Originally posted by: dwcasey

I continue to struggle with these latency issues. We've evacuated all NL disk and are only running on 15K FC disk per HP support direction. 2 controller node, 12-cage/shelf 3PAR F400. Will be running tunesys and possibly tunepd as well ( although PD performance looks find with statpd ).

So what's left? I watched it last night/over night before, during, after the event.

statvlun will show those critical VLUNs during the critical time with terrible latency, while statpd will show all FC PDs mostly balanced and singled digit latency.

The particular host I'm watching is an AIX host ( DB2 database server ) with two hdisks. Nmon showing both hdisks running 100% and with high IOP rates and consistently double-digit servqfull...I asked my teammate if adding disks would help balance the load across ( like 5 250GB hdisks in the VG versus one large 1TB  VG ) and he thinks it would just exacerbate the problem by potentially allowing more data through only to cause more problems.

What is everyone's thought on how the AIX host is setup?

Originally posted by: j.cortez

Hello,

First i would say that i was trying to split those 250 LUN disks to 50GB ou 80GB LUN disks. After that some performance should be noted.

Take care also with Paths, this might help a lot performance.

Regards,
João Bosco Cortez Filho