I got a group of vms on different luns but luns are created from the same rg.
there are certain times during the day when all the vms on these luns would shows red alarms and its disk latency
looking at it from the vsi plugin, one of the luns shows
%Busy maximum is 50.13
is there a problem?
the rg i have is 14disk on 1 enclosure. raid5. all sata1 disks 500gb.
its a 6.5TB rg with 14luns on it.
is there away to check performance on the whole rg?
Navisphere Analyser should be able to help you. You can check the performance of RAID Groups as well as individual LUN's (and SPs, ports, whatever you'd like to see in such a tool)
There are a few important points to note here:
1) VSI will show only show latency values for RAID group LUNs, but not pool LUNs. For pool LUNs, %Busy is shown instead. So are you certain that you are working with an RG and not a pool?
2) There are known problems with VMware's disk latency alarm. Please take a look at these:
You may in fact find that nothing is wrong, but the alarm is incorrectly triggering.
I agree with RRR, use analyser to determine if the array has latency and work outwords from there. It could be an issue somewhere else in the I/O path or in VMware.