Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Wed, Jan 11, 2017 at 05:01:22PM -0500, Mike Snitzer wrote: > But I've seen you reference the need to stop multipath from allocating > its own requests. Are you referring to old request_fn request-based > multipath's clone_old_rq:alloc_old_clone_request? Yes, that one is the issue. It

Re: [PATCH 2/2] sd: Ignore zoned field for host-managed devices

On 01/12/2017 07:25 AM, Damien Le Moal wrote: There is no good match of the zoned filed of the block device characteristics page for host-managed devices. For these devices, the zoning model is derived directly from the device type. So ignore the zoned field for these drives. Signed-off-by:

Re: [PATCH 1/2] sd: Fix wrong DPOFUA disable in sd_read_cache_type

On 01/12/2017 07:25 AM, Damien Le Moal wrote: Zoned block devices force the use of READ/WRITE(16) commands by setting sdkp->use_16_for_rw and clearing sdkp->use_10_for_rw. This result in DPOFUA always being disabled for these drives as the assumed use of the deprecated READ/WRITE(6) commands

[PATCH 2/2] sd: Ignore zoned field for host-managed devices

There is no good match of the zoned filed of the block device characteristics page for host-managed devices. For these devices, the zoning model is derived directly from the device type. So ignore the zoned field for these drives. Signed-off-by: Damien Le Moal ---

[PATCH 1/2] sd: Fix wrong DPOFUA disable in sd_read_cache_type

Zoned block devices force the use of READ/WRITE(16) commands by setting sdkp->use_16_for_rw and clearing sdkp->use_10_for_rw. This result in DPOFUA always being disabled for these drives as the assumed use of the deprecated READ/WRITE(6) commands only looks at sdkp->use_10_for_rw. Strenghten the

[PATCH 0/2] sd fixes for zoned block devices

2 small fixes in this series: (1) Fix sd_read_cache_type so that DPOFUA is not disabled for zoned block devices supporting it. (2) Ignore the zoned field of the block device characteristics page for host-managed zoned block devices as there is no good match defined explicitely for HM by the

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

> > This is a separate topic. The initial proposal is for polling for > interrupt mitigation, you are talking about polling in the context of > polling for completion of an IO. > > We can definitely talk about this form of polling as well, but it should > be a separate topic and probably proposed

[LSF/MM TOPIC][LSF/MM ATTEND] IO completion polling for block drivers

Hi I'd like to discuss the ongoing work in the kernel to enable high priority IO via polling for completion in the blk-mq subsystem. Given that iopoll only really makes sense for low-latency, low queue depth environments (i.e. down below 10-20us) I'd like to discuss which drivers we think will

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

>> >> I'd like to attend LSF/MM and would like to discuss polling for block >> drivers. >> >> Currently there is blk-iopoll but it is neither as widely used as NAPI >> in the networking field and accoring to Sagi's findings in [1] >> performance with polling is not on par with IRQ usage. >> >> On

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 09:36 PM, Stephen Bates wrote: >>> >>> I'd like to attend LSF/MM and would like to discuss polling for block >>> drivers. >>> >>> Currently there is blk-iopoll but it is neither as widely used as NAPI >>> in the networking field and accoring to Sagi's findings in [1] >>> performance

Re: [PATCH 15/15] block: split scsi_request out of struct request

On Tue, Jan 10 2017, Christoph Hellwig wrote: > And require all drivers that want to support BLOCK_PC to allocate it > as the first thing of their private data. To support this the legacy > IDE and BSG code is switched to set cmd_size on their queues to let > the block layer allocate the

Re: [PATCH v2 0/4] cxlflash: Enhancements, cleanup and fixes

> "Uma" == Uma Krishnan writes: Uma> This patch series includes an enhancement to support a new command Uma> queuing model and also cleans up prints throughout the driver. The Uma> last patch in the series fixes a racing issue. Applied to 4.11/scsi-queue. --

