On Mon, Dec 24, 2018 at 03:27:17PM +0300, Alexey Budankov wrote:
>
> 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 <[email protected]>
> ---
> Changes in v2:
> - separated AIO buffers binding to patch 2/4
> ---
> tools/perf/builtin-record.c | 9 +++++++++
> tools/perf/util/evlist.c | 6 +++++-
> tools/perf/util/mmap.c | 12 ++++++++++++
> tools/perf/util/mmap.h | 1 +
> 4 files changed, 27 insertions(+), 1 deletion(-)
>
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index b26febb54d01..eea96794ee45 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -536,6 +536,9 @@ 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,
> @@ -755,6 +758,12 @@ static int record__mmap_read_evlist(struct record *rec,
> struct perf_evlist *evli
> struct perf_mmap *map = &maps[i];
>
> if (map->base) {
> + 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);
all this code depends on aio and LIBNUMA, let's keep it there then
also please add this and the affinity_mask setup code below to a function
thanks,
jirka
> + }
> if (!record__aio_enabled(rec)) {
> if (perf_mmap__push(map, rec, record__pushfn)
> != 0) {
> rc = -1;
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index 60e825be944a..5ca5bb5ea0db 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -1028,7 +1028,11 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist,
> unsigned int pages,
> * Its value is decided by evsel's write_backward.
> * So &mp should not be passed through const pointer.
> */
> - struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity =
> affinity };
> + struct mmap_params mp = {
> + .nr_cblocks = nr_cblocks,
> + .affinity = affinity,
> + .cpu_map = cpus
> + };
>
> if (!evlist->mmap)
> evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
> diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
> index 742fa9a8e498..a2095e4eda4b 100644
> --- a/tools/perf/util/mmap.c
> +++ b/tools/perf/util/mmap.c
> @@ -361,6 +361,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
>
> int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd,
> int cpu)
> {
> + int c, nr_cpus, node;
> /*
> * The last one will be done at perf_mmap__consume(), so that we
> * make sure we don't prevent tools from consuming every last event in
> @@ -389,6 +390,17 @@ int perf_mmap__mmap(struct perf_mmap *map, struct
> mmap_params *mp, int fd, int c
> map->cpu = cpu;
>
> CPU_ZERO(&map->affinity_mask);
> + if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1) {
> + nr_cpus = cpu_map__nr(mp->cpu_map);
> + node = cpu__get_node(map->cpu);
> + for (c = 0; c < nr_cpus; c++) {
> + if (cpu__get_node(c) == node) {
> + CPU_SET(c, &map->affinity_mask);
> + }
> + }
> + } else if (mp->affinity == PERF_AFFINITY_CPU) {
> + CPU_SET(map->cpu, &map->affinity_mask);
> + }
>
> if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
> &mp->auxtrace_mp, map->base, fd))
> diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
> index e566c19b242b..b3f724fad22e 100644
> --- a/tools/perf/util/mmap.h
> +++ b/tools/perf/util/mmap.h
> @@ -72,6 +72,7 @@ enum bkw_mmap_state {
> struct mmap_params {
> int prot, mask, nr_cblocks, affinity;
> struct auxtrace_mmap_params auxtrace_mp;
> + const struct cpu_map *cpu_map;
> };
>
> int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd,
> int cpu);
