public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, paulus@samba.org, hpa@zytor.com,
	mingo@redhat.com, a.p.zijlstra@chello.nl, tglx@linutronix.de,
	cjashfor@linux.vnet.ibm.com, mingo@elte.hu
Subject: [tip:perfcounters/core] perf_counter: optimize mmap/comm tracking
Date: Thu, 9 Apr 2009 09:06:36 GMT	[thread overview]
Message-ID: <tip-e37f8d14c1f56e274b3e827912f23f0b2fb7a7bb@git.kernel.org> (raw)
In-Reply-To: <20090409085524.427173196@chello.nl>

Commit-ID:  e37f8d14c1f56e274b3e827912f23f0b2fb7a7bb
Gitweb:     http://git.kernel.org/tip/e37f8d14c1f56e274b3e827912f23f0b2fb7a7bb
Author:     Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Thu, 9 Apr 2009 10:53:44 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 9 Apr 2009 11:00:53 +0200

perf_counter: optimize mmap/comm tracking

Impact: performance optimization

The mmap/comm tracking code does quite a lot of work before it discovers
there's no interest in it, avoid that by keeping a counter.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090409085524.427173196@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 kernel/perf_counter.c |   32 ++++++++++++++++++++++++++++++--
 1 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index b07195b..af9fd89 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -38,6 +38,10 @@ int perf_max_counters __read_mostly = 1;
 static int perf_reserved_percpu __read_mostly;
 static int perf_overcommit __read_mostly = 1;
 
+static atomic_t nr_mmap_tracking __read_mostly;
+static atomic_t nr_munmap_tracking __read_mostly;
+static atomic_t nr_comm_tracking __read_mostly;
+
 /*
  * Mutex for (sysadmin-configurable) counter reservations:
  */
@@ -1186,6 +1190,13 @@ static void free_counter(struct perf_counter *counter)
 {
 	perf_pending_sync(counter);
 
+	if (counter->hw_event.mmap)
+		atomic_dec(&nr_mmap_tracking);
+	if (counter->hw_event.munmap)
+		atomic_dec(&nr_munmap_tracking);
+	if (counter->hw_event.comm)
+		atomic_dec(&nr_comm_tracking);
+
 	if (counter->destroy)
 		counter->destroy(counter);
 
@@ -2128,7 +2139,12 @@ got_name:
 void perf_counter_mmap(unsigned long addr, unsigned long len,
 		       unsigned long pgoff, struct file *file)
 {
-	struct perf_mmap_event mmap_event = {
+	struct perf_mmap_event mmap_event;
+
+	if (!atomic_read(&nr_mmap_tracking))
+		return;
+
+	mmap_event = (struct perf_mmap_event){
 		.file   = file,
 		.event  = {
 			.header = { .type = PERF_EVENT_MMAP, },
@@ -2146,7 +2162,12 @@ void perf_counter_mmap(unsigned long addr, unsigned long len,
 void perf_counter_munmap(unsigned long addr, unsigned long len,
 			 unsigned long pgoff, struct file *file)
 {
-	struct perf_mmap_event mmap_event = {
+	struct perf_mmap_event mmap_event;
+
+	if (!atomic_read(&nr_munmap_tracking))
+		return;
+
+	mmap_event = (struct perf_mmap_event){
 		.file   = file,
 		.event  = {
 			.header = { .type = PERF_EVENT_MUNMAP, },
@@ -2725,6 +2746,13 @@ done:
 
 	counter->hw_ops = hw_ops;
 
+	if (counter->hw_event.mmap)
+		atomic_inc(&nr_mmap_tracking);
+	if (counter->hw_event.munmap)
+		atomic_inc(&nr_munmap_tracking);
+	if (counter->hw_event.comm)
+		atomic_inc(&nr_comm_tracking);
+
 	return counter;
 }
 

  reply	other threads:[~2009-04-09  9:07 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-04-09  8:53 [PATCH 0/4] perf_counter: fixes and an optimization Peter Zijlstra
2009-04-09  8:53 ` [PATCH 1/4] perf_counter: fix off-by-one on the string lengths Peter Zijlstra
2009-04-09  8:53 ` [PATCH 2/4] perf_counter: optimize mmap/comm tracking Peter Zijlstra
2009-04-09  9:06   ` Peter Zijlstra [this message]
2009-04-09  9:16   ` Ingo Molnar
2009-04-09  9:28     ` Peter Zijlstra
2009-04-09  9:54   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-09  8:53 ` [PATCH 3/4] perf_counter: sysctl for system wide perf counters Peter Zijlstra
2009-04-09  9:06   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-09  9:54   ` Peter Zijlstra
2009-04-09  8:53 ` [PATCH 4/4] perf_counter: log full path names Peter Zijlstra
2009-04-09  9:07   ` [tip:perfcounters/core] " Peter Zijlstra
2009-04-09  9:54   ` Peter Zijlstra
2009-04-09  9:03 ` [PATCH 0/4] perf_counter: fixes and an optimization Ingo Molnar

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=tip-e37f8d14c1f56e274b3e827912f23f0b2fb7a7bb@git.kernel.org \
    --to=a.p.zijlstra@chello.nl \
    --cc=cjashfor@linux.vnet.ibm.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=mingo@redhat.com \
    --cc=paulus@samba.org \
    --cc=tglx@linutronix.de \
    /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