Re: [Condor-users] tuning a file server

[Steffen Grunewald <steffen.grunewald@xxxxxxxxxx>]

On Tue, Aug 02, 2005 at 01:44:46PM +0100, David McBride wrote:
> On Tue, 2005-08-02 at 12:44 +0200, Steffen Grunewald wrote:
> 
> > > The 2.6 IO schedulers tend to _better_ than the 2.4 one.  The default is 
> > > to use the 'anticipatory' scheduler which tends to be excellent for most 
> > > needs.
> > 
> > I suppose it's anticipating the wrong stuff. If 100+ client tasks start
> > to send off 24 nfsd threads to work, probably the scheduler gets a bit
> > confused. I guess that some elevator type would be the better choice?
> > (Can you point me to some docs?)
> 
> http://www.cs.rice.edu/~ssiyer/r/antsched/
> linux-2.6.12.2/Documentation/block/as-iosched.txt
> 
> Aha! The latter has some relavant comments that I wasn't aware of:
> 
> "Attention! Database servers, especially those using "TCQ" disks should
> investigate performance with the 'deadline' IO scheduler. Any system
> with high disk performance requirements should do so, in fact."
> 
> [...]
> 
> "Also, users with hardware RAID controllers, doing striping, may find
> highly variable performance results with using the as-iosched. The
> as-iosched anticipatory implementation is based on the notion that a
> disk device has only one physical seeking head.  A striped RAID
> controller actually has a head for each physical device in the logical
> RAID device."

So at the moment I'm lost: I cannot reboot the server just to put the
"elevator=deadline" kernel parameter into action. The only thing I could
fiddle with is /sys/block/$DEV/queue/iosched/antic_expire which is set
to 6.
I will also look for an explanation of the /sys/block/$DEV/* entries
(what do the contents of stat mean, for instance).
I guess a device/queue_depth of 254 indicates that the initial comment
in as-iosched.txt applies... could not find any info about drive
geometry yet - I'm a newbie with kernels >=2.5 ...

Thanks for pointing me.
 Steffen

-- 
Steffen Grunewald * MPI fuer Gravitationsphysik (Albert-Einstein-Institut)
SciencePark Golm, Am Mühlenberg 1, D-14476 Potsdam * http://www.aei.mpg.de
* e-mail: steffen.grunewald(*)aei.mpg.de * +49-331-567-{fon:7233,fax:7298}
No Word/PPT mails - http://www.gnu.org/philosophy/no-word-attachments.html