From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Jiri Olsa <jolsa@redhat.com>, LKML <linux-kernel@vger.kernel.org>,
David Ahern <dsahern@gmail.com>,
Stephane Eranian <eranian@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Andi Kleen <andi@firstfloor.org>,
Frederic Weisbecker <fweisbec@gmail.com>
Subject: [PATCH 33/37] perf tools: Add front cache for dso data access
Date: Wed, 24 Dec 2014 16:15:29 +0900 [thread overview]
Message-ID: <1419405333-27952-34-git-send-email-namhyung@kernel.org> (raw)
In-Reply-To: <1419405333-27952-1-git-send-email-namhyung@kernel.org>
There's a high contention in dso_cache__find() due to the dso->lock
when dwarf unwinding is done with libunwind. Add last accessed
pointers of dso_cache to lockless lookup. It'll fallback to normal
tree search when it misses the last cache.
The size 16 is arbitrary and works best for my setting.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/util/dso.c | 28 ++++++++++++++++++++++++++--
tools/perf/util/dso.h | 2 ++
2 files changed, 28 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 6c1f5619f423..d8ee1fd826e7 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -466,12 +466,31 @@ dso_cache__free(struct dso *dso)
pthread_mutex_unlock(&dso->lock);
}
+static void update_last_cache(struct dso *dso, struct dso_cache *cache)
+{
+ int i;
+
+ for (i = DSO_LAST_CACHE_NR - 1; i > 0; i--)
+ dso->data.last[i] = dso->data.last[i-1];
+
+ dso->data.last[0] = cache;
+}
+
static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
{
const struct rb_root *root = &dso->data.cache;
struct rb_node * const *p = &root->rb_node;
const struct rb_node *parent = NULL;
struct dso_cache *cache;
+ int i;
+
+ for (i = 0; i < DSO_LAST_CACHE_NR; i++) {
+ cache = dso->data.last[i];
+
+ if (cache && cache->offset <= offset &&
+ offset < cache->offset + DSO__DATA_CACHE_SIZE)
+ return cache;
+ }
pthread_mutex_lock(&dso->lock);
while (*p != NULL) {
@@ -485,8 +504,10 @@ static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
p = &(*p)->rb_left;
else if (offset >= end)
p = &(*p)->rb_right;
- else
+ else {
+ update_last_cache(dso, cache);
goto out;
+ }
}
cache = NULL;
out:
@@ -515,13 +536,16 @@ dso_cache__insert(struct dso *dso, struct dso_cache *new)
p = &(*p)->rb_left;
else if (offset >= end)
p = &(*p)->rb_right;
- else
+ else {
+ update_last_cache(dso, cache);
goto out;
+ }
}
rb_link_node(&new->rb_node, parent, p);
rb_insert_color(&new->rb_node, root);
+ update_last_cache(dso, new);
cache = NULL;
out:
pthread_mutex_unlock(&dso->lock);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index c18fcc0e8081..28e8bb320495 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -136,6 +136,8 @@ struct dso {
/* dso data file */
struct {
struct rb_root cache;
+#define DSO_LAST_CACHE_NR 16
+ struct dso_cache *last[DSO_LAST_CACHE_NR];
int fd;
int status;
u32 status_seen;
--
2.1.3
next prev parent reply other threads:[~2014-12-24 7:17 UTC|newest]
Thread overview: 91+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-12-24 7:14 [RFC/PATCHSET 00/37] perf tools: Speed-up perf report by using multi thread (v1) Namhyung Kim
2014-12-24 7:14 ` [PATCH 01/37] perf tools: Set attr.task bit for a tracking event Namhyung Kim
2014-12-31 11:25 ` Jiri Olsa
2014-12-24 7:14 ` [PATCH 02/37] perf record: Use a software dummy event to track task/mmap events Namhyung Kim
2014-12-26 16:27 ` David Ahern
2014-12-27 5:28 ` Namhyung Kim
2014-12-29 12:58 ` Adrian Hunter
2014-12-30 5:51 ` Namhyung Kim
2014-12-30 9:04 ` Adrian Hunter
2014-12-24 7:14 ` [PATCH 03/37] perf tools: Use perf_data_file__fd() consistently Namhyung Kim
2014-12-26 16:30 ` David Ahern
2014-12-27 5:30 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 04/37] perf tools: Add multi file interface to perf_data_file Namhyung Kim
2014-12-25 22:08 ` Jiri Olsa
2014-12-26 1:19 ` Namhyung Kim
2014-12-31 11:26 ` Jiri Olsa
2014-12-31 14:55 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 05/37] perf tools: Create separate mmap for dummy tracking event Namhyung Kim
2014-12-25 22:08 ` Jiri Olsa
2014-12-26 1:45 ` Namhyung Kim
2014-12-25 22:09 ` Jiri Olsa
2014-12-26 1:55 ` Namhyung Kim
2014-12-26 16:51 ` David Ahern
2014-12-27 5:32 ` Namhyung Kim
2014-12-29 13:44 ` Adrian Hunter
2014-12-30 5:57 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 06/37] perf tools: Introduce perf_evlist__mmap_multi() Namhyung Kim
2014-12-24 7:15 ` [PATCH 07/37] perf tools: Do not use __perf_session__process_events() directly Namhyung Kim
2014-12-31 11:33 ` Jiri Olsa
