All of lore.kernel.org
 help / color / mirror / Atom feed
From: Josef Bacik <josef@toxicpanda.com>
To: linux-btrfs@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH v5 0/8] A variety of lock contention fixes
Date: Fri, 18 Dec 2020 14:24:18 -0500	[thread overview]
Message-ID: <cover.1608319304.git.josef@toxicpanda.com> (raw)

v4->v5:
- Added "btrfs: remove bogus BUG_ON in alloc_reserved_tree_block", as Nikolay
  pointed out I needed to explain why we no longer needed one of the delayed ref
  flushes, which led me down the rabbit hole of trying to understand why it
  wasn't a problem anymore.  Turned out the BUG_ON() is bogus.
- Added "btrfs: move delayed ref flushing for qgroup into qgroup helper",
  instead of removing the flushing for qgroups completely, we still sort of need
  it, even though it's actually still broken, so I've moved it into the qgroup
  helper.
- Added Nikolay's rb for the last patch.

v3->v4:
- I accidentally sent out the v1 version of these patches, because I had fixed
  them on another machine.  This is the proper set with the changes from v2 that
  are properly rebased onto misc-next.

v2->v3:
- Added Nikolay's reviewed by for the second patch.
- Rebased onto the latest misc-next.

v1->v2:
- Fixed the log messages that Nikolay pointed out.
- Added Nikolay's reviewed by for the first patch.
- Removed the unneeded mb for flushing.

--- Original email ---
Hello,

I've been running some stress tests recently in order to try and reproduce some
problems I've tripped over in relocation.  Most of this series is a reposting of
patches I wrote when debugging related issues for Zygo that got lost.  I've
updated one of them to make the lock contention even better, making it so I have
to ramp up my stress test loops because it now finishes way too fast.  Thanks,

Josef

Josef Bacik (8):
  btrfs: do not block on deleted bgs mutex in the cleaner
  btrfs: only let one thread pre-flush delayed refs in commit
  btrfs: delayed refs pre-flushing should only run the heads we have
  btrfs: only run delayed refs once before committing
  btrfs: move delayed ref flushing for qgroup into qgroup helper
  btrfs: remove bogus BUG_ON in alloc_reserved_tree_block
  btrfs: stop running all delayed refs during snapshot
  btrfs: run delayed refs less often in commit_cowonly_roots

 fs/btrfs/block-group.c | 11 +++--
 fs/btrfs/delayed-ref.h | 12 +++---
 fs/btrfs/extent-tree.c |  3 +-
 fs/btrfs/transaction.c | 91 +++++++++++++++++++++---------------------
 4 files changed, 60 insertions(+), 57 deletions(-)

-- 
2.26.2


             reply	other threads:[~2020-12-18 19:25 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-18 19:24 Josef Bacik [this message]
2020-12-18 19:24 ` [PATCH v5 1/8] btrfs: do not block on deleted bgs mutex in the cleaner Josef Bacik
2020-12-18 19:24 ` [PATCH v5 2/8] btrfs: only let one thread pre-flush delayed refs in commit Josef Bacik
2021-01-08 16:01   ` David Sterba
2021-01-11  8:33     ` Nikolay Borisov
2021-01-11 21:50       ` David Sterba
2021-01-12  9:17         ` Nikolay Borisov
2021-01-26 17:36           ` David Sterba
2020-12-18 19:24 ` [PATCH v5 3/8] btrfs: delayed refs pre-flushing should only run the heads we have Josef Bacik
2020-12-18 19:24 ` [PATCH v5 4/8] btrfs: only run delayed refs once before committing Josef Bacik
2020-12-18 19:24 ` [PATCH v5 5/8] btrfs: move delayed ref flushing for qgroup into qgroup helper Josef Bacik
2020-12-18 19:24 ` [PATCH v5 6/8] btrfs: remove bogus BUG_ON in alloc_reserved_tree_block Josef Bacik
2020-12-18 19:24 ` [PATCH v5 7/8] btrfs: stop running all delayed refs during snapshot Josef Bacik
2020-12-18 19:24 ` [PATCH v5 8/8] btrfs: run delayed refs less often in commit_cowonly_roots Josef Bacik
2021-01-26 17:51 ` [PATCH v5 0/8] A variety of lock contention fixes David Sterba

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=cover.1608319304.git.josef@toxicpanda.com \
    --to=josef@toxicpanda.com \
    --cc=kernel-team@fb.com \
    --cc=linux-btrfs@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.