From 8384a2600c7ddfc875f64e160d8b423aca4e203a Mon Sep 17 00:00:00 2001 From: Alexey Budankov Date: Tue, 3 Dec 2019 14:45:27 +0300 Subject: perf record: Adapt affinity to machines with #CPUs > 1K Use struct mmap_cpu_mask type for the tool's thread and mmap data buffers to overcome current 1024 CPUs mask size limitation of cpu_set_t type. Currently glibc's cpu_set_t type has an internal mask size limit of 1024 CPUs. Moving to the 'struct mmap_cpu_mask' type allows overcoming that limit. The tools bitmap API is used to manipulate objects of 'struct mmap_cpu_mask' type. Committer notes: To print the 'nbits' struct member we must use %zd, since it is a size_t, this fixes the build in some toolchains/arches. Reported-by: Andi Kleen Signed-off-by: Alexey Budankov Acked-by: Jiri Olsa Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/96d7e2ff-ce8b-c1e0-d52c-aa59ea96f0ea@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mmap.c | 28 ++++++++++++++++++++++------ tools/perf/util/mmap.h | 2 +- 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'tools/perf/util') diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c index 2ee4faacca21..3b664fa673a6 100644 --- a/tools/perf/util/mmap.c +++ b/tools/perf/util/mmap.c @@ -219,6 +219,8 @@ static void perf_mmap__aio_munmap(struct mmap *map __maybe_unused) void mmap__munmap(struct mmap *map) { + bitmap_free(map->affinity_mask.bits); + perf_mmap__aio_munmap(map); if (map->data != NULL) { munmap(map->data, mmap__mmap_len(map)); @@ -227,7 +229,7 @@ void mmap__munmap(struct mmap *map) auxtrace_mmap__munmap(&map->auxtrace_mmap); } -static void build_node_mask(int node, cpu_set_t *mask) +static void build_node_mask(int node, struct mmap_cpu_mask *mask) { int c, cpu, nr_cpus; const struct perf_cpu_map *cpu_map = NULL; @@ -240,17 +242,23 @@ static void build_node_mask(int node, cpu_set_t *mask) 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); + set_bit(cpu, mask->bits); } } -static void perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) +static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp) { - CPU_ZERO(&map->affinity_mask); + map->affinity_mask.nbits = cpu__max_cpu(); + map->affinity_mask.bits = bitmap_alloc(map->affinity_mask.nbits); + if (!map->affinity_mask.bits) + return -1; + if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask); else if (mp->affinity == PERF_AFFINITY_CPU) - CPU_SET(map->core.cpu, &map->affinity_mask); + set_bit(map->core.cpu, map->affinity_mask.bits); + + return 0; } int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) @@ -261,7 +269,15 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu) return -1; } - perf_mmap__setup_affinity_mask(map, mp); + if (mp->affinity != PERF_AFFINITY_SYS && + perf_mmap__setup_affinity_mask(map, mp)) { + pr_debug2("failed to alloc mmap affinity mask, error %d\n", + errno); + return -1; + } + + if (verbose == 2) + mmap_cpu_mask__scnprintf(&map->affinity_mask, "mmap"); map->core.flush = mp->flush; diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h index ef51667fabcb..9d5f589f02ae 100644 --- a/tools/perf/util/mmap.h +++ b/tools/perf/util/mmap.h @@ -40,7 +40,7 @@ struct mmap { int nr_cblocks; } aio; #endif - cpu_set_t affinity_mask; + struct mmap_cpu_mask affinity_mask; void *data; int comp_level; }; -- cgit v1.2.3