From: Hannes Reinecke <hare@suse.de>
To: Christoph Hellwig <hch@lst.de>,
James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Jens Axboe <axboe@kernel.dk>,
Bart Van Assche <bvanassche@fusionio.com>,
Robert Elliott <Elliott@hp.com>,
linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 06/14] scsi: convert target_busy to an atomic_t
Date: Wed, 09 Jul 2014 13:15:39 +0200 [thread overview]
Message-ID: <53BD245B.1060709@suse.de> (raw)
In-Reply-To: <1403715121-1201-7-git-send-email-hch@lst.de>
On 06/25/2014 06:51 PM, Christoph Hellwig wrote:
> Avoid taking the host-wide host_lock to check the per-target queue limit.
> Instead we do an atomic_inc_return early on to grab our slot in the queue,
> and if nessecary decrement it after finishing all checks.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
> drivers/scsi/scsi_lib.c | 52 ++++++++++++++++++++++++++------------------
> include/scsi/scsi_device.h | 4 ++--
> 2 files changed, 33 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
> index 18e6449..5e269d6 100644
> --- a/drivers/scsi/scsi_lib.c
> +++ b/drivers/scsi/scsi_lib.c
> @@ -294,7 +294,7 @@ void scsi_device_unbusy(struct scsi_device *sdev)
>
> spin_lock_irqsave(shost->host_lock, flags);
> shost->host_busy--;
> - starget->target_busy--;
> + atomic_dec(&starget->target_busy);
> if (unlikely(scsi_host_in_recovery(shost) &&
> (shost->host_failed || shost->host_eh_scheduled)))
> scsi_eh_wakeup(shost);
> @@ -361,7 +361,7 @@ static inline int scsi_device_is_busy(struct scsi_device *sdev)
> static inline int scsi_target_is_busy(struct scsi_target *starget)
> {
> return ((starget->can_queue > 0 &&
> - starget->target_busy >= starget->can_queue) ||
> + atomic_read(&starget->target_busy) >= starget->can_queue) ||
> starget->target_blocked);
> }
>
> @@ -1305,37 +1305,49 @@ static inline int scsi_target_queue_ready(struct Scsi_Host *shost,
> struct scsi_device *sdev)
> {
> struct scsi_target *starget = scsi_target(sdev);
> - int ret = 0;
> + unsigned int busy;
>
> - spin_lock_irq(shost->host_lock);
> if (starget->single_lun) {
> + spin_lock_irq(shost->host_lock);
> if (starget->starget_sdev_user &&
> - starget->starget_sdev_user != sdev)
> - goto out;
> + starget->starget_sdev_user != sdev) {
> + spin_unlock_irq(shost->host_lock);
> + return 0;
> + }
> starget->starget_sdev_user = sdev;
> + spin_unlock_irq(shost->host_lock);
> }
>
> - if (starget->target_busy == 0 && starget->target_blocked) {
> + busy = atomic_inc_return(&starget->target_busy) - 1;
> + if (busy == 0 && starget->target_blocked) {
> /*
> * unblock after target_blocked iterates to zero
> */
> - if (--starget->target_blocked != 0)
> - goto out;
> + spin_lock_irq(shost->host_lock);
> + if (--starget->target_blocked != 0) {
> + spin_unlock_irq(shost->host_lock);
> + goto out_dec;
> + }
> + spin_unlock_irq(shost->host_lock);
>
> SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget,
> "unblocking target at zero depth\n"));
> }
>
> - if (scsi_target_is_busy(starget)) {
> - list_move_tail(&sdev->starved_entry, &shost->starved_list);
> - goto out;
> - }
> + if (starget->can_queue > 0 && busy >= starget->can_queue)
> + goto starved;
> + if (starget->target_blocked)
> + goto starved;
>
> - scsi_target(sdev)->target_busy++;
> - ret = 1;
> -out:
> + return 1;
> +
> +starved:
> + spin_lock_irq(shost->host_lock);
