writeback: add new tracepoints
in [Kernel]
|
Prev: hw-breakpoints, kgdb, x86: add a flag topassDIE_DEBUG notification
Next: writeback: optimize periodic bdi thread wakeups
From: Christoph Hellwig on 23 Jul 2010 12:30 On Fri, Jul 23, 2010 at 06:05:54PM +0300, Artem Bityutskiy wrote: > From: Artem Bityutskiy <Artem.Bityutskiy(a)nokia.com> > > Add 2 new trace points to the periodic write-back wake up case, just like we do > in the 'bdi_queue_work()' function. Namely, introduce: > > 1. trace_writeback_wakeup(bdi) > 2. trace_writeback_wakeup_nothread(bdi) > > The first event is triggered every time we wake up a bdi thread to start > periodic background write-out. The second event is triggered only when the bdi > thread does not exist and should be created by the forker thread. > > This patch was suggested by Dave Chinner <david(a)fromorbit.com> As mentioned before doing the wakeup just for the case where we really wake up the flusher thead is much better. It's not 100% clear for bdi_queue_work as we queue the work in either case, but I'd prefer to fix that one up as well (not in your series anyway) -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Artem Bityutskiy on 24 Jul 2010 02:10
On Fri, 2010-07-23 at 12:29 -0400, Christoph Hellwig wrote: > On Fri, Jul 23, 2010 at 06:05:54PM +0300, Artem Bityutskiy wrote: > > From: Artem Bityutskiy <Artem.Bityutskiy(a)nokia.com> > > > > Add 2 new trace points to the periodic write-back wake up case, just like we do > > in the 'bdi_queue_work()' function. Namely, introduce: > > > > 1. trace_writeback_wakeup(bdi) > > 2. trace_writeback_wakeup_nothread(bdi) > > > > The first event is triggered every time we wake up a bdi thread to start > > periodic background write-out. The second event is triggered only when the bdi > > thread does not exist and should be created by the forker thread. > > > > This patch was suggested by Dave Chinner <david(a)fromorbit.com> > > As mentioned before doing the wakeup just for the case where we > really wake up the flusher thead is much better. It's not 100% > clear for bdi_queue_work as we queue the work in either case, but > I'd prefer to fix that one up as well (not in your series anyway) OK, I'll do it your way. Many thanks for review! -- Best Regards, Artem Bityutskiy (Артём Битюцкий) -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |