diff options
author | Arnaldo Carvalho de Melo <acme@redhat.com> | 2011-01-03 19:45:52 (GMT) |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2011-01-04 02:22:55 (GMT) |
commit | c52b12ed2511e6c031a0295fd903ea72b93701fb (patch) | |
tree | 770915627e789401b820a104c1ed23a212e7bd50 /tools/perf/util | |
parent | 70d544d0576775a2b3923a7e68cb49b0313d80c9 (diff) | |
download | linux-fsl-qoriq-c52b12ed2511e6c031a0295fd903ea72b93701fb.tar.xz |
perf evsel: Steal the counter reading routines from stat
Making them hopefully generic enough to be used in 'perf test',
well see.
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
LKML-Reference: <new-submission>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util')
-rw-r--r-- | tools/perf/util/evsel.c | 88 | ||||
-rw-r--r-- | tools/perf/util/evsel.h | 79 |
2 files changed, 167 insertions, 0 deletions
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6539ec9..3f5de51 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1,6 +1,8 @@ #include "evsel.h" #include "util.h" +#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) + struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx) { struct perf_evsel *evsel = zalloc(sizeof(*evsel)); @@ -21,15 +23,101 @@ int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) return evsel->fd != NULL ? 0 : -ENOMEM; } +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) +{ + evsel->counts = zalloc((sizeof(*evsel->counts) + + (ncpus * sizeof(struct perf_counts_values)))); + return evsel->counts != NULL ? 0 : -ENOMEM; +} + void perf_evsel__free_fd(struct perf_evsel *evsel) { xyarray__delete(evsel->fd); evsel->fd = NULL; } +void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + int cpu, thread; + + for (cpu = 0; cpu < ncpus; cpu++) + for (thread = 0; thread < nthreads; ++thread) { + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } +} + void perf_evsel__delete(struct perf_evsel *evsel) { assert(list_empty(&evsel->node)); xyarray__delete(evsel->fd); free(evsel); } + +int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, + int cpu, int thread, bool scale) +{ + struct perf_counts_values count; + size_t nv = scale ? 3 : 1; + + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; + + if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) + return -errno; + + if (scale) { + if (count.run == 0) + count.val = 0; + else if (count.run < count.ena) + count.val = (u64)((double)count.val * count.ena / count.run + 0.5); + } else + count.ena = count.run = 0; + + evsel->counts->cpu[cpu] = count; + return 0; +} + +int __perf_evsel__read(struct perf_evsel *evsel, + int ncpus, int nthreads, bool scale) +{ + size_t nv = scale ? 3 : 1; + int cpu, thread; + struct perf_counts_values *aggr = &evsel->counts->aggr, count; + + aggr->val = 0; + + for (cpu = 0; cpu < ncpus; cpu++) { + for (thread = 0; thread < nthreads; thread++) { + if (FD(evsel, cpu, thread) < 0) + continue; + + if (readn(FD(evsel, cpu, thread), + &count, nv * sizeof(u64)) < 0) + return -errno; + + aggr->val += count.val; + if (scale) { + aggr->ena += count.ena; + aggr->run += count.run; + } + } + } + + evsel->counts->scaled = 0; + if (scale) { + if (aggr->run == 0) { + evsel->counts->scaled = -1; + aggr->val = 0; + return 0; + } + + if (aggr->run < aggr->ena) { + evsel->counts->scaled = 1; + aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5); + } + } else + aggr->ena = aggr->run = 0; + + return 0; +} diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 8a5cfb6..8b48ef1 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -2,15 +2,34 @@ #define __PERF_EVSEL_H 1 #include <linux/list.h> +#include <stdbool.h> #include <linux/perf_event.h> #include "types.h" #include "xyarray.h" + +struct perf_counts_values { + union { + struct { + u64 val; + u64 ena; + u64 run; + }; + u64 values[3]; + }; +}; + +struct perf_counts { + s8 scaled; + struct perf_counts_values aggr; + struct perf_counts_values cpu[]; +}; struct perf_evsel { struct list_head node; struct perf_event_attr attr; char *filter; struct xyarray *fd; + struct perf_counts *counts; int idx; void *priv; }; @@ -19,10 +38,70 @@ struct perf_evsel *perf_evsel__new(u32 type, u64 config, int idx); void perf_evsel__delete(struct perf_evsel *evsel); int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); void perf_evsel__free_fd(struct perf_evsel *evsel); +void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads); #define perf_evsel__match(evsel, t, c) \ (evsel->attr.type == PERF_TYPE_##t && \ evsel->attr.config == PERF_COUNT_##c) +int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, + int cpu, int thread, bool scale); + +/** + * perf_evsel__read_on_cpu - Read out the results on a CPU and thread + * + * @evsel - event selector to read value + * @cpu - CPU of interest + * @thread - thread of interest + */ +static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel, + int cpu, int thread) +{ + return __perf_evsel__read_on_cpu(evsel, cpu, thread, false); +} + +/** + * perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled + * + * @evsel - event selector to read value + * @cpu - CPU of interest + * @thread - thread of interest + */ +static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel, + int cpu, int thread) +{ + return __perf_evsel__read_on_cpu(evsel, cpu, thread, true); +} + +int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads, + bool scale); + +/** + * perf_evsel__read - Read the aggregate results on all CPUs + * + * @evsel - event selector to read value + * @ncpus - Number of cpus affected, from zero + * @nthreads - Number of threads affected, from zero + */ +static inline int perf_evsel__read(struct perf_evsel *evsel, + int ncpus, int nthreads) +{ + return __perf_evsel__read(evsel, ncpus, nthreads, false); +} + +/** + * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled + * + * @evsel - event selector to read value + * @ncpus - Number of cpus affected, from zero + * @nthreads - Number of threads affected, from zero + */ +static inline int perf_evsel__read_scaled(struct perf_evsel *evsel, + int ncpus, int nthreads) +{ + return __perf_evsel__read(evsel, ncpus, nthreads, true); +} + #endif /* __PERF_EVSEL_H */ |