Optimize perf stat for large number of events/cpus v1
This patch kit optimizes perf stat for a large number of events on systems with many CPUs and PMUs.
Some profiling shows that the most overhead is doing IPIs to all the target CPUs. We can optimize this by using sched_setaffinity to set the affinity to a target CPU once and then doing the perf operation for all events on that CPU. This requires some restructuring, but cuts the set up time quite a bit.
In theory we could go further by parallelizing these setups too, but that would be much more complicated and for now just batching it per CPU seems to be sufficient. At some point with many more cores parallelization or a better bulk perf setup API might be needed though.
In addition perf does a lot of redundant /sys accesses with many PMUs, which can be also expensve. This is also optimized.
On a large test case (>700 events with many weak groups) on a 94 CPU system I go from
real 0m8.607s
user 0m0.550s
sys 0m8.041s
to
real 0m3.269s
user 0m0.760s
sys 0m1.694s
so shaving ~6 seconds of system time, at slightly more cost in perf stat itself. On a 4 socket system with the savings are more dramatic:
real 0m15.641s
user 0m0.873s
sys 0m14.729s
to
real 0m4.493s
user 0m1.578s
sys 0m2.444s
so 11s difference in the user visible set up time.
Also available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc perf/stat-scale-3
v1: Initial post.
-Andi
PATCH 1/9 perf evsel: Always preserve errno while cleaning up perf_event_open failures
From: Andi Kleen <[email protected]>
In some cases when perf_event_open fails, it may do some closes to clean up. In special cases these closes can fail too, which overwrites the errno of the perf_event_open, which is then incorrectly reported.
Save/restore errno around closes.
--- tools/perf/util/evsel.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
tools/perf/util/evsel.c +4 -2
@@ -1740,7 +1740,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, {int cpu, thread, nthreads;unsigned long flags =PERF_FLAG_FD_CLOEXEC ; -int pid =-1 , err; +int pid =-1 , err, old_errno;enum {NO_CHANGE ,SET_TO_MAX ,INCREASED_MAX } set_rlimit =NO_CHANGE ; if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) ||
@@ -1893,8 +1893,8 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,*/ if (err == -EMFILE && set_rlimit <INCREASED_MAX ) {struct rlimit l; -int old_errno = errno; + old_errno = errno;if (getrlimit (RLIMIT_NOFILE , &l) ==0 ) {if (set_rlimit ==NO_CHANGE ) l.rlim_cur = l.rlim_max;
@@ -1978,6 +1978,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,if (err) threads->err_thread = thread; + old_errno = errno; do { while (--thread >= 0) { close(FD(evsel, cpu, thread));
@@ -1985,6 +1986,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, } thread = nthreads; }while (--cpu >=0 ); + errno = old_errno;return err; }
Signature · 1 line
2.21.0
PATCH 2/9 perf evsel: Avoid close(-1)
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
In some weak fallback cases close can be called a lot with -1. Check for this case and avoid calling close then.
This is mainly to shut up valgrind which complains about this case.
--- tools/perf/lib/evsel.c | 3 ++- tools/perf/util/evsel.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)
tools/perf/lib/evsel.c +2 -1
@@ -120,7 +120,8 @@ void perf_evsel__close_fd(struct perf_evsel *evsel)for (cpu =0 ; cpu <xyarray__max_x (evsel->fd); cpu++)for (thread =0 ; thread <xyarray__max_y (evsel->fd); ++thread) { -close (FD (evsel, cpu, thread)); +if (FD (evsel, cpu, thread) >=0 ) +close (FD (evsel, cpu, thread));FD (evsel, cpu, thread) =-1 ; } }
tools/perf/util/evsel.c +2 -1
@@ -1981,7 +1981,8 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, old_errno = errno; do { while (--thread >= 0) { - close(FD(evsel, cpu, thread)); + if (FD(evsel, cpu, thread) >= 0) + close(FD(evsel, cpu, thread)); FD(evsel, cpu, thread) = -1; } thread = nthreads;
Signature · 1 line
2.21.0
PATCH 3/9 perf pmu: Use file system cache to optimize sysfs access
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
pmu.c does a lot of redundant /sys accesses while parsing aliases and probing for PMUs. On large systems with a lot of PMUs this can get expensive (>2s):
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
27.25 1.227847 8 160888 16976 openat 26.42 1.190481 7 164224 164077 stat
Add a cache to remember if specific file names exist or don't exist, which eliminates most of this overhead.