2014-12-24 7:15 ` [PATCH 08/37] perf tools: Handle multi-file session properly Namhyung Kim
2014-12-31 12:01 ` Jiri Olsa
2014-12-31 14:53 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 09/37] perf record: Add -M/--multi option for multi file recording Namhyung Kim
2014-12-24 7:15 ` [PATCH 10/37] perf report: Skip dummy tracking event Namhyung Kim
2014-12-24 7:15 ` [PATCH 11/37] perf tools: Introduce thread__comm_time() helpers Namhyung Kim
2014-12-26 17:00 ` David Ahern
2014-12-27 5:36 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 12/37] perf tools: Add a test case for thread comm handling Namhyung Kim
2014-12-24 7:15 ` [PATCH 13/37] perf tools: Use thread__comm_time() when adding hist entries Namhyung Kim
2014-12-25 22:53 ` Jiri Olsa
2014-12-26 2:10 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 14/37] perf tools: Convert dead thread list into rbtree Namhyung Kim
2014-12-25 23:05 ` Jiri Olsa
2014-12-26 2:26 ` Namhyung Kim
2014-12-26 17:14 ` David Ahern
2014-12-27 5:42 ` Namhyung Kim
2014-12-27 15:31 ` David Ahern
2014-12-28 13:24 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 15/37] perf tools: Introduce machine__find*_thread_time() Namhyung Kim
2014-12-27 16:33 ` David Ahern
2014-12-28 14:50 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 16/37] perf tools: Add a test case for timed thread handling Namhyung Kim
2014-12-31 14:17 ` Jiri Olsa
2014-12-31 15:32 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 17/37] perf tools: Maintain map groups list in a leader thread Namhyung Kim
2014-12-24 7:15 ` [PATCH 18/37] perf tools: Remove thread when map groups initialization failed Namhyung Kim
2014-12-28 0:45 ` David Ahern
2014-12-29 7:08 ` Namhyung Kim
2014-12-24 7:15 ` [PATCH 19/37] perf tools: Introduce thread__find_addr_location_time() and friends Namhyung Kim
2014-12-24 7:15 ` [PATCH 20/37] perf tools: Add a test case for timed map groups handling Namhyung Kim
2014-12-24 7:15 ` [PATCH 21/37] perf tools: Protect dso symbol loading using a mutex Namhyung Kim
2014-12-24 7:15 ` [PATCH 22/37] perf tools: Protect dso cache tree using dso->lock Namhyung Kim
2014-12-24 7:15 ` [PATCH 23/37] perf tools: Protect dso cache fd with a mutex Namhyung Kim
2014-12-24 7:15 ` [PATCH 24/37] perf session: Pass struct events stats to event processing functions Namhyung Kim
2014-12-24 7:15 ` [PATCH 25/37] perf hists: Pass hists struct to hist_entry_iter functions Namhyung Kim
2014-12-24 7:15 ` [PATCH 26/37] perf tools: Move BUILD_ID_SIZE definition to perf.h Namhyung Kim
2014-12-24 7:15 ` [PATCH 27/37] perf report: Parallelize perf report using multi-thread Namhyung Kim
2014-12-24 7:15 ` [PATCH 28/37] perf tools: Add missing_threads rb tree Namhyung Kim
2014-12-24 7:15 ` [PATCH 29/37] perf top: Always creates thread in the current task tree Namhyung Kim
2014-12-24 7:15 ` [PATCH 30/37] perf tools: Fix progress ui to support multi thread Namhyung Kim
2014-12-24 7:15 ` [PATCH 31/37] perf record: Show total size of multi file data Namhyung Kim
2014-12-24 7:15 ` [PATCH 32/37] perf report: Add --multi-thread option and config item Namhyung Kim
2014-12-24 7:15 ` Namhyung Kim [this message]
2014-12-24 7:15 ` [PATCH 34/37] perf tools: Convert lseek + read to pread Namhyung Kim
2014-12-24 7:15 ` [PATCH 35/37] perf callchain: Save eh/debug frame offset for dwarf unwind Namhyung Kim
2014-12-24 7:15 ` [PATCH 36/37] perf tools: Add new perf data command Namhyung Kim
2014-12-24 7:15 ` [PATCH 37/37] perf data: Implement 'split' subcommand Namhyung Kim
2014-12-24 13:51 ` Arnaldo Carvalho de Melo
2014-12-24 14:14 ` Namhyung Kim
2014-12-24 14:45 ` Arnaldo Carvalho de Melo
2014-12-26 13:59 ` Jiri Olsa
2014-12-27 5:21 ` Namhyung Kim
2014-12-26 14:02 ` [RFC/PATCHSET 00/37] perf tools: Speed-up perf report by using multi thread (v1) Jiri Olsa
2014-12-27 5:23 ` Namhyung Kim
2015-01-05 18:48 ` Andi Kleen
2015-01-06 15:50 ` Stephane Eranian
2015-01-07 7:13 ` Namhyung Kim
2015-01-07 15:14 ` Stephane Eranian
2015-01-08 5:19 ` Namhyung Kim
2015-01-07 6:58 ` Namhyung Kim
2015-01-08 14:52 ` Andi Kleen
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=1419405333-27952-34-git-send-email-namhyung@kernel.org \
--to=namhyung@kernel.org \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=andi@firstfloor.org \
--cc=dsahern@gmail.com \
--cc=eranian@google.com \
--cc=fweisbec@gmail.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.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
all inboxes | Powered by JetHome®