All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nadia Derbey <Nadia.Derbey@bull.net>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, y-goto@jp.fujitsu.com,
	linux-mm@kvack.org, containers@lists.linux-foundation.org,
	matthltc@us.ibm.com, cmm@us.ibm.com
Subject: Re: [PATCH 1/8] Scaling msgmni to the amount of lowmem
Date: Mon, 18 Feb 2008 10:19:08 +0100	[thread overview]
Message-ID: <47B94D8C.8040605@bull.net> (raw)
In-Reply-To: <20080215215916.8566d337.akpm@linux-foundation.org>

Andrew Morton wrote:
> On Mon, 11 Feb 2008 15:16:47 +0100 Nadia.Derbey@bull.net wrote:
> 
> 
>>[PATCH 01/08]
>>
>>This patch computes msg_ctlmni to make it scale with the amount of lowmem.
>>msg_ctlmni is now set to make the message queues occupy 1/32 of the available
>>lowmem.
>>
>>Some cleaning has also been done for the MSGPOOL constant: the msgctl man page
>>says it's not used, but it also defines it as a size in bytes (the code
>>expresses it in Kbytes).
>>
> 
> 
> Something's wrong here.  Running LTP's msgctl08 (specifically:
> ltp-full-20070228) cripples the machine.  It's a 4-way 4GB x86_64.
> 
> http://userweb.kernel.org/~akpm/config-x.txt
> http://userweb.kernel.org/~akpm/dmesg-x.txt
> 
> Normally msgctl08 will complete in a second or two.  With this patch I
> don't know how long it will take to complete, and the machine is horridly
> bogged down.  It does recover if you manage to kill msgctl08.  Feels like
> a terrible memory shortage, but there's plenty of memory free and it isn't
> swapping.
> 
> 
> 

Before the patchset, msgctl08 used to be run with the old msgmni value: 
16. Now it is run with a much higher msgmni value (1746 in my case), 
since it scales to the memory size.
When I call "msgctl08 100000 16" it completes fast.

Doing the follwing on the ref kernel:
echo 1746 > /proc/sys/kernel/msgmni
msgctl08 100000 1746

makes th test block too :-(

Will check to see where the problem comes from.

Rgards,
Nadia

WARNING: multiple messages have this Message-ID (diff)
From: Nadia Derbey <Nadia.Derbey@bull.net>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, y-goto@jp.fujitsu.com,
	linux-mm@kvack.org, containers@lists.linux-foundation.org,
	matthltc@us.ibm.com, cmm@us.ibm.com
Subject: Re: [PATCH 1/8] Scaling msgmni to the amount of lowmem
Date: Mon, 18 Feb 2008 10:19:08 +0100	[thread overview]
Message-ID: <47B94D8C.8040605@bull.net> (raw)
In-Reply-To: <20080215215916.8566d337.akpm@linux-foundation.org>

Andrew Morton wrote:
> On Mon, 11 Feb 2008 15:16:47 +0100 Nadia.Derbey@bull.net wrote:
> 
> 
>>[PATCH 01/08]
>>
>>This patch computes msg_ctlmni to make it scale with the amount of lowmem.
>>msg_ctlmni is now set to make the message queues occupy 1/32 of the available
>>lowmem.
>>
>>Some cleaning has also been done for the MSGPOOL constant: the msgctl man page
>>says it's not used, but it also defines it as a size in bytes (the code
>>expresses it in Kbytes).
>>
> 
> 
> Something's wrong here.  Running LTP's msgctl08 (specifically:
> ltp-full-20070228) cripples the machine.  It's a 4-way 4GB x86_64.
> 
> http://userweb.kernel.org/~akpm/config-x.txt
> http://userweb.kernel.org/~akpm/dmesg-x.txt
> 
> Normally msgctl08 will complete in a second or two.  With this patch I
> don't know how long it will take to complete, and the machine is horridly
> bogged down.  It does recover if you manage to kill msgctl08.  Feels like
> a terrible memory shortage, but there's plenty of memory free and it isn't
> swapping.
> 
> 
> 

Before the patchset, msgctl08 used to be run with the old msgmni value: 
16. Now it is run with a much higher msgmni value (1746 in my case), 
since it scales to the memory size.
When I call "msgctl08 100000 16" it completes fast.

Doing the follwing on the ref kernel:
echo 1746 > /proc/sys/kernel/msgmni
msgctl08 100000 1746

makes th test block too :-(

Will check to see where the problem comes from.