Re: [PATCH] lpfc: avoid double free of resource identifiers

> "Johannes" == Johannes Thumshirn writes: Johannes> Set variables initialized in Johannes> lpfc_sli4_alloc_resource_identifiers() to NULL if an error Johannes> occurred. Otherwise, lpfc_sli4_driver_resource_unset() Johannes> attempts to free the memory again. Applied to

Re: [PATCH] qla4xxx: remove two unused MSI-X related #defines

> "Christoph" == Christoph Hellwig writes: Christoph> Spotted while preparing qla2xxx changes as the symbols exist Christoph> in both drivers (sigh..). Applied to 4.11/scsi-queue. -- Martin K. Petersen Oracle Linux Engineering -- To unsubscribe from this list: send the

Re: two fixes for the qla2xxx MSI-X changes in 4.10-rc

> "Christoph" == Christoph Hellwig writes: Christoph> Hi Himanshu, two small updates to to a) fix the way affinity Christoph> is assigned for qla2xxx, and b) remove the dead interrupt Christoph> affinity notifiers. Applied to 4.10/scsi-fixes. -- Martin K. Petersen Oracle

Re: [PATCH v1] scsi: ufs: fix arguments order some trace calls

> "Subhash" == Subhash Jadavani writes: Subhash> Colin Ian King reported that with Subhash> commit 7ff5ab473633 ("scsi: ufs: add tracing support") static Subhash> analysis is reporting that we may have swapped arguments on Subhash> calls

Re: [PATCH] vmw_pvscsi: switch to pci_alloc_irq_vectors

> "Christoph" == Christoph Hellwig writes: Christoph> And simply the interrupt handler by splitting the INTx case Christoph> that needs to deal with shared interrupts into a separate Christoph> helper. Applied to 4.11/scsi-queue. -- Martin K. Petersen Oracle Linux

Re: [PATCH] virtio_scsi: Reject commands when virtqueue is broken

On Wed, 01/11 17:02, Eric Farman wrote: > In the case of a graceful set of detaches, where the virtio-scsi-ccw > disk is removed from the guest prior to the controller, the guest > behaves quite normally. Specifically, the detach gets us into > sd_sync_cache to issue a Synchronize Cache(10)

[Bug 62971] Kernel 3.11.1 and higher does not boot on VMware VM

https://bugzilla.kernel.org/show_bug.cgi?id=62971 Bojan Smojver changed: What|Removed |Added Status|NEW |RESOLVED

[PATCH v2 4/4] cxlflash: Cancel scheduled workers before stopping AFU

When processing an AFU asynchronous interrupt, if the action results in an operation that requires off level processing (a link reset for example), the worker thread is scheduled. In the meantime a reset event (i.e.: EEH) could unmap the AFU to recover. This results in an Oops when the worker

[PATCH v2 1/4] cxlflash: Refactor context reset to share reset logic

From: "Matthew R. Ochs" As staging for supporting hardware with different context reset registers but a similar reset procedure, refactor the existing context reset routine to move the reset logic to a common routine. This will allow hardware with a different reset

[PATCH v2 3/4] cxlflash: Cleanup prints

From: "Matthew R. Ochs" The usage of prints within the cxlflash driver is inconsistent. This hinders debug and makes the driver source and log output appear sloppy. The following cleanups help unify the prints within cxlflash: - move all prints to dev-* where

[PATCH v2 2/4] cxlflash: Support SQ Command Mode

From: "Matthew R. Ochs" The SISLite specification outlines a new queuing model to improve over the MMIO-based IOARRIN model that exists today. This new model uses a submission queue that exists in host memory and is shared with the device. Each entry in the queue is an

[PATCH v2 0/4] cxlflash: Enhancements, cleanup and fixes

This patch series includes an enhancement to support a new command queuing model and also cleans up prints throughout the driver. The last patch in the series fixes a racing issue. The series is based upon v4.10-rc2, intended for 4.11 and is bisectable. v2 Changes: - Fixed SOBs for all the

Re: [PATCH 05/15] dm: remove incomple BLOCK_PC support

On Tue, Jan 10 2017 at 10:06am -0500, Christoph Hellwig wrote: > DM tries to copy a few fields around for BLOCK_PC requests, but given > that no dm-target ever wires up scsi_cmd_ioctl BLOCK_PC can't actually > be sent to dm. > > Signed-off-by: Christoph Hellwig > ---

Re: [PATCH] drivers: block: Remove unnecessary cast

Quoting Greg KH : On Wed, Jan 11, 2017 at 12:41:05PM -0600, Gustavo A. R. Silva wrote: This issue was detected using Coccinelle and the following semantic patch: @@ expression * e; expression arg1, arg2; type T; @@ - e = (T *) + e = kmalloc(arg1, arg2);

Re: [PATCH] vmw_pvscsi: switch to pci_alloc_irq_vectors

acked by Jim Gill (jg...@vmware.com) looks good to me. Signed-off-by: Christoph Hellwig --- drivers/scsi/vmw_pvscsi.c | 104 +- drivers/scsi/vmw_pvscsi.h |   5 --- 2 files changed, 38 insertions(+), 71 deletions(-) diff --git

Re: [PATCH 02/11] qla2xxx: Cleanup TMF code translation from qla_target.

On 1/11/17, 1:08 PM, "Bart Van Assche" wrote: >On 12/23/2016 08:23 PM, Himanshu Madhani wrote: >> From: Quinn Tran >> >> Move code code which converts Task Mgmt Command flags for >> ATIO to TCM #defines, from qla2xxx driver to tcm_qla2xxx >>

Re: RFC: split scsi passthrough fields out of struct request

On Tue, Jan 10 2017 at 10:06am -0500, Christoph Hellwig wrote: > Hi all, > > this series splits the support for SCSI passthrough commands from the > main struct request used all over the block layer into a separate > scsi_request structure that drivers that want to support SCSI

Re: [LSF/MM TOPIC][LSF/MM ATTEND] multipath redesign

On Wed, Jan 11 2017 at 4:44am -0500, Hannes Reinecke wrote: > Hi all, > > I'd like to attend LSF/MM this year, and would like to discuss a > redesign of the multipath handling. > > With recent kernels we've got quite some functionality required for > multipathing already

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Wed, Jan 11 2017 at 4:37am -0500, Hannes Reinecke wrote: > On 01/11/2017 10:01 AM, Christoph Hellwig wrote: > > On Wed, Jan 11, 2017 at 09:59:17AM +0100, Hannes Reinecke wrote: > >> I'd advocate to discuss this at LSF. > >> Now that Mike moved the bio-based mpath stuff back in

[PATCH] virtio_scsi: Reject commands when virtqueue is broken

In the case of a graceful set of detaches, where the virtio-scsi-ccw disk is removed from the guest prior to the controller, the guest behaves quite normally. Specifically, the detach gets us into sd_sync_cache to issue a Synchronize Cache(10) command, which immediately fails (and is retried a

[PATCH] virtio_scsi: Reject commands when virtqueue is broken

While doing some disruptive testing with QEMU/KVM, I have encountered some guest problems during hot unplug of virtio-scsi devices depending on the order of operations in which they are performed. The following notes describe my setup (s390x), and how I'm able to reproduce the error and test the

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Wed, Jan 11 2017 at 3:45am -0500, Christoph Hellwig wrote: > On Wed, Jan 11, 2017 at 09:42:44AM +0100, Johannes Thumshirn wrote: > > On Tue, Jan 10, 2017 at 04:06:19PM +0100, Christoph Hellwig wrote: > > > Simply the boilerplate code needed for bsg nodes a bit. > > > > > >

Re: [PATCH 02/11] qla2xxx: Cleanup TMF code translation from qla_target.

On 12/23/2016 08:23 PM, Himanshu Madhani wrote: > From: Quinn Tran > > Move code code which converts Task Mgmt Command flags for > ATIO to TCM #defines, from qla2xxx driver to tcm_qla2xxx > driver. > > Reviewed-by: Christoph Hellwig > Signed-off-by: Quinn

Re: [PATCH 11/11] qla2xxx: Improve RSCN handling in driver

On Fri, 2016-12-23 at 20:23 -0800, Himanshu Madhani wrote: > +void qlt_unknown_atio_work_fn(struct delayed_work *work) > +{ > + struct scsi_qla_host *vha = container_of(work, struct scsi_qla_host, > + unknown_atio_work); > + qlt_try_to_dequeue_unknown_atios(vha, 0); > +

Re: [PATCH 03/11] qla2xxx: Make trace flags more readable.

