Re: [PATCH v3 0/11] Fix race conditions related to stopping block layer queues

Hi Bart, I'm running linux 4.9-rc1 + linux-block/for-linus, and alternating tests with and without this series. Without this, I'm not seeing any problems in a link-down test while running fio after ~30 runs. With this series, I only see the test pass infrequently. Most of the time I observe one

Re: [PATCH 3/3 v2] md: unblock array if bad blocks have been acknowledged

On Tue, Oct 18, 2016 at 04:10:24PM +0200, Tomasz Majchrzak wrote: > Once external metadata handler acknowledges all bad blocks (by writing > to rdev 'bad_blocks' sysfs file), it requests to unblock the array. > Check if all bad blocks are actually acknowledged as there might be a > race if new bad

Re: [PATCH v3 08/11] SRP transport: Move queuecommand() wait code to SCSI core

Looks fine, Reviewed-by: Christoph Hellwig -- To unsubscribe from this list: send the line "unsubscribe linux-block" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

Re: [PATCH v3 09/11] SRP transport, scsi-mq: Wait for .queue_rq() if necessary

Looks fine, Reviewed-by: Christoph Hellwig -- To unsubscribe from this list: send the line "unsubscribe linux-block" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

Re: [PATCH v3 05/11] blk-mq: Add a kick_requeue_list argument to blk_mq_requeue_request()

On Tue, Oct 18, 2016 at 02:51:02PM -0700, Bart Van Assche wrote: > Most blk_mq_requeue_request() and blk_mq_add_to_requeue_list() calls > are followed by kicking the requeue list. Hence add an argument to > these two functions that allows to kick the requeue list. This was > proposed by Christoph

Re: [PATCH v3 04/11] blk-mq: Introduce blk_mq_quiesce_queue()

> +/** > + * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have > finished > + * > + * Note: this function does not prevent that the struct request end_io() > + * callback function is invoked. Additionally, it is not prevented that > + * new queue_rq() calls occur unless the

Re: [PATCH v3 06/11] dm: Use BLK_MQ_S_STOPPED instead of QUEUE_FLAG_STOPPED in blk-mq code

This looks good: Reviewed-by: Christoph Hellwig On Tue, Oct 18, 2016 at 02:51:33PM -0700, Bart Van Assche wrote: > static void dm_mq_start_queue(struct request_queue *q) > { > - unsigned long flags; > - > - spin_lock_irqsave(q->queue_lock, flags); > -

Re: [PATCH v3 07/11] dm: Fix a race condition related to stopping and starting queues

Looks good: Reviewed-by: Christoph Hellwig FYI, I wonder how many of the blk_mq_stop_hw_queues do not need the quiesce call. In the long run it might be better to have blk_mq_stop_hw_queues to stop an quiesce, and have a __blk_mq_stop_hw_queues variant to just stop. -- To

Re: [PATCH v3 10/11] nvme: Use BLK_MQ_S_STOPPED instead of QUEUE_FLAG_STOPPED in blk-mq code

Looks fine, Reviewed-by: Christoph Hellwig -- To unsubscribe from this list: send the line "unsubscribe linux-block" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

Re: [PATCH v3 04/11] blk-mq: Introduce blk_mq_quiesce_queue()

On 10/19/2016 06:23 AM, Christoph Hellwig wrote: +/** + * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have finished + * + * Note: this function does not prevent that the struct request end_io() + * callback function is invoked. Additionally, it is not prevented that + * new

Re: [PATCH v6 1/3] block: Add iocontext priority to request

On 10/19/2016 12:05 PM, Tejun Heo wrote: Hello, On Mon, Oct 17, 2016 at 11:27:28AM -0700, Adam Manzanares wrote: Patch adds an association between iocontext ioprio and the ioprio of a request. This is done to enable request based drivers the ability to act on priority information stored in the

Re: [PATCH v6 3/3] ata: ATA Command Priority Disabled By Default

The 10/19/2016 14:05, Tejun Heo wrote: > On Mon, Oct 17, 2016 at 11:27:30AM -0700, Adam Manzanares wrote: > > Add a sysfs entry to turn on priority information being passed > > to a ATA device. By default this feature is turned off. > > > > This patch depends on ata: Enabling ATA Command

Re: [PATCH v6 1/3] block: Add iocontext priority to request

Hello, On Mon, Oct 17, 2016 at 11:27:28AM -0700, Adam Manzanares wrote: > Patch adds an association between iocontext ioprio and the ioprio of a > request. This is done to enable request based drivers the ability to > act on priority information stored in the request. An example being > ATA

Re: [PATCH v6 3/3] ata: ATA Command Priority Disabled By Default

Hello, Removed ata_ncq_prio_on() and renamed _on to _enable. If I messed up anything, please let me know. Also, can you please send a follow-up patch to make the store function reject prio enabling if the device doesn't support it? Thanks. -- 8< -- >From

Re: [PATCH 1/3] memremap.c : Add support for ZONE_DEVICE IO memory with struct pages.

On Wed, Oct 19, 2016 at 10:50:25AM -0700, Dan Williams wrote: > On Tue, Oct 18, 2016 at 2:42 PM, Stephen Bates wrote: > > From: Logan Gunthorpe > > > > We build on recent work that adds memory regions owned by a device > > driver (ZONE_DEVICE) [1] and to

Re: [PATCH v3 02/11] blk-mq: Introduce blk_mq_hctx_stopped()

On Tue, Oct 18, 2016 at 02:49:09PM -0700, Bart Van Assche wrote: > Multiple functions test the BLK_MQ_S_STOPPED bit so introduce > a helper function that performs this test. Looks sensible. Any reason to have it in the public blk-mq.h instead of the private one, though? I see that dm is using

Re: [PATCH v3 01/11] blk-mq: Do not invoke .queue_rq() for a stopped queue

Good catch, Reviewed-by: Christoph Hellwig -- To unsubscribe from this list: send the line "unsubscribe linux-block" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html

Re: [PATCH 1/3] memremap.c : Add support for ZONE_DEVICE IO memory with struct pages.

On Tue, Oct 18, 2016 at 2:42 PM, Stephen Bates wrote: > From: Logan Gunthorpe > > We build on recent work that adds memory regions owned by a device > driver (ZONE_DEVICE) [1] and to add struct page support for these new > regions of memory [2]. > > 1.

Re: [PATCH v6 3/3] ata: ATA Command Priority Disabled By Default

On Mon, Oct 17, 2016 at 11:27:30AM -0700, Adam Manzanares wrote: > Add a sysfs entry to turn on priority information being passed > to a ATA device. By default this feature is turned off. > > This patch depends on ata: Enabling ATA Command Priorities > > Signed-off-by: Adam Manzanares