Rgards,
Nadia

--
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:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2008-02-18  9:20 UTC|newest]

Thread overview: 117+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-02-11 14:16 [PATCH 0/8] Change default MSGMNI tunable to scale with lowmem (v3) Nadia.Derbey
2008-02-11 14:16 ` Nadia.Derbey
2008-02-11 14:16 ` [PATCH 1/8] Scaling msgmni to the amount of lowmem Nadia.Derbey-6ktuUTfB/bM
2008-02-11 14:16 ` Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
     [not found]   ` <20080211141813.354484000-6ktuUTfB/bM@public.gmane.org>
2008-02-16  5:59     ` Andrew Morton
2008-02-16  5:59       ` Andrew Morton
2008-02-16  5:59       ` Andrew Morton
     [not found]       ` <20080215215916.8566d337.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2008-02-18  9:19         ` Nadia Derbey
2008-02-18  9:19       ` Nadia Derbey [this message]
2008-02-18  9:19         ` Nadia Derbey
     [not found]         ` <47B94D8C.8040605-6ktuUTfB/bM@public.gmane.org>
2008-02-18 13:08           ` Nadia Derbey
2008-02-18 13:08         ` Nadia Derbey
2008-02-18 13:08           ` Nadia Derbey
     [not found]           ` <47B9835A.3060507-6ktuUTfB/bM@public.gmane.org>
2008-02-19  8:50             ` [LTP] " Subrata Modak
2008-02-19  8:50           ` Subrata Modak
2008-02-19  8:50             ` Subrata Modak
     [not found]             ` <1203411055.4612.5.camel-NRFfyExJdYpgXGGE5LP+UZlqa2bBAFbm0E9HWUfgJXw@public.gmane.org>
2008-02-19 17:16               ` Nadia Derbey
2008-02-19 17:16             ` Nadia Derbey
     [not found]               ` <47BB0EDC.5000002-6ktuUTfB/bM@public.gmane.org>
2008-02-19 22:16                 ` Matt Helsley
2008-02-20  9:44                 ` Subrata Modak
2008-02-19 22:16               ` Matt Helsley
2008-02-19 22:16                 ` Matt Helsley
2008-02-21  8:39                 ` Nadia Derbey
2008-02-21  8:39                   ` Nadia Derbey
     [not found]                 ` <1203459418.7408.39.camel-bi+AKbBUZKY6gyzm1THtWbp2dZbC/Bob@public.gmane.org>
2008-02-21  8:39                   ` Nadia Derbey
2008-02-21 12:36                   ` Nadia Derbey
2008-02-21 12:36                 ` Nadia Derbey
2008-02-21 12:36                   ` Nadia Derbey
     [not found]                   ` <47BD705A.9020309-6ktuUTfB/bM@public.gmane.org>
2008-02-21 13:02                     ` Nadia Derbey
2008-02-21 13:02                   ` Nadia Derbey
2008-02-21 13:39                     ` Subrata Modak
2008-02-21 13:39                       ` Subrata Modak
2008-02-22  6:25                       ` Nadia Derbey
     [not found]                         ` <47BE6AD0.6070309-6ktuUTfB/bM@public.gmane.org>
2008-02-22  8:41                           ` Subrata Modak
2008-02-22  8:41                         ` Subrata Modak
2008-02-22  8:41                           ` Subrata Modak
     [not found]                       ` <1203601178.4604.18.camel-NRFfyExJdYpgXGGE5LP+UZlqa2bBAFbm0E9HWUfgJXw@public.gmane.org>
2008-02-22  6:25                         ` Nadia Derbey
     [not found]                     ` <47BD7648.5010309-6ktuUTfB/bM@public.gmane.org>
2008-02-21 13:39                       ` Subrata Modak
2008-02-20  9:44               ` Subrata Modak
2008-02-20  9:44                 ` Subrata Modak
2008-04-29 20:28     ` Tony Luck
2008-04-29 20:28   ` Tony Luck
2008-04-29 20:28     ` Tony Luck
     [not found]     ` <12c511ca0804291328v2f0b87csd0f2cf3accc6ad00-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2008-05-05  8:45       ` Nadia Derbey
2008-05-05  8:45     ` Nadia Derbey
2008-05-05  8:45       ` Nadia Derbey
2008-05-06 16:42       ` Luck, Tony
2008-05-06 16:42         ` Luck, Tony
     [not found]         ` <1FE6DD409037234FAB833C420AA843EC014392F9-7XlYjKTK0pM64kNsxIetb7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2008-05-06 18:05           ` Serge E. Hallyn
2008-05-07  5:13           ` Nadia Derbey
2008-05-06 18:05         ` Serge E. Hallyn
2008-05-06 18:05           ` Serge E. Hallyn
     [not found]           ` <20080506180527.GA8315-6s5zFf/epYLPQpwDFJZrxKsjOiXwFzmk@public.gmane.org>
2008-05-07  5:37             ` Nadia Derbey
2008-05-07  5:37           ` Nadia Derbey
2008-05-07  5:37             ` Nadia Derbey
2008-05-07 13:17             ` Serge E. Hallyn
2008-05-07 13:17               ` Serge E. Hallyn
