[Top] [All Lists]

Re: Extreme slowness with xfs [WAS: Re: Slowness with new pc]

To: xfs@xxxxxxxxxxx
Subject: Re: Extreme slowness with xfs [WAS: Re: Slowness with new pc]
From: Martin Steigerwald <Martin@xxxxxxxxxxxx>
Date: Wed, 26 Nov 2008 13:30:26 +0100
In-reply-to: <1227647010.7992.34.camel@chevrolet>
References: <1226760254.5089.11.camel@chevrolet> <492B5684.2080107@xxxxxxxxxxx> <1227647010.7992.34.camel@chevrolet> (sfid-20081125_220944_366364_C8DFDCD4)
User-agent: KMail/1.9.9
Am Dienstag 25 November 2008 schrieb Stian Jordet:
> ma., 24.11.2008 kl. 19.36 -0600, skrev Eric Sandeen:
> > I don't know if the storage you're on passes barriers or not, but xfs
> > has barriers on by default, while ext3 does not.  ext3 will still
> > likely
> > win the "untar a kernel" race, but for a fairer test, make the
> > barrier settings consistent between the two.
> As I wrote earlier, the point wasn't to find the fastest fs. That's not
> what I'm looking for. I just want xfs to perform at least as good on my
> new workstation as it did on my six years old other workstation.
> Which disabling barriers helped (notice the rm -rf with barriers...
> nobarrier is almost 200 times faster, 10 times faster on the
> unpacking):


> ### Ext3
> time bash -c 'tar xjf linux- ; sync'
> real 0m18.663s
> user 0m14.693s
> sys 0m2.828s
> time bash -c 'rm -r linux- ; sync'
> real 0m0.635s
> user 0m0.028s
> sys 0m0.564s

It would be interesting to know the value on Ext3 with barriers.

I wonder whether XFS performance with barriers enabled can be improved? 
And whether XFS with disabled write cache (via hdparm) but without 
barriers might even be *faster* than XFS with barriers... One thing to 
test eventually.

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>