Hi everyone!
There is a 5-node SQL Server 2012 failover cluster based on Windows server 2012 Datacenter and built on IBM Bladecenter
HS23 type 7875. Cluster nodes are using SAN-boot from IBM Storwize v3700 and LUN's from IBM
Storwize v7000.
On 3 of 5 cluster nodes, on all volumes, including system periodicly appears an errorEvent ID 154 The IO operation at logical block address XXXX for Disk XX failed due to a hardware
error, or warining Event ID 153 The IO operation at logical block address XXXX for Disk XX was retried. OS experiencing these errors painless, but if error appears on LUN, where SQL temp DB or logs are placed SQL instance using them hangs
or reboots.
All of nodes were deployed using the same image using WDS, they have the same updates and hotfixes installed and there is no records about dropped packets in FC-switch logs.
I tried change disk timeout, as written here http://support.microsoft.com/kb/2806730/ru but it won't
help.