> + list_move_tail(&sdev->starved_entry, &shost->starved_list);
> spin_unlock_irq(shost->host_lock);
> - return ret;
> +out_dec:
> + atomic_dec(&starget->target_busy);
> + return 0;
> }
>
> /*
> @@ -1445,7 +1457,7 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
> spin_unlock(sdev->request_queue->queue_lock);
> spin_lock(shost->host_lock);
> shost->host_busy++;
> - starget->target_busy++;
> + atomic_inc(&starget->target_busy);
> spin_unlock(shost->host_lock);
> spin_lock(sdev->request_queue->queue_lock);
>
> @@ -1615,9 +1627,7 @@ static void scsi_request_fn(struct request_queue *q)
> return;
>
> host_not_ready:
> - spin_lock_irq(shost->host_lock);
> - scsi_target(sdev)->target_busy--;
> - spin_unlock_irq(shost->host_lock);
> + atomic_dec(&scsi_target(sdev)->target_busy);
> not_ready:
> /*
> * lock q, handle tag, requeue req, and decrement device_busy. We
> diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
> index 816e8a2..446f741 100644
> --- a/include/scsi/scsi_device.h
> +++ b/include/scsi/scsi_device.h
> @@ -290,8 +290,8 @@ struct scsi_target {
> unsigned int expecting_lun_change:1; /* A device has reported
> * a 3F/0E UA, other devices on
> * the same target will also. */
> - /* commands actually active on LLD. protected by host lock. */
> - unsigned int target_busy;
> + /* commands actually active on LLD. */
> + atomic_t target_busy;
> /*
> * LLDs should set this in the slave_alloc host template callout.
> * If set to zero then there is not limit.
>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Cheers,
Hannes
--
Dr. Hannes Reinecke zSeries & Storage
hare@suse.de +49 911 74053 688
SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: J. Hawn, J. Guild, F. Imendörffer, HRB 16746 (AG Nürnberg)
next prev parent reply other threads:[~2014-07-09 11:15 UTC|newest]
Thread overview: 86+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-25 16:51 scsi-mq V2 Christoph Hellwig
2014-06-25 16:51 ` [PATCH 01/14] sd: don't use rq->cmd_len before setting it up Christoph Hellwig
2014-07-09 11:12 ` Hannes Reinecke
2014-07-09 15:03 ` Christoph Hellwig
2014-06-25 16:51 ` [PATCH 02/14] scsi: split __scsi_queue_insert Christoph Hellwig
2014-07-09 11:12 ` Hannes Reinecke
2014-06-25 16:51 ` [PATCH 03/14] scsi: centralize command re-queueing in scsi_dispatch_fn Christoph Hellwig
2014-07-08 20:51 ` Elliott, Robert (Server Storage)
2014-07-09 6:40 ` Christoph Hellwig
2014-07-09 11:13 ` Hannes Reinecke
2014-06-25 16:51 ` [PATCH 04/14] scsi: set ->scsi_done before calling scsi_dispatch_cmd Christoph Hellwig
2014-07-09 11:14 ` Hannes Reinecke
2014-06-25 16:51 ` [PATCH 05/14] scsi: push host_lock down into scsi_{host,target}_queue_ready Christoph Hellwig
2014-07-09 11:14 ` Hannes Reinecke
2014-06-25 16:51 ` [PATCH 06/14] scsi: convert target_busy to an atomic_t Christoph Hellwig
2014-07-09 11:15 ` Hannes Reinecke [this message]
2014-06-25 16:51 ` [PATCH 07/14] scsi: convert host_busy to atomic_t Christoph Hellwig
2014-07-09 11:15 ` Hannes Reinecke
2014-06-25 16:51 ` [PATCH 08/14] scsi: convert device_busy " Christoph Hellwig
2014-07-09 11:16 ` Hannes Reinecke
2014-07-09 16:49 ` James Bottomley
2014-07-10 6:01 ` Christoph Hellwig
2014-06-25 16:51 ` [PATCH 09/14] scsi: fix the {host,target,device}_blocked counter mess Christoph Hellwig
2014-07-09 11:12 ` Hannes Reinecke
