Build node cpu masks for mmap data buffers. Apply node cpu masks to tool thread every time it references data buffers cross node or cross cpu.
Signed-off-by: Alexey Budankov <alexey.budan...@linux.intel.com> --- Changes in v5: - avoided multiple allocations of online cpu maps by implementing it once in cpu_map__online() Changes in v4: - corrected mmap_params->cpu_map initialization to be based on /sys/devices/system/cpu/online - separated node cpu map generation into build_node_mask() Changes in v3: - separated mask manipulations into __adjust_affinity() and __setup_affinity_mask() - implemented mapping of c index into online cpu index Changes in v2: - separated AIO buffers binding to patch 2/4 --- tools/perf/builtin-record.c | 14 ++++++++++++++ tools/perf/util/cpumap.c | 10 ++++++++++ tools/perf/util/cpumap.h | 1 + tools/perf/util/mmap.c | 28 +++++++++++++++++++++++++++- 4 files changed, 52 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 370a68487532..142d109bc53d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -537,6 +537,9 @@ static int record__mmap_evlist(struct record *rec, struct record_opts *opts = &rec->opts; char msg[512]; + if (opts->affinity != PERF_AFFINITY_SYS) + cpu__setup_cpunode_map(); + if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, opts->auxtrace_mmap_pages, opts->auxtrace_snapshot_mode, @@ -729,6 +732,16 @@ static struct perf_event_header finished_round_event = { .type = PERF_RECORD_FINISHED_ROUND, }; +static void record__adjust_affinity(struct record *rec, struct perf_mmap *map) +{ + if (rec->opts.affinity != PERF_AFFINITY_SYS && + !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) { + CPU_ZERO(&rec->affinity_mask); + CPU_OR(&rec->affinity_mask, &rec->affinity_mask, &map->affinity_mask); + sched_setaffinity(0, sizeof(rec->affinity_mask), &rec->affinity_mask); + } +} + static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist, bool overwrite) { @@ -756,6 +769,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli struct perf_mmap *map = &maps[i]; if (map->base) { + record__adjust_affinity(rec, map); if (!record__aio_enabled(rec)) { if (perf_mmap__push(map, rec, record__pushfn) != 0) { rc = -1; diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 1ccbd3342069..a5523ba05cf1 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -723,3 +723,13 @@ size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size) buf[size - 1] = '\0'; return ptr - buf; } + +const struct cpu_map *cpu_map__online(void) /* thread unsafe */ +{ + static const struct cpu_map *online = NULL; + + if (!online) + online = cpu_map__new(NULL); /* from /sys/devices/system/cpu/online */ + + return online; +} diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index ed8999d1a640..f00ce624b9f7 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -29,6 +29,7 @@ int cpu_map__get_core_id(int cpu); int cpu_map__get_core(struct cpu_map *map, int idx, void *data); int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp); int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep); +const struct cpu_map *cpu_map__online(void); /* thread unsafe */ struct cpu_map *cpu_map__get(struct cpu_map *map); void cpu_map__put(struct cpu_map *map); diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 34be9f900575..995c282fcd21 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -383,6 +383,32 @@ void perf_mmap__munmap(struct perf_mmap *map) auxtrace_mmap__munmap(&map->auxtrace_mmap); } +static void build_node_mask(int node, cpu_set_t *mask) +{ + int c, cpu, nr_cpus; + const struct cpu_map *cpu_map = NULL; + + cpu_map = cpu_map__online(); + if (!cpu_map) + return; + + nr_cpus = cpu_map__nr(cpu_map); + for (c = 0; c < nr_cpus; c++) { + cpu = cpu_map->map[c]; /* map c index to online cpu index */ + if (cpu__get_node(cpu) == node) + CPU_SET(cpu, mask); + } +} + +static void perf_mmap__setup_affinity_mask(struct perf_mmap *map, struct mmap_params *mp) +{ + CPU_ZERO(&map->affinity_mask); + if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) + build_node_mask(cpu__get_node(map->cpu), &map->affinity_mask); + else if (mp->affinity == PERF_AFFINITY_CPU) + CPU_SET(map->cpu, &map->affinity_mask); +} + int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int cpu) { /* @@ -412,7 +438,7 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c map->fd = fd; map->cpu = cpu; - CPU_ZERO(&map->affinity_mask); + perf_mmap__setup_affinity_mask(map, mp); if (auxtrace_mmap__mmap(&map->auxtrace_mmap, &mp->auxtrace_mp, map->base, fd))