xfs
[Top] [All Lists]

Re: Can I make my blocksize > 4k during mkfs.xfs?

To: Austin Gonyou <austin@xxxxxxxxxxxxxxx>
Subject: Re: Can I make my blocksize > 4k during mkfs.xfs?
From: utz lehmann <xfs@xxxxxxxxxx>
Date: Tue, 4 Jun 2002 23:34:08 +0200
Cc: Eric Sandeen <sandeen@xxxxxxx>, linux-xfs@xxxxxxxxxxx
In-reply-to: <1023224585.9286.1.camel@UberGeek>
References: <1023220656.17830.42.camel@xxxxxxxxxxxxxxxxxxxxxx> <1023224585.9286.1.camel@UberGeek>
Sender: owner-linux-xfs@xxxxxxxxxxx
User-agent: Mutt/1.2.5i
btw: is there any advantage for xfs if (hypotheitcally) using 
block size > page size?

On an classic block allocation based fs you will gain performance due less
fragmentation. But on xfs the files are stored in large contiguous
extents.

My guess is, that it will not make a difference, only space is wasted.


utz

Austin Gonyou [austin@xxxxxxxxxxxxxxx] wrote:
> So say, with NTFS...you *can* do that..is that because they make it do
> that..but it can be slower?
> 
> On Tue, 2002-06-04 at 14:57, Eric Sandeen wrote:
> > On Tue, 2002-06-04 at 14:57, Austin Gonyou wrote:
> > 
> > > Ahh..I seee....so IA32 cannot handle this at all?
> > 
> > There is no support in XFS for filesystem block size > page size for
> > any
> > architecture...
> > 
> > -Eric
> -- 
> Austin Gonyou
> Systems Architect, CCNA
> Coremetrics, Inc.
> Phone: 512-698-7250
> email: austin@xxxxxxxxxxxxxxx
> 
> "One ought never to turn one's back on a threatened danger and 
> try to run away from it. If you do that, you will double the danger. 
> But if you meet it promptly and without flinching, you will 
> reduce the danger by half."
> Sir Winston Churchill



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