Dave, Normally, when there is little to no activity on a device, the response time may appear slower than devices that are busy. At least this is what I have observed.
I am no expert but my assumption is that when there are vary few I/O operations done, then the chances of the seeks being 'closer' to each other is lower and hence the higher response time. During normal active periods, this is less true and you may see better response time number. I am sure others will correct me if I am wrong. Aria. On Wed, 21 Jan 2009 10:20:06 -0500 David L. Craig said: >I was collecting monitor data on the Monday holiday >to see what idle looks like on our 7060 running >VM/ESA 2.2 and noticed DASD Response Time was being >reported every ten minutes around 4 ms for the most >part, when 1-2 is normal. The average for the whole >day (8 AM to 6 PM) was only 1.6, though. I've put an >analysis at http://www.radix.net/~dlc/DASD_Response.pdf >for anyone interested to look at that includes the same >numbers for Tuesday, a more normal sample. Is this >just a bug in VMPRF or is something else going on here? > >-- > >May the LORD God bless you exceedingly abundantly! > >Dave Craig > >- - - - - - - - - - - - - - - - - - - - >"'So the universe is not quite as you thought it was. > You'd better rearrange your beliefs, then. > Because you certainly can't rearrange the universe.'" > >--from _Nightfall_ by Asimov/Silverberg >
