Re: Q: Filesystem block sizes available?

[Seth Mos <knuffie@xxxxxxxxx>]

At 15:41 13-11-2001 +0100, Roy Sigurd Karlsbakk wrote:
> Hi
>
> What block sizes are available on XFS filesystems?

4KB on IA32, 8kb on Alpha I believe and 8KB by default on IA64

> I've seen the note
> 'Filesystem block size' on the features list, and it says it's limited to
> the page size on the given architecture (eg .4k on ia64).
>
> I'm running a lab at Compaq in Oslo now, and some guy at storage told me
> 4k's a waste, and that the SCSI drives wanted 256kB data blocks to really
> speed it all up. Could XFS help me out? I need REALLY HIGH-SPEED access to
> the drives.... Software or hardware RAID - I don't care... I just need the
> speed.

The fs blocksize has not much to do with the amount it writes in one go. 
XFS uses delayed allocation so it will probably write a lot of data at once 
anyways.

If you can give some

Use software raid 0 over multiple 15K RPM scsi disks or go fiber and make a 
raid 0 out of that.
You can even mix them, for optimal effect use disks that are the same size.
more spindles == higher speed. Make sure to use multiple controllers to 
spread the bus activity.

XFS also has some builtin heuristics in mkfs.xfs that will detect the 
striping and make some reasonable assumptions on how to optimize the fs layout.

Cheers

--
Seth
Every program has two purposes one for which
it was written and another for which it wasn't
I use the last kind.