It ssems that we have a alignment problem, too:

 

nfsstat:

Misaligned Read request stats

BIN-0    BIN-1    BIN-2    BIN-3    BIN-4    BIN-5    BIN-6    BIN-7

1096332359 1984142147 16821356 3951254  469217191 6145276  94494489 245873608

Misaligned Write request stats

BIN-0    BIN-1    BIN-2    BIN-3    BIN-4    BIN-5    BIN-6    BIN-7

252471989 1287671452 52026962 32535853 278299197 40175418 38565555 692647941

 

I'll do a reallocate measurement tomorrow.

 

greets

 

Steffen

 

 

 

Von: toasters-bounces@teaparty.net [mailto:toasters-bounces@teaparty.net] Im Auftrag von Jeremy Page
Gesendet: Dienstag, 25. September 2012 14:23
An: toasters@teaparty.net
Betreff: Re: Raidgroupsize and I/O Performance

 

If you're considering getting a cache adapter I'd hold off on messing with the RAID config until afterwards - tuning for writes is different than tuning for IO in general since you're looking for free space and generally the more contiguous the better.

Have you done a reallocate measurement, are your VMDK files all aligned?

On 09/25/2012 04:19 AM, Steffen Knauf wrote:

Hello,

 

i'll try to improve our I/0 Perfomance. We have a raidgroup with 16 disks (SAS), 1 aggregate and 1 volume (dedup enabled). The volume is the storage for 100 VM's on the VMware Cluser (access via NFS). Does it make sense to increase the raidgroup?  90% Percent of the Disk I/O are Read Ops, so i'll buy a PAM Card for our FAS3240,too.

 

And what's your Experience with the Raidgroupsize of a Raidgroup with SATA Disks (now: 11+1)?

 

Thanks and greets !

 

Steffen

 

 

 




_______________________________________________
Toasters mailing list
Toasters@teaparty.net
http://www.teaparty.net/mailman/listinfo/toasters



Please be advised that this email may contain confidential information. If you are not the intended recipient, please notify us by email by replying to the sender and delete this message. The sender disclaims that the content of this email constitutes an offer to enter into, or the acceptance of, any agreement; provided that the foregoing does not invalidate the binding effect of any digital or other electronic reproduction of a manual signature that is included in any attachment.