xfs
[Top] [All Lists]

Re: ZFS, XFS, and EXT4 compared

To: xfs@xxxxxxxxxxx
Subject: Re: ZFS, XFS, and EXT4 compared
From: Federico Sevilla III <jijo@xxxxxx>
Date: Sat, 01 Sep 2007 23:07:23 +0800
In-reply-to: <1188513751.24970.109.camel@edge.yarra.acx>
Organization: F S 3 Consulting Inc.
References: <1188454611.23311.13.camel@toonses.gghcwest.com> <1188457666.24970.94.camel@edge.yarra.acx> <20070830132002.GA4086@infradead.org> <1188513751.24970.109.camel@edge.yarra.acx>
Sender: xfs-bounce@xxxxxxxxxxx
On Fri, 2007-08-31 at 08:42 +1000, Nathan Scott wrote:
> Possibly.  Far more importantly for XFS, there really needs to be some
> way for RAID drivers to say "even though I support write barriers, its
> not a good idea for filesystems to enable write barriers by default on
> me".  Enabling write barriers everywhere, by default, seems to have a
> far worse impact than any mkfs/mount option tweaking.

On all my systems with software RAID or dm-crypt (or both), mounting XFS
gives me a message about barriers being disabled because the underlying
device doesn't support it. For good measure I disable write caching on
all my systems with either software RAID or dm-crypt (or both).

Am I reading the thread correctly that even with this message showing
up, I still need to mount with nobarrier explicitly to improve
performance?

I also think it would be nice to add something like a modern-day tuning
FAQ for XFS. I know there's a bit on the FAQ already but perhaps it
needs an update?

Thanks.

-- 
Federico Sevilla III
F S 3 Consulting Inc.
http://www.fs3.ph

Attachment: signature.asc
Description: This is a digitally signed message part

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