From: Mike Snitzer <snitzer@redhat.com>
To: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Ming Lin <mlin@kernel.org>,
axboe@fb.com, Christoph Hellwig <hch@infradead.org>,
device-mapper development <dm-devel@redhat.com>,
Ming Lei <ming.lei@canonical.com>, Christoph Hellwig <hch@lst.de>,
Alasdair Kergon <agk@redhat.com>,
Lars Ellenberg <drbd-dev@lists.linbit.com>,
Philip Kelleher <pjk1939@linux.vnet.ibm.com>,
Kent Overstreet <kent.overstreet@gmail.com>,
Nitin Gupta <ngupta@vflare.org>,
Ming Lin <ming.l@ssi.samsung.com>,
Oleg Drokin <oleg.drokin@intel.com>,
Al Viro <viro@zeniv.linux.org.uk>, Jens Axboe <axboe@kernel.dk>,
Andreas Dilger <andreas.dilger@intel.com>,
Geoff Levand <geoff@infradead.org>, Jiri Kosina <jkosina@suse.cz>,
lkml <linux-kernel@vger.kernel.org>, Jim Paris <jim@jtan.com>,
Minchan Kim <minchan@kernel.org>, Dongsu Park <dpark@posteo.net>,
drbd-user@lists.linbit.com, Joe Thornber <ejt@redhat.com>
Subject: Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios
Date: Tue, 11 Aug 2015 13:47:17 -0400 [thread overview]
Message-ID: <20150811174717.GA30439@redhat.com> (raw)
In-Reply-To: <yq17fp1hgm0.fsf@sermon.lab.mkp.net>
On Tue, Aug 11 2015 at 1:36pm -0400,
Martin K. Petersen <martin.petersen@oracle.com> wrote:
> >>>>> "Mike" == Mike Snitzer <snitzer@redhat.com> writes:
>
> Mike> DM-thinp processes discards internally before it passes them down
> Mike> (if configured to do so). If a discard is smaller than the
> Mike> granularity of a thinp block (whose size is configurable) or if
> Mike> the start and end of the discard's extent is misaligned (relative
> Mike> to the thinp blocks mapped to the logical extent) then the discard
> Mike> won't actually discard partial thinp blocks.
>
> That's fine. You can throw away anything you don't like as long as
> discard_zeroes_data=0.
Correct, dm-thinp sets discard_zeroes_data=0
> But I don't understand why having an artificial cap at 2GB fixes
> things. Other than making it less likely for you to receive a runt by
> virtue of being aligned to a power of two.
That is the benefit. And when coupled with the new default max_discard
of 64K (pending change from Jens for 4.3) this 2GB upper limit really
isn't such a big deal. Unless I'm missing something...
WARNING: multiple messages have this Message-ID (diff)
From: Mike Snitzer <snitzer-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: "Martin K. Petersen"
<martin.petersen-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Cc: Ming Lei <ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>,
device-mapper development
<dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>,
Alasdair Kergon <agk-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
Lars Ellenberg <drbd-dev-cunTk1MwBs8qoQakbn7OcQ@public.gmane.org>,
Philip Kelleher
<pjk1939-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>,
Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>,
Kent Overstreet
<kent.overstreet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
Nitin Gupta <ngupta-KNmc09w0p+Ednm+yROfE0A@public.gmane.org>,
Ming Lin <ming.l-Vzezgt5dB6uUEJcrhfAQsw@public.gmane.org>,
Oleg Drokin <oleg.drokin-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
Al Viro <viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org>,
Ming Lin <mlin-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>,
axboe-b10kYP2dOMg@public.gmane.org,
Andreas Dilger
<andreas.dilger-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
Geoff Levand <geoff-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>,
Jiri Kosina <jkosina-AlSwsSmVLrQ@public.gmane.org>,
lkml <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Jim Paris <jim-XrPbb/hENzg@public.gmane.org>,
Minchan Kim <minchan-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
Joe Thornber <ejt-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
Dongsu Park <dpark-VwIFZPTo/vqsTnJN9+BGXg@public.gmane.org>,
drbd-user-cunTk1MwBs8qoQakbn7OcQ@public.gmane.org
Subject: Re: [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios
Date: Tue, 11 Aug 2015 13:47:17 -0400 [thread overview]
Message-ID: <20150811174717.GA30439@redhat.com> (raw)
In-Reply-To: <yq17fp1hgm0.fsf-+q57XtR/GgMb6DWv4sQWN6xOck334EZe@public.gmane.org>
On Tue, Aug 11 2015 at 1:36pm -0400,
Martin K. Petersen <martin.petersen-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org> wrote:
> >>>>> "Mike" == Mike Snitzer <snitzer-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> writes:
>
> Mike> DM-thinp processes discards internally before it passes them down
> Mike> (if configured to do so). If a discard is smaller than the
> Mike> granularity of a thinp block (whose size is configurable) or if
> Mike> the start and end of the discard's extent is misaligned (relative
> Mike> to the thinp blocks mapped to the logical extent) then the discard
> Mike> won't actually discard partial thinp blocks.
