From: Eric Sandeen <sandeen@redhat.com>
To: "Ted Ts'o" <tytso@mit.edu>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
Mike Snitzer <snitzer@redhat.com>,
Jens Axboe <jaxboe@fusionio.com>,
"James.Bottomley@hansenpartnership
Subject: Re: I/O topology fixes for big physical block size
Date: Thu, 30 Sep 2010 12:07:02 -0500 [thread overview]
Message-ID: <4CA4C3B6.9000104@redhat.com> (raw)
In-Reply-To: <20100930163047.GA4098@thunk.org>
On 09/30/2010 11:30 AM, Ted Ts'o wrote:
> On Tue, Sep 28, 2010 at 04:36:42PM -0500, Eric Sandeen wrote:
>> Ok, then it sounds like mkfs.ext4's refusal to make fs blocksize less
>> than device physical sectorsize without -F is broken, and that should
>> be removed. I'd say issue a warning in the case but if there's a 16k
>> physical device maybe there's no point in warning either?
>
> If the device physical sectorsize is that big, should we perhaps use
> that as a hint to align writes to that blocks aligned with that
> physical sectorsize? Right now we use the optimal I/O size, but if
> the optimal I/O size is not specified and the physical sectorsize is,
I can't keep track of all the parameters, is it ever true that optimal
I/O size isn't specified?
> say, 16k or 32k, maybe we should use to calculate for
> s_raid_stripe_width?
Perhaps, though really ext4 still doesn't do -that- much with the value,
anyway...
-Eric
next prev parent reply other threads:[~2010-09-30 17:07 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-09-27 16:41 I/O topology fixes for big physical block size Martin K. Petersen
2010-09-27 16:41 ` [PATCH 1/2] block: Ensure physical block size is unsigned int Martin K. Petersen
2010-09-27 17:40 ` Mike Snitzer
2010-10-08 5:15 ` Martin K. Petersen
2010-10-13 19:12 ` Mike Snitzer
2010-10-13 19:15 ` Jens Axboe
2010-09-27 16:41 ` [PATCH 2/2] sd: Fix overflow with big physical blocks Martin K. Petersen
2010-09-27 17:42 ` Mike Snitzer
2010-09-27 18:13 ` [PATCH] block: eliminate potential for infinite loop in blkdev_issue_discard Mike Snitzer
2010-10-14 21:37 ` Mike Snitzer
2010-10-15 11:05 ` Jens Axboe
2010-09-27 16:54 ` I/O topology fixes for big physical block size Jens Axboe
2010-09-27 17:20 ` Martin K. Petersen
2010-09-27 22:21 ` Jens Axboe
2010-09-27 22:36 ` Martin K. Petersen
2010-09-27 23:15 ` Mike Snitzer
2010-09-28 4:30 ` Jens Axboe
2010-09-28 5:20 ` Eric Sandeen
2010-09-28 14:15 ` Mike Snitzer
2010-09-28 20:57 ` Ted Ts'o
2010-09-28 21:24 ` Martin K. Petersen
2010-09-28 21:24 ` Martin K. Petersen
2010-09-28 21:36 ` Eric Sandeen
2010-09-30 16:30 ` Ted Ts'o
2010-09-30 17:07 ` Eric Sandeen
2010-09-30 17:07 ` Eric Sandeen [this message]
2010-09-30 17:33 ` Mike Snitzer
2010-10-01 14:24 ` Ted Ts'o
2010-10-01 22:19 ` Martin K. Petersen
2010-10-01 22:19 ` Martin K. Petersen
2010-10-02 2:31 ` Ted Ts'o
2010-10-02 3:03 ` Daniel Taylor
2010-10-04 19:49 ` Martin K. Petersen
2010-10-04 19:49 ` Martin K. Petersen
2010-09-27 17:23 ` Mike Snitzer
2010-09-27 21:58 ` James Bottomley
2010-09-27 22:03 ` Jens Axboe
2010-09-27 22:14 ` Martin K. Petersen
2010-09-27 22:24 ` Jens Axboe
2010-09-28 18:48 ` Martin K. Petersen
2010-09-28 18:54 ` Mike Snitzer
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=4CA4C3B6.9000104@redhat.com \
--to=sandeen@redhat.com \
--cc=jaxboe@fusionio.com \
--cc=martin.petersen@oracle.com \
--cc=snitzer@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.