From: Ming Lei <ming.lei@redhat.com>
To: Hannes Reinecke <hare@suse.de>
Cc: Jens Axboe <axboe@kernel.dk>,
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 08/11] block: add blk_end_flush_machinery
Date: Sat, 25 Apr 2020 11:47:45 +0800 [thread overview]
Message-ID: <20200425034745.GH477579@T590> (raw)
In-Reply-To: <390e713c-8289-ba35-4e4a-86f0d1ba0cf4@suse.de>
On Fri, Apr 24, 2020 at 03:47:28PM +0200, Hannes Reinecke wrote:
> On 4/24/20 12:23 PM, Ming Lei wrote:
> > Flush requests aren't same with normal FS request:
> >
> > 1) one dedicated per-hctx flush rq is pre-allocated for sending flush request
> >
> > 2) flush request si issued to hardware via one machinary so that flush merge
> > can be applied
> >
> > We can't simply re-submit flush rqs via blk_steal_bios(), so add
> > blk_end_flush_machinery to collect flush requests which needs to
> > be resubmitted:
> >
> > - if one flush command without DATA is enough, send one flush, complete this
> > kind of requests
> >
> > - otherwise, add the request into a list and let caller re-submit it.
> >
> > 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>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > Signed-off-by: Ming Lei <ming.lei@redhat.com>
> > ---
> > block/blk-flush.c | 123 +++++++++++++++++++++++++++++++++++++++++++---
> > block/blk.h | 4 ++
> > 2 files changed, 120 insertions(+), 7 deletions(-)
> >
> > diff --git a/block/blk-flush.c b/block/blk-flush.c
> > index 977edf95d711..745d878697ed 100644
> > --- a/block/blk-flush.c
> > +++ b/block/blk-flush.c
> > @@ -170,10 +170,11 @@ static void blk_flush_complete_seq(struct request *rq,
> > unsigned int cmd_flags;
> > BUG_ON(rq->flush.seq & seq);
> > - rq->flush.seq |= seq;
> > + if (!error)
> > + rq->flush.seq |= seq;
> > cmd_flags = rq->cmd_flags;
> > - if (likely(!error))
> > + if (likely(!error && !fq->flush_queue_terminating))
> > seq = blk_flush_cur_seq(rq);
> > else
> > seq = REQ_FSEQ_DONE;
> > @@ -200,9 +201,15 @@ static void blk_flush_complete_seq(struct request *rq,
> > * normal completion and end it.
> > */
> > BUG_ON(!list_empty(&rq->queuelist));
> > - list_del_init(&rq->flush.list);
> > - blk_flush_restore_request(rq);
> > - blk_mq_end_request(rq, error);
> > +
> > + /* Terminating code will end the request from flush queue */
> > + if (likely(!fq->flush_queue_terminating)) {
> > + list_del_init(&rq->flush.list);
> > + blk_flush_restore_request(rq);
> > + blk_mq_end_request(rq, error);
> > + } else {
> > + list_move_tail(&rq->flush.list, pending);
> > + }
> > break;
> > default:
> > @@ -279,7 +286,8 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
> > struct request *flush_rq = fq->flush_rq;
> > /* C1 described at the top of this file */
> > - if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending))
> > + if (fq->flush_pending_idx != fq->flush_running_idx ||
> > + list_empty(pending) || fq->flush_queue_terminating)
> > return;
> > /* C2 and C3
> > @@ -331,7 +339,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
> > struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx);
> > if (q->elevator) {
> > - WARN_ON(rq->tag < 0);
> > + WARN_ON(rq->tag < 0 && !fq->flush_queue_terminating);
> > blk_mq_put_driver_tag(rq);
> > }
> > @@ -503,3 +511,104 @@ void blk_free_flush_queue(struct blk_flush_queue *fq)
> > kfree(fq->flush_rq);
> > kfree(fq);
> > }
> > +
> > +static void __blk_end_queued_flush(struct blk_flush_queue *fq,
> > + unsigned int queue_idx, struct list_head *resubmit_list,
> > + struct list_head *flush_list)
> > +{
> > + struct list_head *queue = &fq->flush_queue[queue_idx];
> > + struct request *rq, *nxt;
> > +
> > + list_for_each_entry_safe(rq, nxt, queue, flush.list) {
> > + unsigned int seq = blk_flush_cur_seq(rq);
> > +
> > + list_del_init(&rq->flush.list);
> > + blk_flush_restore_request(rq);
> > + if (!blk_rq_sectors(rq) || seq == REQ_FSEQ_POSTFLUSH )
> > + list_add_tail(&rq->queuelist, flush_list);
> > + else
> > + list_add_tail(&rq->queuelist, resubmit_list);
> > + }
> > +}
> > +
> > +static void blk_end_queued_flush(struct blk_flush_queue *fq,
> > + struct list_head *resubmit_list, struct list_head *flush_list)
> > +{
> > + unsigned long flags;
> > +
> > + spin_lock_irqsave(&fq->mq_flush_lock, flags);
> > + __blk_end_queued_flush(fq, 0, resubmit_list, flush_list);
> > + __blk_end_queued_flush(fq, 1, resubmit_list, flush_list);
> > + spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
> > +}
> > +
> > +/* complete requests which just requires one flush command */
> > +static void blk_complete_flush_requests(struct blk_flush_queue *fq,
> > + struct list_head *flush_list)
> > +{
> > + struct block_device *bdev;
> > + struct request *rq;
> > + int error = -ENXIO;
> > +
> > + if (list_empty(flush_list))
> > + return;
> > +
> > + rq = list_first_entry(flush_list, struct request, queuelist);
> > +
> > + /* Send flush via one active hctx so we can move on */
> > + bdev = bdget_disk(rq->rq_disk, 0);
> > + if (bdev) {
> > + error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL);
> > + bdput(bdev);
> > + }
> > +
> > + while (!list_empty(flush_list)) {
> > + rq = list_first_entry(flush_list, struct request, queuelist);
> > + list_del_init(&rq->queuelist);
> > + blk_mq_end_request(rq, error);
> > + }
> > +}
> > +
> I must admit I'm getting nervous if one mixes direct request manipulations
> with high-level 'blkdev_XXX' calls.
> Can't we just requeue everything including the flush itself, and letting the
> requeue algorithm pick a new hctx?
No, the biggest problem is that rq->mq_hctx is bound to the hctx(becomes inactive now)
since request allocation, so we can't requeue them simply.
What we need here is simply one flush command, blkdev_issue_flush() does
exactly what we want.
Thanks,
Ming
next prev parent reply other threads:[~2020-04-25 3:48 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 [this message]
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
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=20200425034745.GH477579@T590 \
--to=ming.lei@redhat.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=hare@suse.com \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=john.garry@huawei.com \
--cc=linux-block@vger.kernel.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).