From: Hannes Reinecke <hare@suse.de>
To: Ming Lei <ming.lei@redhat.com>, Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, John Garry <john.garry@huawei.com>,
Bart Van Assche <bvanassche@acm.org>,
Hannes Reinecke <hare@suse.com>, Christoph Hellwig <hch@lst.de>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH V8 11/11] block: deactivate hctx when the hctx is actually inactive
Date: Fri, 24 Apr 2020 15:56:34 +0200 [thread overview]
Message-ID: <0638a28c-9cbe-fbd2-9123-69efee737565@suse.de> (raw)
In-Reply-To: <20200424102351.475641-12-ming.lei@redhat.com>
On 4/24/20 12:23 PM, Ming Lei wrote:
> Run queue on dead CPU still may be triggered in some corner case,
> such as one request is requeued after CPU hotplug is handled.
>
> So handle this corner case during run queue.
>
> Cc: John Garry <john.garry@huawei.com>
> Cc: Bart Van Assche <bvanassche@acm.org>
> Cc: Hannes Reinecke <hare@suse.com>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> ---
> block/blk-mq.c | 30 ++++++++++--------------------
> 1 file changed, 10 insertions(+), 20 deletions(-)
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index a4a26bb23533..68088ff5460c 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -43,6 +43,8 @@
> static void blk_mq_poll_stats_start(struct request_queue *q);
> static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
>
> +static void blk_mq_hctx_deactivate(struct blk_mq_hw_ctx *hctx);
> +
> static int blk_mq_poll_stats_bkt(const struct request *rq)
> {
> int ddir, sectors, bucket;
> @@ -1376,28 +1378,16 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
> int srcu_idx;
>
> /*
> - * We should be running this queue from one of the CPUs that
> - * are mapped to it.
> - *
> - * There are at least two related races now between setting
> - * hctx->next_cpu from blk_mq_hctx_next_cpu() and running
> - * __blk_mq_run_hw_queue():
> - *
> - * - hctx->next_cpu is found offline in blk_mq_hctx_next_cpu(),
> - * but later it becomes online, then this warning is harmless
> - * at all
> - *
> - * - hctx->next_cpu is found online in blk_mq_hctx_next_cpu(),
> - * but later it becomes offline, then the warning can't be
> - * triggered, and we depend on blk-mq timeout handler to
> - * handle dispatched requests to this hctx
> + * BLK_MQ_S_INACTIVE may not deal with some requeue corner case:
> + * one request is requeued after cpu unplug is handled, so check
> + * if the hctx is actually inactive. If yes, deactive it and
> + * re-submit all requests in the queue.
> */
> if (!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
> - cpu_online(hctx->next_cpu)) {
> - printk(KERN_WARNING "run queue from wrong CPU %d, hctx %s\n",
> - raw_smp_processor_id(),
> - cpumask_empty(hctx->cpumask) ? "inactive": "active");
> - dump_stack();
> + cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) >=
> + nr_cpu_ids) {
> + blk_mq_hctx_deactivate(hctx);
> + return;
> }
>
> /*
>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Cheers,
Hannes
--
Dr. Hannes Reinecke Teamlead Storage & Networking
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:[~2020-04-24 13:56 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-24 10:23 [PATCH V8 00/11] blk-mq: improvement CPU hotplug Ming Lei
2020-04-24 10:23 ` [PATCH V8 01/11] block: clone nr_integrity_segments and write_hint in blk_rq_prep_clone Ming Lei
2020-04-24 10:32 ` Christoph Hellwig
2020-04-24 12:43 ` Hannes Reinecke
2020-04-24 16:11 ` Martin K. Petersen
