From: "tj@kernel.org" <tj@kernel.org>
To: Bart Van Assche <Bart.VanAssche@wdc.com>
Cc: "jbacik@fb.com" <jbacik@fb.com>, "jack@suse.cz" <jack@suse.cz>,
"clm@fb.com" <clm@fb.com>, "axboe@kernel.dk" <axboe@kernel.dk>,
"kernel-team@fb.com" <kernel-team@fb.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"peterz@infradead.org" <peterz@infradead.org>,
"linux-btrfs@vger.kernel.org" <linux-btrfs@vger.kernel.org>,
"linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
"jianchao.w.wang@oracle.com" <jianchao.w.wang@oracle.com>
Subject: Re: [PATCH 2/8] blk-mq: protect completion path with RCU
Date: Tue, 9 Jan 2018 08:19:14 -0800 [thread overview]
Message-ID: <20180109161914.GM3668920@devbig577.frc2.facebook.com> (raw)
In-Reply-To: <1515514359.2721.9.camel@wdc.com>
Hello, Bart.
On Tue, Jan 09, 2018 at 04:12:40PM +0000, Bart Van Assche wrote:
> I'm concerned about the additional CPU cycles needed for the new blk_mq_map_queue()
> call, although I know this call is cheap. Would the timeout code really get that
So, if that is really a concern, let's cache that mapping instead of
changing synchronization rules for that.
> much more complicated if the hctx_lock() and hctx_unlock() calls would be changed
> into rcu_read_lock() and rcu_read_unlock() calls? Would it be sufficient if
> "if (has_rcu) synchronize_rcu();" would be changed into "synchronize_rcu();" in
> blk_mq_timeout_work()?
Code-wise, it won't be too much extra code but I think diverging the
sync methods between issue and completion paths is more fragile and
likely to invite confusions and mistakes in the future. We have the
normal path (issue&completion) synchronizing against the exception
path (timeout). I think it's best to keep the sync constructs aligned
with that conceptual picture.
Thanks.
--
tejun
next prev parent reply other threads:[~2018-01-09 16:19 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-08 19:15 [PATCHSET v4] blk-mq: reimplement timeout handling Tejun Heo
2018-01-08 19:15 ` [PATCH 1/8] blk-mq: move hctx lock/unlock into a helper Tejun Heo
2018-01-08 19:24 ` Bart Van Assche
2018-01-08 19:24 ` Bart Van Assche
2018-01-08 19:15 ` [PATCH 2/8] blk-mq: protect completion path with RCU Tejun Heo
2018-01-08 19:57 ` Holger Hoffstätte
2018-01-08 20:15 ` Jens Axboe
2018-01-08 22:55 ` Jens Axboe
2018-01-08 23:27 ` Holger Hoffstätte
2018-01-08 23:33 ` Holger Hoffstätte
2018-01-09 7:08 ` Hannes Reinecke
2018-01-09 15:22 ` Jens Axboe
2018-01-09 16:12 ` Bart Van Assche
2018-01-09 16:12 ` Bart Van Assche
2018-01-09 16:17 ` Jens Axboe
2018-01-09 16:19 ` tj [this message]
2018-01-09 16:22 ` Jens Axboe
2018-01-08 19:15 ` [PATCH 3/8] blk-mq: replace timeout synchronization with a RCU and generation based scheme Tejun Heo
2018-01-08 21:06 ` Bart Van Assche
2018-01-08 21:06 ` Bart Van Assche
2018-01-09 15:46 ` tj
2018-01-08 23:29 ` Bart Van Assche
2018-01-08 23:29 ` Bart Van Assche
2018-01-09 15:46 ` tj
2018-01-08 19:15 ` [PATCH 4/8] blk-mq: use blk_mq_rq_state() instead of testing REQ_ATOM_COMPLETE Tejun Heo
2018-01-08 22:03 ` Bart Van Assche
2018-01-08 22:03 ` Bart Van Assche
2018-01-08 19:15 ` [PATCH 5/8] blk-mq: make blk_abort_request() trigger timeout path Tejun Heo
2018-01-08 22:10 ` Bart Van Assche
2018-01-08 22:10 ` Bart Van Assche
2018-01-09 16:02 ` tj
2018-01-08 19:15 ` [PATCH 6/8] blk-mq: remove REQ_ATOM_COMPLETE usages from blk-mq Tejun Heo
2018-01-08 23:36 ` Bart Van Assche
2018-01-08 23:36 ` Bart Van Assche
2018-01-08 19:15 ` [PATCH 7/8] blk-mq: remove REQ_ATOM_STARTED Tejun Heo
2018-01-08 23:47 ` Bart Van Assche
2018-01-08 23:47 ` Bart Van Assche
2018-01-08 19:15 ` [PATCH 8/8] blk-mq: rename blk_mq_hw_ctx->queue_rq_srcu to ->srcu Tejun Heo
2018-01-08 23:48 ` Bart Van Assche
2018-01-08 23:48 ` Bart Van Assche
2018-01-09 16:29 [PATCHSET v5] blk-mq: reimplement timeout handling Tejun Heo
2018-01-09 16:29 ` [PATCH 2/8] blk-mq: protect completion path with RCU Tejun Heo
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=20180109161914.GM3668920@devbig577.frc2.facebook.com \
--to=tj@kernel.org \
--cc=Bart.VanAssche@wdc.com \
--cc=axboe@kernel.dk \
--cc=clm@fb.com \
--cc=jack@suse.cz \
--cc=jbacik@fb.com \
--cc=jianchao.w.wang@oracle.com \
--cc=kernel-team@fb.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.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.