Date:   Wed, 13 Dec 2017 17:10:02 -0500
From:   Jeff Layton <jlayton@...nel.org>
To:     "J. Bruce Fields" <bfields@...ldses.org>
Cc:     linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
        hch@....de, neilb@...e.de, amir73il@...il.com, jack@...e.de,
        viro@...iv.linux.org.uk
Subject: Re: [PATCH 00/19] fs: rework and optimize i_version handling in
 filesystems

On Wed, 2017-12-13 at 15:14 -0500, Jeff Layton wrote:
> On Wed, 2017-12-13 at 10:05 -0500, J. Bruce Fields wrote:
> > This is great, thanks.
> > 
> > On Wed, Dec 13, 2017 at 09:19:58AM -0500, Jeff Layton wrote:
> > > With this, we reduce inode metadata updates across all 3 filesystems
> > > down to roughly the frequency of the timestamp granularity, particularly
> > > when it's not being queried (the vastly common case).
> > > 
> > > The pessimal workload here is 1 byte writes, and it helps that
> > > significantly. Of course, that's not what we'd consider a real-world
> > > workload.
> > > 
> > > A tiobench-example.fio workload also shows some modest performance
> > > gains, and I've gotten mails from the kernel test robot that show some
> > > significant performance gains on some microbenchmarks (case-msync-mt in
> > > the vm-scalability testsuite to be specific), with an earlier version of
> > > this set.
> > > 
> > > With larger writes, the gains with this patchset mostly vaporize,
> > > but it does not seem to cause performance to regress anywhere, AFAICT.
> > > 
> > > I'm happy to run other workloads if anyone can suggest them.
> > > 
> > > At this point, the patchset works and does what it's expected to do in
> > > my own testing. It seems like it's at least a modest performance win
> > > across all 3 major disk-based filesystems. It may also encourage others
> > > to implement i_version as well since it reduces the cost.
> > 
> > Do you have an idea what the remaining cost is?
> > 
> > Especially in the ext4 case, are you still able to measure any
> > difference in performance between the cases where i_version is turned on
> > and off, after these patches?
> 
> Attached is a fio jobfile + the output from 3 different runs using it
> with ext4. This one is using 4k writes. There was no querying of
> i_version during the runs.  I've done several runs with each and these
> are pretty representative of the results:
> 
> old = 4.15-rc3, i_version enabled
> ivers = 4.15-rc3 + these patches, i_version enabled
> noivers = 4.15-rc3 + these patches, i_version disabled
> 
> To snip out the run status lines:
> 
> old:
> WRITE: bw=85.6MiB/s (89.8MB/s), 9994KiB/s-11.1MiB/s (10.2MB/s-11.7MB/s), io=50.2GiB (53.8GB), run=600001-600001msec
> 
> ivers:
> WRITE: bw=110MiB/s (115MB/s), 13.5MiB/s-14.2MiB/s (14.1MB/s-14.9MB/s), io=64.3GiB (69.0GB), run=600001-600001msec
> 
> noivers:
> WRITE: bw=117MiB/s (123MB/s), 14.2MiB/s-15.2MiB/s (14.9MB/s-15.9MB/s), io=68.7GiB (73.8GB), run=600001-600001msec
> 
> So, I see some performance degradation with -o iversion compared to not
> having it enabled (maybe due to the extra atomic fetches?), but this set
> erases most of the difference.
> 
> > > 
> > > [1]: On ext4 it must be turned on with the i_version mount option,
> > >      mostly due to fears of incurring this impact, AFAICT.
> > 
> > So xfs and btrfs both have i_version updates on by default at this
> > point?  (Assuming the filesystem's created with recent enough tools,
> > etc.)
> > 
> 
> Yes. With xfs and btrfs, I don't think you can disable it these days.
> 

...and for completeness, I'm seeing better performance with 4k writes on
xfs with this set as well:


old:
WRITE: bw=86.7MiB/s (90.0MB/s), 9689KiB/s-11.7MiB/s (9921kB/s-12.2MB/s), io=50.8GiB (54.6GB), run=600001-600002msec

new:
WRITE: bw=129MiB/s (136MB/s), 15.8MiB/s-16.6MiB/s (16.6MB/s-17.4MB/s), io=75.9GiB (81.5GB), run=600001-600001msec


btrfs doesn't show much change ... it's possible that that patch isn't
quite right:

old:
WRITE: bw=49.1MiB/s (51.5MB/s), 5656KiB/s-7011KiB/s (5792kB/s-7179kB/s), io=28.8GiB (30.9GB), run=600001-600003msec

new:
WRITE: bw=50.3MiB/s (52.7MB/s), 5753KiB/s-7264KiB/s (5891kB/s-7438kB/s), io=29.5GiB (31.6GB), run=600001-600002msec


This is with the kernel running in a KVM guest, virtio disk in guest
backed by a LVM volume on a bog-standard ssd. Performance
characteristics could be different on a different setup, but I think
this is encouraging.

Note that this patchset requires some prerequisite patches that Andrew
is carrying. The complete series is here for anyone who wants to play
with it:

https://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux.git/log/?h=iversion

-- 
Jeff Layton <jlayton@...nel.org>
View attachment "btrfs-new-4k" of type "text/plain" (13057 bytes)

View attachment "btrfs-old-4k" of type "text/plain" (13078 bytes)

View attachment "xfs-new-4k" of type "text/plain" (12469 bytes)

View attachment "xfs-old-4k" of type "text/plain" (12705 bytes)

Powered by blists - more mailing lists