Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-26 Thread Peter Zijlstra
On Tue, Nov 26, 2013 at 03:31:06PM +1100, NeilBrown wrote: > The stack trace in the previous email seemed to suggest that a process was > blocking inside a wake_up call, but it wasn't at all conclusive. And I've > seen a few wake_ups in other stack traces which seem to be connected with > other

Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-26 Thread Peter Zijlstra
On Tue, Nov 26, 2013 at 03:31:06PM +1100, NeilBrown wrote: The stack trace in the previous email seemed to suggest that a process was blocking inside a wake_up call, but it wasn't at all conclusive. And I've seen a few wake_ups in other stack traces which seem to be connected with other

Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-25 Thread NeilBrown
On Mon, 25 Nov 2013 10:53:23 +0100 Peter Zijlstra wrote: > On Mon, Nov 25, 2013 at 10:35:22AM +1100, NeilBrown wrote: > > Ingo/Peter: is it considered OK to call wake_up while holding a spinlock? > > Yes, very much so. Doing a wakeup isn't _that_ expensive. Oh good. Thanks. > > > Could

Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-25 Thread Peter Zijlstra
On Mon, Nov 25, 2013 at 10:35:22AM +1100, NeilBrown wrote: > Ingo/Peter: is it considered OK to call wake_up while holding a spinlock? Yes, very much so. Doing a wakeup isn't _that_ expensive. > Could "sleeping spinlocks" affect this at all? (some sample stack traces are > below). Not entirely

Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-25 Thread Peter Zijlstra
On Mon, Nov 25, 2013 at 10:35:22AM +1100, NeilBrown wrote: Ingo/Peter: is it considered OK to call wake_up while holding a spinlock? Yes, very much so. Doing a wakeup isn't _that_ expensive. Could sleeping spinlocks affect this at all? (some sample stack traces are below). Not entirely sure,

Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-25 Thread NeilBrown
On Mon, 25 Nov 2013 10:53:23 +0100 Peter Zijlstra pet...@infradead.org wrote: On Mon, Nov 25, 2013 at 10:35:22AM +1100, NeilBrown wrote: Ingo/Peter: is it considered OK to call wake_up while holding a spinlock? Yes, very much so. Doing a wakeup isn't _that_ expensive. Oh good. Thanks.

Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-24 Thread NeilBrown
On Sat, 23 Nov 2013 11:22:05 +0800 fengguang...@intel.com wrote: > Shaohua, > > FYI, we are still seeing this bug.. dmesg attached. Thanks for the report. However the dmesg you attached doesn't mention: kernel BUG at drivers/md/raid5.c:693! at all. It is quite different.

Re: kernel BUG at drivers/md/raid5.c:693!

2013-11-24 Thread NeilBrown
On Sat, 23 Nov 2013 11:22:05 +0800 fengguang...@intel.com wrote: Shaohua, FYI, we are still seeing this bug.. dmesg attached. Thanks for the report. However the dmesg you attached doesn't mention: kernel BUG at drivers/md/raid5.c:693! at all. It is quite different. The BUG