After upgrading our GPFS cluster from 126.96.36.199 to 188.8.131.52, the average IO size on our NSDs to the LUNs dropped by about 30%, with an associated increase in the requests/sec, queue sizes and average wait time. We believe this is the cause of a significant increase in the run time of many of our processes after the upgrade. We did not make any OS or GPFS configuration changes, and upgrading to 184.108.40.206 did not resolve the issue. Has any one else experienced this issue?
We use do not use NFS; our cluster is composed of dozens of GPFS clients connected to three NSD servers.