All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: Hannes Reinecke <hare@suse.de>,
	linux-block@vger.kernel.org, linux-scsi@vger.kernel.org,
	linux-ide@vger.kernel.org
Cc: David Miller <davem@davemloft.net>
Subject: Re: [PATCH 04/28] ide: convert to blk-mq
Date: Sat, 27 Oct 2018 10:51:07 -0600	[thread overview]
Message-ID: <e45360e3-28b7-8742-bd75-ea05ff0fde3b@kernel.dk> (raw)
In-Reply-To: <bbdcdea9-96a9-b753-6f74-96565ad7fa91@suse.de>

On 10/27/18 4:51 AM, Hannes Reinecke wrote:
> On 10/25/18 11:10 PM, Jens Axboe wrote:
>> ide-disk and ide-cd tested as working just fine, ide-tape and
>> ide-floppy haven't. But the latter don't require changes, so they
>> should work without issue.
>>
>> Add helper function to insert a request from a work queue, since we
>> cannot invoke the blk-mq request insertion from IRQ context.
>>
>> Cc: David Miller <davem@davemloft.net>
>> Signed-off-by: Jens Axboe <axboe@kernel.dk>
>> ---
>>   drivers/ide/ide-atapi.c |  25 ++++--
>>   drivers/ide/ide-cd.c    | 175 +++++++++++++++++++++-------------------
>>   drivers/ide/ide-disk.c  |   5 +-
>>   drivers/ide/ide-io.c    | 101 +++++++++++++----------
>>   drivers/ide/ide-park.c  |   4 +-
>>   drivers/ide/ide-pm.c    |  28 ++-----
>>   drivers/ide/ide-probe.c |  68 +++++++++++-----
>>   include/linux/ide.h     |  13 ++-
>>   8 files changed, 240 insertions(+), 179 deletions(-)
>>
> There are some things here which are curious (like always setting the 
> queue depth to 32, and the insert_head thingie), but as this is legacy 
> anyway:

The insert head addition is needed, the alternative would be
making the blk-mq locks irq safe. And that would be a performance
hit that isn't acceptable. Perhaps I should make that clearer
in the commit message...

The 32 hard code is a bit strange, but I doubt it matters that much.
It's enough to saturate the drive for sure, and it'll be twice that
number if a scheduler is attached, ensuring we have plenty of
request to get the merging we want.

> Reviewed-by: Hannes Reinecke <hare@suse.com>

Thanks!

-- 
Jens Axboe

  reply	other threads:[~2018-10-27 16:51 UTC|newest]

