From: Kanchan Joshi <joshi.k@samsung.com>
To: linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org
Cc: tytso@mit.edu, adilger.kernel@dilger.ca, jack@suse.com,
viro@zeniv.linux.org.uk, darrick.wong@oracle.com,
axboe@kernel.dk, jrdr.linux@gmail.com, ebiggers@google.com,
jooyoung.hwang@samsung.com, chur.lee@samsung.com,
prakash.v@samsung.com, Kanchan Joshi <joshi.k@samsung.com>
Subject: [PATCH 0/2] fs,ext4,jbd2: Specifying write-hint for Ext4 journal
Date: Mon, 10 Dec 2018 18:20:02 +0530 [thread overview]
Message-ID: <1544446204-5291-1-git-send-email-joshi.k@samsung.com> (raw)
In-Reply-To: CGME20181210125245epcas2p202bc4336e91a55cee3786ed6abffea05@epcas2p2.samsung.com
For NAND-based SSDs, mixing of data with different life-time reduces
efficiency of garbage-collection. During FS operations, series of journal
updates will follow/precede series of data/meta updates, causing intermixing
inside SSD. By passing a write-hint (a.k.a stream) with journal, its writes
can be isolated from other meta/data writes, leading to performance/endurance
benefit on multi-stream SSD.
This is described in greater detail (along with results) in this "FAST 2018"
paper - https://www.usenix.org/system/files/conference/fast18/fast18-rho.pdf
This patch is split into two parts. First patch introduces APIs to send
write-hint with buffer-head. Second one implement "journal_writehint" mount
option (inspired from "journal_ioprio") in Ext4/JBD2.
Kanchan Joshi (2):
fs: introduce APIs to enable sending write-hint with buffer-head
fs/ext4,jbd2: Add support for passing write-hint with journal.
fs/buffer.c | 21 +++++++++++++++++++++
fs/ext4/super.c | 33 +++++++++++++++++++++++++++------
fs/jbd2/commit.c | 11 +++++++----
fs/jbd2/journal.c | 2 +-
fs/jbd2/revoke.c | 2 +-
include/linux/buffer_head.h | 3 +++
include/linux/jbd2.h | 7 +++++++
7 files changed, 67 insertions(+), 12 deletions(-)
--
2.7.4
next parent reply other threads:[~2018-12-10 12:52 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20181210125245epcas2p202bc4336e91a55cee3786ed6abffea05@epcas2p2.samsung.com>
2018-12-10 12:50 ` Kanchan Joshi [this message]
[not found] ` <CGME20181210125251epcas1p3023db72cc08d6b2f899141d551d53f61@epcas1p3.samsung.com>
2018-12-10 12:50 ` [PATCH 1/2] fs: introduce APIs to enable sending write-hint with buffer-head Kanchan Joshi
2018-12-10 13:49 ` Jan Kara
2018-12-11 11:57 ` Kanchan Joshi
[not found] ` <CGME20181210125256epcas1p1e4142cfefb9b21dfb8dad927fbd49143@epcas1p1.samsung.com>
2018-12-10 12:50 ` [PATCH 2/2] fs/ext4,jbd2: Add support for passing write-hint with journal Kanchan Joshi
2018-12-10 14:12 ` Jan Kara
2018-12-10 15:17 ` Jens Axboe
2018-12-10 15:41 ` Jan Kara
2018-12-10 15:44 ` Jens Axboe
2018-12-11 4:07 ` Dave Chinner
2018-12-11 5:07 ` Jens Axboe
2018-12-11 13:53 ` Kanchan Joshi
2018-12-11 21:54 ` Dave Chinner
2018-12-12 22:21 ` Dave Chinner
2018-12-19 14:10 ` Kanchan Joshi
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=1544446204-5291-1-git-send-email-joshi.k@samsung.com \
--to=joshi.k@samsung.com \
--cc=adilger.kernel@dilger.ca \
--cc=axboe@kernel.dk \
--cc=chur.lee@samsung.com \
--cc=darrick.wong@oracle.com \
--cc=ebiggers@google.com \
--cc=jack@suse.com \
--cc=jooyoung.hwang@samsung.com \
--cc=jrdr.linux@gmail.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=prakash.v@samsung.com \
--cc=tytso@mit.edu \
--cc=viro@zeniv.linux.org.uk \
/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).