any advice to find root cause of "Falling back to HPET" ?

Bond Masuda bond.masuda at jlbond.com
Sun May 23 20:01:14 CDT 2010


On Sun, 2010-05-23 at 21:11 -0300, Andrew Reid wrote:
> A few  random thoughts:
> 
> Any chance the RAID is still rebuilding.
> 
> Is slow unit truly slower, that is  does it take longer as YOU measure 
> it to do a significant task. I ask because a bad clock will would make 
> it report longer times due to time measurement errors.
> 
> A comparison of the actual number of interrupts (cat /proc/interrupts) 
> on both machines after they have been up for similar periods, doing 
> similar things may give a hint as to who has 'stolen' your CPU.

Yes, tasks do take longer in real time. (a lot longer)

The RAID was not rebuilding.

The 2nd chassis started behaving strangely, and upon reboot would not
finish booting. The guys at the hosting company said the server was
still booting up after 15 minutes and going VERY VERY slowly. They
finally gave up and decided to swap chassis again (on 3rd chassis now).

This time around, on 3rd chassis, the "lost ticks" are no longer, the
server is fast/normal again, and all is well. I just can't believe we
ran into 2 servers with the same issue back to back??? (the guys at the
hosting company are usually great, but it almost makes me doubt that
they did the 1st chassis swap??)

Anyway, all is well again....  bizarre weekend indeed.
-Bond



More information about the Linux-PowerEdge mailing list