| To: | Harry Mangalam <hjm@xxxxxxxxx> |
|---|---|
| Subject: | Re: 3ware + RAID5 + xfs performance |
| From: | Jan-Frode Myklebust <Jan-Frode.Myklebust@xxxxxxxxxxx> |
| Date: | Wed, 27 Jul 2005 19:36:29 +0200 |
| Cc: | linux-raid@xxxxxxxxxxxxxxx, linux-xfs@xxxxxxxxxxx |
| In-reply-to: | <200507270915.32011.hjm@xxxxxxxxx> |
| References: | <Pine.SOL.4.58.0507252110320.2683@xxxxxxxxxxxxxxxxxxxxx> <200507252134.13869.hjm@xxxxxxxxx> <20050727092104.GA6215@xxxxxxxxx> <200507270915.32011.hjm@xxxxxxxxx> |
| Sender: | linux-xfs-bounce@xxxxxxxxxxx |
On Wed, Jul 27, 2005 at 09:15:31AM -0700, Harry Mangalam wrote: > That's very impressive! How many config iterations did you have to do to get > this perf? Not too many I think.. only tried a few tunings of stripe-unit in the 3ware CLI, and scratched my heads a few times to try to understand the mkfs.xfs sunit/swidth-options.. > > I'd certainly consider GPFS but I was under the impression that it was only > available for IBM-branded Linux boxes w/ customized kernels. Can you buy it > a la carte? Yes, and maybe even for free from the IBM Scholars programme if you qualify. But yes, it does require a couple of "GPFS" kernel modules, which will typically only build for vendor kernels (i.e. not keeping up with the latest kernel.org releases). We're running a RHEL-3 clone, so that's not been a problem for us so far. -jf |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: 3ware + RAID5 + xfs performance, Harry Mangalam |
|---|---|
| Next by Date: | TAKE 918919 - xfsdump, Nathan Scott |
| Previous by Thread: | Re: 3ware + RAID5 + xfs performance, Harry Mangalam |
| Next by Thread: | TAKE 918919 - xfsdump, Nathan Scott |
| Indexes: | [Date] [Thread] [Top] [All Lists] |