2020-04-24 10:23 ` [PATCH V8 02/11] block: add helper for copying request Ming Lei
2020-04-24 10:35 ` Christoph Hellwig
2020-04-24 12:43 ` Hannes Reinecke
2020-04-24 16:12 ` Martin K. Petersen
2020-04-24 10:23 ` [PATCH V8 03/11] blk-mq: mark blk_mq_get_driver_tag as static Ming Lei
2020-04-24 12:44 ` Hannes Reinecke
2020-04-24 16:13 ` Martin K. Petersen
2020-04-24 10:23 ` [PATCH V8 04/11] blk-mq: assign rq->tag in blk_mq_get_driver_tag Ming Lei
2020-04-24 10:35 ` Christoph Hellwig
2020-04-24 13:02 ` Hannes Reinecke
2020-04-25 2:54 ` Ming Lei
2020-04-25 18:26 ` Hannes Reinecke
2020-04-24 10:23 ` [PATCH V8 05/11] blk-mq: support rq filter callback when iterating rqs Ming Lei
2020-04-24 13:17 ` Hannes Reinecke
2020-04-25 3:04 ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 06/11] blk-mq: prepare for draining IO when hctx's all CPUs are offline Ming Lei
2020-04-24 13:23 ` Hannes Reinecke
2020-04-25 3:24 ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 07/11] blk-mq: stop to handle IO and drain IO before hctx becomes inactive Ming Lei
2020-04-24 10:38 ` Christoph Hellwig
2020-04-25 3:17 ` Ming Lei
2020-04-25 8:32 ` Christoph Hellwig
2020-04-25 9:34 ` Ming Lei
2020-04-25 9:53 ` Ming Lei
2020-04-25 15:48 ` Christoph Hellwig
2020-04-26 2:06 ` Ming Lei
2020-04-26 8:19 ` John Garry
2020-04-27 15:36 ` Christoph Hellwig
2020-04-28 1:10 ` Ming Lei
2020-04-27 19:03 ` Paul E. McKenney
2020-04-28 6:54 ` Christoph Hellwig
2020-04-28 15:58 ` Peter Zijlstra
2020-04-29 2:16 ` Ming Lei
2020-04-29 8:07 ` Will Deacon
2020-04-29 9:46 ` Ming Lei
2020-04-29 12:27 ` Will Deacon
2020-04-29 13:43 ` Ming Lei
2020-04-29 17:34 ` Will Deacon
2020-04-30 0:39 ` Ming Lei
2020-04-30 11:04 ` Will Deacon
2020-04-30 14:02 ` Ming Lei
2020-05-05 15:46 ` Christoph Hellwig
2020-05-06 1:24 ` Ming Lei
2020-05-06 7:28 ` Will Deacon
2020-05-06 8:07 ` Ming Lei
2020-05-06 9:56 ` Will Deacon
2020-05-06 10:22 ` Ming Lei
2020-04-29 17:46 ` Paul E. McKenney
2020-04-30 0:43 ` Ming Lei
2020-04-24 13:27 ` Hannes Reinecke
2020-04-25 3:30 ` Ming Lei
2020-04-24 13:42 ` John Garry
2020-04-25 3:41 ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 08/11] block: add blk_end_flush_machinery Ming Lei
2020-04-24 10:41 ` Christoph Hellwig
2020-04-25 3:44 ` Ming Lei
2020-04-25 8:11 ` Christoph Hellwig
2020-04-25 9:51 ` Ming Lei
2020-04-24 13:47 ` Hannes Reinecke
2020-04-25 3:47 ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 09/11] blk-mq: add blk_mq_hctx_handle_dead_cpu for handling cpu dead Ming Lei
2020-04-24 10:42 ` Christoph Hellwig
2020-04-25 3:48 ` Ming Lei
2020-04-24 13:48 ` Hannes Reinecke
2020-04-24 10:23 ` [PATCH V8 10/11] blk-mq: re-submit IO in case that hctx is inactive Ming Lei
2020-04-24 10:44 ` Christoph Hellwig
2020-04-25 3:52 ` Ming Lei
2020-04-24 13:55 ` Hannes Reinecke
2020-04-25 3:59 ` Ming Lei
2020-04-24 10:23 ` [PATCH V8 11/11] block: deactivate hctx when the hctx is actually inactive Ming Lei
2020-04-24 10:43 ` Christoph Hellwig
2020-04-24 13:56 ` Hannes Reinecke [this message]
2020-04-24 15:23 ` [PATCH V8 00/11] blk-mq: improvement CPU hotplug Jens Axboe
2020-04-24 15:40 ` Christoph Hellwig
2020-04-24 15:41 ` Jens Axboe
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=0638a28c-9cbe-fbd2-9123-69efee737565@suse.de \
--to=hare@suse.de \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=hare@suse.com \
--cc=hch@lst.de \
--cc=john.garry@huawei.com \
--cc=linux-block@vger.kernel.org \
--cc=ming.lei@redhat.com \
--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).