xfs
[Top] [All Lists]

Re: Linux Software RAID 5 + XFS Multi-Benchmarks / 10 Raptors Again

To: Greg Cormier <gcormier@xxxxxxxxx>
Subject: Re: Linux Software RAID 5 + XFS Multi-Benchmarks / 10 Raptors Again
From: Justin Piszcz <jpiszcz@xxxxxxxxxxxxxxx>
Date: Fri, 18 Jan 2008 10:58:40 -0500 (EST)
Cc: linux-raid@xxxxxxxxxxxxxxx, xfs@xxxxxxxxxxx, Alan Piszcz <ap@xxxxxxxxxxxxx>
In-reply-to: <29a863790801180743y2e90e37aj70c556dc9192a15d@xxxxxxxxxxxxxx>
References: <alpine.DEB.0.999999.0801161105510.16168@xxxxxxxxxxxxxxxx> <29a863790801180735n379a27f1t4987686b2ec1aa50@xxxxxxxxxxxxxx> <alpine.DEB.0.999999.0801181036260.23565@xxxxxxxxxxxxxxxx> <29a863790801180743y2e90e37aj70c556dc9192a15d@xxxxxxxxxxxxxx>
Sender: xfs-bounce@xxxxxxxxxxx
User-agent: Alpine 0.999999 (DEB 847 2007-12-06)


On Fri, 18 Jan 2008, Greg Cormier wrote:

Also, don't use ext*, XFS can be up to 2-3x faster (in many of the
benchmarks).

I'm going to swap file systems and give it a shot right now! :)

How is stability of XFS? I heard recovery is easier with ext2/3 due to
more people using it, more tools available, etc?

Greg


Recovery is actually easier with XFS because the repair filesystem code is built-into the kernel (you dont need a utility to fix it)-- however, there is xfs_repair (if) the in-kernel-tree part could not fix it.

I have been using it for > 4-5 years? now.

Also, with CoRaids (ATA over Ethernet) many of them are above 8TB and ext3 only works up to 8TB, so its not even an option any longer.

Justin.


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