On Tue, Nov 30, 2010 at 11:39:06AM +1100, Neil Brown wrote:
quoted text
> On Mon, 29 Nov 2010 14:05:36 -0800 "Darrick J. Wong" <djwong@us.ibm.com>
> wrote:
> 
> > On certain types of hardware, issuing a write cache flush takes a considerable
> > amount of time.  Typically, these are simple storage systems with write cache
> > enabled and no battery to save that cache after a power failure.  When we
> > encounter a system with many I/O threads that write data and then call fsync
> > after more transactions accumulate, ext4_sync_file performs a data-only flush,
> > the performance of which is suboptimal because each of those threads issues its
> > own flush command to the drive instead of trying to coordinate the flush,
> > thereby wasting execution time.
> > 
> > Instead of each fsync call initiating its own flush, there's now a flag to
> > indicate if (0) no flushes are ongoing, (1) we're delaying a short time to
> > collect other fsync threads, or (2) we're actually in-progress on a flush.
> > 
> > So, if someone calls ext4_sync_file and no flushes are in progress, the flag
> > shifts from 0->1 and the thread delays for a short time to see if there are any
> > other threads that are close behind in ext4_sync_file.  After that wait, the
> > state transitions to 2 and the flush is issued.  Once that's done, the state
> > goes back to 0 and a completion is signalled.
> 
> I haven't seen any of the preceding discussion do I might be missing
> something important, but this seems needlessly complex and intrusive.
> In particular, I don't like adding code to md to propagate these timings up
> to the fs, and I don't the arbitrary '2ms' number.
> 
> Would it not be sufficient to simply gather flushes while a flush is pending.
> i.e
>   - if no flush is pending, set the 'flush pending' flag, submit a flush,
>     then clear the flag.
>   - if a flush is pending, then wait for it to complete, and then submit a
>     single flush on behalf of all pending flushes.
> 
> That way when flush is fast, you do a flush every time, and when it is slow
> you gather multiple flushes together.
> I think it would issues a few more flushes than your scheme, but it would be
> a much neater solution.  Have you tried that and found it to be insufficient?

Some time ago I actually did test the patchset with the schedule_hrtimeout
removed, which I think is fairly close to what you've suggested.  As I recall,
it did help a bit, though not as much as also instituting the wait to limit the
% of disk execution time spent on flushes.  That said, I think you might be
right about the completion races, so I'll try to code up your suggestion to
see what happens with a newer kernel.

--D
quoted text
> 
> Thanks,
> NeilBrown
> 
> 
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/