Also optimize some stat() calls to be slightly cheaper access()
Resulting in:
0.18 0.004166 2 1851 305 open 0.08 0.001970 2 829 622 access
--- tools/perf/util/Build | 1 + tools/perf/util/fncache.c | 52 ++++++++++++++++++++++++++++++++++++ tools/perf/util/fncache.h | 8 ++++++ tools/perf/util/pmu.c | 55 ++++++++++++++++++++++++--------------- tools/perf/util/srccode.c | 9 +------ 5 files changed, 96 insertions(+), 29 deletions(-) create mode 100644 tools/perf/util/fncache.c create mode 100644 tools/perf/util/fncache.h
tools/perf/util/Build +1 -0
@@ -46,6 +46,7 @@ perf-y += header.o perf-y += callchain.o perf-y += values.o perf-y += debug.o +perf-y += fncache.o perf-y += machine.o perf-y += map.o perf-y += pstack.o
tools/perf/util/fncache.c new file +52 -0
52 lines not on this page · raw message
tools/perf/util/fncache.h new file +8 -0
@@ -0,0 +1,8 @@ +#ifndef _FCACHE_H +#define _FCACHE_H 1 + +unsigned shash (const unsigned char *s); +void update_fncache (const char *name,bool res); +bool lookup_fncache (const char *name,bool *res); + +#endif
tools/perf/util/pmu.c +34 -21
145 lines not on this page · raw message
tools/perf/util/srccode.c +1 -8
@@ -16,6 +16,7 @@#include "srccode.h" #include "debug.h" #include "util.h" +#include "fncache.h" #define MAXSRCCACHE (32*1024*1024)#define MAXSRCFILES 64
@@ -36,14 +37,6 @@ static LIST_HEAD(srcfile_list);static long map_total_sz;static int num_srcfiles; -static unsigned shash (unsigned char *s) -{ -unsigned h =0 ; -while (*s) - h =65599 * h + *s++; -return h ^ (h >>16 ); -} -static int countlines (char *map,int maplen) {int numl;
Signature · 1 line
2.21.0
PATCH 4/9 perf affinity: Add infrastructure to save/restore affinity
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
The kernel perf subsystem has to IPI to the target CPU for many operations. On systems with many CPUs and when managing many events the overhead can be dominated by lots of IPIs.
An alternative is to set up CPU affinity in the perf tool, then set up all the events for that CPU, and then move on to the next CPU.
Add some affinity management infrastructure to enable such a model. Used in followon patches.
--- tools/perf/util/Build | 1 + tools/perf/util/affinity.c | 71 ++++++++++++++++++++++++++++++++++++++ tools/perf/util/affinity.h | 15 ++++++++ 3 files changed, 87 insertions(+) create mode 100644 tools/perf/util/affinity.c create mode 100644 tools/perf/util/affinity.h
tools/perf/util/Build +1 -0
@@ -74,6 +74,7 @@ perf-y += sort.o perf-y += hist.o perf-y += util.o perf-y += cpumap.o +perf-y += affinity.o perf-y += cputopo.o perf-y += cgroup.o perf-y += target.o
tools/perf/util/affinity.c new file +71 -0
71 lines not on this page · raw message
tools/perf/util/affinity.h new file +15 -0
@@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef AFFINITY_H +#define AFFINITY_H 1 + +struct affinity { +unsigned char *orig_cpus; +unsigned char *sched_cpus; +bool changed; +}; + +void affinity__cleanup (struct affinity *a); +void affinity__set (struct affinity *a,int cpu); +int affinity__setup (struct affinity *a); + +#endif
Signature · 1 line
2.21.0
PATCH 5/9 perf evsel: Add iterator to iterate over events ordered by CPU
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Add some common code that is needed to iterate over all events in CPU order. Used in followon patches
--- tools/perf/util/evlist.c | 33 +++++++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 4 ++++ tools/perf/util/evsel.h | 1 + 3 files changed, 38 insertions(+)
tools/perf/util/evlist.c +33 -0
@@ -324,6 +324,39 @@ static int perf_evlist__nr_threads(struct evlist *evlist,return perf_thread_map__nr (evlist->core.threads); } +struct perf_cpu_map *evlist__cpu_iter_start (struct evlist *evlist) +{ +struct perf_cpu_map *cpus; +struct evsel *pos; + +/* +* evlist->cpus is not necessarily a superset of all the +* event's cpus, so compute our own super set. This +* assume that there is a super set +*/ + cpus = evlist->core.cpus; +evlist__for_each_entry (evlist, pos) { + pos->cpu_index =0 ; +if (pos->core.cpus->nr > cpus->nr) + cpus = pos->core.cpus; + } +return cpus; +} + +bool evlist__cpu_iter_skip (struct evsel *ev,int cpu) +{ +if (ev->cpu_index >= ev->core.cpus->nr) +return true; +if (cpu >=0 && ev->core.cpus->map[ev->cpu_index] != cpu) +return true; +return false; +} + +void evlist__cpu_iter_next (struct evsel *ev) +{ + ev->cpu_index++; +} +void evlist__disable (struct evlist *evlist) {struct evsel *pos;
tools/perf/util/evlist.h +4 -0
@@ -309,6 +309,10 @@ void perf_evlist__to_front(struct evlist *evlist,void perf_evlist__set_tracking_event (struct evlist *evlist,struct evsel *tracking_evsel); +struct perf_cpu_map *evlist__cpu_iter_start (struct evlist *evlist); +bool evlist__cpu_iter_skip (struct evsel *ev,int cpu); +void evlist__cpu_iter_next (struct evsel *ev); +struct evsel *perf_evlist__find_evsel_by_str (struct evlist *evlist,const char *str);
tools/perf/util/evsel.h +1 -0
@@ -172,6 +172,7 @@ struct evsel {bool collect_stat;bool weak_group;bool percore; +int cpu_index;const char *pmu_name;struct {perf_evsel__sb_cb_t *cb;
Signature · 1 line
2.21.0
PATCH 6/9 perf stat: Use affinity for closing file descriptors
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Closing a perf fd can also trigger an IPI to the target CPU. Use the same affinity technique as we use for reading/enabling events to closing to optimize the CPU transitions.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
32.56 3.085463 50 61483 close
After:
10.54 0.735704 11 61485 close
--- tools/perf/lib/evsel.c | 27 +++++++++++++++++++------ tools/perf/lib/include/perf/evsel.h | 1 + tools/perf/util/evlist.c | 31 +++++++++++++++++++++++++++-- tools/perf/util/evsel.c | 2 +- tools/perf/util/evsel.h | 2 ++ 5 files changed, 54 insertions(+), 9 deletions(-)
tools/perf/lib/evsel.c +21 -6
@@ -114,16 +114,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,return err; } +static void perf_evsel__close_fd_cpu (struct perf_evsel *evsel,int cpu) +{ +int thread; + +for (thread =0 ; thread <xyarray__max_y (evsel->fd); ++thread) { +if (FD (evsel, cpu, thread) >=0 ) +close (FD (evsel, cpu, thread)); +FD (evsel, cpu, thread) =-1 ; + } +} +void perf_evsel__close_fd (struct perf_evsel *evsel) { -int cpu, thread; +int cpu;for (cpu =0 ; cpu <xyarray__max_x (evsel->fd); cpu++) -for (thread =0 ; thread <xyarray__max_y (evsel->fd); ++thread) { -if (FD (evsel, cpu, thread) >=0 ) -close (FD (evsel, cpu, thread)); -FD (evsel, cpu, thread) =-1 ; - } +perf_evsel__close_fd_cpu (evsel, cpu); }void perf_evsel__free_fd (struct perf_evsel *evsel)
@@ -141,6 +148,14 @@ void perf_evsel__close(struct perf_evsel *evsel)perf_evsel__free_fd (evsel); } +void perf_evsel__close_cpu (struct perf_evsel *evsel,int cpu) +{ +if (evsel->fd ==NULL ) +return ; + +perf_evsel__close_fd_cpu (evsel, cpu); +} +int perf_evsel__read_size (struct perf_evsel *evsel) {u64 read_format = evsel->attr.read_format;
tools/perf/lib/include/perf/evsel.h +1 -0
@@ -28,6 +28,7 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,struct perf_thread_map *threads); LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel); +LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
tools/perf/util/evlist.c +29 -2
@@ -17,6 +17,7 @@#include "debug.h" #include "units.h" #include "util.h" +#include "affinity.h" #include "../perf.h" #include "asm/bug.h" #include "bpf-event.h"
@@ -1342,9 +1343,35 @@ void perf_evlist__set_selected(struct evlist *evlist,void evlist__close (struct evlist *evlist) {struct evsel *evsel; +struct affinity affinity; +struct perf_cpu_map *cpus; +int i; + +/* So far record doesn't set this up */ +if (!evlist->core.cpus) { +evlist__for_each_entry_reverse (evlist, evsel) +evsel__close (evsel); +return ; + } -evlist__for_each_entry_reverse (evlist, evsel) -evsel__close (evsel); +if (affinity__setup (&affinity) <0 ) +return ; + cpus =evlist__cpu_iter_start (evlist); +for (i =0 ; i < cpus->nr; i++) { +int cpu = cpus->map[i]; +affinity__set (&affinity, cpu); + +evlist__for_each_entry_reverse (evlist, evsel) { +if (evlist__cpu_iter_skip (evsel, cpu)) +continue ; +perf_evsel__close_cpu (&evsel->core, evsel->cpu_index); +evlist__cpu_iter_next (evsel); + } + } +evlist__for_each_entry_reverse (evlist, evsel) { +perf_evsel__free_fd (&evsel->core); +perf_evsel__free_id (evsel); + } }static int perf_evlist__create_syswide_maps (struct evlist *evlist)
tools/perf/util/evsel.c +1 -1
@@ -1248,7 +1248,7 @@ int perf_evsel__alloc_id(struct evsel *evsel, int ncpus, int nthreads)return 0 ; } -static void perf_evsel__free_id (struct evsel *evsel) +void perf_evsel__free_id (struct evsel *evsel) {xyarray__delete (evsel->sample_id); evsel->sample_id =NULL ;
tools/perf/util/evsel.h +2 -0
@@ -511,4 +511,6 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,struct perf_env *perf_evsel__env (struct evsel *evsel);int perf_evsel__store_ids (struct evsel *evsel,struct evlist *evlist); +void perf_evsel__free_id (struct evsel *evsel); +#endif /* __PERF_EVSEL_H */
Signature · 1 line
2.21.0
PATCH 7/9 perf stat: Use affinity for opening events
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Restructure the event opening in perf stat to cycle through the events by CPU after setting affinity to that CPU. This eliminates IPI overhead in the perf API.
We have to loop through the CPU in the outter builtin-stat code instead of leaving that to low level functions.
It has to change the weak group fallback strategy slightly. Since we cannot easily undo the opens for other CPUs move the weak group retry to a separate loop.
