From: Omar Sandoval <osandov@osandov.com>
To: Ming Lei <ming.lei@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, Theodore Ts'o <tytso@mit.edu>,
Omar Sandoval <osandov@fb.com>, Sagi Grimberg <sagi@grimberg.me>,
Dave Chinner <dchinner@redhat.com>,
Kent Overstreet <kent.overstreet@gmail.com>,
Mike Snitzer <snitzer@redhat.com>,
dm-devel@redhat.com, Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org, Shaohua Li <shli@kernel.org>,
linux-raid@vger.kernel.org, David Sterba <dsterba@suse.com>,
linux-btrfs@vger.kernel.org,
"Darrick J . Wong" <darrick.wong@oracle.com>,
linux-xfs@vger.kernel.org, Gao Xiang <gaoxiang25@huawei.com>,
Christoph Hellwig <hch@lst.de>,
linux-ext4@vger.kernel.org, Coly Li <colyli@suse.de>,
linux-bcache@vger.kernel.org, Boaz Harrosh <oo>
Subject: Re: [PATCH V12 03/20] block: remove the "cluster" flag
Date: Mon, 26 Nov 2018 14:12:56 -0800 [thread overview]
Message-ID: <20181126221256.GD30411@vader> (raw)
In-Reply-To: <20181126021720.19471-4-ming.lei@redhat.com>
On Mon, Nov 26, 2018 at 10:17:03AM +0800, Ming Lei wrote:
> From: Christoph Hellwig <hch@lst.de>
>
> The cluster flag implements some very old SCSI behavior. As far as I
> can tell the original intent was to enable or disable any kind of
> segment merging. But the actually visible effect to the LLDD is that
> it limits each segments to be inside a single page, which we can
> also affect by setting the maximum segment size and the segment
> boundary.
Reviewed-by: Omar Sandoval <osandov@fb.com>
One comment typo below.
> Signed-off-by: Christoph Hellwig <hch@lst.de>
>
> Replace virt boundary with segment boundary limit.
>
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> ---
> block/blk-merge.c | 20 ++++++++------------
> block/blk-settings.c | 3 ---
> block/blk-sysfs.c | 5 +----
> drivers/scsi/scsi_lib.c | 20 ++++++++++++++++----
> include/linux/blkdev.h | 6 ------
> 5 files changed, 25 insertions(+), 29 deletions(-)
>
[snip]
> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
> index 0df15cb738d2..78d6d05992b0 100644
> --- a/drivers/scsi/scsi_lib.c
> +++ b/drivers/scsi/scsi_lib.c
> @@ -1810,6 +1810,8 @@ static int scsi_map_queues(struct blk_mq_tag_set *set)
> void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
> {
> struct device *dev = shost->dma_dev;
> + unsigned max_segment_size = dma_get_max_seg_size(dev);
> + unsigned long segment_boundary = shost->dma_boundary;
>
> /*
> * this limit is imposed by hardware restrictions
> @@ -1828,13 +1830,23 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
> blk_queue_max_hw_sectors(q, shost->max_sectors);
> if (shost->unchecked_isa_dma)
> blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
> - blk_queue_segment_boundary(q, shost->dma_boundary);
> dma_set_seg_boundary(dev, shost->dma_boundary);
>
> - blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
> + /*
> + * Clustering is a really old concept from the stone age of Linux
> + * SCSI support. But the basic idea is that we never give the
> + * driver a segment that spans multiple pages. For that we need
> + * to limit the segment size, and set the segment boundary so that
> + * we never merge a second segment which is no page aligned.
Typo, "which is not page aligned".
