From: Marcelo Tosatti <marcelo.tosatti@cyclades.com>
To: Con Kolivas <kernel@kolivas.org>
Cc: Andrew Morton <akpm@osdl.org>,
raybry@sgi.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
riel@redhat.com, piggin@cyberone.com.au, mbligh@aracnet.com
Subject: Re: swapping and the value of /proc/sys/vm/swappiness
Date: Tue, 7 Sep 2004 23:18:16 -0300 [thread overview]
Message-ID: <20040908021816.GB2942@logos.cnet> (raw)
In-Reply-To: <20040907212051.GC3492@logos.cnet>
> Spent some time doing a few tests.
>
> A contained test (512MB box, allocate 450MB of memory, touch and sleep +
> huge dd) show's that 2.6.6 and 2.6.7 are equivalent (swapout 120-150M when the "dd"
> starts writing out data).
>
> 2.6.9-rc1 swaps out 350M on the same test. Doenst seem nice, I'll try to isolate
> what causes this tomorrow (this is probably what is hitting desktop users which
> is fixed by Con's patches). Thats problem #1. Something needs a little tweaking
> I think.
>
> Ray, I see the additional swapouts increase the dd performance for your particular testcase:
>
> on 2.6.6:
> Total I/O Avg Swap min max pg cache min max
> ----------- --------- ------- ------ --------- ------- -------
> 0 242.47 MB/s 0 MB ( 0, 0) 3195 MB ( 3138, 3266)
> 20 256.06 MB/s 0 MB ( 0, 0) 3170 MB ( 3074, 3234)
> 40 267.29 MB/s 0 MB ( 0, 0) 3189 MB ( 3137, 3234)
> 60 289.43 MB/s 666 MB ( 72, 1680) 3847 MB ( 3296, 4817) <----------
>
> So for this one testcase it is being beneficial.
>
> However, decreasing the "swappiness" value does not seem to make much of a difference:
>
> Kernel Version 2.6.8.1-mm4:
> Total I/O Avg Swap min max pg cache min max
> ----------- --------- ------- ------ --------- ------- -------
> 0 287.28 MB/s 710 MB ( 46, 3060) 4082 MB ( 3426, 6308)
> 20 288.05 MB/s 508 MB ( 94, 1417) 3848 MB ( 3442, 4739)
> 40 287.03 MB/s 588 MB ( 199, 1251) 3909 MB ( 3570, 4515)
> 60 290.08 MB/s 640 MB ( 210, 1190) 3976 MB ( 3538, 4531)
> 80 287.73 MB/s 693 MB ( 316, 1195) 4049 MB ( 3713, 4545)
> 100 166.17 MB/s 26001 MB ( 26001, 26002) 28798 MB ( 28740, 28852)
>
> Kernel Version 2.6.9-rc1-mm3:
> Total I/O Avg Swap min max pg cache min max
> ----------- --------- ------- ------ --------- ------- -------
> 0 274.80 MB/s 10511 MB ( 5644, 14492) 13293 MB ( 8596, 17156)
> 20 267.02 MB/s 12624 MB ( 5578, 16287) 15298 MB ( 8468, 18889)
> 40 267.66 MB/s 13541 MB ( 6619, 17461) 16199 MB ( 9393, 20044)
> 60 233.73 MB/s 18094 MB ( 16550, 19676) 20629 MB ( 19103, 22192)
> 80 213.64 MB/s 20950 MB ( 15844, 22977) 23450 MB ( 18496, 25440)
> 100 164.58 MB/s 26004 MB ( 26004, 26004) 28410 MB ( 28327, 28455)
>
> And that is a problem #2 - swappinness not being honoured. Guys,
> any ideas on the reason for that?
Hum I just tested it on my 512MB box and swappiness is working fine on 2.6.8.. (it
has expected effects), unlike Ray's tests.
>
> Andrew, dirty_ratio and dirty_background_ratio (as low as 5% each) did not significantly
> affect the amount of swapped out data, only a small effect on _how soon_ anonymous
> memory was swapped out.
>
> And finally, Ray, the difference you see between 2.6.6 and 2.6.7 can be explained,
> as noted by others in this thread, to vmscan.c changes (page replacement/scanning policy
> changes were made).
>
> Will continue with more tests tomorrow.
WARNING: multiple messages have this Message-ID (diff)
From: Marcelo Tosatti <marcelo.tosatti@cyclades.com>
To: Con Kolivas <kernel@kolivas.org>
Cc: Andrew Morton <akpm@osdl.org>,
raybry@sgi.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
riel@redhat.com, piggin@cyberone.com.au, mbligh@aracnet.com
Subject: Re: swapping and the value of /proc/sys/vm/swappiness
Date: Tue, 7 Sep 2004 23:18:16 -0300 [thread overview]
Message-ID: <20040908021816.GB2942@logos.cnet> (raw)
In-Reply-To: <20040907212051.GC3492@logos.cnet>
> Spent some time doing a few tests.
