[Top] [All Lists]

Re: Performance question

To: Nathan Scott <nathans@xxxxxxx>
Subject: Re: Performance question
From: Eric Sandeen <sandeen@xxxxxxx>
Date: 18 Feb 2004 14:51:48 -0600
Cc: Joshua Baker-LePain <jlb17@xxxxxxxx>, Linux xfs mailing list <linux-xfs@xxxxxxxxxxx>
In-reply-to: <20040219071800.F244261@xxxxxxxxxxxxxxxxxxxxxxxx>
Organization: Eric Conspiracy Secret Labs
References: <Pine.LNX.4.58.0402181131210.25541@xxxxxxxxxxxxxxxxxx> <20040219071800.F244261@xxxxxxxxxxxxxxxxxxxxxxxx>
Sender: linux-xfs-bounce@xxxxxxxxxxx
> Sounds like Eric's area of expertise. :)  Could be another
> case of inodes not being reclaimed aggresively enough, and
> OOM follows...?

Ah... sure... :)

Can you watch /proc/slabinfo as this happens, is any particular slab
cache growing extremely large?  Where is the memory going?

Glen suggested that perhaps your directory with all the inodes is
terribly fragmented, can you try 

# xfs_bmap /path/to/big/dir

and see how many extents it has...


Eric Sandeen      [C]XFS for Linux   http://oss.sgi.com/projects/xfs
sandeen@xxxxxxx   SGI, Inc.          651-683-3102

<Prev in Thread] Current Thread [Next in Thread>