Messages in this thread | | | Date | Tue, 11 Sep 2012 16:50:32 -0700 | From | John Stultz <> | Subject | Re: BUG: soft lockup - CPU#1 stuck for 1024s! |
| |
On 09/11/2012 04:41 PM, Fengguang Wu wrote: > On Mon, Sep 10, 2012 at 10:06:33AM -0700, John Stultz wrote: >> On 09/09/2012 12:59 AM, Fengguang Wu wrote: >>> Hi John, >>> >>> The below lockup warning pops up very occasionally in kvm guest >>> kernels and it's bisected down to >>> >>> commit 2a8c0883c3cfffcc148ea606e2a4e7453cd75e73 >>> Author: John Stultz <john.stultz@linaro.org> >>> Date: Fri Jul 13 01:21:56 2012 -0400 >>> >>> time: Move xtime_nsec adjustment underflow handling timekeeping_adjust >>> >>> [ 8.340327] Freeing unused kernel memory: 460k freed >>> [ 1107.515496] [sched_delayed] sched: RT throttling activated >>> [ 1107.516439] BUG: soft lockup - CPU#1 stuck for 1024s! [swapper/1:0] >> >> Thanks so much for sending this. One detail I'm curious about is >> that these kernels from the Bug messages seem to be v3.6-rc1 or >> earlier. >> >> Ingo had a fix 1d17d17484d40f2d5b35c79518597a2b25296996 ("time: Fix >> adjustment cleanup bug in timekeeping_adjust") that landed in >> 3.6-rc2 >> >> Has this issue actually been seen on a 3.6-rc2+ kernel? > Nope. I tested -rc5 for 10000+ boots and it's obviously free from the bug. > Sorry for the noise!
No worries. Thanks so much for following up on this, and your continued testing! -john
| |