[tip:perf/core] perf record: Bind the AIO user space buffers to nodes

From: tip-bot for Alexey Budankov
Date: Sat Feb 09 2019 - 07:46:29 EST


Commit-ID: c44a8b44ca9f156a5395597109987d1c462ba655
Gitweb: https://git.kernel.org/tip/c44a8b44ca9f156a5395597109987d1c462ba655
Author: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
AuthorDate: Tue, 22 Jan 2019 20:48:54 +0300
Committer: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Wed, 6 Feb 2019 10:00:39 -0300

perf record: Bind the AIO user space buffers to nodes

Allocate and bind AIO user space buffers to the memory nodes that mmap
kernel buffers are bound to.

Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
Reviewed-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/5a5adebc-afe0-4806-81cd-180d49ec043f@xxxxxxxxxxxxxxx
[ Do not use 'index' as a variable name, it is a define in older glibcs ]
Link: http://lkml.kernel.org/r/20190205151526.GC10613@xxxxxxxxxx
[ Add -lnuma to the python build when -DHAVE_LIBNUMA_SUPPORT is present, fixing 'perf test python' ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/util/mmap.c | 77 +++++++++++++++++++++++++++++++++++++++++++++---
tools/perf/util/setup.py | 5 ++++
2 files changed, 78 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index e68ba754a8e2..d882f43148c3 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -10,6 +10,9 @@
#include <sys/mman.h>
#include <inttypes.h>
#include <asm/bug.h>
+#ifdef HAVE_LIBNUMA_SUPPORT
+#include <numaif.h>
+#endif
#include "debug.h"
#include "event.h"
#include "mmap.h"
@@ -154,9 +157,72 @@ void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __mayb
}

#ifdef HAVE_AIO_SUPPORT
+
+#ifdef HAVE_LIBNUMA_SUPPORT
+static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx)
+{
+ map->aio.data[idx] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+ MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+ if (map->aio.data[idx] == MAP_FAILED) {
+ map->aio.data[idx] = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int idx)
+{
+ if (map->aio.data[idx]) {
+ munmap(map->aio.data[idx], perf_mmap__mmap_len(map));
+ map->aio.data[idx] = NULL;
+ }
+}
+
+static int perf_mmap__aio_bind(struct perf_mmap *map, int idx, int cpu, int affinity)
+{
+ void *data;
+ size_t mmap_len;
+ unsigned long node_mask;
+
+ if (affinity != PERF_AFFINITY_SYS && cpu__max_node() > 1) {
+ data = map->aio.data[idx];
+ mmap_len = perf_mmap__mmap_len(map);
+ node_mask = 1UL << cpu__get_node(cpu);
+ if (mbind(data, mmap_len, MPOL_BIND, &node_mask, 1, 0)) {
+ pr_err("Failed to bind [%p-%p] AIO buffer to node %d: error %m\n",
+ data, data + mmap_len, cpu__get_node(cpu));
+ return -1;
+ }
+ }
+
+ return 0;
+}
+#else
+static int perf_mmap__aio_alloc(struct perf_mmap *map, int idx)
+{
+ map->aio.data[idx] = malloc(perf_mmap__mmap_len(map));
+ if (map->aio.data[idx] == NULL)
+ return -1;
+
+ return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int idx)
+{
+ zfree(&(map->aio.data[idx]));
+}
+
+static int perf_mmap__aio_bind(struct perf_mmap *map __maybe_unused, int idx __maybe_unused,
+ int cpu __maybe_unused, int affinity __maybe_unused)
+{
+ return 0;
+}
+#endif
+
static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
{
- int delta_max, i, prio;
+ int delta_max, i, prio, ret;

map->aio.nr_cblocks = mp->nr_cblocks;
if (map->aio.nr_cblocks) {
@@ -177,11 +243,14 @@ static int perf_mmap__aio_mmap(struct perf_mmap *map, struct mmap_params *mp)
}
delta_max = sysconf(_SC_AIO_PRIO_DELTA_MAX);
for (i = 0; i < map->aio.nr_cblocks; ++i) {
- map->aio.data[i] = malloc(perf_mmap__mmap_len(map));
- if (!map->aio.data[i]) {
+ ret = perf_mmap__aio_alloc(map, i);
+ if (ret == -1) {
pr_debug2("failed to allocate data buffer area, error %m");
return -1;
}
+ ret = perf_mmap__aio_bind(map, i, map->cpu, mp->affinity);
+ if (ret == -1)
+ return -1;
/*
* Use cblock.aio_fildes value different from -1
* to denote started aio write operation on the
@@ -210,7 +279,7 @@ static void perf_mmap__aio_munmap(struct perf_mmap *map)
int i;

for (i = 0; i < map->aio.nr_cblocks; ++i)
- zfree(&map->aio.data[i]);
+ perf_mmap__aio_free(map, i);
if (map->aio.data)
zfree(&map->aio.data);
zfree(&map->aio.cblocks);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index d3ffc18424b5..5b5a167b43ce 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -53,9 +53,14 @@ ext_sources = [f.strip() for f in open('util/python-ext-sources')
# use full paths with source files
ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))

+extra_libraries = []
+if '-DHAVE_LIBNUMA_SUPPORT' in cflags:
+ extra_libraries = [ 'numa' ]
+
perf = Extension('perf',
sources = ext_sources,
include_dirs = ['util/include'],
+ libraries = extra_libraries,
extra_compile_args = cflags,
extra_objects = [libtraceevent, libapikfs],
)