From: Hannes Reinecke <hare@suse.de>
To: Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
linux-block@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Jens Axboe <axboe@kernel.dk>,
Thomas Gleixner <tglx@linutronix.de>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>
Subject: Re: [PATCH 2/3] blk-mq: Always complete remote completions requests in softirq
Date: Mon, 25 Jan 2021 08:10:16 +0100 [thread overview]
Message-ID: <30ce5ce2-8b9a-8873-4b37-c8720300942b@suse.de> (raw)
In-Reply-To: <20210123201027.3262800-3-bigeasy@linutronix.de>
On 1/23/21 9:10 PM, Sebastian Andrzej Siewior wrote:
> Controllers with multiple queues have their IRQ-handelers pinned to a
> CPU. The core shouldn't need to complete the request on a remote CPU.
>
> Remove this case and always raise the softirq to complete the request.
>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
> ---
> block/blk-mq.c | 14 +-------------
> 1 file changed, 1 insertion(+), 13 deletions(-)
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index f285a9123a8b0..90348ae518461 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -628,19 +628,7 @@ static void __blk_mq_complete_request_remote(void *data)
> {
> struct request *rq = data;
>
> - /*
> - * For most of single queue controllers, there is only one irq vector
> - * for handling I/O completion, and the only irq's affinity is set
> - * to all possible CPUs. On most of ARCHs, this affinity means the irq
> - * is handled on one specific CPU.
> - *
> - * So complete I/O requests in softirq context in case of single queue
> - * devices to avoid degrading I/O performance due to irqsoff latency.
> - */
> - if (rq->q->nr_hw_queues == 1)
> - blk_mq_trigger_softirq(rq);
> - else
> - rq->q->mq_ops->complete(rq);
> + blk_mq_trigger_softirq(rq);
> }
>
> static inline bool blk_mq_complete_need_ipi(struct request *rq)
>
I don't get this.
This code is about _avoiding_ having to raise a softirq if the driver
exports more than one hardware queue.
So where exactly does the remote CPU case come in here?
Cheers,
Hannes
--
Dr. Hannes Reinecke Kernel Storage Architect
hare@suse.de +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Felix Imendörffer
next prev parent reply other threads:[~2021-01-25 7:52 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-23 20:10 [PATCH v3 0/3] blk-mq: Don't complete in IRQ, use llist_head Sebastian Andrzej Siewior
2021-01-23 20:10 ` [PATCH 1/3] smp: Process pending softirqs in flush_smp_call_function_from_idle() Sebastian Andrzej Siewior
2021-02-01 19:35 ` Sebastian Andrzej Siewior
2021-02-09 10:02 ` Peter Zijlstra
2021-02-09 11:35 ` Sebastian Andrzej Siewior
2021-01-23 20:10 ` [PATCH 2/3] blk-mq: Always complete remote completions requests in softirq Sebastian Andrzej Siewior
2021-01-25 7:10 ` Hannes Reinecke [this message]
2021-01-25 8:25 ` Christoph Hellwig
2021-01-25 8:30 ` Sebastian Andrzej Siewior
2021-01-25 8:32 ` Christoph Hellwig
2021-01-25 9:29 ` Sebastian Andrzej Siewior
2021-01-25 8:22 ` Christoph Hellwig
2021-01-25 8:49 ` Christoph Hellwig
2021-01-27 11:22 ` Daniel Wagner
2021-01-23 20:10 ` [PATCH 3/3] blk-mq: Use llist_head for blk_cpu_done Sebastian Andrzej Siewior
2021-01-25 8:30 ` Christoph Hellwig
2021-01-25 8:32 ` Sebastian Andrzej Siewior
2021-01-25 8:39 ` Christoph Hellwig
2021-01-25 9:54 ` [PATCH 3/3 v2] " Sebastian Andrzej Siewior
2021-01-25 10:14 ` Christoph Hellwig
2021-01-27 11:23 ` Daniel Wagner
2021-01-25 4:27 ` [PATCH v3 0/3] blk-mq: Don't complete in IRQ, use llist_head Jens Axboe
2021-02-10 14:43 ` Jens Axboe
-- strict thread matches above, loose matches on Subject: below --
2020-12-04 19:13 [PATCH 0/3 v2] " Sebastian Andrzej Siewior
2020-12-04 19:13 ` [PATCH 2/3] blk-mq: Always complete remote completions requests in softirq Sebastian Andrzej Siewior
2020-12-07 23:52 ` Jens Axboe
2020-12-08 8:22 ` Sebastian Andrzej Siewior
2020-12-08 8:44 ` Daniel Wagner
2020-12-08 11:36 ` Daniel Wagner
2020-12-08 11:49 ` Sebastian Andrzej Siewior
2020-12-08 12:41 ` Daniel Wagner
2020-12-08 12:52 ` Sebastian Andrzej Siewior
2020-12-08 12:57 ` Sebastian Andrzej Siewior
2020-12-08 13:27 ` Daniel Wagner
2020-12-17 16:45 ` Jens Axboe
2020-12-17 16:49 ` Daniel Wagner
2020-12-17 16:54 ` Jens Axboe
2020-12-08 13:13 ` Christoph Hellwig
2020-12-17 16:43 ` Sebastian Andrzej Siewior
2020-12-17 16:55 ` Jens Axboe
2020-12-17 16:58 ` Sebastian Andrzej Siewior
2020-12-17 17:05 ` Daniel Wagner
2020-12-17 18:16 ` Daniel Wagner
2020-12-17 18:22 ` Jens Axboe
2020-12-17 18:41 ` Daniel Wagner
2020-12-17 18:46 ` Jens Axboe
2020-12-17 19:07 ` Daniel Wagner
2020-12-17 19:13 ` Jens Axboe
2020-12-17 19:15 ` Daniel Wagner
2020-10-28 6:56 [PATCH RFC] blk-mq: Don't IPI requests on PREEMPT_RT Christoph Hellwig
2020-10-28 14:12 ` [PATCH 1/3] blk-mq: Don't complete on a remote CPU in force threaded mode Sebastian Andrzej Siewior
2020-10-28 14:12 ` [PATCH 2/3] blk-mq: Always complete remote completions requests in softirq Sebastian Andrzej Siewior
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=30ce5ce2-8b9a-8873-4b37-c8720300942b@suse.de \
--to=hare@suse.de \
--cc=axboe@kernel.dk \
--cc=bigeasy@linutronix.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
/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).