linux-btrfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Qu Wenruo <quwenruo@cn.fujitsu.com>
To: linux-btrfs@vger.kernel.org
Cc: quwenruo@cn.fujitsu.com
Subject: [PATCH 0/9] btrfs: Replace the btrfs_workers with kernel workqueue
Date: Wed, 11 Sep 2013 16:52:29 +0800	[thread overview]
Message-ID: <1378889558-21514-1-git-send-email-quwenruo@cn.fujitsu.com> (raw)

Use kernel workqueue and kernel workqueue based new btrfs_workqueue_struct to replace
the old btrfs_workers.
The main goal is to reduce the redundant codes(800 lines vs 200 lines) and
try to get benefits from the latest workqueue changes.

About the performance, the test suite I used is bonnie++,
and there seems no significant regression.

The patched kernel get the following difference vs the 3.10 kernel on an HDD
with a two-way 4cores server.(10times each and compare the average)

putc:			-0.97%
getc:			+1.48%
random_del:		+2.38%
random_create:		-2.27%
seq_del			+0.94%

Other changes are smaller than 0.5% and can be ignored.
Since the tests are not enough and maybe unstable,
any further tests are welcome.

Qu Wenruo (9):
  btrfs: Cleanup the unused struct async_sched.
  btrfs: use kernel workqueue to replace the btrfs_workers functions
  btrfs: Added btrfs_workqueue_struct implemented ordered execution
    based on kernel workqueue
  btrfs: Add high priority workqueue support for btrfs_workqueue_struct
  btrfs: Use btrfs_workqueue_struct to replace the fs_info->workers
  btrfs: Use btrfs_workqueue_struct to replace the
    fs_info->delalloc_workers
  btrfs: Replace the fs_info->submit_workers with kernel workqueue.
  btrfs: Cleanup the old btrfs workqueue
  btrfs: Replace thread_pool_size with workqueue default value

 fs/btrfs/Makefile        |   5 +-
 fs/btrfs/async-thread.c  | 714 -----------------------------------------------
 fs/btrfs/async-thread.h  | 119 --------
 fs/btrfs/bwq.c           | 136 +++++++++
 fs/btrfs/bwq.h           |  67 +++++
 fs/btrfs/ctree.h         |  46 ++-
 fs/btrfs/delayed-inode.c |   9 +-
 fs/btrfs/dev-replace.c   |   1 -
 fs/btrfs/disk-io.c       | 238 ++++++----------
 fs/btrfs/extent-tree.c   |   6 +-
 fs/btrfs/inode.c         |  57 ++--
 fs/btrfs/ordered-data.c  |  11 +-
 fs/btrfs/ordered-data.h  |   4 +-
 fs/btrfs/qgroup.c        |  16 +-
 fs/btrfs/raid56.c        |  38 ++-
 fs/btrfs/reada.c         |   8 +-
 fs/btrfs/relocation.c    |   1 -
 fs/btrfs/scrub.c         |  78 +++---
 fs/btrfs/super.c         |  41 ++-
 fs/btrfs/volumes.c       |  25 +-
 fs/btrfs/volumes.h       |   3 +-
 21 files changed, 451 insertions(+), 1172 deletions(-)
 delete mode 100644 fs/btrfs/async-thread.c
 delete mode 100644 fs/btrfs/async-thread.h
 create mode 100644 fs/btrfs/bwq.c
 create mode 100644 fs/btrfs/bwq.h

-- 
1.8.4

             reply	other threads:[~2013-09-11  8:51 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-09-11  8:52 Qu Wenruo [this message]
2013-09-11  8:52 ` [PATCH 1/9] btrfs: Cleanup the unused struct async_sched Qu Wenruo
2013-09-11  8:52 ` [PATCH 2/9] btrfs: use kernel workqueue to replace the btrfs_workers functions Qu Wenruo
2013-09-11 13:02   ` Stefan Behrens
2013-09-12  0:56     ` Qu Wenruo
2013-09-11  8:52 ` [PATCH 3/9] btrfs: Added btrfs_workqueue_struct implemented ordered execution based on kernel workqueue Qu Wenruo
2013-09-11  8:52 ` [PATCH 4/9] btrfs: Add high priority workqueue support for btrfs_workqueue_struct Qu Wenruo
2013-09-11  8:52 ` [PATCH 5/9] btrfs: Use btrfs_workqueue_struct to replace the fs_info->workers Qu Wenruo
2013-09-11  8:52 ` [PATCH 6/9] btrfs: Use btrfs_workqueue_struct to replace the fs_info->delalloc_workers Qu Wenruo
2013-09-11  8:52 ` [PATCH 7/9] btrfs: Replace the fs_info->submit_workers with kernel workqueue Qu Wenruo
2013-09-11  8:52 ` [PATCH 8/9] btrfs: Cleanup the old btrfs workqueue Qu Wenruo
2013-09-11 17:39   ` Zach Brown
2013-09-11  8:52 ` [PATCH 9/9] btrfs: Replace thread_pool_size with workqueue default value Qu Wenruo

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=1378889558-21514-1-git-send-email-quwenruo@cn.fujitsu.com \
    --to=quwenruo@cn.fujitsu.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 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).