Before with a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
42.75 4.050910 67 60046 110 perf_event_open
After:
26.86 0.944396 16 58069 110 perf_event_open
(the number changes slightly because the weak group retries work differently and the test case relies on weak groups)
--- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-stat.c | 194 +++++++++++++++++++++++++-------- tools/perf/tests/event-times.c | 4 +- tools/perf/util/evlist.c | 6 +- tools/perf/util/evlist.h | 3 +- tools/perf/util/evsel.c | 18 ++- tools/perf/util/evsel.h | 5 +- tools/perf/util/stat.c | 5 +- tools/perf/util/stat.h | 3 +- 9 files changed, 180 insertions(+), 60 deletions(-)
tools/perf/builtin-record.c +1 -1
@@ -773,7 +773,7 @@ static int record__open(struct record *rec)if ((errno ==EINVAL || errno ==EBADF ) && pos->leader != pos && pos->weak_group) { - pos =perf_evlist__reset_weak_group (evlist, pos); + pos =perf_evlist__reset_weak_group (evlist, pos, true); goto try_again; } rc = -errno;
tools/perf/builtin-stat.c +149 -45
238 lines not on this page · raw message
tools/perf/tests/event-times.c +2 -2
@@ -126,7 +126,7 @@ static int attach__cpu_disabled(struct evlist *evlist) evsel->core.attr.disabled =1 ; - err =perf_evsel__open_per_cpu (evsel, cpus); + err =perf_evsel__open_per_cpu (evsel, cpus,-1 );if (err) {if (err == -EACCES )return TEST_SKIP ;
@@ -153,7 +153,7 @@ static int attach__cpu_enabled(struct evlist *evlist)return -1 ; } - err =perf_evsel__open_per_cpu (evsel, cpus); + err =perf_evsel__open_per_cpu (evsel, cpus,-1 );if (err == -EACCES )return TEST_SKIP ;
tools/perf/util/evlist.c +4 -2
@@ -1822,7 +1822,8 @@ void perf_evlist__force_leader(struct evlist *evlist) }struct evsel *perf_evlist__reset_weak_group (struct evlist *evsel_list, -struct evsel *evsel) +struct evsel *evsel, +bool close) {struct evsel *c2, *leader;bool is_open = true;
@@ -1839,10 +1840,11 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,if (c2 == evsel) is_open = false;if (c2->leader == leader) { -if (is_open) +if (is_open && close)perf_evsel__close (&c2->core); c2->leader = c2; c2->core.nr_members =0 ; + c2->reset_group = true; } }return leader;
tools/perf/util/evlist.h +2 -1
@@ -324,5 +324,6 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist);void perf_evlist__force_leader (struct evlist *evlist);struct evsel *perf_evlist__reset_weak_group (struct evlist *evlist, -struct evsel *evsel); +struct evsel *evsel, +bool close);#endif /* __PERF_EVLIST_H */
tools/perf/util/evsel.c +13 -5
@@ -1735,8 +1735,9 @@ static int perf_event_open(struct evsel *evsel,return fd; } -int evsel__open (struct evsel *evsel,struct perf_cpu_map *cpus, -struct perf_thread_map *threads) +static int evsel__open_cpu (struct evsel *evsel,struct perf_cpu_map *cpus, +struct perf_thread_map *threads, +int start_cpu,int end_cpu) {int cpu, thread, nthreads;unsigned long flags =PERF_FLAG_FD_CLOEXEC ;
@@ -1813,7 +1814,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,display_attr (&evsel->core.attr); -for (cpu =0 ; cpu < cpus->nr; cpu++) { +for (cpu = start_cpu; cpu < end_cpu; cpu++) {for (thread =0 ; thread < nthreads; thread++) {int fd, group_fd;
@@ -1991,6 +1992,12 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,return err; } +int evsel__open (struct evsel *evsel,struct perf_cpu_map *cpus, +struct perf_thread_map *threads) +{ +return evsel__open_cpu (evsel, cpus, threads,0 , cpus ? cpus->nr :1 ); +} +void evsel__close (struct evsel *evsel) {perf_evsel__close (&evsel->core);