WARNING: multiple messages have this Message-ID (diff)
From: Omar Sandoval <osandov@osandov.com>
To: Ming Lei <ming.lei@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, Theodore Ts'o <tytso@mit.edu>,
Omar Sandoval <osandov@fb.com>, Sagi Grimberg <sagi@grimberg.me>,
Dave Chinner <dchinner@redhat.com>,
Kent Overstreet <kent.overstreet@gmail.com>,
Mike Snitzer <snitzer@redhat.com>,
dm-devel@redhat.com, Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org, Shaohua Li <shli@kernel.org>,
linux-raid@vger.kernel.org, David Sterba <dsterba@suse.com>,
linux-btrfs@vger.kernel.org,
"Darrick J . Wong" <darrick.wong@oracle.com>,
linux-xfs@vger.kernel.org, Gao Xiang <gaoxiang25@huawei.com>,
Christoph Hellwig <hch@lst.de>,
linux-ext4@vger.kernel.org, Coly Li <colyli@suse.de>,
linux-bcache@vger.kernel.org, Boaz Harrosh <ooo@electrozaur.com>,
Bob Peterson <rpeterso@redhat.com>,
cluster-devel@redhat.com
Subject: Re: [PATCH V12 03/20] block: remove the "cluster" flag
Date: Mon, 26 Nov 2018 14:12:56 -0800 [thread overview]
Message-ID: <20181126221256.GD30411@vader> (raw)
In-Reply-To: <20181126021720.19471-4-ming.lei@redhat.com>
On Mon, Nov 26, 2018 at 10:17:03AM +0800, Ming Lei wrote:
> From: Christoph Hellwig <hch@lst.de>
>
> The cluster flag implements some very old SCSI behavior. As far as I
> can tell the original intent was to enable or disable any kind of
> segment merging. But the actually visible effect to the LLDD is that
> it limits each segments to be inside a single page, which we can
> also affect by setting the maximum segment size and the segment
> boundary.
Reviewed-by: Omar Sandoval <osandov@fb.com>
One comment typo below.
> Signed-off-by: Christoph Hellwig <hch@lst.de>
>
> Replace virt boundary with segment boundary limit.
>
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> ---
> block/blk-merge.c | 20 ++++++++------------
> block/blk-settings.c | 3 ---
> block/blk-sysfs.c | 5 +----
> drivers/scsi/scsi_lib.c | 20 ++++++++++++++++----
> include/linux/blkdev.h | 6 ------
> 5 files changed, 25 insertions(+), 29 deletions(-)
>
[snip]
> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
> index 0df15cb738d2..78d6d05992b0 100644
> --- a/drivers/scsi/scsi_lib.c
> +++ b/drivers/scsi/scsi_lib.c
> @@ -1810,6 +1810,8 @@ static int scsi_map_queues(struct blk_mq_tag_set *set)
> void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
> {
> struct device *dev = shost->dma_dev;
> + unsigned max_segment_size = dma_get_max_seg_size(dev);
> + unsigned long segment_boundary = shost->dma_boundary;
>
> /*
> * this limit is imposed by hardware restrictions
> @@ -1828,13 +1830,23 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
> blk_queue_max_hw_sectors(q, shost->max_sectors);
> if (shost->unchecked_isa_dma)
> blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
> - blk_queue_segment_boundary(q, shost->dma_boundary);
> dma_set_seg_boundary(dev, shost->dma_boundary);
>
> - blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
> + /*
> + * Clustering is a really old concept from the stone age of Linux
> + * SCSI support. But the basic idea is that we never give the
> + * driver a segment that spans multiple pages. For that we need
> + * to limit the segment size, and set the segment boundary so that
> + * we never merge a second segment which is no page aligned.
Typo, "which is not page aligned".
WARNING: multiple messages have this Message-ID (diff)
From: Omar Sandoval <osandov@osandov.com>
To: cluster-devel.redhat.com
Subject: [Cluster-devel] [PATCH V12 03/20] block: remove the "cluster" flag
Date: Mon, 26 Nov 2018 14:12:56 -0800 [thread overview]
Message-ID: <20181126221256.GD30411@vader> (raw)
In-Reply-To: <20181126021720.19471-4-ming.lei@redhat.com>
On Mon, Nov 26, 2018 at 10:17:03AM +0800, Ming Lei wrote:
> From: Christoph Hellwig <hch@lst.de>
>
> The cluster flag implements some very old SCSI behavior. As far as I
> can tell the original intent was to enable or disable any kind of
> segment merging. But the actually visible effect to the LLDD is that
> it limits each segments to be inside a single page, which we can
> also affect by setting the maximum segment size and the segment
> boundary.
