From: Mike Fedyk <mfedyk@mikefedyk.com>
To: Josef Bacik <josef@redhat.com>
Cc: linux-btrfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, hch@infradead.org,
akpm@linux-foundation.org
Subject: Re: [PATCH 3/6] direct-io: do not merge logically non-contiguous requests
Date: Fri, 21 May 2010 18:47:36 -0700 [thread overview]
Message-ID: <AANLkTikwPL8-WefVIMF1ldTZpWVHvS1Lbh4YB8MZ4eu0@mail.gmail.com> (raw)
In-Reply-To: <1274461422-18433-3-git-send-email-josef@redhat.com>
On Fri, May 21, 2010 at 10:03 AM, Josef Bacik <josef@redhat.com> wrote:
> Btrfs cannot handle having logically non-contiguous requests submitte=
d. =C2=A0For
> example if you have
>
> Logical: =C2=A0[0-4095][HOLE][8192-12287]
> Physical: [0-4095] =C2=A0 =C2=A0 =C2=A0[4096-8191]
>
> Normally the DIO code would put these into the same BIO's. =C2=A0The =
problem is we
> need to know exactly what offset is associated with what BIO so we ca=
n do our
> checksumming and unlocking properly, so putting them in the same BIO =
doesn't
> work. =C2=A0So add another check where we submit the current BIO if t=
he physical
> blocks are not contigous OR the logical blocks are not contiguous.
>
> Signed-off-by: Josef Bacik <josef@redhat.com>
> ---
>
> V1->V2
> -Be more verbose in the in-code comment
>
> =C2=A0fs/direct-io.c | =C2=A0 20 ++++++++++++++++++--
> =C2=A01 files changed, 18 insertions(+), 2 deletions(-)
>
Btrfs has been pretty much self-contained (working well compiled
against 2.6.32 for example). Is there a way that this wouldn't just
start silently breaking for people compiling the latest btrfs with
dkms against older kernels?
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" =
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2010-05-22 1:47 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-21 17:03 [PATCH 1/6] fs: allow short direct-io reads to be completed via buffered IO Josef Bacik
2010-05-21 17:03 ` [PATCH 2/6] direct-io: add a hook for the fs to provide its own submit_bio function Josef Bacik
2010-05-21 17:03 ` [PATCH 3/6] direct-io: do not merge logically non-contiguous requests Josef Bacik
2010-05-22 1:47 ` Mike Fedyk [this message]
2010-05-22 14:02 ` Josef Bacik
2010-05-21 17:03 ` [PATCH 4/6] fs: kill blockdev_direct_IO_no_locking Josef Bacik
2010-05-21 17:03 ` [PATCH 5/6] Btrfs: add basic DIO read/write support Josef Bacik
2010-05-21 17:03 ` [PATCH 6/6] Btrfs: do aio_write instead of write Josef Bacik
2010-05-23 8:31 ` Shi Weihua
2010-05-23 23:59 ` Josef Bacik
2010-05-27 3:06 ` liubo
2010-05-27 3:13 ` liubo
2010-05-27 12:59 ` Chris Mason
2010-05-28 1:42 ` liubo
2010-05-30 9:33 ` Dmitri Nikulin
2010-06-01 13:19 ` Chris Mason
2010-06-01 23:20 ` Dmitri Nikulin
-- strict thread matches above, loose matches on Subject: below --
2010-05-19 20:24 [PATCH 1/6] fs: allow short direct-io reads to be completed via buffered IO V2 Josef Bacik
2010-05-19 20:24 ` [PATCH 3/6] direct-io: do not merge logically non-contiguous requests Josef Bacik
2010-05-21 15:21 ` Christoph Hellwig
2010-05-21 15:37 ` Josef Bacik
2010-05-21 15:35 ` 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=AANLkTikwPL8-WefVIMF1ldTZpWVHvS1Lbh4YB8MZ4eu0@mail.gmail.com \
--to=mfedyk@mikefedyk.com \
--cc=akpm@linux-foundation.org \
--cc=hch@infradead.org \
--cc=josef@redhat.com \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@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).