>
> A contained test (512MB box, allocate 450MB of memory, touch and sleep +
> huge dd) show's that 2.6.6 and 2.6.7 are equivalent (swapout 120-150M when the "dd"
> starts writing out data).
>
> 2.6.9-rc1 swaps out 350M on the same test. Doenst seem nice, I'll try to isolate
> what causes this tomorrow (this is probably what is hitting desktop users which
> is fixed by Con's patches). Thats problem #1. Something needs a little tweaking
> I think.
>
> Ray, I see the additional swapouts increase the dd performance for your particular testcase:
>
> on 2.6.6:
> Total I/O Avg Swap min max pg cache min max
> ----------- --------- ------- ------ --------- ------- -------
> 0 242.47 MB/s 0 MB ( 0, 0) 3195 MB ( 3138, 3266)
> 20 256.06 MB/s 0 MB ( 0, 0) 3170 MB ( 3074, 3234)
> 40 267.29 MB/s 0 MB ( 0, 0) 3189 MB ( 3137, 3234)
> 60 289.43 MB/s 666 MB ( 72, 1680) 3847 MB ( 3296, 4817) <----------
>
> So for this one testcase it is being beneficial.
>
> However, decreasing the "swappiness" value does not seem to make much of a difference:
>
> Kernel Version 2.6.8.1-mm4:
> Total I/O Avg Swap min max pg cache min max
> ----------- --------- ------- ------ --------- ------- -------
> 0 287.28 MB/s 710 MB ( 46, 3060) 4082 MB ( 3426, 6308)
> 20 288.05 MB/s 508 MB ( 94, 1417) 3848 MB ( 3442, 4739)
> 40 287.03 MB/s 588 MB ( 199, 1251) 3909 MB ( 3570, 4515)
> 60 290.08 MB/s 640 MB ( 210, 1190) 3976 MB ( 3538, 4531)
> 80 287.73 MB/s 693 MB ( 316, 1195) 4049 MB ( 3713, 4545)
> 100 166.17 MB/s 26001 MB ( 26001, 26002) 28798 MB ( 28740, 28852)
>
> Kernel Version 2.6.9-rc1-mm3:
> Total I/O Avg Swap min max pg cache min max
> ----------- --------- ------- ------ --------- ------- -------
> 0 274.80 MB/s 10511 MB ( 5644, 14492) 13293 MB ( 8596, 17156)
> 20 267.02 MB/s 12624 MB ( 5578, 16287) 15298 MB ( 8468, 18889)
> 40 267.66 MB/s 13541 MB ( 6619, 17461) 16199 MB ( 9393, 20044)
> 60 233.73 MB/s 18094 MB ( 16550, 19676) 20629 MB ( 19103, 22192)
> 80 213.64 MB/s 20950 MB ( 15844, 22977) 23450 MB ( 18496, 25440)
> 100 164.58 MB/s 26004 MB ( 26004, 26004) 28410 MB ( 28327, 28455)
>
> And that is a problem #2 - swappinness not being honoured. Guys,
> any ideas on the reason for that?
Hum I just tested it on my 512MB box and swappiness is working fine on 2.6.8.. (it
has expected effects), unlike Ray's tests.
>
> Andrew, dirty_ratio and dirty_background_ratio (as low as 5% each) did not significantly
> affect the amount of swapped out data, only a small effect on _how soon_ anonymous
> memory was swapped out.
>
> And finally, Ray, the difference you see between 2.6.6 and 2.6.7 can be explained,
> as noted by others in this thread, to vmscan.c changes (page replacement/scanning policy
> changes were made).
