xfs
[Top] [All Lists]

Re: [RFC, PATCH 0/7] XFS: dynamic busy extent tracking

To: linux-xfs@xxxxxxxxxxx
Subject: Re: [RFC, PATCH 0/7] XFS: dynamic busy extent tracking
From: Martin Steigerwald <Martin@xxxxxxxxxxxx>
Date: Fri, 10 Oct 2008 09:11:18 +0200
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
In-reply-to: <20081009223328.GI9597@disturbed>
References: <1223417377-8679-1-git-send-email-david@xxxxxxxxxxxxx> <200810092017.33042.Martin@xxxxxxxxxxxx> <20081009223328.GI9597@disturbed> (sfid-20081010_090018_216466_C5ADA5AA)
User-agent: KMail/1.9.9
Am Freitag 10 Oktober 2008 schrieben Sie:
> On Thu, Oct 09, 2008 at 08:17:32PM +0200, Martin Steigerwald wrote:
> > Hi Dave,

[...]

> > A student in the Linux Performance Tuning course I hold this week
> > compared this with ext3, even with the improved mkfs.xfs options (but
> > without lazy-count=1, cause mkfs.xfs from Debian Etch is too old) and
> > even with noop as IO scheduler. AFAIR XFS took roughly 3-4 times as
> > long as Ext3, I did not note the exact numbers. This was with 2.6.25.
> > I can repeat the test locally with 2.6.26.5 if wanted.
>
> Yes, that's par for the course. XFS journals transactions almost
> immediately, whereas ext3 gathers lots of changees in memory and
> checkpoints infrequently. Hence XFS writes a lot more to the
> journal and is hence slower. The dynamic extent tracking is a
> necessary step to moving the XFS journalling to a more
> checkpoint-like setup which would perform much less journal
> I/O and hence run substantially faster....
>
> See the asynchronous transaction aggregation section here:
>
> http://xfs.org/index.php/Improving_Metadata_Performance_By_Reducing_Jou
>rnal_Overhead

Thanks for the info Dave.

I still have your three mails about future improvements on XFS on my 
reading list. I just read a bit of the first one.

Ciao,
-- 
Martin 'Helios' Steigerwald - http://www.Lichtvoll.de
GPG: 03B0 0D6C 0040 0710 4AFA  B82F 991B EAAC A599 84C7

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