>
> That's fine. You can throw away anything you don't like as long as
> discard_zeroes_data=0.
Correct, dm-thinp sets discard_zeroes_data=0
> But I don't understand why having an artificial cap at 2GB fixes
> things. Other than making it less likely for you to receive a runt by
> virtue of being aligned to a power of two.
That is the benefit. And when coupled with the new default max_discard
of 64K (pending change from Jens for 4.3) this 2GB upper limit really
isn't such a big deal. Unless I'm missing something...
next prev parent reply other threads:[~2015-08-11 17:47 UTC|newest]
Thread overview: 103+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-06 7:44 [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios Ming Lin
2015-07-06 7:44 ` [PATCH v5 02/11] block: simplify bio_add_page() Ming Lin
2015-07-06 7:44 ` [PATCH v5 03/11] bcache: remove driver private bio splitting code Ming Lin
2015-07-06 7:44 ` [PATCH v5 04/11] btrfs: remove bio splitting and merge_bvec_fn() calls Ming Lin
2015-07-06 7:44 ` [PATCH v5 05/11] block: remove split code in blkdev_issue_discard Ming Lin
2015-07-06 7:44 ` [PATCH v5 06/11] md/raid5: split bio for chunk_aligned_read Ming Lin
2015-07-06 7:44 ` [PATCH v5 07/11] md/raid5: get rid of bio_fits_rdev() Ming Lin
2015-07-06 7:44 ` [PATCH v5 08/11] block: kill merge_bvec_fn() completely Ming Lin
2015-07-06 7:44 ` [PATCH v5 09/11] fs: use helper bio_add_page() instead of open coding on bi_io_vec Ming Lin
2015-07-06 7:44 ` [PATCH v5 10/11] block: remove bio_get_nr_vecs() Ming Lin
2015-07-06 10:58 ` Steven Whitehouse
2015-07-06 17:21 ` Ming Lin
2015-07-07 9:04 ` Steven Whitehouse
2015-07-06 7:44 ` [PATCH v5 11/11] Documentation: update notes in biovecs about arbitrarily sized bios Ming Lin
2015-07-31 19:23 ` [PATCH v5 01/11] block: make generic_make_request handle " Mike Snitzer
2015-07-31 21:19 ` Ming Lin
2015-07-31 21:19 ` Ming Lin
2015-07-31 21:38 ` Mike Snitzer
2015-07-31 21:38 ` Mike Snitzer
2015-07-31 22:02 ` Ming Lin
2015-07-31 22:18 ` Ming Lin
2015-08-01 6:58 ` Ming Lin
2015-08-01 6:58 ` Ming Lin
2015-08-01 16:33 ` Mike Snitzer
2015-08-03 5:58 ` Ming Lin
2015-08-03 5:58 ` Ming Lin
2015-08-04 11:36 ` Christoph Hellwig
2015-08-05 6:03 ` Ming Lin
2015-08-05 6:03 ` Ming Lin
2015-08-07 7:30 ` Christoph Hellwig
2015-08-07 7:30 ` Christoph Hellwig
2015-08-07 23:40 ` Ming Lin
2015-08-07 23:40 ` Ming Lin
2015-08-08 0:30 ` Kent Overstreet
2015-08-08 5:17 ` Ming Lin
2015-08-08 5:17 ` Ming Lin
2015-08-08 5:22 ` Kent Overstreet
2015-08-08 12:35 ` Christoph Hellwig
2015-08-08 12:35 ` Christoph Hellwig
2015-08-08 8:52 ` [dm-devel] " Hannes Reinecke
2015-08-08 9:02 ` Kent Overstreet
2015-08-13 6:04 ` Hannes Reinecke
2015-08-07 0:00 ` Kent Overstreet
2015-08-07 7:30 ` Christoph Hellwig
2015-08-07 7:30 ` Christoph Hellwig
2015-08-08 16:19 ` [dm-devel] " Martin K. Petersen
2015-08-08 16:19 ` Martin K. Petersen