2014-07-10 6:06 ` Christoph Hellwig
2014-06-25 16:51 ` [PATCH 10/14] scsi: only maintain target_blocked if the driver has a target queue limit Christoph Hellwig
2014-07-09 11:19 ` Hannes Reinecke
2014-07-09 15:05 ` Christoph Hellwig
2014-06-25 16:51 ` [PATCH 11/14] scsi: unwind blk_end_request_all and blk_end_request_err calls Christoph Hellwig
2014-07-09 11:20 ` Hannes Reinecke
2014-06-25 16:51 ` [PATCH 12/14] scatterlist: allow chaining to preallocated chunks Christoph Hellwig
2014-07-09 11:21 ` Hannes Reinecke
2014-06-25 16:52 ` [PATCH 13/14] scsi: add support for a blk-mq based I/O path Christoph Hellwig
2014-07-09 11:25 ` Hannes Reinecke
2014-07-16 11:13 ` Mike Christie
2014-07-16 11:16 ` Christoph Hellwig
2014-06-25 16:52 ` [PATCH 14/14] fnic: reject device resets without assigned tags for the blk-mq case Christoph Hellwig
2014-07-09 11:27 ` Hannes Reinecke
2014-06-26 4:50 ` scsi-mq V2 Jens Axboe
2014-06-26 22:07 ` Elliott, Robert (Server Storage)
2014-06-27 14:42 ` Bart Van Assche
2014-06-30 15:20 ` Jens Axboe
2014-06-30 15:25 ` Christoph Hellwig
2014-06-30 15:54 ` Martin K. Petersen
2014-07-08 14:48 ` Christoph Hellwig
2014-07-09 16:39 ` Douglas Gilbert
2014-07-09 19:38 ` Jens Axboe
2014-07-10 0:53 ` Elliott, Robert (Server Storage)
2014-07-10 6:20 ` Christoph Hellwig
2014-07-10 13:36 ` Benjamin LaHaise
2014-07-10 13:39 ` Jens Axboe
2014-07-10 13:44 ` Benjamin LaHaise
2014-07-10 13:48 ` Jens Axboe
2014-07-10 13:50 ` Benjamin LaHaise
2014-07-10 13:52 ` Jens Axboe
2014-07-10 13:50 ` Christoph Hellwig
2014-07-10 13:52 ` Jens Axboe
2014-07-10 14:36 ` Elliott, Robert (Server Storage)
2014-07-10 14:45 ` Benjamin LaHaise
2014-07-10 15:11 ` Jeff Moyer
2014-07-10 19:59 ` Jens Axboe
2014-07-10 20:05 ` Jeff Moyer
2014-07-10 20:06 ` Jens Axboe
2014-07-10 15:51 ` Elliott, Robert (Server Storage)
2014-07-10 16:04 ` Christoph Hellwig
2014-07-10 16:14 ` Christoph Hellwig
2014-07-10 18:49 ` Elliott, Robert (Server Storage)
2014-07-10 19:14 ` Jeff Moyer
2014-07-10 19:36 ` Jeff Moyer
2014-07-10 21:10 ` Elliott, Robert (Server Storage)
2014-07-11 6:02 ` Elliott, Robert (Server Storage)
2014-07-11 6:14 ` Christoph Hellwig
2014-07-11 14:33 ` Elliott, Robert (Server Storage)
2014-07-11 14:55 ` Benjamin LaHaise
2014-07-12 21:50 ` Elliott, Robert (Server Storage)
2014-07-12 23:20 ` Elliott, Robert (Server Storage)
2014-07-13 17:15 ` Elliott, Robert (Server Storage)
2014-07-14 17:15 ` Benjamin LaHaise
2014-07-14 9:13 ` Sagi Grimberg
2014-08-21 12:32 ` Performance degradation in IO writes vs. reads (was scsi-mq V2) Sagi Grimberg
2014-08-21 13:03 ` Christoph Hellwig
2014-08-21 14:02 ` Sagi Grimberg
2014-08-24 16:41 ` Sagi Grimberg
-- strict thread matches above, loose matches on Subject: below --
2014-07-18 10:12 scsi-mq V4 Christoph Hellwig
2014-07-18 10:13 ` [PATCH 06/14] scsi: convert target_busy to an atomic_t Christoph Hellwig
2014-07-22 3:56 ` Martin K. Petersen
2014-06-12 13:48 scsi-mq Christoph Hellwig
2014-06-12 13:48 ` [PATCH 06/14] scsi: convert target_busy to an atomic_t Christoph Hellwig
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=53BD245B.1060709@suse.de \
--to=hare@suse.de \
--cc=Elliott@hp.com \
--cc=James.Bottomley@HansenPartnership.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@fusionio.com \
--cc=hch@lst.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome