From: John Garry <john.g.garry@oracle.com>
To: Christoph Hellwig <hch@lst.de>
Cc: "Darrick J. Wong" <djwong@kernel.org>,
axboe@kernel.dk, kbusch@kernel.org, sagi@grimberg.me,
jejb@linux.ibm.com, martin.petersen@oracle.com,
viro@zeniv.linux.org.uk, brauner@kernel.org, dchinner@redhat.com,
jack@suse.cz, linux-block@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org,
linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
tytso@mit.edu, jbongio@google.com, linux-scsi@vger.kernel.org,
ming.lei@redhat.com, jaswin@linux.ibm.com, bvanassche@acm.org
Subject: Re: [PATCH v2 00/16] block atomic writes
Date: Wed, 17 Jan 2024 16:16:56 +0000 [thread overview]
Message-ID: <16a6e6e9-b7b0-40bb-9860-324ab7515a5a@oracle.com> (raw)
In-Reply-To: <20240117150200.GA30112@lst.de>
On 17/01/2024 15:02, Christoph Hellwig wrote:
> On Tue, Jan 16, 2024 at 11:35:47AM +0000, John Garry wrote:
>> As such, we then need to set atomic write unit max = min(queue max
>> segments, BIO_MAX_VECS) * LBS. That would mean atomic write unit max 256 *
>> 512 = 128K (for 512B LBS). For a DMA controller of max segments 64, for
>> example, then we would have 32K. These seem too low.
>
> I don't see how this would work if support multiple sectors.
>
>>
>> Alternative I'm thinking that we should just limit to 1x iovec always, and
>> then atomic write unit max = (min(queue max segments, BIO_MAX_VECS) - 1) *
>> PAGE_SIZE [ignoring first/last iovec contents]. It also makes support for
>> non-enterprise NVMe drives more straightforward. If someone wants, they can
>> introduce support for multi-iovec later, but it would prob require some
>> more iovec length/alignment rules.
>
> Supporting just a single iovec initially is fine with me, as extending
> that is pretty easy. Just talk to your potential users that they can
> live with it.
Yeah, any porting I know about has just been using aio with
IO_CMD_PWRITE, so would be ok
>
> I'd probably still advertise the limits even if it currently always is 1.
>
I suppose that we don't need any special rule until we support > 1, as
we cannot break anyone already using > 1 :)
Thanks,
John
next prev parent reply other threads:[~2024-01-17 16:17 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-12 11:08 John Garry
2023-12-12 11:08 ` [PATCH v2 01/16] block: Add atomic write operations to request_queue limits John Garry
2023-12-13 1:25 ` Ming Lei
2023-12-13 9:13 ` John Garry
2023-12-13 12:28 ` Ming Lei
2023-12-13 19:01 ` John Garry
2023-12-14 4:38 ` Martin K. Petersen
2023-12-14 13:46 ` Ming Lei
2023-12-14 4:34 ` Martin K. Petersen
2023-12-14 16:12 ` Christoph Hellwig
2023-12-12 11:08 ` [PATCH v2 02/16] block: Limit atomic writes according to bio and queue limits John Garry
2023-12-12 11:08 ` [PATCH v2 03/16] fs/bdev: Add atomic write support info to statx John Garry
2023-12-13 10:24 ` Jan Kara
2023-12-13 11:02 ` John Garry
2023-12-12 11:08 ` [PATCH v2 04/16] fs: Increase fmode_t size John Garry
2023-12-13 11:20 ` Jan Kara
2023-12-13 13:03 ` John Garry
2023-12-13 13:02 ` Christian Brauner
2023-12-13 13:15 ` John Garry
2023-12-13 16:03 ` Christoph Hellwig
2023-12-14 8:56 ` John Garry
2023-12-12 11:08 ` [PATCH v2 05/16] fs: Add RWF_ATOMIC and IOCB_ATOMIC flags for atomic write support John Garry
2023-12-13 13:31 ` Al Viro
2023-12-13 16:02 ` John Garry
2024-01-22 8:29 ` John Garry
2023-12-12 11:08 ` [PATCH v2 06/16] block: Add REQ_ATOMIC flag John Garry
2023-12-12 11:08 ` [PATCH v2 07/16] block: Pass blk_queue_get_max_sectors() a request pointer John Garry
2023-12-12 11:08 ` [PATCH v2 08/16] block: Limit atomic write IO size according to atomic_write_max_sectors John Garry
2023-12-15 2:27 ` Ming Lei
2023-12-15 13:55 ` John Garry
2023-12-12 11:08 ` [PATCH v2 09/16] block: Error an attempt to split an atomic write bio John Garry
2023-12-12 11:08 ` [PATCH v2 10/16] block: Add checks to merging of atomic writes John Garry
2023-12-12 11:08 ` [PATCH v2 11/16] block: Add fops atomic write support John Garry
2023-12-12 11:08 ` [PATCH v2 12/16] scsi: sd: Support reading atomic write properties from block limits VPD John Garry
2023-12-12 11:08 ` [PATCH v2 13/16] scsi: sd: Add WRITE_ATOMIC_16 support John Garry
2023-12-12 11:08 ` [PATCH v2 14/16] scsi: scsi_debug: Atomic write support John Garry
2023-12-12 11:08 ` [PATCH v2 15/16] nvme: Support atomic writes John Garry
2023-12-12 11:08 ` [PATCH v2 16/16] nvme: Ensure atomic writes will be executed atomically John Garry
2023-12-12 16:32 ` [PATCH v2 00/16] block atomic writes Christoph Hellwig
2023-12-13 9:32 ` John Garry
2023-12-13 15:44 ` Christoph Hellwig
2023-12-13 16:27 ` John Garry
2023-12-14 14:37 ` Christoph Hellwig
2023-12-14 15:46 ` John Garry
2023-12-18 22:50 ` Keith Busch
2023-12-19 5:14 ` Darrick J. Wong
2023-12-19 5:21 ` Christoph Hellwig
2023-12-19 12:41 ` John Garry
2023-12-19 15:17 ` Christoph Hellwig
2023-12-19 16:53 ` John Garry
2023-12-21 6:50 ` Christoph Hellwig
2023-12-21 9:49 ` John Garry
2023-12-21 12:19 ` Christoph Hellwig
2023-12-21 12:48 ` John Garry
2023-12-21 12:57 ` Christoph Hellwig
2023-12-21 13:18 ` John Garry
2023-12-21 13:22 ` Christoph Hellwig
2023-12-21 13:56 ` John Garry
2024-01-16 11:35 ` John Garry
2024-01-17 15:02 ` Christoph Hellwig
2024-01-17 16:16 ` John Garry [this message]
2024-01-09 9:55 ` John Garry
2024-01-09 16:02 ` Christoph Hellwig
2024-01-09 16:52 ` John Garry
2024-01-09 23:04 ` Dave Chinner
2024-01-10 8:55 ` John Garry
2024-01-10 9:19 ` Christoph Hellwig
2024-01-11 1:40 ` Darrick J. Wong
2024-01-11 5:02 ` Christoph Hellwig
2024-01-11 9:55 ` John Garry
2024-01-11 14:45 ` Christoph Hellwig
2024-01-11 16:11 ` John Garry
2024-01-11 16:15 ` 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=16a6e6e9-b7b0-40bb-9860-324ab7515a5a@oracle.com \
--to=john.g.garry@oracle.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=bvanassche@acm.org \
--cc=dchinner@redhat.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jaswin@linux.ibm.com \
--cc=jbongio@google.com \
--cc=jejb@linux.ibm.com \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-scsi@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=sagi@grimberg.me \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®