Reviewed-by: Omar Sandoval <osandov@fb.com>
One comment typo below.
> Signed-off-by: Christoph Hellwig <hch@lst.de>
>
> Replace virt boundary with segment boundary limit.
>
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> ---
> block/blk-merge.c | 20 ++++++++------------
> block/blk-settings.c | 3 ---
> block/blk-sysfs.c | 5 +----
> drivers/scsi/scsi_lib.c | 20 ++++++++++++++++----
> include/linux/blkdev.h | 6 ------
> 5 files changed, 25 insertions(+), 29 deletions(-)
>
[snip]
> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
> index 0df15cb738d2..78d6d05992b0 100644
> --- a/drivers/scsi/scsi_lib.c
> +++ b/drivers/scsi/scsi_lib.c
> @@ -1810,6 +1810,8 @@ static int scsi_map_queues(struct blk_mq_tag_set *set)
> void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
> {
> struct device *dev = shost->dma_dev;
> + unsigned max_segment_size = dma_get_max_seg_size(dev);
> + unsigned long segment_boundary = shost->dma_boundary;
>
> /*
> * this limit is imposed by hardware restrictions
> @@ -1828,13 +1830,23 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
> blk_queue_max_hw_sectors(q, shost->max_sectors);
> if (shost->unchecked_isa_dma)
> blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
> - blk_queue_segment_boundary(q, shost->dma_boundary);
> dma_set_seg_boundary(dev, shost->dma_boundary);
>
> - blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
> + /*
> + * Clustering is a really old concept from the stone age of Linux
> + * SCSI support. But the basic idea is that we never give the
> + * driver a segment that spans multiple pages. For that we need
> + * to limit the segment size, and set the segment boundary so that
> + * we never merge a second segment which is no page aligned.
Typo, "which is not page aligned".
next prev parent reply other threads:[~2018-11-26 22:12 UTC|newest]
Thread overview: 144+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-26 2:17 [PATCH V12 00/20] block: support multi-page bvec Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 2:17 ` [PATCH V12 01/20] btrfs: remove various bio_offset arguments Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:28 ` Omar Sandoval
2018-11-26 22:28 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:28 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 02/20] btrfs: look at bi_size for repair decisions Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:46 ` Omar Sandoval
2018-11-26 22:46 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:46 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 03/20] block: remove the "cluster" flag Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:12 ` Omar Sandoval [this message]
2018-11-26 22:12 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:12 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 04/20] block: don't use bio->bi_vcnt to figure out segment number Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:14 ` Omar Sandoval
2018-11-26 22:14 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:14 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 05/20] block: remove bvec_iter_rewind() Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 12:53 ` Christoph Hellwig
2018-11-26 12:53 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 12:53 ` Christoph Hellwig
2018-11-26 22:16 ` Omar Sandoval
2018-11-26 22:16 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:16 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 06/20] block: rename bvec helpers Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 8:17 ` Miguel Ojeda
2018-11-26 8:17 ` [Cluster-devel] " Miguel Ojeda
2018-11-26 12:54 ` Christoph Hellwig
2018-11-26 12:54 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 12:54 ` Christoph Hellwig
2018-11-26 22:18 ` Omar Sandoval
2018-11-26 22:18 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:18 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 07/20] block: introduce multi-page " Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 12:55 ` Christoph Hellwig
2018-11-26 12:55 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 12:55 ` Christoph Hellwig
2018-11-26 2:17 ` [PATCH V12 08/20] block: introduce bio_for_each_bvec() and rq_for_each_bvec() Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 12:55 ` Christoph Hellwig
