From: Bart Van Assche <Bart.VanAssche@wdc.com>
To: "jbacik@fb.com" <jbacik@fb.com>, "tj@kernel.org" <tj@kernel.org>,
"jack@suse.cz" <jack@suse.cz>, "clm@fb.com" <clm@fb.com>,
"axboe@kernel.dk" <axboe@kernel.dk>
Cc: "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 16:12:40 +0000 [thread overview]
Message-ID: <1515514359.2721.9.camel@wdc.com> (raw)
In-Reply-To: <20180108191542.379478-3-tj@kernel.org>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WARNING: multiple messages have this Message-ID (diff)
From: Bart Van Assche <Bart.VanAssche@wdc.com>
To: "jbacik@fb.com" <jbacik@fb.com>, "tj@kernel.org" <tj@kernel.org>,
"jack@suse.cz" <jack@suse.cz>, "clm@fb.com" <clm@fb.com>,
"axboe@kernel.dk" <axboe@kernel.dk>
Cc: "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 16:12:40 +0000 [thread overview]
Message-ID: <1515514359.2721.9.camel@wdc.com> (raw)
In-Reply-To: <20180108191542.379478-3-tj@kernel.org>
On Mon, 2018-01-08 at 11:15 -0800, Tejun Heo wrote:
> Currently, blk-mq protects only the issue path with RCU. This patch
> puts the completion path under the same RCU protection. This will be
> used to synchronize issue/completion against timeout by later patches,
> which will also add the comments.
>
> Signed-off-by: Tejun Heo <tj@kernel.org>
> ---
> block/blk-mq.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index ddc9261..6741c3e 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -584,11 +584,16 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
> void blk_mq_complete_request(struct request *rq)
> {
> struct request_queue *q = rq->q;
> + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
> + int srcu_idx;
>
> if (unlikely(blk_should_fake_timeout(q)))
> return;
> +
> + hctx_lock(hctx, &srcu_idx);
> if (!blk_mark_rq_complete(rq))
> __blk_mq_complete_request(rq);
> + hctx_unlock(hctx, srcu_idx);
> }
> EXPORT_SYMBOL(blk_mq_complete_request);
Hello Tejun,
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
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()?
Thanks,
Bart.
next prev parent reply other threads:[~2018-01-09 16:12 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 [this message]
2018-01-09 16:12 ` Bart Van Assche
2018-01-09 16:17 ` Jens Axboe
2018-01-09 16:19 ` tj
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=1515514359.2721.9.camel@wdc.com \
--to=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 \
--cc=tj@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.