On Thu, Apr 20, 2006 at 11:28:50AM +0200, George Magklaras wrote: > Hi Ray, > > Sorry, I lost the thread on my browser. I have looked at the figures and > no I do not see an excessive number of page faults. The vmstat you > indicated on a very quiet system does indeed point to an unusually high > number of interrupts. > > If you still have this issue, try booting on a uniprocessor kernel or > boot with the 'noapic' option and see if you face the symptom or your > system boots properly. I also note that the kernel you mentioned did not > appear to be the latest. So, I would up2date the system, see if the > problem goes away and then on the up-to-date kernel (2.6.9-34.ELsmp as > we speak) boot with the noapic option and see if you see a difference. I have tried noapic mode, but I do not remember the results unfortunately. Will give it a shot again and document. Also will upgrade the kernel, but just a side note -- I built a custom kernel based on 2.6.16 and the load is a *lot* closer to where I would expect it. Well not quite -- but the I/O "glitches" are gone although the load still never gets to 0.00 even on a completely idle box. Need to compare vmstat output from that kernel to what I'm using now. I suspect the combo of the ata_piix driver and software raid, but need a way to prove or disprove that connection. :) Thanks for the help, Ray -- redhat-list mailing list unsubscribe mailto:redhat-list-request@xxxxxxxxxx?subject=unsubscribe https://www.redhat.com/mailman/listinfo/redhat-list
