I am running an FC13 (fedora core) system with 6 x 2TB disks, software raid5. The machine has 4gb ram, 4cores at 2.66mhz
frequently disk & writes reads hang for periods of up 30 seconds.
for example:
at other times the same request is serviced immediately.
I have tried changing the IO scheduler from cfq to deadline but it does not help.
I cannot find any logs for the software raid process (md1_raid5)
Does anyone have any clues as to what is going wrong here?
Or how I can debug the kernel to see why the system is hanging.