Linux XFS filesystem development
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <djwong@kernel.org>
To: Leah Rumancik <leah.rumancik@gmail.com>
Cc: linux-xfs@vger.kernel.org
Subject: Re: [PATCH 5.15 CANDIDATE 0/4] xfs stable candidates for 5.15.y (part 2)
Date: Fri, 8 Jul 2022 08:50:59 -0700	[thread overview]
Message-ID: <YshSY9sXGg9Ox1cM@magnolia> (raw)
In-Reply-To: <20220707223828.599185-1-leah.rumancik@gmail.com>

On Thu, Jul 07, 2022 at 03:38:24PM -0700, Leah Rumancik wrote:
> Hello again,
> 
> These are a subset of the patches from the v1 5.15 part 1 which are
> not applicable to 5.10.y. These patches were rebased and applied on top
> of the accepted part 1 patches. 100 runs of each test on mulitple configs
> were completed and no regressions found.
> 
> Additional testing:
> c8c568259772 "xfs: don't include bnobt blocks when reserving free block pool"
>     Observed the hang before the patches but not after

Yep, that's the correct outcome.

> 919edbadebe1 "xfs: drop async cache flushes from CIL commits."
>     Ran dbench as in the commit and confirmed performance improved
> 
> clients   before      after
> 1         220.493     260.359
> 8         732.807     1068.64
> 16        749.677     1293.06
> 32        737.9       1247.17
> 128       680.674     1077.0
> 512       602.674     884.48

Daaaaang. :)

Acked-by: Darrick J. Wong <djwong@kernel.org>

--D


> Thanks,
> Leah
> 
> 
> Darrick J. Wong (2):
>   xfs: only run COW extent recovery when there are no live extents
>   xfs: don't include bnobt blocks when reserving free block pool
> 
> Dave Chinner (2):
>   xfs: run callbacks before waking waiters in
>     xlog_state_shutdown_callbacks
>   xfs: drop async cache flushes from CIL commits.
> 
>  fs/xfs/xfs_bio_io.c      | 35 ------------------------
>  fs/xfs/xfs_fsops.c       |  2 +-
>  fs/xfs/xfs_linux.h       |  2 --
>  fs/xfs/xfs_log.c         | 58 +++++++++++++++++-----------------------
>  fs/xfs/xfs_log_cil.c     | 42 +++++++++--------------------
>  fs/xfs/xfs_log_priv.h    |  3 +--
>  fs/xfs/xfs_log_recover.c | 24 ++++++++++++++++-
>  fs/xfs/xfs_mount.c       | 12 +--------
>  fs/xfs/xfs_mount.h       | 15 +++++++++++
>  fs/xfs/xfs_reflink.c     |  5 +++-
>  fs/xfs/xfs_super.c       |  9 -------
>  11 files changed, 82 insertions(+), 125 deletions(-)
> 
> -- 
> 2.37.0.rc0.161.g10f37bed90-goog
> 

      parent reply	other threads:[~2022-07-08 15:51 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-07 22:38 [PATCH 5.15 CANDIDATE 0/4] xfs stable candidates for 5.15.y (part 2) Leah Rumancik
2022-07-07 22:38 ` [PATCH 5.15 CANDIDATE 1/4] xfs: only run COW extent recovery when there are no live extents Leah Rumancik
2022-07-07 22:38 ` [PATCH 5.15 CANDIDATE 2/4] xfs: don't include bnobt blocks when reserving free block pool Leah Rumancik
2022-07-07 22:38 ` [PATCH 5.15 CANDIDATE 3/4] xfs: run callbacks before waking waiters in xlog_state_shutdown_callbacks Leah Rumancik
2022-07-07 22:38 ` [PATCH 5.15 CANDIDATE 4/4] xfs: drop async cache flushes from CIL commits Leah Rumancik
2022-07-08 15:50 ` Darrick J. Wong [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=YshSY9sXGg9Ox1cM@magnolia \
    --to=djwong@kernel.org \
    --cc=leah.rumancik@gmail.com \
    --cc=linux-xfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox