Relative hrtimers with a large timeout value might end up as negative timer values, when the current time is added in hrtimer_start(). This in turn is causing the clockevents_set_next() function to set an huge timeout and sleep for quite a long time when we have a clock source which is capable of long sleeps like HPET. With PIT this almost goes unnoticed as the maximum delta is ~27ms. The non-hrt/nohz code sorts this out in the next timer interrupt, so we never noticed that problem which has been there since the first day of hrtimers. This bug became more apparent in 2.6.24 which activates HPET on more hardware. Solution: apply the folowing patch: http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=62f0f61e6673e67151a7c8c0f9a09c7ea43fe2b5 Reproducible: Always
Fixed in 2.6.23.10: http://www.kernel.org/pub/linux/kernel/v2.6/ChangeLog-2.6.23.10
Included in >=gentoo-sources-2.6.23-r4
Sorry for the bugspam, I'm going to add back kernel alias until we figure out what were doing.
latest update from 2008 please close
