From: Jens Axboe <axboe@kernel.dk>
To: Bart Van Assche <bart.vanassche@wdc.com>
Cc: linux-block@vger.kernel.org, Christoph Hellwig <hch@lst.de>,
Damien Le Moal <Damien.LeMoal@wdc.com>,
Akhil Bhansali <Akhil.Bhansali@wdc.com>
Subject: Re: [PATCH 00/55] Convert skd driver to blk-mq
Date: Fri, 18 Aug 2017 08:46:33 -0600 [thread overview]
Message-ID: <20170818144632.GA21786@kernel.dk> (raw)
In-Reply-To: <20170817201338.16537-1-bart.vanassche@wdc.com>
On Thu, Aug 17 2017, Bart Van Assche wrote:
> Hello Jens,
>
> As you know all existing single queue block drivers have to be converted
> to blk-mq before the single queue block layer can be removed. Hence this
> patch series that converts the skd (sTec s1120) driver to blk-mq. As the
> following performance numbers show, this patch series does not affect
> performance of the skd driver significantly:
Applied for 4.14. Would still appreciate a followup patch to kill the
versioning nonsense.
--
Jens Axboe
next prev parent reply other threads:[~2017-08-18 14:46 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-08-17 20:12 [PATCH 00/55] Convert skd driver to blk-mq Bart Van Assche
2017-08-17 20:12 ` [PATCH 01/55] block: Relax a check in blk_start_queue() Bart Van Assche
2017-08-17 20:12 ` [PATCH 02/55] skd: Avoid that module unloading triggers a use-after-free Bart Van Assche
2017-08-17 20:12 ` [PATCH 03/55] skd: Submit requests to firmware before triggering the doorbell Bart Van Assche
2017-08-17 20:12 ` [PATCH 04/55] skd: Switch to GPLv2 Bart Van Assche
2017-08-17 20:12 ` [PATCH 05/55] skd: Update maintainer information Bart Van Assche
2017-08-17 20:12 ` [PATCH 06/55] skd: Remove unneeded #include directives Bart Van Assche
2017-08-17 20:12 ` [PATCH 07/55] skd: Remove ESXi code Bart Van Assche
2017-08-17 20:12 ` [PATCH 08/55] skd: Remove unnecessary blank lines Bart Van Assche
2017-08-17 20:12 ` [PATCH 09/55] skd: Avoid that gcc 7 warns about fall-through when building with W=1 Bart Van Assche
2017-08-17 20:12 ` [PATCH 10/55] skd: Fix spelling in a source code comment Bart Van Assche
2017-08-17 20:12 ` [PATCH 11/55] skd: Fix a function name in a comment Bart Van Assche
2017-08-17 20:12 ` [PATCH 12/55] skd: Remove set-but-not-used local variables Bart Van Assche
2017-08-17 20:12 ` [PATCH 13/55] skd: Remove a set-but-not-used variable from struct skd_device Bart Van Assche
2017-08-17 20:12 ` [PATCH 14/55] skd: Remove useless barrier() calls Bart Van Assche
2017-08-17 20:12 ` [PATCH 15/55] skd: Switch from the pr_*() to the dev_*() logging functions Bart Van Assche
2017-08-17 20:12 ` [PATCH 16/55] skd: Fix endianness annotations Bart Van Assche
2017-08-17 20:13 ` [PATCH 17/55] skd: Document locking assumptions Bart Van Assche
2017-08-17 20:13 ` [PATCH 18/55] skd: Introduce the symbolic constant SKD_MAX_REQ_PER_MSG Bart Van Assche
2017-08-17 20:13 ` [PATCH 19/55] skd: Introduce SKD_SKCOMP_SIZE Bart Van Assche
2017-08-17 20:13 ` [PATCH 20/55] skd: Fix size argument in skd_free_skcomp() Bart Van Assche
2017-08-17 20:13 ` [PATCH 21/55] skd: Reorder the code in skd_process_request() Bart Van Assche
2017-08-17 20:13 ` [PATCH 22/55] skd: Simplify the code for deciding whether or not to send a FIT msg Bart Van Assche
2017-08-17 20:13 ` [PATCH 23/55] skd: Simplify the code for allocating DMA message buffers Bart Van Assche
