Date: Sun, 17 Aug 2003 17:40:26 -0700
From: William Lee Irwin III <wli@holomorphy.com>
To: Duraid Madina <duraid@octopus.com.au>, linux-ia64@linuxia64.org,
       linux-kernel@vger.kernel.org
Subject: Re: kswapd is having a party
Message-ID: <20030818004026.GT32488@holomorphy.com>
Mail-Followup-To: William Lee Irwin III <wli@holomorphy.com>,
	Duraid Madina <duraid@octopus.com.au>, linux-ia64@linuxia64.org,
	linux-kernel@vger.kernel.org
References: <3F400B57.2090806@octopus.com.au> <20030818003300.GS32488@holomorphy.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20030818003300.GS32488@holomorphy.com>
Organization: The Domain of Holomorphy
User-Agent: Mutt/1.5.4i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 896
Lines: 20

On Mon, Aug 18, 2003 at 09:10:15AM +1000, Duraid Madina wrote:
>> 	Does anyone have _any_ idea what kswapd might actually be doing? I 
>> checked: not a single page was swapped in our out througout the duration 
>> of this test. Is there a chance that spinning on some lock (I have no 
>> idea how LAM does its synchronization), or perhaps even just idling, 
>> might be counted as kswapd0?

On Sun, Aug 17, 2003 at 05:33:00PM -0700, William Lee Irwin III wrote:
> I'd look for dirty memory; kswapd does do some page cleaning, though
> pdflush is supposed to do most of it.

Also, please log vmstat and take regular snapshots of /proc/vmstat.


-- wli
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/