On 1/11/17, 12:47 PM, "Bart Van Assche" wrote: >On Fri, 2016-12-23 at 20:23 -0800, Himanshu Madhani wrote: >> From: Quinn Tran >> >> This patch does not change any functionality. > >Please also mention in the patch description what the

Re: [PATCH 02/11] qla2xxx: Cleanup TMF code translation from qla_target.

On 1/11/17, 12:05 PM, "Bart Van Assche" wrote: >On 12/23/2016 08:23 PM, Himanshu Madhani wrote: >> static int tcm_qla2xxx_handle_tmr(struct qla_tgt_mgmt_cmd *mcmd, uint32_t >> lun, >> -uint8_t tmr_func, uint32_t tag) >> +uint16_t tmr_func, uint32_t tag) >>

Re: [PATCH 03/11] qla2xxx: Make trace flags more readable.

On Fri, 2016-12-23 at 20:23 -0800, Himanshu Madhani wrote: > From: Quinn Tran > > This patch does not change any functionality. Please also mention in the patch description what the purpose of cmd_flags is. If I remember correctly the only purpose of most flags is to make

Re: [PATCH] drivers: block: Remove unnecessary cast

On Wed, Jan 11, 2017 at 12:41:05PM -0600, Gustavo A. R. Silva wrote: > This issue was detected using Coccinelle and the following semantic patch: > > @@ > expression * e; > expression arg1, arg2; > type T; > @@ > > - e = (T *) > + e = > kmalloc(arg1, arg2); > > Signed-off-by: Gustavo A. R.

Re: [PATCH 08/11] qla2xxx: Add framework for Async fabric discovery.

On 12/23/2016 08:23 PM, Himanshu Madhani wrote: > + sess->logout_completed = 0; > + be_sid[0] = sess->d_id.b.domain; > + be_sid[1] = sess->d_id.b.area; > + be_sid[2] = sess->d_id.b.al_pa; Hello Himanshu and Quinn, When building the qlt_create_sess() code with W=1 the compiler

Re: [PATCH 09/11] qla2xxx: Add Dual mode support in the driver

On 12/23/2016 08:23 PM, Himanshu Madhani wrote: > -#define QLA_TGT_MODE_ENABLED() (ql2x_ini_mode != QLA2XXX_INI_MODE_ENABLED) > +#define QLA_TGT_MODE_ENABLED() \ > + ((ql2x_ini_mode != QLA2XXX_INI_MODE_ENABLED) || \ > + (ql2x_ini_mode == QLA2XXX_INI_MODE_DUAL)) Hello Himanshu and Quinn,

Re: [PATCH 02/11] qla2xxx: Cleanup TMF code translation from qla_target.

On 12/23/2016 08:23 PM, Himanshu Madhani wrote: > static int tcm_qla2xxx_handle_tmr(struct qla_tgt_mgmt_cmd *mcmd, uint32_t > lun, > - uint8_t tmr_func, uint32_t tag) > + uint16_t tmr_func, uint32_t tag) > { > struct qla_tgt_sess *sess = mcmd->sess; > struct se_cmd *se_cmd =

Re: [PATCH] lpfc: avoid double free of resource identifiers

looks good. Thanks Signed-off-by: James Smart -- james On 1/11/2017 2:06 AM, Johannes Thumshirn wrote: From: Roberto Sassu Set variables initialized in lpfc_sli4_alloc_resource_identifiers() to NULL if an error occurred. Otherwise,

[PATCH] ibmvscsis: Fix max transfer length

Current code incorrectly calculates the max transfer length, since it is assuming a 4k page table, but ppc64 all run on 64k page tables. Cc: sta...@vger.kernel.org Reported-by: Steven Royer Tested-by: Steven Royer Signed-off-by: Bryant G.