Thread overview: 90+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-25 21:10 [PATCHSET 0/28] blk-mq driver conversions and legacy path removal Jens Axboe
2018-10-25 21:10 ` [PATCH 01/28] sunvdc: convert to blk-mq Jens Axboe
2018-10-27 10:42   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 02/28] ms_block: " Jens Axboe
2018-10-27 10:43   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 03/28] mspro_block: " Jens Axboe
2018-10-27 10:44   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 04/28] ide: " Jens Axboe
2018-10-27 10:51   ` Hannes Reinecke
2018-10-27 16:51     ` Jens Axboe [this message]
2018-10-25 21:10 ` [PATCH 05/28] IB/srp: remove old request_fn_active check Jens Axboe
2018-10-25 21:23   ` Bart Van Assche
2018-10-25 21:24     ` Jens Axboe
2018-10-26  7:08   ` Hannes Reinecke
2018-10-26 14:32     ` Jens Axboe
2018-10-26 15:03       ` Bart Van Assche
2018-10-25 21:10 ` [PATCH 06/28] blk-mq: remove the request_list usage Jens Axboe
2018-10-27 10:52   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 07/28] blk-mq: remove legacy check in queue blk_freeze_queue() Jens Axboe
2018-10-27 10:52   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 08/28] scsi: kill off the legacy IO path Jens Axboe
2018-10-25 21:36   ` Bart Van Assche
2018-10-25 22:18     ` Jens Axboe
2018-10-25 22:44       ` Madhani, Himanshu
2018-10-25 23:00         ` Jens Axboe
2018-10-25 23:06           ` Madhani, Himanshu
2018-10-29  6:48   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 09/28] dm: remove " Jens Axboe
2018-10-29  6:53   ` Hannes Reinecke
2018-10-29 14:17     ` Jens Axboe
2018-10-25 21:10 ` [PATCH 10/28] dasd: remove dead code Jens Axboe
2018-10-29  6:54   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 11/28] bsg: pass in desired timeout handler Jens Axboe
2018-10-28 15:53   ` Christoph Hellwig
2018-10-28 23:05     ` Jens Axboe
2018-10-29  6:55   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 12/28] bsg: provide bsg_remove_queue() helper Jens Axboe
2018-10-28 15:53   ` Christoph Hellwig
2018-10-29  6:55   ` Hannes Reinecke
2018-10-29 10:16   ` Johannes Thumshirn
2018-10-29 14:15     ` Jens Axboe
2018-10-25 21:10 ` [PATCH 13/28] bsg: convert to use blk-mq Jens Axboe
2018-10-28 16:07   ` Christoph Hellwig
2018-10-28 23:25     ` Jens Axboe
2018-10-29  6:57   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 14/28] block: remove blk_complete_request() Jens Axboe
2018-10-29  6:59   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 15/28] blk-wbt: kill check for legacy queue type Jens Axboe
2018-10-29  6:59   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 16/28] blk-cgroup: remove legacy queue bypassing Jens Axboe
2018-10-29  7:00   ` Hannes Reinecke
2018-10-29 11:00   ` Johannes Thumshirn
2018-10-29 14:23     ` Jens Axboe
2018-10-29 14:25       ` Johannes Thumshirn
2018-10-29 14:59         ` Jens Axboe
2018-10-25 21:10 ` [PATCH 17/28] block: remove legacy rq tagging Jens Axboe
2018-10-29  7:01   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 18/28] block: remove non mq parts from the flush code Jens Axboe
2018-10-29  7:02   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 19/28] block: remove legacy IO schedulers Jens Axboe
2018-10-25 21:10 ` [PATCH 20/28] block: remove dead elevator code Jens Axboe
2018-10-25 21:10 ` [PATCH 21/28] block: remove __blk_put_request() Jens Axboe
2018-10-29  7:03   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 22/28] block: kill legacy parts of timeout handling Jens Axboe
2018-10-29  7:04   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 23/28] block: kill lld busy Jens Axboe
2018-10-25 21:42   ` Bart Van Assche
2018-10-25 22:18     ` Jens Axboe
2018-10-29  7:10   ` Hannes Reinecke
2018-10-29 14:25     ` Jens Axboe
2018-10-29 15:51       ` Mike Snitzer
2018-10-29 16:26         ` Jens Axboe
2018-10-25 21:10 ` [PATCH 24/28] block: remove request_list code Jens Axboe
2018-10-29  7:10   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 25/28] block: kill request slab cache Jens Axboe
2018-10-29  7:11   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 26/28] block: remove req_no_special_merge() from merging code Jens Axboe
2018-10-29  7:12   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 27/28] blk-merge: kill dead queue lock held check Jens Axboe
2018-10-29  7:12   ` Hannes Reinecke
2018-10-25 21:10 ` [PATCH 28/28] block: get rid of blk_queued_rq() Jens Axboe
2018-10-29  7:12   ` Hannes Reinecke
2018-10-25 23:09 ` [PATCHSET 0/28] blk-mq driver conversions and legacy path removal Bart Van Assche
2018-10-25 23:11   ` Jens Axboe
2018-10-29 12:00 ` Ming Lei
2018-10-29 14:50   ` Jens Axboe
2018-10-29 15:04     ` Jens Axboe
2018-10-30  9:41       ` Ming Lei
2018-10-30 14:13         ` Jens Axboe
2018-10-29 15:05     ` 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=e45360e3-28b7-8742-bd75-ea05ff0fde3b@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=davem@davemloft.net \
    --cc=hare@suse.de \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-ide@vger.kernel.org \
    --cc=linux-scsi@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.