2017-08-17 20:13 ` [PATCH 24/55] skd: Use a structure instead of hardcoding structure offsets Bart Van Assche
2017-08-17 20:13 ` [PATCH 25/55] skd: Check structure sizes at build time Bart Van Assche
2017-08-17 20:13 ` [PATCH 26/55] skd: Use __packed only when needed Bart Van Assche
2017-08-17 20:13 ` [PATCH 27/55] skd: Make the skd_isr() code more brief Bart Van Assche
2017-08-17 20:13 ` [PATCH 28/55] skd: Use ARRAY_SIZE() where appropriate Bart Van Assche
2017-08-17 20:13 ` [PATCH 29/55] skd: Simplify the code for handling data direction Bart Van Assche
2017-08-17 20:13 ` [PATCH 30/55] skd: Remove superfluous initializations from skd_isr_completion_posted() Bart Van Assche
2017-08-17 20:13 ` [PATCH 31/55] skd: Drop second argument of skd_recover_requests() Bart Van Assche
2017-08-17 20:13 ` [PATCH 32/55] skd: Use for_each_sg() Bart Van Assche
2017-08-17 20:13 ` [PATCH 33/55] skd: Remove a redundant init_timer() call Bart Van Assche
2017-08-17 20:13 ` [PATCH 34/55] skd: Remove superfluous occurrences of the 'volatile' keyword Bart Van Assche
2017-08-17 20:13 ` [PATCH 35/55] skd: Use kcalloc() instead of kzalloc() with multiply Bart Van Assche
2017-08-17 20:13 ` [PATCH 36/55] skb: Use symbolic names for SCSI opcodes Bart Van Assche
2017-08-17 20:13 ` [PATCH 37/55] skd: Move a function definition Bart Van Assche
2017-08-17 20:13 ` [PATCH 38/55] skd: Rework request failing code path Bart Van Assche
2017-08-17 20:13 ` [PATCH 39/55] skd: Convert explicit skd_request_fn() calls Bart Van Assche
2017-08-17 20:13 ` [PATCH 40/55] skd: Remove SG IO support Bart Van Assche
2017-08-17 20:13 ` [PATCH 41/55] skd: Remove dead code Bart Van Assche
2017-08-17 20:13 ` [PATCH 42/55] skd: Initialize skd_special_context.req.n_sg to one Bart Van Assche
2017-08-17 20:13 ` [PATCH 43/55] skd: Enable request tags for the block layer queue Bart Van Assche
2017-08-17 20:13 ` [PATCH 44/55] skd: Convert several per-device scalar variables into atomics Bart Van Assche
2017-08-17 20:13 ` [PATCH 45/55] skd: Introduce skd_process_request() Bart Van Assche
2017-08-17 20:13 ` [PATCH 46/55] skd: Split skd_recover_requests() Bart Van Assche
2017-08-17 20:13 ` [PATCH 47/55] skd: Move skd_free_sg_list() up Bart Van Assche
2017-08-17 20:13 ` [PATCH 48/55] skd: Coalesce struct request and struct skd_request_context Bart Van Assche
2017-08-17 20:13 ` [PATCH 49/55] skd: Convert to blk-mq Bart Van Assche
2017-08-17 20:13 ` [PATCH 50/55] skd: Switch to block layer timeout mechanism Bart Van Assche
2017-08-17 20:13 ` [PATCH 51/55] skd: Remove skd_device.in_flight Bart Van Assche
2017-08-17 20:13 ` [PATCH 52/55] skd: Reduce memory usage Bart Van Assche
2017-08-17 20:13 ` [PATCH 53/55] skd: Remove several local variables Bart Van Assche
2017-08-17 20:13 ` [PATCH 54/55] skd: Optimize locking Bart Van Assche
2017-08-17 20:13 ` [PATCH 55/55] skd: Bump driver version Bart Van Assche
2017-08-17 20:45 ` Jens Axboe
2017-08-17 20:44 ` [PATCH 00/55] Convert skd driver to blk-mq Jens Axboe
2017-08-18 14:46 ` Jens Axboe [this message]
2017-08-18 15:05 ` Bart Van Assche
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=20170818144632.GA21786@kernel.dk \
--to=axboe@kernel.dk \
--cc=Akhil.Bhansali@wdc.com \
--cc=Damien.LeMoal@wdc.com \
--cc=bart.vanassche@wdc.com \
--cc=hch@lst.de \
--cc=linux-block@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 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.