We went with the following config:
Exchange\iSCSI
(3) 1GbE Cu in a MM VIF + (3) 1GbE Cu in a MM VIF = Single Mode VIF (3) 14D+2P Raid Groups per AGGR, 2 AGGRs using 144GB 15K FC drives
VMWare\NFS (2) 10GbE in a MM VIF + (2) 10GbE in a MM VIF = Single Mode VIF (2) 14D+2P Raid Groups per AGGR, 2 AGGRs using 300GB 15K FC drives
Both are under the same Filers, but separate aggregates and loops and interfaces.
So far, so good
-----Original Message----- From: Sto Rage(c) [mailto:netbacker@gmail.com] Sent: Monday, November 03, 2008 7:33 PM To: Glenn Walker Cc: toasters@mathworks.com Subject: Re: Brief outages on the filer?
On Mon, Nov 3, 2008 at 12:02 PM, Glenn Walker ggwalker@mindspring.com wrote:
FAS6070 and the busy time is recorded around 6000 NFS IOPS. That
said, we
did a stress test with about 25 guests running IOMeter and were able
to push
15000 NFS OPS on node 1, 10000 NFS OPS on node 2 (a combined 400MB/s
write,
300MB/s read) without any sort of reported performance problems.
May I know how big your aggregates are in terms of spindle count and disk size. We are trying to size our VMWare infrastructure using NFS on a FAS3070 cluster, with two 40-disk aggregates (300GB FC) each. Like you we are running Exchange on iSCSI on these filers now. On the network side, we have separate 3-port multi-vif for iSCSIand NFS traffic.
TIA