perf_event_open02: stop groups with hw counters first
PATCH 1/2 perf_event_open02: stop groups with hw counters first
Nick reports that prctl(PR_TASK_PERF_EVENTS_DISABLE) doesn't stop tsk0 as last one, which sometimes causes test to fail, because of way test calculates 'ratio' value and very low tolerance.
Looking at implementation, prctl() walks the list and does appear to disable events in order they were created (tsk0 first).
Stop groups with hw counters before tsk0.
ratio Before After mean 4.99921 4.99871 stdev 0.00006315 0.0000746
--- testcases/kernel/syscalls/perf_event_open/perf_event_open02.c | 6 ++++++ 1 file changed, 6 insertions(+)
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +6 -0
@@ -324,6 +324,12 @@ static void verify(void)do_work (); +/* stop groups with hw counters first before tsk0 */ +for (i =0 ; i < n; i++) { +ioctl (hwfd[i],PERF_EVENT_IOC_DISABLE ); +ioctl (tskfd[i],PERF_EVENT_IOC_DISABLE ); + } +if (prctl (PR_TASK_PERF_EVENTS_DISABLE ) ==-1 ) {tst_brkm (TBROK |TERRNO , cleanup,"prctl(PR_TASK_PERF_EVENTS_DISABLE) failed" );
Signature · 1 line
1.8.3.1
PATCH 2/2 perf_event_open02: make test more reliable on -rt kernels
Test is failing on -rt kernels quite reliably as reported here:
https://lkml.org/lkml/2019/8/14/714
Suspected cause is extra time spend in scheduler, which counts towards test process hw counters.
Pin test process to single CPU (doesn't matter which one) to lessen effects from scheduling:
ratio Before After
mean 5.02582 4.99844
stdev 0.0090435 0.0000272
95+% FAIL 100% PASSTested with "perf_event_open02: stop groups with hw counters first" patch on RHEL8 kernel-rt 4.18.0-147.rt24.93.el8.x86_64 (HP dl380g7).
--- .../kernel/syscalls/perf_event_open/perf_event_open02.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +15 -0
@@ -52,6 +52,7 @@ Usage is: ./performance_counter02 [-v]The -v flag makes it print out the values of each counter. */ +#define _GNU_SOURCE#include <stdio.h> #include <stddef.h> #include <stdlib.h>
@@ -222,6 +223,20 @@ static void setup(void)int i;struct perf_event_attr tsk_event, hw_event; +#ifdef HAVE_SCHED_GETCPU +cpu_set_t mask; +int cpu =sched_getcpu (); + +if (cpu ==-1 ) +tst_brkm (TBROK |TERRNO ,NULL ,"sched_getcpu() failed" ); + +CPU_ZERO (&mask); +CPU_SET (cpu, &mask); + +if (sched_setaffinity (0 ,sizeof (cpu_set_t), &mask) ==-1 ) +tst_brkm (TBROK |TERRNO ,NULL ,"sched_setaffinity() failed" ); +#endif +/* * According to perf_event_open's manpage, the official way of * knowing if perf_event_open() support is enabled is checking for
Signature · 1 line
1.8.3.1
PATCH 2/2 perf_event_open02: make test more reliable on -rt kernels
Hi!
Quoted 18 lines
Signed-off-by Jan Stancek <[email protected]>--- .../kernel/syscalls/perf_event_open/perf_event_open02.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +1
-0@@ -52,6 +52,7 @@ Usage is: ./performance_counter02 [-v]The -v flag makes it print out the values of each counter. */ +#define _GNU_SOURCE#include <stdio.h> #include <stddef.h> #include <stdlib.h>
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c static void setup(void) · line 227
Quoted 5 lines
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +2
-0@@ -222,6 +223,20 @@ static void setup(void)int i;struct perf_event_attr tsk_event, hw_event; +#ifdef HAVE_SCHED_GETCPU +cpu_set_t mask;
Don't we have to allocate the mask dynamically so that we do not fail on systems with more than CPU_SETSIZE (1024) CPUs?
We already have fallback macros for older libc in include/lapi/cpuset.h so that we can use CPU_ALLOC() unconditionally.
