> * non-volatile media on completion.
> + * WRITE_BG Background write. This is for background activity like
> + * the periodic flush and background threshold writeback
> *
> */
> #define RW_MASK REQ_OP_WRITE
> @@ -202,6
On 10/27/2016 12:53 AM, 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 Hellwig.
>
>
On 10/27/2016 12:54 AM, Bart Van Assche wrote:
> Instead of manipulating both QUEUE_FLAG_STOPPED and BLK_MQ_S_STOPPED
> in the dm start and stop queue functions, only manipulate the latter
> flag. Change blk_queue_stopped() tests into blk_mq_queue_stopped().
>
> Signed-off-by: Bart Van Assche
Hi Robert,
please explain your use cases that isn't handled. The one and only
reason to set MSDBD to 1 is to make the code a lot simpler given that
there is no real use case for supporting more.
RDMA uses memory registrations to register large and possibly
discontiguous data regions for a
Hi Robert,
There is no feature called "Multiple SGL in one NVMe capsule". The
NVMe over Fabrics specification allows a controller to advertise how
many SGL descriptors it supports using the MSDBD Identify field:
"Maximum SGL Data Block Descriptors (MSDBD): This field indicates the
maximum
Hi Christoph,
Thanks , got it.
Could you please do me favor to let me know the background why we ONLY support
" MSDBD ==1"? I am NOT trying to resist or oppose anything , I just want to
know the reason. You know, it is a little wired for me, as "MSDBD ==1" does
not fulfill all the use
On Thu, Oct 27, 2016 at 11:26 AM, Jan Kara wrote:
> On Wed 26-10-16 10:12:38, Jens Axboe wrote:
>> On 10/26/2016 10:04 AM, Paolo Valente wrote:
>> >
>> >>Il giorno 26 ott 2016, alle ore 17:32, Jens Axboe ha
>> >>scritto:
>> >>
>> >>On 10/26/2016 09:29 AM,
You do realise that local filesystems can silently change the
location of file data at any point in time, so there is no such
thing as a "stable mapping" of file data to block device addresses
in userspace?
If you want remote access to the blocks owned and controlled by a
filesystem, then you
Add ECC error codes to enable the appropriate handling in the target.
Signed-off-by: Javier González
---
include/linux/lightnvm.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index e3ccaff..33643ae 100644
---
Device blocks should be marked by the device and considered as bad
blocks by the media manager. Thus, do not make assumptions on which
blocks are going to be used by the device. In doing so we might lose
valid blocks from the free list.
Signed-off-by: Javier González
---
Bad blocks should be managed by block owners. This would be either
targets for data blocks or sysblk for system blocks.
In order to support this, export two functions: One to mark a block as
an specific type (e.g., bad block) and another to update the bad block
table on the device.
Move bad
On 10/26/2016 10:52 PM, Hannes Reinecke wrote:
Hmm. Can't say I like having to have two RCU structure for the same
purpose, but I guess that can't be helped.
Hello Hannes,
There are two RCU structures because of BLK_MQ_F_BLOCKING. Today only
the nbd driver sets that flag. If the nbd driver
On Thu, Oct 27, 2016 at 01:22:49PM +0300, Sagi Grimberg wrote:
> Christoph, did you manage to leap to the future and solve the
> RDMA persistency hole? :)
>
> e.g. what happens with O_DSYNC in this model? Or you did
> a message exchange for commits?
Yes, pNFS calls this the layoutcommit. That
Looks good,
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
On target initialization, targets use callbacks to the media manager to
configure the LUNs they use. In order to simplify the flow, drop this
callbacks and manage everything internally on the media manager.
By making use of the newly introduce LUN management structure, the media
manager knows
rrpc cannot handle bios of size > 256kb due to NVME's 64 bit completion
bitmap. If a larger bio comes, split it explicitly.
Signed-off-by: Javier González
---
drivers/lightnvm/rrpc.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/lightnvm/rrpc.c
Erases might be subject to host hints. An example is multi-plane
programming to erase blocks in parallel. Enable targets to specify this
hints.
Signed-off-by: Javier González
---
drivers/lightnvm/core.c | 9 ++---
drivers/lightnvm/gennvm.c| 5 ++---
> > Hi Robert,
>
> Hey Robert, Christoph,
>
> > please explain your use cases that isn't handled. The one and only
> > reason to set MSDBD to 1 is to make the code a lot simpler given that
> > there is no real use case for supporting more.
> >
> > RDMA uses memory registrations to register
LUNs can be exclusively owned by a target through the media manager's
reserve_lun function. In this case, the target should implement its own
provisioning and manage internally the free/used/bad block list.
This patch introduces a LUN management structure that can be passed on
to LUN exclusive
If CONFIG_NVM is disabled, loading null_block module with use_lightnvm=1
fails. But there are no messages and documents related to the failure.
So the patch adds the notes to use LightNVM.
Signed-off-by: Yasuaki Ishimatsu
Cc: Jens Axboe
---
Device blocks should be marked by the device and considered as bad
blocks by the media manager. Thus, do not make assumptions on which
blocks are going to be used by the device. In doing so we might lose
valid blocks from the free list.
Signed-off-by: Javier González
---
On Thu, Oct 27, 2016 at 08:41:27PM +0100, Mark Brown wrote:
> Plus the benchmarking to verify that it works well of course, especially
> initially where it'll also be a new queue infrastructure as well as the
> blk-mq conversion itself. It does feel like something that's going to
> take at least
V2: Rebase patches on Matias' for-next
Javier González (7):
lightnvm: enable to send hint to erase command
lightnvm: do not decide on device blocks
lightnvm: manage block list on LUN owner
lightnvm: drop reserve and release LUN callbacks
lightnvm: export set bad block table
lightnvm:
[...]
>> Instead, what I can tell, as we have been looking into converting mmc
>> (which I maintains) and that is indeed a significant amount of work.
>> We will need to rip out all of the mmc request management, and most
>> likely we also need to extend the blkmq interface - as to be able to
>>
On Thu, Oct 27, 2016 at 12:21:06PM -0600, Jens Axboe wrote:
> On 10/27/2016 12:13 PM, Ulf Hansson wrote:
> > I can imagine, that it's not always a straight forward "convert to blk
> > mq" patch for every block device driver.
> Well, I've actually done a few conversions, and it's not difficult at
rrpc cannot handle bios of size > 256kb due to NVMe using a 64 bit
bitmap to signal I/O completion. If a larger bio comes, split it
explicitly.
Signed-off-by: Javier González
---
drivers/lightnvm/rrpc.c | 6 ++
1 file changed, 6 insertions(+)
diff --git
Add ECC error codes to enable the appropriate handling in the target.
Signed-off-by: Javier González
---
include/linux/lightnvm.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index e3ccaff..33643ae 100644
---
From: Javier González
LUNs can be exclusively owned by a target through the media manager's
reserve_lun function. In this case, the target should implement its own
provisioning and manage internally the free/used/bad block list.
This patch introduces a LUN management
From: Javier González
On target initialization, targets use callbacks to the media manager to
configure the LUNs they use. In order to simplify the flow, drop this
callbacks and manage everything internally on the media manager.
By making use of the newly introduce LUN
Erases might be subject to host hints. An example is multi-plane
programming to erase blocks in parallel. Enable targets to specify this
hints.
Signed-off-by: Javier González
---
drivers/lightnvm/core.c | 9 ++---
drivers/lightnvm/gennvm.c| 5 ++---
On 10/27/2016 01:34 PM, Ulf Hansson wrote:
[...]
Instead, what I can tell, as we have been looking into converting mmc
(which I maintains) and that is indeed a significant amount of work.
We will need to rip out all of the mmc request management, and most
likely we also need to extend the
On Wed, Oct 26, 2016 at 03:54:07PM -0700, Bart Van Assche wrote:
> Instead of manipulating both QUEUE_FLAG_STOPPED and BLK_MQ_S_STOPPED
> in the dm start and stop queue functions, only manipulate the latter
> flag. Change blk_queue_stopped() tests into blk_mq_queue_stopped().
