* question: should io_is_direct really return true for DAX inodes?
@ 2015-10-29 14:32 Jeff Moyer
2015-10-29 19:37 ` Dan Williams
0 siblings, 1 reply; 3+ messages in thread
From: Jeff Moyer @ 2015-10-29 14:32 UTC (permalink / raw)
To: dan j. williams; +Cc: linux-nvdimm, linux-fsdevel, Dave Chinner
Hi,
I'm concerned that applications that used to run out of page cache will
experience a performance degradation when being forced into doing I/O
directly to the backing store. What do others think?
Cheers,
Jeff
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: question: should io_is_direct really return true for DAX inodes?
2015-10-29 14:32 question: should io_is_direct really return true for DAX inodes? Jeff Moyer
@ 2015-10-29 19:37 ` Dan Williams
2015-10-29 21:09 ` Dave Chinner
0 siblings, 1 reply; 3+ messages in thread
From: Dan Williams @ 2015-10-29 19:37 UTC (permalink / raw)
To: Jeff Moyer; +Cc: linux-nvdimm, linux-fsdevel, Dave Chinner
[ reply-all re-send, sorry for the duplicate Jeff. ]
On Thu, Oct 29, 2015 at 11:32 PM, Jeff Moyer <jmoyer@redhat.com> wrote:
> Hi,
>
> I'm concerned that applications that used to run out of page cache will
> experience a performance degradation when being forced into doing I/O
> directly to the backing store. What do others think?
>
I would think this is only a problem in the case where the media is
orders of magnitude slower than page cache. That isn't the case with
pmem.
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: question: should io_is_direct really return true for DAX inodes?
2015-10-29 19:37 ` Dan Williams
@ 2015-10-29 21:09 ` Dave Chinner
0 siblings, 0 replies; 3+ messages in thread
From: Dave Chinner @ 2015-10-29 21:09 UTC (permalink / raw)
To: Dan Williams; +Cc: Jeff Moyer, linux-nvdimm, linux-fsdevel, Dave Chinner
On Fri, Oct 30, 2015 at 04:37:36AM +0900, Dan Williams wrote:
> [ reply-all re-send, sorry for the duplicate Jeff. ]
>
> On Thu, Oct 29, 2015 at 11:32 PM, Jeff Moyer <jmoyer@redhat.com> wrote:
> > Hi,
> >
> > I'm concerned that applications that used to run out of page cache will
> > experience a performance degradation when being forced into doing I/O
> > directly to the backing store. What do others think?
>
> I would think this is only a problem in the case where the media is
> orders of magnitude slower than page cache. That isn't the case with
> pmem.
If you're really concerned, I'm addressing this on XFS by making DAX
per-inode selectable (i.e the mount option needs to die). In which
case, users can have the best of both worlds - files marked as DAX
use DAX/direct IO, files that aren't marked can cache and suffer the
lower performance that all that page allocation, dirty tracking and
writeback via memcpy entails..
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-10-29 21:10 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-10-29 14:32 question: should io_is_direct really return true for DAX inodes? Jeff Moyer
2015-10-29 19:37 ` Dan Williams
2015-10-29 21:09 ` Dave Chinner
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).