On Fri, Jul 1, 2011 at 8:27 AM, Andy Levy <andy.levy_at_gmail.com> wrote:
> On Fri, Jul 1, 2011 at 07:55, Nico Kadel-Garcia <nkadel_at_gmail.com> wrote:
>
>> This is more likely to happen in virtualization due to limiting the
>> disk resources. Think hard about your back end disk storage. Let us
>> know if you use attached storage such as a NetApp or fibre channel,
>> I've got some notes on aligning those filesystems for virtualization,
>> which makes a huge performance improvement.
>
> I'd like to see those notes if I can. We're on a NetApp device right
> now but when we upgrade our environment later this year we'll be
> moving storage to an Equallogic device. We have had some Subversion
> performance issues with large checkouts using the NetApp device. The
> Equallogic appears to be better-tuned in general (we've had no trouble
> running a 100GB SQL Server DB off it) but every little bit helps.
The big booby trap was the 4096 byte block alignment, as described at
http://www.citrix.com/site/resources/dynamic/partnerDocs/BestPracticesforFileSystemAlignmentinVirtualEnvironments.pdf.
This is awkward to configure fat installation time for virtualized
OS's, and it makes a huge performance difference. If you look up "4096
byte block NetApp Nico Kadel-Garcia" on Google, you'll see my comments
on this for the last year or so.
My old work accounts at Red Hat and NetApp are no longer active (I
ended that contract and started a new job.), so I don't have access to
the scripts I submitted on their support sites. Do you have Access to
Red Hat's knowledgebase? Some notes are at
https://www.redhat.com/archives/rhelv6-beta-list/2010-August/msg00069.html,
and I can dig around for a published copy of the tools.
Received on 2011-07-01 15:14:18 CEST