From: James Bottomley <James.Bottomley@suse.de>
To: Mark Lord <kernel@teksavvy.com>
Cc: Greg Freemyer <greg.freemyer@gmail.com>,
Jeff Moyer <jmoyer@redhat.com>,
Christoph Hellwig <hch@infradead.org>,
Matthew Wilcox <matthew@wil.cx>, Josef Bacik <josef@redhat.com>,
Lukas Czerner <lczerner@redhat.com>,
tytso@mit.edu, linux-ext4@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
sandeen@redhat.com
Subject: Re: [PATCH 1/2] fs: Do not dispatch FITRIM through separate super_operation
Date: Thu, 18 Nov 2010 15:50:09 -0600 [thread overview]
Message-ID: <1290117009.11007.42.camel@mulgrave.site> (raw)
In-Reply-To: <4CE59E57.2090009@teksavvy.com>
On Thu, 2010-11-18 at 16:44 -0500, Mark Lord wrote:
> On 10-11-18 03:04 PM, Greg Freemyer wrote:
> >
> > 2) FITRIM doesn't leverage the fact the a TRIM command can handle
> > multiple ranges per TRIM command payload. I haven't seen any FITRIM
> > vs. wiper.sh benchmarks, so I don't know what impact that has in
> > practice. Mark Lord thought that this lacking feature would cause
> > FITRIM to take minutes or hours with some hardware. Especially early
> > generation SSDs.
>
> If FITRIM is still issuing single-range-at-a-time TRIMs,
> then I'd call that a BUG that needs fixing. Doing TRIM like that
> causes tons of unnecessary ERASE cycles, shortening the SSD lifetime.
> It really needs to batch them into groups of (up to) 64 ranges at a time
> (64 ranges fits into a single 512-byte parameter block).
Before we go gung ho on this, there's no evidence that N discontiguous
ranges in one command are any better than the ranges sent N times ...
the same amount of erase overhead gets sent on SSDs. However, we also
have to remember Thin Provisioning. Right at the moment WRITE SAME
seems to be preferred to UNMAP ... and WRITE SAME only has a single
effective range.
Now if you're thinking of multiple contiguous ranges because of the LBA
limits to TRIM, then yes, I'm fine with that because WRITE SAME doesn't
have that problem and we can do the translation in the SATL.
James
next prev parent reply other threads:[~2010-11-18 21:50 UTC|newest]
Thread overview: 106+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-18 7:36 [PATCH 1/2] fs: Do not dispatch FITRIM through separate super_operation Lukas Czerner
2010-11-18 7:36 ` [PATCH 2/2] ext4: Add EXT4_IOC_TRIM ioctl to handle batched discard Lukas Czerner
2010-11-19 16:19 ` Ted Ts'o
2010-11-19 16:26 ` Lukas Czerner
2010-11-20 1:37 ` Ted Ts'o
2010-11-18 13:06 ` [PATCH 1/2] fs: Do not dispatch FITRIM through separate super_operation Matthew Wilcox
2010-11-18 13:48 ` Josef Bacik
2010-11-18 14:19 ` Matthew Wilcox
2010-11-18 14:29 ` Christoph Hellwig
2010-11-18 17:19 ` James Bottomley
2010-11-18 17:22 ` Jeff Moyer
2010-11-18 17:41 ` James Bottomley
2010-11-18 20:04 ` Greg Freemyer
2010-11-18 20:04 ` Greg Freemyer
2010-11-18 21:42 ` Mark Lord
2010-11-18 21:44 ` Mark Lord
2010-11-18 21:50 ` James Bottomley [this message]
2010-11-18 22:07 ` Mark Lord
2010-11-19 1:33 ` Ted Ts'o
2010-11-19 3:44 ` Mark Lord
2010-11-19 3:44 ` Mark Lord
2010-11-19 3:44 ` Mark Lord
2010-11-19 13:58 ` Jeff Moyer
