Problem with local datastore on ESXi 4.0 U1

[jcingle]

Hello all,

I have a HP ML330G6 with an internal Smart Array card that is mirroring (R1) two SATA 250GB disks.

The issue I am seeing is the VMs are REALLY slow and non-responsive. I get these errors from from the ESXi host when I see the problems:

Lost connectivity to storage device

naa.600508b10010523953585346555a0100. Path

vmhba1:C0:T0:L0 is down. Affected datastores: "

", "datastore1", "Hypervisor1", "Hypervisor2",

"Hypervisor3".

error

12/8/2009 11:12:28 PM

If I do a constant PING on the VM in question this is what it looks like:

Reply from 192.168.1.4: bytes=32 time=512ms TTL=128

Reply from 192.168.1.4: bytes=32 time=53ms TTL=128

Reply from 192.168.1.4: bytes=32 time=168ms TTL=128

Reply from 192.168.1.4: bytes=32 time=25ms TTL=128

Reply from 192.168.1.4: bytes=32 time=67ms TTL=128

Reply from 192.168.1.4: bytes=32 time=698ms TTL=128

Reply from 192.168.1.4: bytes=32 time=116ms TTL=128

Reply from 192.168.1.4: bytes=32 time<1ms TTL=128

Reply from 192.168.1.4: bytes=32 time=250ms TTL=128

Reply from 192.168.1.4: bytes=32 time=641ms TTL=128

Reply from 192.168.1.4: bytes=32 time=979ms TTL=128

Reply from 192.168.1.4: bytes=32 time<1ms TTL=128

Request timed out.

Request timed out.

Reply from 192.168.1.4: bytes=32 time=2074ms TTL=128

Reply from 192.168.1.4: bytes=32 time=1ms TTL=128

Request timed out.

Request timed out.

Request timed out.

Request timed out.

Request timed out.

Request timed out.

Request timed out.

Reply from 192.168.1.4: bytes=32 time=1987ms TTL=128

Request timed out.

Request timed out.

Request timed out.

Request timed out.

Request timed out.

Request timed out.

Reply from 192.168.1.4: bytes=32 time=3989ms TTL=128

Reply from 192.168.1.4: bytes=32 time=1ms TTL=128

Request timed out.

I have powered off all the VMs and rebooted the host with no resolution.

I looked on VMware's download site and I don't see any driver downloads for that HP server or Array controller.

Any thoughts?

Thanks!

[cdc1]

Installed Firmware level for your Smart Array controller? (Latest is 2.50 (18 Sep 2009)).

Installed BIOS level for your ML330 G6? (Latest is 2009.10.02 (A) (30 Oct 2009)). Incidentally, this BIOS release fixes an issue that could cause "unexpected behavior" of the Smart Array adapter in addition to overal system instability, if the Smart Array adapter is installed in PCIE Slot 4.

Message was edited by: cdc

[jcingle]

Hmm.... it's on 1.66 it looks like. Will try that and let you know!

[DSTAVERT · Accepted solution]

Beyond the firmware update I would check that you have the battery module (BBWC) installed on your controller and write caching enabled. The BBWC module is an option and makes a significant difference in performance.

[jcingle]

I think it is the BBWC (or lack of...).

I upgraded the FW to 2.50 and no change. I am going to enable the WC (without BB) and see if that helps and if it does purchase a BBWC module.

I'll post my findings.

[jcingle]

Enabling the drive write cache didn't help... ;(

Look like I need to buy the BBWC upgrade module....

Will post after purchase and install.

[WazzaE]

Hi

I am experiencing exactly the same issue on the very same server setup with exactly the same specs specificully a RAID 1 mirror its unresponsive and then starts working generates same error

My question is HOW did you resolve this I have recently loaded the same on 5 other servers with no problems same software same specs except they are runing a RAID 5 Hardware config

[tom_e_reynolds]

Hi all,

Last year we had a similar disk performance problem with our older DELL servers we were testing with:

http://communities.vmware.com/message/1222329#1222329

We had to upgrade the firmware on the RAID Controllers and the BIOS, and then we got great performance.

-Tom