>
> Signed-off-by:
Looks good:
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
Looks good,
Reviewed-by: Sagi Grimberg
--
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
On 10/27/2016 08:34 AM, Grozdan wrote:
On Thu, Oct 27, 2016 at 11:26 AM, Jan Kara wrote:
On Wed 26-10-16 10:12:38, Jens Axboe wrote:
On 10/26/2016 10:04 AM, Paolo Valente wrote:
Il giorno 26 ott 2016, alle ore 17:32, Jens Axboe ha scritto:
On 10/26/2016
On 10/27/2016 03:26 AM, Jan Kara wrote:
On Wed 26-10-16 10:12:38, Jens Axboe wrote:
On 10/26/2016 10:04 AM, Paolo Valente wrote:
Il giorno 26 ott 2016, alle ore 17:32, Jens Axboe ha scritto:
On 10/26/2016 09:29 AM, Christoph Hellwig wrote:
On Wed, Oct 26, 2016 at
[...]
>
> I'm hesistant to add a new scheduler because it's very easy to add, very
> difficult to get rid of. If we do add BFQ as a legacy scheduler now,
> it'll take us years and years to get rid of it again. We should be
> moving towards LESS moving parts in the legacy path, not more.
Jens, I
On 10/27/2016 11:32 AM, Ulf Hansson wrote:
[...]
I'm hesistant to add a new scheduler because it's very easy to add, very
difficult to get rid of. If we do add BFQ as a legacy scheduler now,
it'll take us years and years to get rid of it again. We should be
moving towards LESS moving parts in
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
Hi Robert,
Hey Robert, Christoph,
please explain your use cases that isn't handled. The one and only
reason to set MSDBD to 1 is to make the code a lot simpler given that
there is no real use case for supporting more.
RDMA uses memory registrations to register large and possibly
On Wed, Oct 26, 2016 at 03:53:39PM -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
Looks fine,
Reviewed-by: Sagi Grimberg
--
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
On Wed, Oct 26, 2016 at 03:55:00PM -0700, Bart Van Assche wrote:
> Additionally, rename srp_wait_for_queuecommand() into
> scsi_wait_for_queuecommand() and add a comment about the
> queuecommand() call from scsi_send_eh_cmnd().
>
> Signed-off-by: Bart Van Assche
>
On Wed, Oct 26 2016 at 6:54pm -0400,
Bart Van Assche wrote:
> Instead of manipulating both QUEUE_FLAG_STOPPED and BLK_MQ_S_STOPPED
> in the dm start and stop queue functions, only manipulate the latter
> flag. Change blk_queue_stopped() tests into
On Wed, Oct 26, 2016 at 03:55:34PM -0700, Bart Van Assche wrote:
> Ensure that if scsi-mq is enabled that scsi_wait_for_queuecommand()
> waits until ongoing shost->hostt->queuecommand() calls have finished.
>
> Signed-off-by: Bart Van Assche
> Reviewed-by: Christoph
On Wed, Oct 26, 2016 at 03:53:39PM -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
Thanks for moving it,
Reviewed-by: Sagi Grimberg
--
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
Looks good,
Reviewed-by: Sagi Grimberg
--
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
Reviewed-by: Sagi Grimberg
--
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
On Wed, Oct 26, 2016 at 03:52:35PM -0700, Bart Van Assche wrote:
> Move the "hctx stopped" test and the insert request calls into
> blk_mq_direct_issue_request(). Rename that function into
> blk_mq_try_issue_directly() to reflect its new semantics. Pass
> the hctx pointer to that function instead
On Wed, Oct 26, 2016 at 03:50:44PM -0700, Bart Van Assche wrote:
> The meaning of the BLK_MQ_S_STOPPED flag is "do not call
> .queue_rq()". Hence modify blk_mq_make_request() such that requests
> are queued instead of issued if a queue has been stopped.
>
> Reported-by: Ming Lei
On Wed, Oct 26, 2016 at 03:52:35PM -0700, Bart Van Assche wrote:
> Move the "hctx stopped" test and the insert request calls into
> blk_mq_direct_issue_request(). Rename that function into
> blk_mq_try_issue_directly() to reflect its new semantics. Pass
> the hctx pointer to that function instead
On Wed 26-10-16 10:12:38, Jens Axboe wrote:
> On 10/26/2016 10:04 AM, Paolo Valente wrote:
> >
> >>Il giorno 26 ott 2016, alle ore 17:32, Jens Axboe ha
> >>scritto:
> >>
> >>On 10/26/2016 09:29 AM, Christoph Hellwig wrote:
> >>>On Wed, Oct 26, 2016 at 05:13:07PM +0200, Arnd
53 matches
Mail list logo