     [not found]               ` <20080507131712.GA8580-6s5zFf/epYLPQpwDFJZrxKsjOiXwFzmk@public.gmane.org>
2008-05-07 18:12                 ` Matt Helsley
2008-05-07 18:12               ` Matt Helsley
2008-05-07 18:12                 ` Matt Helsley
     [not found]             ` <48214007.7050800-6ktuUTfB/bM@public.gmane.org>
2008-05-07 13:17               ` Serge E. Hallyn
2008-05-07  5:13         ` Nadia Derbey
2008-05-07  5:13           ` Nadia Derbey
     [not found]       ` <481EC917.6070808-6ktuUTfB/bM@public.gmane.org>
2008-05-06 16:42         ` Luck, Tony
2008-02-11 14:16 ` [PATCH 2/8] Scaling msgmni to the number of ipc namespaces Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
2008-02-11 14:16 ` Nadia.Derbey-6ktuUTfB/bM
2008-02-11 14:16 ` [PATCH 3/8] Defining the slab_memory_callback priority as a constant Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
2008-02-11 14:16 ` Nadia.Derbey-6ktuUTfB/bM
2008-02-11 14:16 ` [PATCH 4/8] Recomputing msgmni on memory add / remove Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
2008-02-11 14:16 ` Nadia.Derbey-6ktuUTfB/bM
2008-02-11 14:16 ` [PATCH 5/8] Invoke the ipcns notifier chain as a work item Nadia.Derbey-6ktuUTfB/bM
2008-02-11 14:16 ` Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
2008-02-11 14:16 ` [PATCH 6/8] Recomputing msgmni on ipc namespace creation/removal Nadia.Derbey-6ktuUTfB/bM
2008-02-11 14:16 ` Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
2008-02-11 14:16 ` [PATCH 7/8] Do not recompute msgmni anymore if explicitely set by user Nadia.Derbey-6ktuUTfB/bM
2008-02-11 14:16 ` Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
2008-02-11 20:24   ` Andrew Morton
2008-02-11 20:24     ` Andrew Morton
     [not found]     ` <20080211122408.5008902f.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2008-02-12  9:32       ` Nadia Derbey
2008-02-12  9:32     ` Nadia Derbey
     [not found]       ` <47B167AF.6010008-6ktuUTfB/bM@public.gmane.org>
2008-02-12  9:44         ` Andrew Morton
2008-02-12  9:44           ` Andrew Morton
2008-02-12  9:44           ` Andrew Morton
     [not found]           ` <20080212014444.8bc3791b.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2008-02-12 15:15             ` Nadia Derbey
2008-02-12 15:15           ` Nadia Derbey
2008-02-12 15:15             ` Nadia Derbey
     [not found]             ` <47B1B7F4.8080009-6ktuUTfB/bM@public.gmane.org>
2008-02-12 19:44               ` Andrew Morton
2008-02-12 19:44                 ` Andrew Morton
2008-02-12 19:44                 ` Andrew Morton
     [not found]                 ` <20080212114439.e08085f1.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2008-02-14 11:47                   ` Nadia Derbey
2008-02-14 11:47                 ` Nadia Derbey
2008-02-14 11:47                   ` Nadia Derbey
2008-02-12  9:45         ` Nadia Derbey
2008-02-12  9:45           ` Nadia Derbey
     [not found]   ` <20080211141816.094061000-6ktuUTfB/bM@public.gmane.org>
2008-02-11 20:24     ` Andrew Morton
2008-02-11 14:16 ` [PATCH 8/8] Re-enable msgmni automatic recomputing msgmni if set to negative Nadia.Derbey
2008-02-11 14:16   ` Nadia.Derbey
     [not found]   ` <20080211141816.520049000-6ktuUTfB/bM@public.gmane.org>
2008-02-11 20:27     ` Andrew Morton
2008-02-11 20:27   ` Andrew Morton
2008-02-11 20:27     ` Andrew Morton
     [not found]     ` <20080211122748.64e7bc36.akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
2008-02-12 11:38       ` Nadia Derbey
2008-02-12 11:38     ` Nadia Derbey
2008-02-12 11:38       ` Nadia Derbey
2008-02-11 14:16 ` Nadia.Derbey-6ktuUTfB/bM
  -- strict thread matches above, loose matches on Subject: below --
2008-05-20 14:28 [PATCH 1/8] Scaling msgmni to the amount of lowmem Michael Kerrisk
2008-05-20 14:45 ` Nadia Derbey
2008-05-20 14:56   ` Michael Kerrisk
2008-05-20 14:56     ` Michael Kerrisk
2008-05-21 10:47   ` Michael Kerrisk
2008-05-21 10:47     ` Michael Kerrisk

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=47B94D8C.8040605@bull.net \
    --to=nadia.derbey@bull.net \
    --cc=akpm@linux-foundation.org \
    --cc=cmm@us.ibm.com \
    --cc=containers@lists.linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=matthltc@us.ibm.com \
    --cc=y-goto@jp.fujitsu.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.