From: Andrzej Jakowski <andrzej.jakowski@linux.intel.com>
To: Keith Busch <kbusch@kernel.org>
Cc: axboe@kernel.dk, song@kernel.org, linux-block@vger.kernel.org,
linux-raid@vger.kernel.org,
Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Subject: Re: [PATCH v2 2/2] md: enable io polling
Date: Thu, 13 Feb 2020 13:19:42 -0700 [thread overview]
Message-ID: <f516e2b2-1988-03ca-f966-5f26771717ff@linux.intel.com> (raw)
In-Reply-To: <20200212214207.GA6409@redsun51.ssa.fujisawa.hgst.com>
On 2/12/20 2:42 PM, Keith Busch wrote:
> On Wed, Feb 12, 2020 at 02:00:10PM -0700, Andrzej Jakowski wrote:
>> On 2/11/20 2:13 PM, Keith Busch wrote:
>>> I must be missing something: md's make_request_fn always returns
>>> BLK_QC_T_NONE for the cookie, and that couldn't get past blk_poll's
>>> blk_qc_t_valid(cookie) check. How does the initial blk_poll() caller get
>>> a valid cookie for an md backing device's request_queue? And how is the
>>> same cookie valid for more than one request_queue?
>> That's true md_make_request() always returns BLK_QC_T_NONE. md_make_request()
>> recursively calls generic_make_request() for the underlying device (e.g. nvme).
>> That block io request directed to member disk is added into bio_list and is
>> processed later by top level generic_make_request(). generic_make_request()
>> returns cookie that is returned by blk_mq_make_request().
>> That cookie is later used to poll for completion.
> Okay, that's a nice subtlety. But it means the original caller gets the
> cookie from the last submission in the chain. If md recieves a single
> request that has to be split among more than one member disk, the cookie
> you're using to control the polling is valid only for one of the
> request_queue's and may break others.
Correct, I agree that it is an issue. I can see at least two ways how to solve it:
1. Provide a mechanism in md accounting for outstanding IOs, storing cookie information
for them. md_poll() will then use valid cookie's
2. Provide similar mechanism abstracted for stackable block devices and block layer could
handle completions for subordinate bios in an abstracted way in blk_poll() routine.
How do you Guys see this going?
next prev parent reply other threads:[~2020-02-13 20:19 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-11 19:17 [PATCH v2 0/2] Enable polling on stackable devices Andrzej Jakowski
2020-02-11 19:17 ` [PATCH v2 1/2] block: reintroduce polling on bio level Andrzej Jakowski
2020-02-11 19:17 ` [PATCH v2 2/2] md: enable io polling Andrzej Jakowski
2020-02-11 21:13 ` Keith Busch
2020-02-12 21:00 ` Andrzej Jakowski
2020-02-12 21:42 ` Keith Busch
2020-02-13 20:19 ` Andrzej Jakowski [this message]
2020-02-14 19:25 ` Keith Busch
2020-02-21 15:25 ` Andrzej Jakowski
2020-02-21 16:34 ` Keith Busch
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=f516e2b2-1988-03ca-f966-5f26771717ff@linux.intel.com \
--to=andrzej.jakowski@linux.intel.com \
--cc=artur.paszkiewicz@intel.com \
--cc=axboe@kernel.dk \
--cc=kbusch@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=song@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 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).