xfs
[Top] [All Lists]

Re: XFS performance

To: Alexey Tsyban <leshats@xxxxxxxxxxxxxxxxx>
Subject: Re: XFS performance
From: Simon Matter <simon.matter@xxxxxxxxxxxxxxxx>
Date: Fri, 08 Feb 2002 13:20:56 +0100
>received: from mobile.sauter-bc.com (unknown [10.1.6.21]) by basel1.sauter-bc.com (Postfix) with ESMTP id 4552B57306; Fri, 8 Feb 2002 13:20:57 +0100 (CET)
Cc: linux-xfs <linux-xfs@xxxxxxxxxxx>
Organization: Sauter AG, Basel
References: <4904.195.66.202.195.1013163671.squirrel@webmail.od.anything3d.com>
Sender: owner-linux-xfs@xxxxxxxxxxx
Hi

I don't know exactly how you made your test.
I have made my own tests on a DELL PE1400 with Hardware and Software
RAID1+5 in every possible combination and I got almost the same result
for both ext3 and XFS.

When using XFS and Software RAID5, it is very important to have an
external logdev on a Software RAID1, which can stay on the same disk.
Beside that there was no big difference with both filesystems in my very
mixed load test. I mean tests with network load, CPU load, IO load and
all of them at the same time. The interesting point was that XFS was
always slightly better and much better whith high disk IO load while
using less CPU power which is very important when you have applications
like DB servers.

-Simon


Alexey Tsyban schrieb:
> 
> Hi,
> 
> I just have tested performance of xfs and ext3 on my new Dell PowerEdge 1550
> RERC3/DLC RAID with 3 36Gb disks in RAID5, Dual PIII 1000. Running linux
> slackware 8.0 glibc 2.2.5 with linux 2.4.17 from cvs tree.
> Mkfs options -l size=8192b, partition size 30Gb
> mount options logbufs=4,osyncisdsync
> 
> Bonnie++ XFS results:
> Version 1.02a       ------Sequential Output------ --Sequential Input-
> --Random-
>                     -Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
> --Seeks--
> Machine        Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
> /sec %CP
> power            2G  6938  49  8949   4  7944   6 10619  74 34052  12
> 437.0   2
>                     ------Sequential Create------ --------Random
> Create--------
>                     -Create-- --Read--- -Delete-- -Create-- --Read---
> -Delete--
>               files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
> /sec %CP
>                  16   380   6 +++++ +++   426   6   393   6 +++++ +++
> 348   5
> power,2G,6938,49,8949,4,7944,6,10619,74,34052,12,437.0,2,16,380,6,+++++,+++,426,6,393,6,+++++,+++,348,5
> And ext3 results:
> 
> Version 1.02a       ------Sequential Output------ --Sequential Input-
> --Random-
>                     -Per Chr- --Block-- -Rewrite- -Per Chr- --Block--
> --Seeks--
> Machine        Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP
> /sec %CP
> power            2G 10386  77 13076  11  7428   5 14116  98 25365   8
> 399.4   2
>                     ------Sequential Create------ --------Random
> Create--------
>                     -Create-- --Read--- -Delete-- -Create-- --Read---
> -Delete--
>               files  /sec %CP  /sec %CP  /sec %CP  /sec %CP  /sec %CP
> /sec %CP
>                  16   545  97 +++++ +++ +++++ +++   573  97 +++++ +++
> 2459  94
> power,2G,10386,77,13076,11,7428,5,14116,98,25365,8,399.4,2,16,545,97,+++++,+++,+++++,+++,573,97,+++++,+++,2459,94
> As I see ext3 is match faster. Why??
> May be I should use another mount options or mkfs options to have better
> performance?
> 
> Thank you.
> 
> --
> Alexey Tsyban
> Realtor3D Corp. System Administrator
> ICQ 10195188



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