@@ -1998,9 +2005,10 @@ void evsel__close(struct evsel *evsel) }int perf_evsel__open_per_cpu (struct evsel *evsel, -struct perf_cpu_map *cpus) +struct perf_cpu_map *cpus, +int cpu) { -return evsel__open (evsel, cpus,NULL ); +return evsel__open_cpu (evsel, cpus,NULL , cpu, cpu +1 ); } int perf_evsel__open_per_thread(struct evsel *evsel,
tools/perf/util/evsel.h +4 -1
@@ -171,6 +171,8 @@ struct evsel {struct evsel *metric_leader;bool collect_stat;bool weak_group; +bool reset_group; +bool errored;bool percore;int cpu_index;const char *pmu_name;
@@ -307,7 +309,8 @@ int evsel__enable(struct evsel *evsel);int evsel__disable (struct evsel *evsel);int perf_evsel__open_per_cpu (struct evsel *evsel, -struct perf_cpu_map *cpus); +struct perf_cpu_map *cpus, +int cpu);int perf_evsel__open_per_thread (struct evsel *evsel,struct perf_thread_map *threads); int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
tools/perf/util/stat.c +3 -2
@@ -445,7 +445,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)int create_perf_stat_counter (struct evsel *evsel,struct perf_stat_config *config, -struct target *target) +struct target *target, +int cpu) {struct perf_event_attr *attr = &evsel->core.attr;struct evsel *leader = evsel->leader;
@@ -489,7 +490,7 @@ int create_perf_stat_counter(struct evsel *evsel, }if (target__has_cpu (target) && !target__has_per_thread (target)) -return perf_evsel__open_per_cpu (evsel,evsel__cpus (evsel)); +return perf_evsel__open_per_cpu (evsel,evsel__cpus (evsel), cpu);return perf_evsel__open_per_thread (evsel, evsel->core.threads); }
tools/perf/util/stat.h +2 -1
@@ -209,7 +209,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);int create_perf_stat_counter (struct evsel *evsel,struct perf_stat_config *config, -struct target *target); +struct target *target, +int cpu); int perf_stat_synthesize_config(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist,
Signature · 1 line
2.21.0
PATCH 8/9 perf stat: Use affinity for reading
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Restructure event reading to use affinity to minimize the number of IPIs needed.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
3.16 0.106079 4 22082 read
After:
3.43 0.081295 3 22082 read
--- tools/perf/builtin-stat.c | 97 ++++++++++++++++++++++----------------- tools/perf/util/evsel.h | 1 + 2 files changed, 57 insertions(+), 41 deletions(-)
tools/perf/builtin-stat.c +56 -41
@@ -264,15 +264,10 @@ static int read_single_counter(struct evsel *counter, int cpu,* Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode */ -static int read_counter (struct evsel *counter,struct timespec *rs) +static int read_counter (struct evsel *counter,struct timespec *rs,int cpu) {int nthreads =perf_thread_map__nr (evsel_list->core.threads); -int ncpus, cpu, thread; - -if (target__has_cpu (&target) && !target__has_per_thread (&target)) - ncpus =perf_evsel__nr_cpus (counter); -else - ncpus =1 ; +int thread;if (!counter->supported)return -ENOENT ;
