public inbox for linux-scsi@vger.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@infradead.org>
To: "Nicholas A. Bellinger" <nab@linux-iscsi.org>
Cc: Christoph Hellwig <hch@infradead.org>,
	Jens Axboe <axboe@kernel.dk>,
	James Bottomley <JBottomley@Parallels.com>,
	linux-scsi@vger.kernel.org
Subject: Re: [PATCH 12/15] scsi: initial blk-mq support
Date: Fri, 7 Feb 2014 04:51:47 -0800	[thread overview]
Message-ID: <20140207125147.GA3198@infradead.org> (raw)
In-Reply-To: <1391724663.14985.11.camel@haakon3.risingtidesystems.com>

> Is there extra scsi_mq_done() part that does IPI here even necessary
> anymore..?
> 
> I was under the assumption that blk_mq_end_io() is already taking care
> of this..?

blk_mq_end_io does it, but given that the SCSI-specific I/O completion
path is non-trivial I'd rather run it on the indicated CPU as well,
similar to how the old blk-softirq code works.  I'll send out a patch
series that should make this area a lot cleaner and avoid having to
implement the IPIs in each driver that wants or needs it soon.

> OK, so your in-lining the allocation of data + protection SGLs from
> blk-mq..
> 
> The original prototype code was doing these allocations separately below
> for each pre-allocated cmd, and offering LLD's to optionally
> pre-allocate their own descripts using sh->hostt->cmd_size if
> necessary..
> 
> This was necessary to eliminate all fast-path allocations for
> virtio-scsi, and I'd like to see something similar here as an optional
> feature as well.

It's present.  The cmd_size host_template parameter is added in the
previous series, and we still take it into account.  

  parent reply	other threads:[~2014-02-07 12:51 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-02-05 12:41 [PATCH 00/15] A different approach for using blk-mq in the SCSI layer Christoph Hellwig
2014-02-05 12:41 ` [PATCH 01/15] block: rework flush sequencing for blk-mq Christoph Hellwig
2014-02-06  2:08   ` Muthu Kumar
2014-02-06 16:18     ` Christoph Hellwig
2014-02-05 12:41 ` [PATCH 02/15] blk-mq: support at_head inserations for blk_execute_rq Christoph Hellwig
2014-02-06  2:27   ` Muthu Kumar
2014-02-06 16:17     ` Christoph Hellwig
2014-02-06 17:05       ` Muthu Kumar
2014-02-06 17:10         ` Christoph Hellwig
2014-02-05 12:41 ` [PATCH 03/15] blk-mq: divert __blk_put_request for MQ ops Christoph Hellwig
2014-02-05 12:41 ` [PATCH 04/15] blk-mq: handle dma_drain_size Christoph Hellwig
2014-02-05 12:41 ` [PATCH 05/15] blk-mq: initialize sg_reserved_size Christoph Hellwig
2014-02-05 12:41 ` [PATCH 06/15] scsi: reintroduce scsi_driver.init_command Christoph Hellwig
2014-02-05 12:41 ` [PATCH 07/15] block: remove unprep_rq_fn Christoph Hellwig
2014-02-05 12:41 ` [PATCH 08/15] scsi: cleanup scsi_end_request calling conventions Christoph Hellwig
2014-02-05 12:41 ` [PATCH 09/15] scsi: centralize command re-queueing in scsi_dispatch_fn Christoph Hellwig
2014-02-05 12:41 ` [PATCH 10/15] scsi: split __scsi_queue_insert Christoph Hellwig
2014-02-05 12:41 ` [PATCH 11/15] scsi: factor out __scsi_init_queue Christoph Hellwig
2014-02-05 12:41 ` [PATCH 12/15] scsi: initial blk-mq support Christoph Hellwig
2014-02-06  8:38   ` Sagi Grimberg
2014-02-06 16:16     ` Christoph Hellwig
2014-02-06 22:11   ` Nicholas A. Bellinger
2014-02-07  8:45     ` Mike Christie
2014-02-07 12:42       ` Christoph Hellwig
2014-02-07 12:51     ` Christoph Hellwig [this message]
2014-02-05 12:41 ` [PATCH 13/15] scsi: partially stub out scsi_adjust_queue_depth when using blk-mq Christoph Hellwig
2014-02-05 12:41 ` [PATCH 14/15] iscsi_tcp: use blk_mq Christoph Hellwig
2014-02-05 12:41 ` [PATCH 15/15] virtio_scsi: " Christoph Hellwig
2014-02-10 11:35 ` [PATCH 00/15] A different approach for using blk-mq in the SCSI layer Christoph Hellwig
2014-02-10 19:38   ` Nicholas A. Bellinger
2014-02-24 14:46 ` 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=20140207125147.GA3198@infradead.org \
    --to=hch@infradead.org \
    --cc=JBottomley@Parallels.com \
    --cc=axboe@kernel.dk \
    --cc=linux-scsi@vger.kernel.org \
    --cc=nab@linux-iscsi.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