[PATCH] ibmvscsis: Fix max transfer length

Current code incorrectly calculates the max transfer length, since it is assuming a 4k page table, but ppc64 all run on 64k page tables. Cc: sta...@vger.kernel.org Reported-by: Steven Royer Tested-by: Steven Royer Signed-off-by: Bryant G.

Re: [PATCH] preview - block layer help to detect sequential IO

Hi Kashyap, [auto build test ERROR on v4.9-rc8] [cannot apply to block/for-next linus/master linux/master next-20170111] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system] url: https://github.com/0day-ci/linux/commits/Kashyap-Desai/preview

Re: [PATCH 2/2] qla2xxx: remove irq_affinity_notifier

On 1/11/17, 8:55 AM, "Christoph Hellwig" wrote: >Now that qla2xxx uses the IRQ layer affinity assignment affinity >won't change over the life time of a device and the notifiers are >useless. > >Signed-off-by: Christoph Hellwig >--- > drivers/scsi/qla2xxx/qla_def.h |

Re: [PATCH 1/2] qla2xxx: fix MSI-X vector affinity

On 1/11/17, 8:55 AM, "Christoph Hellwig" wrote: >The first two or three vectors in qla2xxx adapter are global and >not associated with a specific queue. They should not have IRQ >affinity assigned. > >Signed-off-by: Christoph Hellwig >--- >

[PATCH] ibmvscsis: Fix max transfer length

Current code incorrectly calculates the max transfer length, since it is assuming a 4k page table, but ppc64 all run on 64k page tables. Cc: sta...@vger.kernel.org Reported-by: Steven Royer Tested-by: Steven Royer Signed-off-by: Bryant G.

Re: [PATCH] ibmvscsis: Fix max transfer length

On 1/11/17 12:57 PM, Bart Van Assche wrote: On Wed, 2017-01-11 at 12:02 -0600, Bryant G. Ly wrote: Current code incorrectly calculates the max transfer length, since it is assuming a 4k page table, but ppc64 all run on 64k page tables. Cc: sta...@vger.kernel.org Reported-by: Steven Royer

[PATCH] ibmvscsis: fix sleeping in interrupt context

Currently, dma_alloc_coherent is being called with a GFP_KERNEL flag which allows it to sleep in an interrupt context, need to change to GFP_ATOMIC. Cc: sta...@vger.kernel.org Tested-by: Steven Royer Reviewed-by: Michael Cyr Signed-off-by:

Re: [PATCH] ibmvscsis: Fix max transfer length

On Wed, 2017-01-11 at 12:02 -0600, Bryant G. Ly wrote: > Current code incorrectly calculates the max transfer length, since > it is assuming a 4k page table, but ppc64 all run on 64k page tables. > > Cc: sta...@vger.kernel.org > Reported-by: Steven Royer > Tested-by:

[PATCH] drivers: block: Remove unnecessary cast

This issue was detected using Coccinelle and the following semantic patch: @@ expression * e; expression arg1, arg2; type T; @@ - e = (T *) + e = kmalloc(arg1, arg2); Signed-off-by: Gustavo A. R. Silva --- drivers/block/cciss_scsi.c | 3 +-- 1 file changed, 1

[PATCH] ibmvscsis: Fix max transfer length

Current code incorrectly calculates the max transfer length, since it is assuming a 4k page table, but ppc64 all run on 64k page tables. Cc: sta...@vger.kernel.org Reported-by: Steven Royer Tested-by: Steven Royer Signed-off-by: Bryant G.

two fixes for the qla2xxx MSI-X changes in 4.10-rc

Hi Himanshu, two small updates to to a) fix the way affinity is assigned for qla2xxx, and b) remove the dead interrupt affinity notifiers. -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majord...@vger.kernel.org More majordomo info at

[PATCH 1/2] qla2xxx: fix MSI-X vector affinity

The first two or three vectors in qla2xxx adapter are global and not associated with a specific queue. They should not have IRQ affinity assigned. Signed-off-by: Christoph Hellwig --- drivers/scsi/qla2xxx/qla_def.h | 2 +- drivers/scsi/qla2xxx/qla_isr.c | 15 +++ 2

