linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Badari Pulavarty <pbadari@us.ibm.com>
To: Manfred Spraul <manfred@colorfullife.com>
Cc: Andrew Morton <akpm@osdl.org>, linux-mm@kvack.org
Subject: Re: slab fragmentation ?
Date: 05 Oct 2004 07:46:11 -0700	[thread overview]
Message-ID: <1096987570.12861.122.camel@dyn318077bld.beaverton.ibm.com> (raw)
In-Reply-To: <41617567.9010507@colorfullife.com>

[-- Attachment #1: Type: text/plain, Size: 780 bytes --]

On Mon, 2004-10-04 at 09:08, Manfred Spraul wrote:
> Badari Pulavarty wrote:
> 
> >I will enable slab debugging. Someone told me that, by enabling slab
> >debug, it fill force use of different slab for each allocation - there
> >by bloating slab usages and mask the problem. Is it true ?
> >
> >  
> >
> Then set STATS to 1. It's around line 118. This just adds full 
> statistics without changing the allocations.
> Or even better: enable STATS and DEBUG, but not FORCED_DEBUG. You get 
> most internal consistance checks as well, except the tests that rely on 
> redzoning.

Here is the /proc/slabinfo output collected every 1 second while
running the scsi-debug test. I enabled STATS and DEBUG.

Please let me know, what you find and what we should try next.

Thanks,
Badari



[-- Attachment #2: slab.out --]
[-- Type: text/plain, Size: 6092 bytes --]

# name            <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab> : tunables <batchcount> <limit> <sharedfactor> : slabdata <active_slabs> <num_slabs> <sharedavail> : globalstat <listallocs> <maxobjs> <grown> <reaped> <error> <maxfreeable> <freelimit> : cpustat <allochit> <allocmiss> <freehit> <freemiss>
size-40             2088   9760     64   61    1 : tunables   32   16    8 : slabdata    160    160      0 : globalstat    3324   2010   160    0    0    0  173 : cpustat   5675    213   3945      2
size-40             2088   9760     64   61    1 : tunables   32   16    8 : slabdata    160    160      0 : globalstat    3324   2010   160    0    0    0  173 : cpustat   5675    213   3945      2
size-40             2088   9760     64   61    1 : tunables   32   16    8 : slabdata    160    160      0 : globalstat    3324   2010   160    0    0    0  173 : cpustat   5675    213   3945      2
size-40             4582  31110     64   61    1 : tunables   32   16    8 : slabdata    510    510      0 : globalstat    5468   4085   510    0    0    0  173 : cpustat   7924    347   4247      2
size-40             7246  55022     64   61    1 : tunables   32   16    8 : slabdata    902    902      0 : globalstat    7740   6357   902    0    0    0  173 : cpustat  10405    489   4583      2
size-40            10146  80642     64   61    1 : tunables   32   16    8 : slabdata   1322   1322      0 : globalstat   10220   8837  1322    0    0    0  173 : cpustat  13055    644   4941      2
size-40            12959 105835     64   61    1 : tunables   32   16    8 : slabdata   1735   1735      0 : globalstat   12620  11237  1735    0    0    0  173 : cpustat  15685    794   5295      2
size-40            15765 130601     64   61    1 : tunables   32   16    8 : slabdata   2141   2141      0 : globalstat   15020  13637  2141    0    0    0  173 : cpustat  18304    944   5649      2
size-40            18697 156221     64   61    1 : tunables   32   16    8 : slabdata   2561   2561      0 : globalstat   17532  16149  2561    0    0    0  173 : cpustat  20988   1101   6009      2
size-40            21315 179279     64   61    1 : tunables   32   16    8 : slabdata   2939   2939      0 : globalstat   19772  18389  2939    0    0    0  173 : cpustat  23418   1241   6335      2
size-40            24073 204045     64   61    1 : tunables   32   16    8 : slabdata   3345   3345      0 : globalstat   22124  20741  3345    0    0    0  173 : cpustat  25984   1388   6681      2
size-40            26730 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7013      2
size-40            26730 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7013      2
size-40            26723 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7013      2
size-40            26708 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7013      2
size-40            26701 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7013      2
size-40            26696 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7013      2
size-40            26691 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7015      2
size-40            26687 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7015      2
size-40            26685 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7015      2
size-40            26685 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7015      2
size-40            26683 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7018      2
size-40            26682 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7018      2
size-40            26682 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7018      2
size-40            26680 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7021      2
size-40            26680 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7021      2
size-40            26679 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7021      2
size-40            26679 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7021      2
size-40            26676 227530     64   61    1 : tunables   32   16    8 : slabdata   3730   3730      0 : globalstat   24396  23013  3730    0    0    0  173 : cpustat  28454   1530   7025      2

  parent reply	other threads:[~2004-10-05 14:46 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-09-29 23:36 Badari Pulavarty
2004-09-30  3:41 ` Andrew Morton
2004-09-30  4:52   ` badari
2004-09-30 14:49   ` Martin J. Bligh
2004-09-30 14:48     ` Badari Pulavarty
2004-10-03  6:04       ` Manfred Spraul
2004-10-04 15:51         ` Badari Pulavarty
2004-10-04 16:08           ` Manfred Spraul
2004-10-04 17:37             ` Badari Pulavarty
2004-10-05 14:46             ` Badari Pulavarty [this message]
2004-10-05 17:58               ` Manfred Spraul
2004-10-05 18:27                 ` Badari Pulavarty
2004-10-05 18:49                   ` Manfred Spraul
2004-10-05 18:47                     ` Badari Pulavarty
2004-10-05 21:13                     ` Badari Pulavarty
2004-10-05 22:11                       ` Chen, Kenneth W
2004-10-05 22:18                         ` Chen, Kenneth W
2004-10-06 14:58                     ` Badari Pulavarty
2004-10-09 14:28                       ` Manfred Spraul

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=1096987570.12861.122.camel@dyn318077bld.beaverton.ibm.com \
    --to=pbadari@us.ibm.com \
    --cc=akpm@osdl.org \
    --cc=linux-mm@kvack.org \
    --cc=manfred@colorfullife.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