From: Tao Ma <tm@tao.ma>
To: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
David Rientjes <rientjes@google.com>,
Minchan Kim <minchan.kim@gmail.com>, Mel Gorman <mel@csn.ul.ie>,
Johannes Weiner <jweiner@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH] mm: do not drain pagevecs for mlock
Date: Fri, 30 Dec 2011 16:48:35 +0800 [thread overview]
Message-ID: <4EFD7AE3.8020403@tao.ma> (raw)
In-Reply-To: <CAHGf_=qOGy3MQgiFyfeG82+gbDXTBT5KQjgR7JqMfQ7e7RSGpA@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1336 bytes --]
On 12/30/2011 04:11 PM, KOSAKI Motohiro wrote:
> 2011/12/30 Tao Ma <tm@tao.ma>:
>> In our test of mlock, we have found some severe performance regression
>> in it. Some more investigations show that mlocked is blocked heavily
>> by lur_add_drain_all which calls schedule_on_each_cpu and flush the work
>> queue which is very slower if we have several cpus.
>>
>> So we have tried 2 ways to solve it:
>> 1. Add a per cpu counter for all the pagevecs so that we don't schedule
>> and flush the lru_drain work if the cpu doesn't have any pagevecs(I
>> have finished the codes already).
>> 2. Remove the lru_add_drain_all.
>>
>> The first one has some problems since in our product system, all the cpus
>> are busy, so I guess there is very little chance for a cpu to have 0 pagevecs
>> except that you run several consecutive mlocks.
>>
>> From the commit log which added this function(8891d6da), it seems that we
>> don't have to call it. So the 2nd one seems to be both easy and workable and
>> comes this patch.
>
> Could you please show us your system environment and benchmark programs?
> Usually lru_drain_** is very fast than mlock() body because it makes
> plenty memset(page).
The system environment is: 16 core Xeon E5620. 24G memory.
I have attached the program. It is very simple and just uses mlock/munlock.
Thanks
Tao
[-- Attachment #2: test_mlock.c --]
[-- Type: text/x-csrc, Size: 981 bytes --]
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <time.h>
#include <sys/time.h>
#include <sys/mman.h>
#define MM_SZ1 24
#define MM_SZ2 56
#define MM_SZ3 4168
void mlock_test()
{
char ptr1[MM_SZ1];
char ptr2[MM_SZ2];
char ptr3[MM_SZ3];
if(0 != mlock(ptr1, MM_SZ1) )
perror("mlock MM_SZ1\n");
if(0 != mlock(ptr2, MM_SZ2) )
perror("mlock MM_SZ2\n");
if(0 != mlock(ptr3, MM_SZ3) )
perror("mlock MM_SZ3\n");
if(0 != munlock(ptr1, MM_SZ1) )
perror("munlock MM_SZ1\n");
if(0 != munlock(ptr2, MM_SZ2) )
perror("munlock MM_SZ2\n");
if(0 != munlock(ptr3, MM_SZ3) )
perror("munlock MM_SZ3\n");
}
int main(int argc, char *argv[])
{
int ret, opt;
int i,cnt;
while((opt = getopt(argc, argv, "c:")) != -1 )
{
switch(opt){
case 'c':
cnt = atoi(optarg);
break;
default:
printf("Usage: %s [-c count] arg...\n", argv[0]);
exit(EXIT_FAILURE);
}
}
for(i = 0; i < cnt; i++)
mlock_test();
return 0;
}
next prev parent reply other threads:[~2011-12-30 8:48 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-12-30 6:36 [PATCH] mm: do not drain pagevecs for mlock Tao Ma
2011-12-30 8:11 ` KOSAKI Motohiro
2011-12-30 8:48 ` Tao Ma [this message]
2011-12-30 9:31 ` KOSAKI Motohiro
2011-12-30 9:45 ` Tao Ma
2011-12-30 10:07 ` KOSAKI Motohiro
2012-01-01 7:30 ` [PATCH 1/2] mm,mlock: drain pagevecs asynchronously kosaki.motohiro
2012-01-04 1:17 ` Minchan Kim
2012-01-04 2:38 ` KOSAKI Motohiro
2012-01-10 8:53 ` Tao Ma
2012-01-04 2:56 ` Hugh Dickins
2012-01-04 22:05 ` Andrew Morton
2012-01-04 23:33 ` KOSAKI Motohiro
2012-01-05 0:19 ` Hugh Dickins
2012-01-01 7:30 ` [PATCH 2/2] sysvshm: SHM_LOCK use lru_add_drain_all_async() kosaki.motohiro
2012-01-04 1:51 ` Hugh Dickins
2012-01-04 2:19 ` KOSAKI Motohiro
2012-01-04 5:17 ` Hugh Dickins
2012-01-04 8:34 ` KOSAKI Motohiro
2012-01-06 6:13 ` [PATCH] mm: do not drain pagevecs for mlock Tao Ma
2012-01-06 6:18 ` KOSAKI Motohiro
2012-01-06 6:30 ` Tao Ma
2012-01-06 6:33 ` KOSAKI Motohiro
2012-01-06 6:46 ` Tao Ma
2012-01-09 23:58 ` KOSAKI Motohiro
2012-01-10 2:08 ` Tao Ma
2012-01-09 7:25 ` Tao Ma
2011-12-30 10:14 ` KOSAKI Motohiro
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=4EFD7AE3.8020403@tao.ma \
--to=tm@tao.ma \
--cc=akpm@linux-foundation.org \
--cc=jweiner@redhat.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=minchan.kim@gmail.com \
--cc=rientjes@google.com \
/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).