xfs
[Top] [All Lists]

Re: XFS perfomance degradation on growing filesystem size

To: Jens Beyer <jens.beyer@xxxxxxxx>
Subject: Re: XFS perfomance degradation on growing filesystem size
From: Dave Chinner <dchinner@xxxxxxxxx>
Date: Fri, 4 Jul 2008 00:59:41 -0700
Cc: xfs@xxxxxxxxxxx
In-reply-to: <20080704064126.GA14847@xxxxxxxx>
Mail-followup-to: Jens Beyer <jens.beyer@xxxxxxxx>, xfs@xxxxxxxxxxx
References: <20080704064126.GA14847@xxxxxxxx>
Sender: xfs-bounce@xxxxxxxxxxx
User-agent: Mutt/1.4.2.3i
On Fri, Jul 04, 2008 at 08:41:26AM +0200, Jens Beyer wrote:
> 
> Hi,
> 
> I have encountered a strange performance problem during some 
> hardware evaluation tests: 
> 
> I am running a benchmark to measure especially random read/write 
> I/O on an raid device and found that (under some circumstances) 
> the performance of Random Read I/O is inverse proportional to the 
> size of the tested XFS filesystem. 
> 
> In numbers this means that on a 100GB partition I get a throughput 
> of ~25 MB/s and on the same hardware at 1TB FS size only 18 MB/s 
> (and at 2+ TB like 14 MB/s) (absolute values depend on options, 
> kernel version and are for random read i/o at 8k test block size).

Of course - as the filesystem size grows, so does the amount of
each disk in use so the average seek distance increases and hence
read I/Os take longer.

Cheers,

Dave.
-- 
Dave Chinner
dchinner@xxxxxxxxx


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