2015-08-09 5:59 ` Ming Lin
2015-08-09 5:59 ` Ming Lin
2015-08-09 6:41 ` Christoph Hellwig
2015-08-09 6:41 ` Christoph Hellwig
2015-08-09 6:55 ` Ming Lin
2015-08-09 6:55 ` Ming Lin
2015-08-09 7:01 ` Christoph Hellwig
2015-08-09 7:01 ` Christoph Hellwig
2015-08-09 7:18 ` Ming Lin
2015-08-09 7:18 ` Ming Lin
2015-08-10 15:02 ` Mike Snitzer
2015-08-10 15:02 ` Mike Snitzer
2015-08-10 16:14 ` Ming Lin
2015-08-10 16:14 ` Ming Lin
2015-08-10 16:18 ` Ming Lin
2015-08-10 16:18 ` Ming Lin
2015-08-10 16:40 ` Martin K. Petersen
2015-08-10 16:40 ` Martin K. Petersen
2015-08-10 18:13 ` Mike Snitzer
2015-08-10 22:30 ` Ming Lin
2015-08-10 22:30 ` Ming Lin
2015-08-10 16:22 ` Martin K. Petersen
2015-08-10 16:22 ` Martin K. Petersen
2015-08-10 18:18 ` Ming Lin
2015-08-11 2:00 ` Martin K. Petersen
2015-08-11 2:00 ` Martin K. Petersen
2015-08-11 2:41 ` Mike Snitzer
2015-08-11 2:41 ` Mike Snitzer
2015-08-11 3:38 ` Kent Overstreet
2015-08-11 14:08 ` Mike Snitzer
2015-08-11 14:08 ` Mike Snitzer
2015-08-11 17:49 ` Martin K. Petersen
2015-08-11 17:49 ` Martin K. Petersen
2015-08-11 18:05 ` Martin K. Petersen
2015-08-11 18:05 ` Martin K. Petersen
2015-08-11 20:56 ` Ming Lin
2015-08-11 20:56 ` Ming Lin
2015-08-12 0:24 ` Martin K. Petersen
2015-08-12 0:24 ` Martin K. Petersen
2015-08-12 4:41 ` Ming Lin
2015-08-12 4:41 ` Ming Lin
2015-08-11 17:36 ` Martin K. Petersen
2015-08-11 17:36 ` Martin K. Petersen
2015-08-11 17:47 ` Mike Snitzer [this message]
2015-08-11 17:47 ` Mike Snitzer
2015-08-11 18:01 ` [dm-devel] " Martin K. Petersen
2015-08-11 18:01 ` Martin K. Petersen
2015-08-18 5:09 ` Ming Lin
2015-08-18 7:04 ` Ming Lin
2015-08-18 14:45 ` Mike Snitzer
2015-08-18 17:32 ` Ming Lin
2015-08-18 19:59 ` Mike Snitzer
2015-08-18 21:16 ` Ming Lin
2015-08-18 21:22 ` Mike Snitzer
2015-08-18 22:17 ` Ming Lin
-- strict thread matches above, loose matches on Subject: below --
2015-07-06 7:11 [PATCH v5 00/11] simplify block layer based on immutable biovecs mlin
2015-07-06 7:11 ` [PATCH v5 01/11] block: make generic_make_request handle arbitrarily sized bios mlin
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=20150811174717.GA30439@redhat.com \
--to=snitzer@redhat.com \
--cc=agk@redhat.com \
--cc=andreas.dilger@intel.com \
--cc=axboe@fb.com \
--cc=axboe@kernel.dk \
--cc=dm-devel@redhat.com \
--cc=dpark@posteo.net \
--cc=drbd-dev@lists.linbit.com \
--cc=drbd-user@lists.linbit.com \
--cc=ejt@redhat.com \
--cc=geoff@infradead.org \
--cc=hch@infradead.org \
--cc=hch@lst.de \
--cc=jim@jtan.com \
--cc=jkosina@suse.cz \
--cc=kent.overstreet@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=minchan@kernel.org \
--cc=ming.l@ssi.samsung.com \
--cc=ming.lei@canonical.com \
--cc=mlin@kernel.org \
--cc=ngupta@vflare.org \
--cc=oleg.drokin@intel.com \
--cc=pjk1939@linux.vnet.ibm.com \
--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 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.