On Thu, Apr 11, 2013 at 10:57:08PM -0400, Theodore Ts'o wrote: > On Thu, Apr 11, 2013 at 11:33:35PM +0200, Jan Kara wrote: > > I think it might be more enlightening if Mel traced which process in > > which funclion is holding the buffer lock. I suspect we'll find out that > > the flusher thread has submitted the buffer for IO as an async write and > > thus it takes a long time to complete in presence of reads which have > > higher priority. > > That's an interesting theory. If the workload is one which is very > heavy on reads and writes, that could explain the high latency. That > would explain why those of us who are using primarily SSD's are seeing > the problems, because would be reads are nice and fast. > > If that is the case, one possible solution that comes to mind would be > to mark buffer_heads that contain metadata with a flag, so that the > flusher thread can write them back at the same priority as reads.
Ext4 is already using REQ_META for this purpose. I'm surprised that no-one has suggested "change the IO elevator" yet..... Cheers, Dave. -- Dave Chinner da...@fromorbit.com -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
