Re: [dm-devel] [PATCH] multipath-tools:fix unexport/export LUN access permission multipath can't restore

Hi Hannes and Ben's, Thanks for your comments! We are agree with you. It is truly have the potential risk even we trigger an event to fresh udev database and continue to use this multipath but it seems to be not really safe in this way. -original- Hi Ben, On 2018/1/23 21:03, Benjamin

Re: [dm-devel] [PATCH V3] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 04:57:34PM +, Bart Van Assche wrote: > On Wed, 2018-01-24 at 00:37 +0800, Ming Lei wrote: > > On Tue, Jan 23, 2018 at 04:24:20PM +, Bart Van Assche wrote: > > > My opinion about this patch is as follows: > > > * Changing a blk_mq_delay_run_hw_queue() call followed

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 10:01:37PM +, Bart Van Assche wrote: > On Wed, 2018-01-24 at 00:59 +0800, Ming Lei wrote: > > How is that enough to fix the IO hang when driver returns STS_RESOURCE > > and the queue is idle? If you want to follow previous dm-rq's way of > > call

Re: [dm-devel] [PATCH] multipathd: update path's udev in uev_update_path

Hi Ben, Thanks for your reply. The purpose to update the path's udev is that if we want to call interface sysfs_attr_set_value() to trigger uevent for this device might use the old udev_device If this device already received a cheng uevent and updated. If we use the not update pp->udev in

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Wed, 2018-01-24 at 00:59 +0800, Ming Lei wrote: > How is that enough to fix the IO hang when driver returns STS_RESOURCE > and the queue is idle? If you want to follow previous dm-rq's way of > call blk_mq_delay_run_hw_queue() in .queue_rq(), the same trick need > to be applied to other drivers

[dm-devel] [FIX PATCH v2 09/20] libmultipath: hwtable: no_path_retry="queue" for NetApp NVMe

Netapp requested this default setting for NetApp E-Series NVMe in addition to "multibus". Also, finalize the product ID regex after consulting with NetApp (the FW reporting just "ONTAP Controller" was beta only). This obsoletes my previous "FIX" patch 'FIX "libmultipath: hwtable: multibus for

Re: [dm-devel] [PATCH V3] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Wed, 2018-01-24 at 00:37 +0800, Ming Lei wrote: > On Tue, Jan 23, 2018 at 04:24:20PM +, Bart Van Assche wrote: > > My opinion about this patch is as follows: > > * Changing a blk_mq_delay_run_hw_queue() call followed by return > > BLK_STS_DEV_RESOURCE into return BLK_STS_RESOURCE is wrong

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Wed, 2018-01-24 at 00:49 +0800, Ming Lei wrote: > On Tue, Jan 23, 2018 at 04:47:11PM +, Bart Van Assche wrote: > > On Wed, 2018-01-24 at 00:41 +0800, Ming Lei wrote: > > > Could you explain where to call call_rcu()? call_rcu() can't be used in > > > IO path at all. > > > > Can you explain

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 04:54:02PM +, Bart Van Assche wrote: > On Wed, 2018-01-24 at 00:49 +0800, Ming Lei wrote: > > On Tue, Jan 23, 2018 at 04:47:11PM +, Bart Van Assche wrote: > > > On Wed, 2018-01-24 at 00:41 +0800, Ming Lei wrote: > > > > Could you explain where to call call_rcu()?