@@ -281,40 +276,38 @@ static int read_counter(struct evsel *counter, struct timespec *rs) nthreads =1 ;for (thread =0 ; thread < nthreads; thread++) { -for (cpu =0 ; cpu < ncpus; cpu++) { -struct perf_counts_values *count; - - count =perf_counts (counter->counts, cpu, thread); - -/* -* The leader's group read loads data into its group members -* (via perf_evsel__read_counter) and sets threir count->loaded. -*/ -if (!perf_counts__is_loaded (counter->counts, cpu, thread) && -read_single_counter (counter, cpu, thread, rs)) { - counter->counts->scaled =-1 ; -perf_counts (counter->counts, cpu, thread)->ena =0 ; -perf_counts (counter->counts, cpu, thread)->run =0 ; -return -1 ; - } +struct perf_counts_values *count; -perf_counts__set_loaded (counter->counts, cpu, thread, false); + count =perf_counts (counter->counts, cpu, thread); -if (STAT_RECORD ) { -if (perf_evsel__write_stat_event (counter, cpu, thread, count)) { -pr_err ("failed to write stat event\n" ); -return -1 ; - } - } +/* +* The leader's group read loads data into its group members +* (via perf_evsel__read_counter) and sets threir count->loaded. +*/ +if (!perf_counts__is_loaded (counter->counts, cpu, thread) && +read_single_counter (counter, cpu, thread, rs)) { + counter->counts->scaled =-1 ; +perf_counts (counter->counts, cpu, thread)->ena =0 ; +perf_counts (counter->counts, cpu, thread)->run =0 ; +return -1 ; + } + +perf_counts__set_loaded (counter->counts, cpu, thread, false); -if (verbose >1 ) { -fprintf (stat_config.output, -"%s: %d: %" PRIu64" %" PRIu64" %" PRIu64"\n" , -perf_evsel__name (counter), - cpu, - count->val, count->ena, count->run); +if (STAT_RECORD ) { +if (perf_evsel__write_stat_event (counter, cpu, thread, count)) { +pr_err ("failed to write stat event\n" ); +return -1 ; } } + +if (verbose >1 ) { +fprintf (stat_config.output, +"%s: %d: %" PRIu64" %" PRIu64" %" PRIu64"\n" , +perf_evsel__name (counter), + cpu, + count->val, count->ena, count->run); + } }return 0 ;
@@ -323,15 +316,37 @@ static int read_counter(struct evsel *counter, struct timespec *rs)static void read_counters (struct timespec *rs) {struct evsel *counter; -int ret; +struct affinity affinity; +int i, ncpus; +struct perf_cpu_map *cpus; + +if (affinity__setup (&affinity) <0 ) +return ; + + cpus =evlist__cpu_iter_start (evsel_list); + + ncpus = cpus->nr; +if (!(target__has_cpu (&target) && !target__has_per_thread (&target))) + ncpus =1 ; +for (i =0 ; i < ncpus; i++) { +int cpu = cpus->map[i]; +affinity__set (&affinity, cpu); + +evlist__for_each_entry (evsel_list, counter) { +if (evlist__cpu_iter_skip (counter, cpu)) +continue ; + counter->err =read_counter (counter, rs, counter->cpu_index); +evlist__cpu_iter_next (counter); + } + } +affinity__cleanup (&affinity);evlist__for_each_entry (evsel_list, counter) { - ret =read_counter (counter, rs); -if (ret) +if (counter->err)pr_debug ("failed to read counter %s\n" , counter->name); - -if (ret ==0 &&perf_stat_process_counter (&stat_config, counter)) +if (counter->err ==0 &&perf_stat_process_counter (&stat_config, counter))pr_warning ("failed to process counter %s\n" , counter->name); + counter->err =0 ; } }
tools/perf/util/evsel.h +1 -0
@@ -163,6 +163,7 @@ struct evsel {struct list_head config_terms;struct bpf_object *bpf_obj;int bpf_fd; +int err;bool auto_merge_stats;bool merged_stat;const char * metric_expr;
Signature · 1 line
2.21.0
PATCH 9/9 perf stat: Use affinity for enabling/disabling events
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Restructure event enabling/disabling to use affinity, which minimizes the number of IPIs needed.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
54.65 1.899986 22 84812 660 ioctl
after:
39.21 0.930451 10 84796 644 ioctl
