On Wed, 2009-03-11 at 17:34 -0700, john stultz wrote: > I'm still a little baffled, but I figure I can try to reproduce this > myself. So I'm working setting up hercules environment here to see if I > can't trigger it. Any help with config or links to your environment > would be great. Ok. I've got this up and reproduced with the hercules emulator. A couple of interesting hints: * The issue seems to go away if we disable NO_HZ/dynticks in the .config * nohz=off does not affect the issue. * The issue also seems to go away if HZ is anything except 250 * Commenting out clocksource_adjust(), which does the clock steering, seems to avoid the issue. * When the problem triggers we don't seem to transfer to the TOD clock, and the jiffies clocksource seems to be in use. * The jiffies clocksource mult value seems to be ever increasing, again pointing to something wrong in the clock steering. * Reverting both 6c9bacb41c10 and 5cd1c9c5cf30 against 2.6-git did not seem to help the issue, as originally reported. I also reverted 49b5cf34727a as well just in case, and it didn't help either. That's about all I can get for today. I'm out of town until Monday, so I'll start digging back into it then. thanks -john -- To unsubscribe from this list: send the line "unsubscribe linux-s390" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html