sqlio results local disk vs netapp

[sraja2005]

Just to test, I ran SQLIO

on a windows 2008 box (DL785) local disk (4x300G, RAID 10)  vs a Netapp aggregate of 56 disks. Filer is running 7.2.6.1, this is a FC LUN.  Aggregate is not really that loaded.

Surprisingly to me, the results show the C drive to be faster.  I know there are various ways to tweak SQLIO but I still find this odd.  Any suggestions would be appreciated:

SQLIO: 1 thread reading for 30 secs using 2KB IOs over 128KB stripes with 64 IOs per run:

Local C:\     [sqlio -dC]

IOs/sec:  5844.79
MBs/sec:    11.41

Netapp F:\    [sqlio -dF]

IOs/sec: 2547.88
MBs/sec:     4.97

SQLIO: 1 thread writing for 30 secs using 2KB IOs over 128KB stripes with 64 IOs per run:

Local C:\    [sqlio -kW -dC]

IOs/sec: 10116.73
MBs/sec:    19.75

Netapp F:\    [sqlio -kW -dF]

IOs/sec:  1895.42
MBs/sec:     3.70

[evilensky]

Have you check for partition alignment, LUN type mismatch, FC frame errors, other user-level errors?

This discrepancy is shocking and can only be some unoptimized settings.

[evilensky]

What type of disk is the 56 disk aggregate, its RG size?  What is you measure of "not really that loaded" ?  Are disk queue lengths and latency response high in perfmon?  Do you have performance advisor on this aggregate? Are storage latencies high?

[sraja2005]

Aggregate is a 56 disk aggregate, with standard 16 disk raid groups, total aggregate iops in DFM never exceeds 500-1000.  I have to look at all of the other stuff

Suresh

[evilensky]

What speed of disk?

[lwei]

What HBA(s) are you using? How about drivers? Thanks,  -Wei

[sraja2005]

These are Emulex HBA's, with Netapp Host utilities, Snapdrive 6 and MPIO.  Disks on the filer are 15k rpm

[lwei]

Can you provide the Emulex HBA model #? Also, what driver are you using? Version #? How about driver parameter, such as queue depth?

Thanks,

Wei

[p_maniawski]

Has your problem been solved? I think we have Thread Link : 13413. Can you share your thoughts?

[BrendonHiggins]

We had an issue like this at the back end of 2009.  It was caused by a 'rogue' HBA driver that windows had download from the server vender.  Replaced with the NetApp drive and issue resolved.

Hope it helps

Bren

[p_maniawski]

Although we don't have HBA iSCSI NICs, this might be a NIC driver issue (or setting). We're using Broadcom NetXtreme II BCM5709 cards. Had anyone problems with those?

-- edit--

As there are many models with this chipset, I'll be more precise - this is a default NIC implemented in IBM x3550M3 (2 port) + doughter card (2 port)