Quoted 21 lines
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +12
-0+int cpu =sched_getcpu (); + +if (cpu ==-1 ) +tst_brkm (TBROK |TERRNO ,NULL ,"sched_getcpu() failed" ); + +CPU_ZERO (&mask); +CPU_SET (cpu, &mask); + +if (sched_setaffinity (0 ,sizeof (cpu_set_t), &mask) ==-1 ) +tst_brkm (TBROK |TERRNO ,NULL ,"sched_setaffinity() failed" ); +#endif +/* * According to perf_event_open's manpage, the official way of * knowing if perf_event_open() support is enabled is checking for Signature · 5 lines
1.8.3.1 -- Mailing list info: https://lists.linux.it/listinfo/ltp
Signature · 2 lines
Cyril Hrubis [email protected]
PATCH 2/2 perf_event_open02: make test more reliable on -rt kernels
----- Original Message -----
Quoted 24 lines
Hi!
Quoted 23 lines
Signed-off-by Jan Stancek <[email protected]>--- .../kernel/syscalls/perf_event_open/perf_event_open02.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +1
-0@@ -52,6 +52,7 @@ Usage is: ./performance_counter02 [-v]The -v flag makes it print out the values of each counter. */ +#define _GNU_SOURCE#include <stdio.h> #include <stddef.h> #include <stdlib.h> @@ -222,6 +223,20 @@ static void setup(void)int i;struct perf_event_attr tsk_event, hw_event;
Quoted 8 lines
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c static void setup(void) · line 227
Quoted 2 lines
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +2
-0+#ifdef HAVE_SCHED_GETCPU +cpu_set_t mask;Don't we have to allocate the mask dynamically so that we do not fail on systems with more than
CPU_SETSIZE(1024) CPUs?We already have fallback macros for older libc in
include/lapi/cpuset.hso that we can useCPU_ALLOC()unconditionally.
Haven't thought of that. I'll look into adding that for v2.
PATCH v2 1/1 perf_event_open02: make test more reliable on -rt kernels
Test is failing on -rt kernels quite reliably as reported here:
https://lkml.org/lkml/2019/8/14/714
Suspected cause is extra time spend in scheduler, which counts towards test process hw counters.
Pin test process to single CPU (doesn't matter which one) to lessen effects from scheduling:
ratio Before After
mean 5.02582 4.99844
stdev 0.0090435 0.0000272
95+% FAIL 100% PASSTested with "perf_event_open02: stop groups with hw counters first" patch on RHEL8 kernel-rt 4.18.0-147.rt24.93.el8.x86_64 (HP dl380g7).
--- .../syscalls/perf_event_open/perf_event_open02.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+)
testcases/kernel/syscalls/perf_event_open/perf_event_open02.c +19 -0
@@ -52,6 +52,7 @@ Usage is: ./performance_counter02 [-v]The -v flag makes it print out the values of each counter. */ +#define _GNU_SOURCE#include <stdio.h> #include <stddef.h> #include <stdlib.h>
@@ -72,6 +73,7 @@ The -v flag makes it print out the values of each counter.#include "test.h" #include "safe_macros.h" +#include "lapi/cpuset.h" #include "lapi/syscalls.h" char *TCID ="perf_event_open02" ;
@@ -222,6 +224,23 @@ static void setup(void)int i;struct perf_event_attr tsk_event, hw_event; +#ifdef HAVE_SCHED_GETCPU +int cpu =sched_getcpu (); +size_t mask_size; +cpu_set_t *mask; + +if (cpu ==-1 ) +tst_brkm (TBROK |TERRNO ,NULL ,"sched_getcpu() failed" ); + + mask =CPU_ALLOC (cpu +1 ); + mask_size =CPU_ALLOC_SIZE (cpu +1 ); +CPU_ZERO_S (mask_size, mask); +CPU_SET (cpu, mask); +if (sched_setaffinity (0 , mask_size, mask) ==-1 ) +tst_brkm (TBROK |TERRNO ,NULL ,"sched_setaffinity() failed" ); +CPU_FREE (mask); +#endif +/* * According to perf_event_open's manpage, the official way of * knowing if perf_event_open() support is enabled is checking for
Signature · 1 line
1.8.3.1
PATCH v2 1/1 perf_event_open02: make test more reliable on -rt kernels
Hi!
This version looks good, acked.
Signature · 2 lines
Cyril Hrubis [email protected]
PATCH v2 1/1 perf_event_open02: make test more reliable on -rt kernels
----- Original Message -----
Quoted 2 lines
Hi!
This version looks good, acked.
Both pushed.
PATCH 1/2 perf_event_open02: stop groups with hw counters first
In reply to Jan StancekHi!
Acked.
Signature · 2 lines
Cyril Hrubis [email protected]