>
> Will continue with more tests tomorrow.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart@kvack.org"> aart@kvack.org </a>
next prev parent reply other threads:[~2004-09-08 3:42 UTC|newest]
Thread overview: 94+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-09-06 19:11 swapping and the value of /proc/sys/vm/swappiness Ray Bryant
2004-09-06 20:10 ` Andrew Morton
2004-09-06 20:10 ` Andrew Morton
2004-09-06 21:22 ` Ray Bryant
2004-09-06 21:22 ` Ray Bryant
2004-09-06 21:36 ` Andrew Morton
2004-09-06 21:36 ` Andrew Morton
2004-09-06 22:37 ` William Lee Irwin III
2004-09-06 22:37 ` William Lee Irwin III
2004-09-06 23:51 ` Nick Piggin
2004-09-06 23:51 ` Nick Piggin
2004-09-07 0:31 ` Ray Bryant
2004-09-07 0:31 ` Ray Bryant
2004-09-06 22:48 ` William Lee Irwin III
2004-09-06 22:48 ` William Lee Irwin III
2004-09-06 23:09 ` Con Kolivas
2004-09-06 23:09 ` Con Kolivas
2004-09-06 23:27 ` Andrew Morton
2004-09-06 23:27 ` Andrew Morton
2004-09-06 23:34 ` Con Kolivas
2004-09-06 23:34 ` Con Kolivas
2004-09-07 0:03 ` Marcelo Tosatti
2004-09-07 0:03 ` Marcelo Tosatti
2004-09-07 1:34 ` Con Kolivas
2004-09-07 1:34 ` Con Kolivas
2004-09-07 10:38 ` Nick Piggin
2004-09-07 10:38 ` Nick Piggin
2004-09-07 10:56 ` Con Kolivas
2004-09-08 16:45 ` Marcelo Tosatti
2004-09-08 16:45 ` Marcelo Tosatti
2004-09-09 1:12 ` Con Kolivas
2004-09-07 17:03 ` Ray Bryant
2004-09-07 17:03 ` Ray Bryant
2004-09-07 21:20 ` Marcelo Tosatti
2004-09-07 21:20 ` Marcelo Tosatti
2004-09-08 2:18 ` Marcelo Tosatti [this message]
2004-09-08 2:18 ` Marcelo Tosatti
2004-09-08 14:20 ` Ray Bryant
2004-09-08 16:54 ` Marcelo Tosatti
2004-09-08 16:54 ` Marcelo Tosatti
2004-09-08 19:35 ` Ray Bryant
2004-09-08 19:35 ` Ray Bryant
2004-09-08 19:30 ` Marcelo Tosatti
2004-09-08 19:30 ` Marcelo Tosatti
2004-09-09 3:06 ` Ray Bryant
2004-09-09 3:06 ` Ray Bryant
2004-09-09 2:14 ` Marcelo Tosatti
2004-09-09 2:14 ` Marcelo Tosatti
2004-09-09 14:21 ` Ray Bryant
2004-09-09 14:21 ` Ray Bryant
2004-09-09 3:09 ` William Lee Irwin III
2004-09-09 3:09 ` William Lee Irwin III
2004-09-09 14:16 ` Ray Bryant
2004-09-09 17:23 ` William Lee Irwin III
2004-09-09 17:23 ` William Lee Irwin III
2004-09-28 1:54 ` Ray Bryant
2004-09-28 3:36 ` Nick Piggin
2004-09-28 3:36 ` Nick Piggin
2004-09-29 0:36 ` Nick Piggin
2004-09-29 4:23 ` Ray Bryant
2004-09-29 4:23 ` Ray Bryant
2004-09-30 17:15 ` Ray Bryant
2004-09-30 17:15 ` Ray Bryant
2004-09-08 17:31 ` Martin J. Bligh
2004-09-08 17:31 ` Martin J. Bligh
2004-09-08 18:04 ` Rik van Riel
2004-09-08 18:04 ` Rik van Riel
2004-09-08 19:50 ` Diego Calleja
2004-09-08 19:50 ` Diego Calleja
2004-09-08 21:10 ` Martin J. Bligh
2004-09-08 21:10 ` Martin J. Bligh
2004-09-08 21:55 ` Diego Calleja
2004-09-08 21:55 ` Diego Calleja
2004-09-08 22:20 ` Martin J. Bligh
2004-09-08 22:20 ` Martin J. Bligh
2004-09-08 23:22 ` Rik van Riel
2004-09-08 23:22 ` Rik van Riel
2004-09-09 16:26 ` Bill Davidsen
2004-09-08 22:28 ` Alan Cox
2004-09-08 22:28 ` Alan Cox
2004-09-08 23:42 ` Martin J. Bligh
2004-09-08 23:42 ` Martin J. Bligh
2004-09-08 19:54 ` Ray Bryant
2004-09-08 19:54 ` Ray Bryant
2004-09-08 15:19 ` Ray Bryant
2004-09-08 15:19 ` Ray Bryant
2004-09-14 18:31 ` Florin Andrei
2004-09-14 20:15 ` Marcelo Tosatti
2004-09-14 22:53 ` Con Kolivas
2004-09-14 21:41 ` Marcelo Tosatti
2004-09-15 0:22 ` Con Kolivas
2004-09-16 18:50 ` Marcelo Tosatti
2004-09-17 0:22 ` Con Kolivas
2004-09-15 16:54 ` Florin Andrei
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=20040908021816.GB2942@logos.cnet \
--to=marcelo.tosatti@cyclades.com \
--cc=akpm@osdl.org \
--cc=kernel@kolivas.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mbligh@aracnet.com \
--cc=piggin@cyberone.com.au \
--cc=raybry@sgi.com \
--cc=riel@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.