2018-11-26 12:55 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 12:55 ` Christoph Hellwig
2018-11-26 2:17 ` [PATCH V12 09/20] block: use bio_for_each_bvec() to compute multi-page bvec count Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 13:11 ` Christoph Hellwig
2018-11-26 13:11 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 13:11 ` Christoph Hellwig
2018-11-26 22:37 ` Omar Sandoval
2018-11-26 22:37 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:37 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 10/20] block: use bio_for_each_bvec() to map sg Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 13:11 ` Christoph Hellwig
2018-11-26 13:11 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 13:11 ` Christoph Hellwig
2018-11-26 2:17 ` [PATCH V12 11/20] block: introduce bvec_last_segment() Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 2:17 ` [PATCH V12 12/20] fs/buffer.c: use bvec iterator to truncate the bio Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 2:17 ` [PATCH V12 13/20] block: loop: pass multi-page bvec to iov_iter Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:39 ` Omar Sandoval
2018-11-26 22:39 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:39 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 14/20] bcache: avoid to use bio_for_each_segment_all() in bch_bio_alloc_pages() Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:40 ` Omar Sandoval
2018-11-26 22:40 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:40 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 15/20] block: allow bio_for_each_segment_all() to iterate over multi-page bvec Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:42 ` Omar Sandoval
2018-11-26 22:42 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:42 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 16/20] block: enable multipage bvecs Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 12:58 ` Christoph Hellwig
2018-11-26 12:58 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 12:58 ` Christoph Hellwig
2018-11-27 2:25 ` Ming Lei
2018-11-27 2:25 ` [Cluster-devel] " Ming Lei
2018-11-27 2:25 ` Ming Lei
2018-11-26 22:56 ` Omar Sandoval
2018-11-26 22:56 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:56 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 17/20] block: always define BIO_MAX_PAGES as 256 Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 22:44 ` Omar Sandoval
2018-11-26 22:44 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:44 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 18/20] block: document usage of bio iterator helpers Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 12:59 ` Christoph Hellwig
2018-11-26 12:59 ` [Cluster-devel] " Christoph Hellwig
2018-11-26 12:59 ` Christoph Hellwig
2018-11-26 22:43 ` Omar Sandoval
2018-11-26 22:43 ` [Cluster-devel] " Omar Sandoval
2018-11-26 22:43 ` Omar Sandoval
2018-11-26 2:17 ` [PATCH V12 19/20] block: kill QUEUE_FLAG_NO_SG_MERGE Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-26 2:17 ` [PATCH V12 20/20] block: kill BLK_MQ_F_SG_MERGE Ming Lei
2018-11-26 2:17 ` [Cluster-devel] " Ming Lei
2018-11-26 2:17 ` Ming Lei
2018-11-28 13:44 ` [PATCH V12 00/20] block: support multi-page bvec Jens Axboe
2018-11-28 13:44 ` [Cluster-devel] " Jens Axboe
2018-11-28 13:44 ` Jens Axboe
2018-11-29 1:30 ` Ming Lei
2018-11-29 1:30 ` [Cluster-devel] " Ming Lei
2018-11-29 1:30 ` Ming Lei
2018-11-29 1:30 ` Ming Lei
2018-11-29 2:20 ` Jens Axboe
2018-11-29 2:20 ` [Cluster-devel] " Jens Axboe
2018-11-29 2:20 ` Jens Axboe
2018-11-29 3:30 ` Ming Lei
2018-11-29 3:30 ` [Cluster-devel] " Ming Lei
2018-11-29 3:30 ` Ming Lei
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=20181126221256.GD30411@vader \
--to=osandov@osandov.com \
--cc=axboe@kernel.dk \
--cc=colyli@suse.de \
--cc=darrick.wong@oracle.com \
--cc=dchinner@redhat.com \
--cc=dm-devel@redhat.com \
--cc=dsterba@suse.com \
--cc=gaoxiang25@huawei.com \
--cc=hch@lst.de \
--cc=kent.overstreet@gmail.com \
--cc=linux-bcache@vger.kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-raid@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=ming.lei@redhat.com \
--cc=osandov@fb.com \
--cc=sagi@grimberg.me \
--cc=shli@kernel.org \
--cc=snitzer@redhat.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 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.