2010-11-18 23:52 ` Martin K. Petersen
2010-11-19 0:34 ` Mark Lord
2010-11-19 1:16 ` Greg Freemyer
2010-11-19 1:16 ` Greg Freemyer
2010-11-19 11:55 ` Christoph Hellwig
2010-11-19 14:01 ` Mark Lord
2010-11-19 14:06 ` Christoph Hellwig
2010-11-19 14:48 ` Mark Lord
2010-11-19 14:54 ` Christoph Hellwig
2010-11-19 15:24 ` Mark Lord
2010-11-19 15:34 ` Christoph Hellwig
2010-11-19 16:20 ` Greg Freemyer
2010-11-19 16:38 ` Christoph Hellwig
2010-11-19 18:06 ` Lukas Czerner
2010-11-19 18:10 ` Lukas Czerner
2010-11-19 18:14 ` Lukas Czerner
2010-11-19 19:29 ` Chris Mason
2010-11-19 1:49 ` Martin K. Petersen
2010-11-19 3:42 ` Mark Lord
2010-11-18 18:05 ` Jamie Lokier
2010-11-18 19:32 ` Markus Trippelsdorf
2010-11-18 21:45 ` Mark Lord
2010-11-18 21:50 ` Markus Trippelsdorf
2010-11-18 22:09 ` Mark Lord
2010-11-18 17:35 ` Lukas Czerner
2010-11-19 12:16 ` Steven Whitehouse
2010-11-19 13:53 ` Mark Lord
2010-11-19 14:02 ` Ted Ts'o
2010-11-19 14:10 ` Christoph Hellwig
2010-11-19 14:10 ` Christoph Hellwig
2010-11-19 14:10 ` Christoph Hellwig
2010-11-19 15:37 ` Ted Ts'o
2010-11-19 15:50 ` Christoph Hellwig
2010-11-19 15:50 ` Christoph Hellwig
2010-11-19 15:50 ` Christoph Hellwig
2010-11-19 16:16 ` Ted Ts'o
2010-11-19 14:50 ` Mark Lord
2010-11-19 14:50 ` Mark Lord
2010-11-19 14:50 ` Mark Lord
2010-11-19 15:35 ` Mark Lord
2010-11-19 15:35 ` Mark Lord
2010-11-19 15:35 ` Mark Lord
2010-11-19 15:44 ` Lukas Czerner
2010-11-19 16:30 ` Ted Ts'o
2010-11-19 22:49 ` Mark Lord
2010-11-19 22:49 ` Mark Lord
2010-11-19 22:49 ` Mark Lord
2010-11-25 2:48 ` Mark Lord
2010-11-25 2:48 ` Mark Lord
2010-11-25 2:48 ` Mark Lord
2010-11-25 4:23 ` Martin K. Petersen
2010-11-25 14:44 ` Mark Lord
2010-11-25 4:41 ` Greg Freemyer
2010-11-25 4:41 ` Greg Freemyer
2010-11-25 14:53 ` Mark Lord
2010-11-25 16:24 ` Greg Freemyer
2010-11-25 16:24 ` Greg Freemyer
2010-11-26 13:49 ` Mark Lord
2010-11-26 14:00 ` Lukas Czerner
2010-11-18 17:55 ` Chris Mason
2010-12-03 18:24 ` Ric Wheeler
2010-11-18 21:37 ` Mark Lord
2010-11-19 11:09 ` Christoph Hellwig
2010-11-19 13:54 ` Mark Lord
2010-11-19 14:40 ` Chris Mason
2010-11-19 14:53 ` Mark Lord
2010-11-19 14:57 ` Christoph Hellwig
2010-11-19 15:21 ` Mark Lord
2010-12-07 9:27 ` Christoph Hellwig
2010-12-07 16:52 ` Chris Mason
2011-06-02 4:52 ` Kyungmin Park
2011-06-02 8:14 ` Lukas Czerner
2011-06-03 2:06 ` Dave Chinner
2011-06-03 2:06 ` Dave Chinner
2011-06-03 4:25 ` Kyungmin Park
2011-06-03 4:25 ` Kyungmin Park
2010-11-19 15:30 ` Mark Lord
2010-11-21 19:07 ` Valdis.Kletnieks
2010-11-21 20:20 ` James Bottomley
2010-11-18 14:31 ` Josef Bacik
2010-11-18 14:36 ` Tao Ma
2010-11-19 15:41 ` Ted Ts'o
2010-11-19 15:50 ` Christoph Hellwig
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=1290117009.11007.42.camel@mulgrave.site \
--to=james.bottomley@suse.de \
--cc=greg.freemyer@gmail.com \
--cc=hch@infradead.org \
--cc=jmoyer@redhat.com \
--cc=josef@redhat.com \
--cc=kernel@teksavvy.com \
--cc=lczerner@redhat.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=matthew@wil.cx \
--cc=sandeen@redhat.com \
--cc=tytso@mit.edu \
/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.