--- tools/perf/lib/evsel.c | 43 ++++++++++++++++++------- tools/perf/lib/include/perf/evsel.h | 2 ++ tools/perf/util/evlist.c | 50 ++++++++++++++++++++++++++--- tools/perf/util/evsel.c | 13 ++++++++ tools/perf/util/evsel.h | 2 ++ 5 files changed, 93 insertions(+), 17 deletions(-)
tools/perf/lib/evsel.c +31 -12
@@ -198,38 +198,57 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, }static int perf_evsel__run_ioctl (struct perf_evsel *evsel, -int ioc,void *arg) +int ioc,void *arg, +int cpu) { -int cpu, thread; +int thread; -for (cpu =0 ; cpu <xyarray__max_x (evsel->fd); cpu++) { -for (thread =0 ; thread <xyarray__max_y (evsel->fd); thread++) { -int fd =FD (evsel, cpu, thread), - err =ioctl (fd, ioc, arg); +for (thread =0 ; thread <xyarray__max_y (evsel->fd); thread++) { +int fd =FD (evsel, cpu, thread), + err =ioctl (fd, ioc, arg); -if (err) -return err; - } +if (err) +return err; }return 0 ; } +int perf_evsel__enable_cpu (struct perf_evsel *evsel,int cpu) +{ +return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_ENABLE ,0 , cpu); +} +int perf_evsel__enable (struct perf_evsel *evsel) { -return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_ENABLE ,0 ); +int i; +int err =0 ; + +for (i =0 ; i < evsel->cpus->nr && !err; i++) + err =perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_ENABLE ,0 , i); +return err; +} + +int perf_evsel__disable_cpu (struct perf_evsel *evsel,int cpu) +{ +return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_DISABLE ,0 , cpu); }int perf_evsel__disable (struct perf_evsel *evsel) { -return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_DISABLE ,0 ); +int i; +int err =0 ; + +for (i =0 ; i < evsel->cpus->nr && !err; i++) + err =perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_DISABLE ,0 , i); +return err; }int perf_evsel__apply_filter (struct perf_evsel *evsel,const char *filter) {return perf_evsel__run_ioctl (evsel,PERF_EVENT_IOC_SET_FILTER , - (void *)filter); + (void *)filter,-1 ); }struct perf_cpu_map *perf_evsel__cpus (struct perf_evsel *evsel)
tools/perf/lib/include/perf/evsel.h +2 -0
@@ -32,7 +32,9 @@ LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
tools/perf/util/evlist.c +45 -5
71 lines not on this page · raw message
tools/perf/util/evsel.c +13 -0
@@ -1201,13 +1201,26 @@ int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)return perf_evsel__append_filter (evsel,"%s,%s" , filter); } +/* Caller has to clear disabled after going through all CPUs. */ +int evsel__enable_cpu (struct evsel *evsel,int cpu) +{ +int err =perf_evsel__enable_cpu (&evsel->core, cpu); +return err; +} +int evsel__enable (struct evsel *evsel) {int err =perf_evsel__enable (&evsel->core);if (!err) evsel->disabled = false; +return err; +} +/* Caller has to set disabled after going through all CPUs. */ +int evsel__disable_cpu (struct evsel *evsel,int cpu) +{ +int err =perf_evsel__disable_cpu (&evsel->core, cpu);return err; }
tools/perf/util/evsel.h +2 -0
@@ -306,8 +306,10 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter);int perf_evsel__append_tp_filter (struct evsel *evsel,const char *filter);int perf_evsel__append_addr_filter (struct evsel *evsel,const char *filter); +int evsel__enable_cpu (struct evsel *evsel,int cpu);int evsel__enable (struct evsel *evsel);int evsel__disable (struct evsel *evsel); +int evsel__disable_cpu (struct evsel *evsel,int cpu); int perf_evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
Signature · 1 line
2.21.0