Sorry for the lack of a reply and thanks for all of the suggestions. So far I have been able to get both top and iostat data during a slowdown. Unfortunately, neither have showed any reason for the slow down.
Idle CPU never dropped below 85%, swap memory use has stayed at 0% and we continue to have the same amount of free memory available. For running processes, top did not show any abnormal processes or more than 4 processes running at any given time (and none of the 4 were using more than 3 - 4% CPU each). The only thing that I have noticed is an increase in output queue drops on the switch of the primary interface for the system. I'm going to continue to run the top and iostat captures as well as look at nmon. I will probably also fail over to the secondary interface (which is on our other core switch). On Wed, Feb 15, 2012 at 11:22 PM, Bill Hager <[email protected]> wrote: > On Wed, Feb 15, 2012 at 12:57 PM, Dean, Mike <[email protected]> wrote: > >> Unfortunately, I have not been able to get a snapshot from top when it is >> running slow. The slowdowns typically only last a few seconds and do not >> occur with any sort of regularity (that I've been able to determine, >> anyway. >> >> > nmon is a nice tool for collecting a bunch of info including CPU, Memory, > VM, Network, Disk, and Top processes. You can view data live or dump the > data to CSV for further analysis later. > > http://nmon.sourceforge.net/ >
