]>

It's not possible to run a package event and a per cpu event in the same group. This is used by some of the power metrics. They work correctly when not using a group.

Normally weak groups should handle that, but in this case EBADF is returned instead of the normal EINVAL.

strace -e perf_event_open ./perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
Using CPUID GenuineIntel-6-3E
perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, PERF_FLAG_FD_CLOEXEC) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument) perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = 3 perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, 3, 0) = 4 perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 1, 0, 0) = -1 EBADF (Bad file descriptor)

and perf errors out.

Make weak groups trigger a fall back for EBADF too. Then this case works correctly:

$ ./perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
Using CPUID GenuineIntel-6-3E
Weak group for cstate_pkg/c2-residency//2 failed
cstate_pkg/c2-residency/: 476709882 1000598460 1000598460
msr/tsc/: 39625837911 12007369110 12007369110

Performance counter stats for 'system wide':

       476,709,882      cstate_pkg/c2-residency/
    39,625,837,911      msr/tsc/

       1.000697588 seconds time elapsed

This fixes perf stat -M Power ...

$ ./perf stat -M Power --metric-only -a sleep 1
Quoted 8 lines

Performance counter stats for 'system wide':

Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.0 0.7 30.0 0.0 0.9 0.1 0.4 0.0

1.001240740 seconds time elapsed

seems ok me

thanks,
jirka

#2 lore raw

[tip:perf/core] perf stat: Fall weak group back even for EBADF

In reply to Andi Kleen
perf stat: Fall weak group back even for EBADF
Commit-ID:  35c1980eb3d1acb3cac11c38252339399dca77e3
Gitweb:     http://git.kernel.org/tip/35c1980eb3d1acb3cac11c38252339399dca77e3
Author:     Andi Kleen <[email protected]>
AuthorDate: Tue, 5 Sep 2017 14:13:24 -0700
Committer:  Arnaldo Carvalho de Melo <[email protected]>
CommitDate: Wed, 13 Sep 2017 09:49:16 -0300

perf stat: Fall weak group back even for EBADF

It's not possible to run a package event and a per cpu event in the same group. This is used by some of the power metrics. They work correctly when not using a group.

Normally weak groups should handle that, but in this case EBADF is returned instead of the normal EINVAL.

  $ strace -e perf_event_open ./perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
  Using CPUID GenuineIntel-6-3E
  perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, PERF_FLAG_FD_CLOEXEC) = -1 EINVAL (Invalid argument)
  perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument)
  perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument)
  perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument)
  perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = 3
  perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, 3, 0) = 4
  perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 1, 0, 0) = -1 EBADF (Bad file descriptor)

and perf errors out.

Make weak groups trigger a fall back for EBADF too. Then this case works correctly:

  $ perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
  Using CPUID GenuineIntel-6-3E
  Weak group for cstate_pkg/c2-residency//2 failed
  cstate_pkg/c2-residency/: 476709882 1000598460 1000598460
  msr/tsc/: 39625837911 12007369110 12007369110

Performance counter stats for 'system wide':

         476,709,882      cstate_pkg/c2-residency/
      39,625,837,911      msr/tsc/

         1.000697588 seconds time elapsed

This fixes perf stat -M Power ...

  $ perf stat -M Power --metric-only -a sleep 1

Performance counter stats for 'system wide':

Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.0 0.7 30.0 0.0 0.9 0.1 0.4 0.0

1.001240740 seconds time elapsed

---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-stat.c +1 -1
index 88f1d5f..dd52541 100644
@@ -656,7 +656,7 @@ try_again:
 		if (create_perf_stat_counter(counter) < 0) {
 
 			/* Weak group failed. Reset the group. */
-			if (errno == EINVAL &&
+			if ((errno == EINVAL || errno == EBADF) &&
 			    counter->leader != counter &&
 			    counter->weak_group) {
 				counter = perf_evsel__reset_weak_group(counter);