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 v2 1/4] perf record: allocate affinity masks
Date: Thu, 13 Dec 2018 10:18:40 +0300 [thread overview]
Message-ID: <090df1eb-598b-cc31-0a47-63c3c8692c6b@linux.intel.com> (raw)
In-Reply-To: <26031ab1-f39d-b0c3-8862-c17540f50705@linux.intel.com>
Allocate affinity option and masks for mmap data buffers and
record thread as well as initialize allocated objects.
Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
---
Changes in v2:
- made debug affinity mode message user friendly
- converted affinity mode defines to enum values
---
tools/perf/builtin-record.c | 13 ++++++++++++-
tools/perf/perf.h | 8 ++++++++
tools/perf/util/evlist.c | 6 +++---
tools/perf/util/evlist.h | 2 +-
tools/perf/util/mmap.c | 2 ++
tools/perf/util/mmap.h | 3 ++-
6 files changed, 28 insertions(+), 6 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 882285fb9f64..b26febb54d01 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -81,12 +81,17 @@ struct record {
bool timestamp_boundary;
struct switch_output switch_output;
unsigned long long samples;
+ cpu_set_t affinity_mask;
};
static volatile int auxtrace_record__snapshot_started;
static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
static DEFINE_TRIGGER(switch_output_trigger);
+static const char* affinity_tags[PERF_AFFINITY_EOF] = {
+ "SYS", "NODE", "CPU"
+};
+
static bool switch_output_signal(struct record *rec)
{
return rec->switch_output.signal &&
@@ -533,7 +538,8 @@ static int record__mmap_evlist(struct record *rec,
if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
opts->auxtrace_mmap_pages,
- opts->auxtrace_snapshot_mode, opts->nr_cblocks) < 0) {
+ opts->auxtrace_snapshot_mode,
+ opts->nr_cblocks, opts->affinity) < 0) {
if (errno == EPERM) {
pr_err("Permission error mapping pages.\n"
"Consider increasing "
@@ -1980,6 +1986,9 @@ int cmd_record(int argc, const char **argv)
# undef REASON
#endif
+ CPU_ZERO(&rec->affinity_mask);
+ rec->opts.affinity = PERF_AFFINITY_SYS;
+
rec->evlist = perf_evlist__new();
if (rec->evlist == NULL)
return -ENOMEM;
@@ -2143,6 +2152,8 @@ int cmd_record(int argc, const char **argv)
if (verbose > 0)
pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
+ pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+
err = __cmd_record(&record, argc, argv);
out:
perf_evlist__delete(rec->evlist);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 388c6dd128b8..69f54529d81f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -83,6 +83,14 @@ struct record_opts {
clockid_t clockid;
u64 clockid_res_ns;
int nr_cblocks;
+ int affinity;
+};
+
+enum perf_affinity {
+ PERF_AFFINITY_SYS = 0,
+ PERF_AFFINITY_NODE,
+ PERF_AFFINITY_CPU,
+ PERF_AFFINITY_EOF
};
struct option;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e90575192209..60e825be944a 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1018,7 +1018,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
*/
int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
unsigned int auxtrace_pages,
- bool auxtrace_overwrite, int nr_cblocks)
+ bool auxtrace_overwrite, int nr_cblocks, int affinity)
{
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
@@ -1028,7 +1028,7 @@ 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 };
+ struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity };
if (!evlist->mmap)
evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1060,7 +1060,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
{
- return perf_evlist__mmap_ex(evlist, pages, 0, false, 0);
+ return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
}
int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 868294491194..72728d7f4432 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -162,7 +162,7 @@ unsigned long perf_event_mlock_kb_in_pages(void);
int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
unsigned int auxtrace_pages,
- bool auxtrace_overwrite, int nr_cblocks);
+ bool auxtrace_overwrite, int nr_cblocks, int affinity);
int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
void perf_evlist__munmap(struct perf_evlist *evlist);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 8fc39311a30d..e68ba754a8e2 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -343,6 +343,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
map->fd = fd;
map->cpu = cpu;
+ CPU_ZERO(&map->affinity_mask);
+
if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
&mp->auxtrace_mp, map->base, fd))
return -1;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index aeb6942fdb00..e566c19b242b 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -38,6 +38,7 @@ struct perf_mmap {
int nr_cblocks;
} aio;
#endif
+ cpu_set_t affinity_mask;
};
/*
@@ -69,7 +70,7 @@ enum bkw_mmap_state {
};
struct mmap_params {
- int prot, mask, nr_cblocks;
+ int prot, mask, nr_cblocks, affinity;
struct auxtrace_mmap_params auxtrace_mp;
};
next prev parent reply other threads:[~2018-12-13 7:18 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-13 7:07 [PATCH v2 0/4] Reduce NUMA related overhead in perf record profiling on large server systems Alexey Budankov
2018-12-13 7:18 ` Alexey Budankov [this message]
2018-12-13 7:19 ` [PATCH v2 2/4] perf record: bind the AIO user space buffers to nodes Alexey Budankov
2018-12-13 7:20 ` [PATCH v2 3/4] perf record: apply affinity masks when reading mmap, buffers Alexey Budankov
2018-12-13 7:20 ` [PATCH v2 4/4] perf record: implement --affinity=node|cpu option Alexey Budankov
2018-12-24 12:11 [PATCH v2 0/4] Reduce NUMA related overhead in perf record profiling on large server systems Alexey Budankov
2018-12-24 12:23 ` [PATCH v2 1/4] perf record: allocate affinity masks Alexey Budankov
2019-01-01 21:39 ` Jiri Olsa
2019-01-09 9:10 ` 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=090df1eb-598b-cc31-0a47-63c3c8692c6b@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).