leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

perf record: Adapt affinity to machines with #CPUs > 1K

Browse Source 
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 <ak@linux.intel.com>
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/96d7e2ff-ce8b-c1e0-d52c-aa59ea96f0ea@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Alexey Budankov
2019-12-03 14:45:27 +03:00
committed by Arnaldo Carvalho de Melo
parent 9c080c0279
commit 8384a2600c
3 changed files with 45 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
tools/perf/util/mmap.c
View File

@@ -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;