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 04:47:11PM +, Bart Van Assche wrote: > On Wed, 2018-01-24 at 00:41 +0800, Ming Lei wrote: > > Could you explain where to call call_rcu()? call_rcu() can't be used in > > IO path at all. > > Can you explain what makes you think that call_rcu() can't be used in the >

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Wed, 2018-01-24 at 00:41 +0800, Ming Lei wrote: > Could you explain where to call call_rcu()? call_rcu() can't be used in > IO path at all. Can you explain what makes you think that call_rcu() can't be used in the I/O path? As you know call_rcu() invokes a function asynchronously. From

Re: [dm-devel] [PATCH V3] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 04:24:20PM +, Bart Van Assche wrote: > On Wed, 2018-01-24 at 00:16 +0800, Ming Lei wrote: > > @@ -1280,10 +1282,18 @@ bool blk_mq_dispatch_rq_list(struct request_queue > > *q, struct list_head *list, > > * - Some but not all block drivers stop a queue

Re: [dm-devel] [PATCH] block: neutralize blk_insert_cloned_request IO stall regression (was: Re: [RFC PATCH] blk-mq: fixup RESTART when queue becomes idle)

On Tue, 2018-01-23 at 10:22 +0100, Mike Snitzer wrote: > On Thu, Jan 18 2018 at 5:20pm -0500, > Bart Van Assche wrote: > > > On Thu, 2018-01-18 at 17:01 -0500, Mike Snitzer wrote: > > > And yet Laurence cannot reproduce any such lockups with your test... > > > > Hmm ...

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On 01/23/18 08:26, Ming Lei wrote: On Tue, Jan 23, 2018 at 08:17:02AM -0800, Bart Van Assche wrote: On 01/22/18 16:57, Ming Lei wrote: Even though RCU lock is held during dispatch, preemption or interrupt can happen too, so it is simply wrong to depend on the timing to make sure

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 08:37:26AM -0800, Bart Van Assche wrote: > On 01/23/18 08:26, Ming Lei wrote: > > On Tue, Jan 23, 2018 at 08:17:02AM -0800, Bart Van Assche wrote: > > > On 01/22/18 16:57, Ming Lei wrote: > > > > Even though RCU lock is held during dispatch, preemption or interrupt > > > >

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 08:17:02AM -0800, Bart Van Assche wrote: > > > On 01/22/18 16:57, Ming Lei wrote: > > Even though RCU lock is held during dispatch, preemption or interrupt > > can happen too, so it is simply wrong to depend on the timing to make > > sure __blk_mq_run_hw_queue() can see

Re: [dm-devel] [PATCH V3] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Wed, 2018-01-24 at 00:16 +0800, Ming Lei wrote: > @@ -1280,10 +1282,18 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, > struct list_head *list, >* - Some but not all block drivers stop a queue before >* returning BLK_STS_RESOURCE. Two exceptions are

Re: [dm-devel] [PATCH V3] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23 2018 at 11:16am -0500, Ming Lei wrote: > This status is returned from driver to block layer if device related > resource is run out of, but driver can guarantee that IO dispatch will > be triggered in future when the resource is available. > > This patch

Re: [dm-devel] [PATCH 1/5] blk-mq: introduce BLK_STS_DEV_RESOURCE

On 01/22/18 16:57, Ming Lei wrote: Even though RCU lock is held during dispatch, preemption or interrupt can happen too, so it is simply wrong to depend on the timing to make sure __blk_mq_run_hw_queue() can see the request in this situation. It is very unlikely that this race will ever be

Re: [dm-devel] [PATCH] multipathd: update path's udev in uev_update_path

On Tue, 2018-01-23 at 06:39 -0600, Benjamin Marzinski wrote: > On Mon, Jan 22, 2018 at 11:34:15AM +0100, Martin Wilck wrote: > > On Sat, 2018-01-20 at 02:30 +, Wuchongyun wrote: > > > Hi Martin and Ben, > > > Could you help to review this patch, thanks. > > > > > > When receiving a change

Re: [dm-devel] [PATCH V2] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, 2018-01-23 at 09:44 -0500, Mike Snitzer wrote: > On Tue, Jan 23 2018 at  9:27am -0500, > Ming Lei wrote: > > > Hello Martin, > > > > On Tue, Jan 23, 2018 at 08:30:41AM -0500, Martin K. Petersen wrote: > > > > > > Ming, > > > > > > > + * Block layer and block

Re: [dm-devel] [PATCH V2] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23 2018 at 9:27am -0500, Ming Lei wrote: > Hello Martin, > > On Tue, Jan 23, 2018 at 08:30:41AM -0500, Martin K. Petersen wrote: > > > > Ming, > > > > > + * Block layer and block driver specific status, which is ususally > > > returnd > >

Re: [dm-devel] [PATCH V2] blk-mq: introduce BLK_STS_DEV_RESOURCE

Hello Martin, On Tue, Jan 23, 2018 at 08:30:41AM -0500, Martin K. Petersen wrote: > > Ming, > > > + * Block layer and block driver specific status, which is ususally returnd > ^^^ > > + * from driver to block layer in IO

Re: [dm-devel] [PATCH V2] blk-mq: introduce BLK_STS_DEV_RESOURCE

On Tue, Jan 23, 2018 at 08:30:41AM -0500, Martin K. Petersen wrote: > > Ming, > > > + * Block layer and block driver specific status, which is ususally returnd > ^^^ > > + * from driver to block layer in IO path. > >

Re: [dm-devel] [PATCH V2] blk-mq: introduce BLK_STS_DEV_RESOURCE

Ming, > + * Block layer and block driver specific status, which is ususally returnd ^^^ > + * from driver to block layer in IO path. Given that the comment blurb is long and the flag not defined until later, it is not

Re: [dm-devel] [PATCH] multipath-tools:fix unexport/export LUN access permission multipath can't restore

Hi Ben, On 2018/1/23 21:03, Benjamin Marzinski wrote: > On Tue, Jan 23, 2018 at 10:52:35AM +0100, Hannes Reinecke wrote: >> On 01/23/2018 10:25 AM, Wuchongyun wrote: >>> Hi Christophe, Hannes, Martin, Xose and Benjamin, >>> >>> We meet below issue when doing the unexport/export LUN's access

Re: [dm-devel] [PATCH] multipath-tools:fix unexport/export LUN access permission multipath can't restore

On Tue, Jan 23, 2018 at 10:52:35AM +0100, Hannes Reinecke wrote: > On 01/23/2018 10:25 AM, Wuchongyun wrote: > > Hi Christophe, Hannes, Martin, Xose and Benjamin, > > > > We meet below issue when doing the unexport/export LUN's access permission > > test, this patch is a method to fix this

Re: [dm-devel] [PATCH] multipathd: update path's udev in uev_update_path

On Mon, Jan 22, 2018 at 11:34:15AM +0100, Martin Wilck wrote: > On Sat, 2018-01-20 at 02:30 +, Wuchongyun wrote: > > Hi Martin and Ben, > > Could you help to review this patch, thanks. > > > > When receiving a change uevent and calling uev_update_path, current > > code > > not update the

Re: [dm-devel] block: neutralize blk_insert_cloned_request IO stall regression (was: Re: [RFC PATCH] blk-mq: fixup RESTART when queue becomes idle)

On Tue, Jan 23 2018 at 7:17am -0500, Ming Lei wrote: > On Tue, Jan 23, 2018 at 8:15 PM, Mike Snitzer wrote: > > On Tue, Jan 23 2018 at 5:53am -0500, > > Ming Lei wrote: > > > >> Hi Mike, > >> > >> On Tue, Jan 23, 2018 at

Re: [dm-devel] block: neutralize blk_insert_cloned_request IO stall regression (was: Re: [RFC PATCH] blk-mq: fixup RESTART when queue becomes idle)

On Tue, Jan 23, 2018 at 8:15 PM, Mike Snitzer wrote: > On Tue, Jan 23 2018 at 5:53am -0500, > Ming Lei wrote: > >> Hi Mike, >> >> On Tue, Jan 23, 2018 at 10:22:04AM +0100, Mike Snitzer wrote: >> > On Thu, Jan 18 2018 at 5:20pm -0500, >> > Bart Van

Re: [dm-devel] block: neutralize blk_insert_cloned_request IO stall regression (was: Re: [RFC PATCH] blk-mq: fixup RESTART when queue becomes idle)

On Tue, Jan 23 2018 at 5:53am -0500, Ming Lei wrote: > Hi Mike, > > On Tue, Jan 23, 2018 at 10:22:04AM +0100, Mike Snitzer wrote: > > On Thu, Jan 18 2018 at 5:20pm -0500, > > Bart Van Assche wrote: > > > > > On Thu, 2018-01-18 at 17:01 -0500,

[dm-devel] [PATCH V2] blk-mq: introduce BLK_STS_DEV_RESOURCE

This status is returned from driver to block layer if device related resource is run out of, but driver can guarantee that IO dispatch will be triggered in future when the resource is available. This patch converts some drivers to use this return value. Meantime if driver returns BLK_STS_RESOURCE

Re: [dm-devel] [PATCH] block: neutralize blk_insert_cloned_request IO stall regression (was: Re: [RFC PATCH] blk-mq: fixup RESTART when queue becomes idle)

Hi Mike, On Tue, Jan 23, 2018 at 10:22:04AM +0100, Mike Snitzer wrote: > On Thu, Jan 18 2018 at 5:20pm -0500, > Bart Van Assche wrote: > > > On Thu, 2018-01-18 at 17:01 -0500, Mike Snitzer wrote: > > > And yet Laurence cannot reproduce any such lockups with your test...

Re: [dm-devel] multipath-tools: add INSPUR/MCS to hardware table

Hi, Xose, Thank you for your review work and suggestions. Attachment is the patch file generated by git format-patch, and pasted below. Please help to submit, thank you. >From 091bae5fec22c61f0c3e6f9ab848fecae5203122 Mon Sep 17 00:00:00 2001 From: Tom Geng Date: Tue,

Re: [dm-devel] [PATCH] multipath-tools:fix unexport/export LUN access permission multipath can't restore

On 01/23/2018 10:25 AM, Wuchongyun wrote: > Hi Christophe, Hannes, Martin, Xose and Benjamin, > > We meet below issue when doing the unexport/export LUN's access permission > test, this patch is a method to fix this issue. > If it is convenient for some of you, please help to review this patch,

[dm-devel] [PATCH] block: neutralize blk_insert_cloned_request IO stall regression (was: Re: [RFC PATCH] blk-mq: fixup RESTART when queue becomes idle)

On Thu, Jan 18 2018 at 5:20pm -0500, Bart Van Assche wrote: > On Thu, 2018-01-18 at 17:01 -0500, Mike Snitzer wrote: > > And yet Laurence cannot reproduce any such lockups with your test... > > Hmm ... maybe I misunderstood Laurence but I don't think that Laurence has >

[dm-devel] [PATCH] multipath-tools:fix unexport/export LUN access permission multipath can't restore

Hi Christophe, Hannes, Martin, Xose and Benjamin, We meet below issue when doing the unexport/export LUN's access permission test, this patch is a method to fix this issue. If it is convenient for some of you, please help to review this patch, thanks. fix unexport/export LUN access permission

Re: [dm-devel] [PATCH 4/5] blk-mq: introduce blk_get_request_notify

On Mon, Jan 22, 2018 at 05:13:03PM +, Bart Van Assche wrote: > On Mon, 2018-01-22 at 11:35 +0800, Ming Lei wrote: > > DM-MPATH need to allocate request from underlying queue, but when the > > allocation fails, there is no way to make underlying queue's RESTART > > to restart DM's queue. > > >

Re: [dm-devel] [PATCH 4/5] blk-mq: introduce blk_get_request_notify

On Mon, 2018-01-22 at 11:35 +0800, Ming Lei wrote: > DM-MPATH need to allocate request from underlying queue, but when the > allocation fails, there is no way to make underlying queue's RESTART > to restart DM's queue. > > This patch introduces blk_get_request_notify() for this purpose, and >