topic Re: IO Error in XP Storage

IO Error

Venkat74 — Fri, 10 Apr 2009 13:50:01 GMT

We are facing this sort of I/O errors in EMS event logs (CSTM errors). The I/O errors are pointing to XP LUNs. There is no error pointing to the FC interface here. I do not suspect the FC card or the PCI slot as there is no error related to the FC HBA. I suspect something outside the server. Is my understanding correct that if these sort of errors are seen in CSTM only for XP luns, it need not be a FC card or PCI slot error?

I have given the errors details here. There are two cards, but, the errors are seen only in one path. So, i do not suspect the driver as well.

Entry Type: I/O Error
Entry logged on Fri Apr 10 09:57:54 2009
Entry id: 0x49decaca00000002

Device Path: 0/3/2/0.2.13.0.1.0.2
Product: XP Array
Product Qualifier: HPOPEN-E
Logger: sdisk
Device Type: Disk
Device Qualifier: Array

---------------------------------------------------------------------------

Description of Error:

The hardware responded to the initial query, but then it stopped
responding to more requests by the driver. The I/O request was not
completed.

Probable Cause / Recommended Action:

The bus device reset may have occurred or the device has failed. The bus
device reset could have occurred because the power was cycled or that the
device is a part of an enclosure and a device in that enclosure was pulled
out or put in, or that the interface card had a problem and it reset the
bus. If these errors continue, there may be a problem with the device or
the card.

Re: IO Error

IBaltay — Fri, 10 Apr 2009 14:02:34 GMT

Hi,
check the SAN switch port (SFP/cable) which the host HBA is connected to...
The quick method is to compare the error statistics of the port via the porterrshow: if the error counters are growing, there should by any of the marginal link symptom root cause:
(SAN switch port SFP, cable between the host HBA and SAN switch port or the SAN switch mainboard)...

Re: IO Error

Venkat74 — Fri, 10 Apr 2009 14:39:52 GMT

Thanks for your reply. I am seeing "Link Fail" increasing at the storage port side (Storage to Switch) in porterrshow.

So, I believe this could be due to the storage controller or the SAN switch port.

However, I have a doubt as to whether there can be a problem at the host side in terms of PCI FC card or the PCI slot? Can a FC HBA create "Link Fail" in storage connectivity?

Re: IO Error

IBaltay — Fri, 10 Apr 2009 15:55:20 GMT

then you should check
the cable
between the storage front port and the SAN switch port (first disable the port and then mechanicaly unplug/replug) enable the port. Then if this does not improve the connectivity, you should check the cable connection also on the storage front port. Then run the porterrshow again and check if the error counters stopped growing.

If it does not improve the issue

do the same with the storage port SFP (replace it)
check it with the porterrshow

if the error counters are still growing, then the problem should be on the storage front port side and the SFP needs to be changed also there...

...