From: Christoph Hellwig <hch@lst.de>
To: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Jens Axboe <axboe@kernel.dk>, Ming Lei <ming.lei@redhat.com>,
Hannes Reinecke <hare@suse.com>,
Paul Mackerras <paulus@ozlabs.org>,
Juergen Gross <jgross@suse.com>,
linux-scsi@vger.kernel.org, linux-block@vger.kernel.org
Subject: remove the "clustering" flag
Date: Thu, 6 Dec 2018 07:52:49 -0800 [thread overview]
Message-ID: <20181206155258.11465-1-hch@lst.de> (raw)
The block layer has been carrying around a magic clustering flag,
which is an artefact of prehistoric scsi layer design decisions.
Originally it controller if any segment merging happens at all for a
given LLLD, but with merging moving to the block layer and massively
more complex now it now essentically means that no segment shall be
larger than a page, and no segment shall cross a page boundary if
clustering is not enabled. Unfortunately the SCSI layer historically
defaults to disabled clustering, but fortunately most drivers actually
enable it, and very few drivers do not set an explicit flag.
So this series first flips the default to be sensible, and then replaces
the magic flag with setting an explicit dma boundary and max segment
size to reuse the existing mechanisms. It also fixes up a few drivers
where the no clustering setting was clearly bogus, although we can
probably lift these limits for others as well eventually.
next reply other threads:[~2018-12-06 15:53 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-06 15:52 Christoph Hellwig [this message]
2018-12-06 15:52 ` [PATCH 1/9] scsi: flip the default on use_clustering Christoph Hellwig
2018-12-06 17:05 ` Bart Van Assche
2018-12-06 15:52 ` [PATCH 2/9] scsi: introduce a max_segment_size host_template parameters Christoph Hellwig
2018-12-06 17:15 ` Bart Van Assche
2018-12-11 2:02 ` Ming Lei
2018-12-11 14:05 ` Christoph Hellwig
2018-12-06 15:52 ` [PATCH 3/9] myrb: remove the DISABLE_CLUSTERING flag Christoph Hellwig
2018-12-06 15:52 ` [PATCH 4/9] myrs: " Christoph Hellwig
2018-12-06 15:52 ` [PATCH 5/9] xen-scsifront: remove DISABLE_CLUSTERING Christoph Hellwig
2018-12-06 15:52 ` [PATCH 6/9] mesh: " Christoph Hellwig
2018-12-06 22:07 ` Paul Mackerras
2018-12-06 15:52 ` [PATCH 7/9] mac53c94: " Christoph Hellwig
2018-12-06 22:07 ` Paul Mackerras
2018-12-06 15:52 ` [PATCH 8/9] scsi: remove the use_clustering flag Christoph Hellwig
2018-12-06 17:13 ` Bart Van Assche
2018-12-08 17:51 ` Christoph Hellwig
2018-12-06 15:52 ` [PATCH 9/9] block: remove the cluster flag 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=20181206155258.11465-1-hch@lst.de \
--to=hch@lst.de \
--cc=axboe@kernel.dk \
--cc=hare@suse.com \
--cc=jgross@suse.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=paulus@ozlabs.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).