xfs
[Top] [All Lists]

Re: mkfs options for a 16x hw raid5 and xfs (mostly large files)

To: linux-xfs@xxxxxxxxxxx
Subject: Re: mkfs options for a 16x hw raid5 and xfs (mostly large files)
From: KELEMEN Peter <Peter.Kelemen@xxxxxxx>
Date: Tue, 25 Sep 2007 14:57:33 +0200
Domainkey-status: no signature - Generated by CERN IT/IS DomainKeys v1.0
In-reply-to: <20070925123501.GA20499@xxxxxxxxxxxxxxxxxxxxxxxxx>
Keywords: CERN SpamKiller Note: -51 Charset: west-latin
Mail-followup-to: linux-xfs@xxxxxxxxxxx
Organization: CERN European Laboratory for Particle Physics, Switzerland
References: <20070923093841.GH19983@xxxxxxxxxxxxxxxxxxxxxxxxx> <20070924173155.GI19983@xxxxxxxxxxxxxxxxxxxxxxxxx> <Pine.LNX.4.64.0709241400370.12025@xxxxxxxxxxxxxxxx> <20070924203958.GA4082@xxxxxxxxxxxxxxxxxxxxxxxxx> <Pine.LNX.4.64.0709241642110.19847@xxxxxxxxxxxxxxxx> <20070924213358.GB4082@xxxxxxxxxxxxxxxxxxxxxxxxx> <Pine.LNX.4.64.0709241736370.19847@xxxxxxxxxxxxxxxx> <20070924215223.GC4082@xxxxxxxxxxxxxxxxxxxxxxxxx> <20070925123501.GA20499@xxxxxxxxxxxxxxxxxxxxxxxxx>
Sender: xfs-bounce@xxxxxxxxxxx
User-agent: Mutt/1.5.13 (2006-08-11)
* Ralf Gross (ralf-lists@xxxxxxxxxxxx) [20070925 14:35]:

> There is a second RAID device attached to the server (24x
> RAID5). The numbers I get from this device are a bit worse than
> the 16x RAID 5 numbers (150MB/s read with dd).

You are expecting 24 spindles to align up when you have a write
request, which has to be 23*chunksize bytes in order to avoid RMW.
Additionally, your array is so big that you're very likely to hit
another error while rebuilding.  Chop up your monster RAID5 array
into smaller arrays and stripe across them.  Even better, consider
RAID10.

Peter

-- 
    .+'''+.         .+'''+.         .+'''+.         .+'''+.         .+''
 Kelemen Péter     /       \       /       \     Peter.Kelemen@xxxxxxx
.+'         `+...+'         `+...+'         `+...+'         `+...+'


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