From: Alexey Budankov <alexey.budankov@linux.intel.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>
Cc: Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Andi Kleen <ak@linux.intel.com>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: [PATCH v5 2/4] perf record: bind the AIO user space buffers to nodes
Date: Tue, 22 Jan 2019 20:48:54 +0300 [thread overview]
Message-ID: <5a5adebc-afe0-4806-81cd-180d49ec043f@linux.intel.com> (raw)
In-Reply-To: <af72a20b-117c-ec65-5fc9-35f4e81b26bd@linux.intel.com>
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@linux.intel.com>
---
Changes in v4:
- fixed compilation issue converting pr_warn() to pr_warning()
- implemented stop if mbind() fails
Changes in v3:
- corrected code style issues
- adjusted __aio_alloc,__aio_bind,__aio_free() implementation
Changes in v2:
- implemented perf_mmap__aio_alloc, perf_mmap__aio_free, perf_mmap__aio_bind
and put HAVE_LIBNUMA_SUPPORT #ifdefs in there
---
tools/perf/util/mmap.c | 77 +++++++++++++++++++++++++++++++++++++++---
1 file changed, 73 insertions(+), 4 deletions(-)
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index e68ba754a8e2..34be9f900575 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 index)
+{
+ map->aio.data[index] = mmap(NULL, perf_mmap__mmap_len(map), PROT_READ|PROT_WRITE,
+ MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
+ if (map->aio.data[index] == MAP_FAILED) {
+ map->aio.data[index] = NULL;
+ return -1;
+ }
+
+ return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int index)
+{
+ if (map->aio.data[index]) {
+ munmap(map->aio.data[index], perf_mmap__mmap_len(map));
+ map->aio.data[index] = NULL;
+ }
+}
+
+static int perf_mmap__aio_bind(struct perf_mmap *map, int index, 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[index];
+ 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 index)
+{
+ map->aio.data[index] = malloc(perf_mmap__mmap_len(map));
+ if (map->aio.data[index] == NULL)
+ return -1;
+
+ return 0;
+}
+
+static void perf_mmap__aio_free(struct perf_mmap *map, int index)
+{
+ zfree(&(map->aio.data[index]));
+}
+
+static int perf_mmap__aio_bind(struct perf_mmap *map __maybe_unused, int index __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);
next prev parent reply other threads:[~2019-01-22 17:49 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-22 17:45 [PATCH v5 0/4] Reduce NUMA related overhead in perf record profiling on large server systems Alexey Budankov
2019-01-22 17:47 ` [PATCH v5 1/4] perf record: allocate affinity masks Alexey Budankov
2019-02-09 12:45 ` [tip:perf/core] perf record: Allocate " tip-bot for Alexey Budankov
2019-01-22 17:48 ` Alexey Budankov [this message]
2019-02-04 19:29 ` [PATCH v5 2/4] perf record: bind the AIO user space buffers to nodes Arnaldo Carvalho de Melo
2019-02-04 19:47 ` Alexey Budankov
2019-02-05 15:15 ` Arnaldo Carvalho de Melo
2019-02-05 15:34 ` Alexey Budankov
2019-02-09 12:46 ` [tip:perf/core] perf record: Bind " tip-bot for Alexey Budankov
2019-01-22 17:50 ` [PATCH v5 3/4] perf record: apply affinity masks when reading mmap buffers Alexey Budankov
2019-02-09 12:47 ` [tip:perf/core] perf record: Apply " tip-bot for Alexey Budankov
2019-01-22 17:52 ` [PATCH v5 4/4] perf record: implement --affinity=node|cpu option Alexey Budankov
2019-02-15 9:25 ` [tip:perf/core] perf record: Implement " tip-bot for Alexey Budankov
2019-01-28 7:13 ` [PATCH v5 0/4] Reduce NUMA related overhead in perf record profiling on large server systems Alexey Budankov
2019-01-28 8:20 ` Jiri Olsa
2019-01-28 8:39 ` Alexey Budankov
2019-01-28 11:27 ` Jiri Olsa
2019-01-31 9:52 ` Alexey Budankov
2019-02-01 16:31 ` Arnaldo Carvalho de Melo
2019-01-29 9:14 ` Arnaldo Carvalho de Melo
2019-01-29 10:22 ` Alexey Budankov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=5a5adebc-afe0-4806-81cd-180d49ec043f@linux.intel.com \
--to=alexey.budankov@linux.intel.com \
--cc=acme@kernel.org \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).