[PATCH 2/2] qla2xxx: remove irq_affinity_notifier

Now that qla2xxx uses the IRQ layer affinity assignment affinity won't change over the life time of a device and the notifiers are useless. Signed-off-by: Christoph Hellwig --- drivers/scsi/qla2xxx/qla_def.h | 1 - drivers/scsi/qla2xxx/qla_isr.c | 73

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 05:26 PM, Bart Van Assche wrote: > On Wed, 2017-01-11 at 17:22 +0100, Hannes Reinecke wrote: >> On 01/11/2017 05:12 PM, h...@infradead.org wrote: >>> On Wed, Jan 11, 2017 at 04:08:31PM +, Bart Van Assche wrote: A typical Ethernet network adapter delays the generation of an

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On Wed, 2017-01-11 at 17:22 +0100, Hannes Reinecke wrote: > On 01/11/2017 05:12 PM, h...@infradead.org wrote: > > On Wed, Jan 11, 2017 at 04:08:31PM +, Bart Van Assche wrote: > > > A typical Ethernet network adapter delays the generation of an > > > interrupt > > > after it has received a

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 05:12 PM, h...@infradead.org wrote: > On Wed, Jan 11, 2017 at 04:08:31PM +, Bart Van Assche wrote: >> A typical Ethernet network adapter delays the generation of an interrupt >> after it has received a packet. A typical block device or HBA does not delay >> the generation of an

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 09:12 AM, h...@infradead.org wrote: > On Wed, Jan 11, 2017 at 04:08:31PM +, Bart Van Assche wrote: >> A typical Ethernet network adapter delays the generation of an interrupt >> after it has received a packet. A typical block device or HBA does not delay >> the generation of an

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On Wed, Jan 11, 2017 at 04:08:31PM +, Bart Van Assche wrote: [...] > A typical Ethernet network adapter delays the generation of an interrupt > after it has received a packet. A typical block device or HBA does not delay > the generation of an interrupt that reports an I/O completion. I

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On Wed, 2017-01-11 at 14:43 +0100, Johannes Thumshirn wrote: > I'd like to attend LSF/MM and would like to discuss polling for block > drivers. > > Currently there is blk-iopoll but it is neither as widely used as NAPI in > the networking field and accoring to Sagi's findings in [1] performance >

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On Wed, Jan 11, 2017 at 04:08:31PM +, Bart Van Assche wrote: > A typical Ethernet network adapter delays the generation of an interrupt > after it has received a packet. A typical block device or HBA does not delay > the generation of an interrupt that reports an I/O completion. NVMe allows

Re: Advanced Format SAT devices show incorrect physical block size

On Tue, 10 Jan 2017, James Bottomley wrote: > On Tue, 2017-01-10 at 16:00 -0500, Alan Stern wrote: > > In theory, I suppose we could change the kernel so that it would > > default to READ CAPACITY(16) for devices that report a SCSI level >= > > 3, or something along those lines. In general we

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 04:07 PM, Jens Axboe wrote: > On 01/11/2017 06:43 AM, Johannes Thumshirn wrote: >> Hi all, >> >> I'd like to attend LSF/MM and would like to discuss polling for block >> drivers. >> >> Currently there is blk-iopoll but it is neither as widely used as NAPI in the >> networking field

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 08:07 AM, Jens Axboe wrote: > On 01/11/2017 06:43 AM, Johannes Thumshirn wrote: >> Hi all, >> >> I'd like to attend LSF/MM and would like to discuss polling for block >> drivers. >> >> Currently there is blk-iopoll but it is neither as widely used as NAPI in the >> networking field

Re: Advanced Format SAT devices show incorrect physical block size

On Wed, 11 Jan 2017, Pali Rohár wrote: > On Tuesday 10 January 2017 15:29:23 Alan Stern wrote: > > > Tom Yan wrote that smartctl/hdparm "works" because they use the SCSI ATA > > > PASSTHROUGH command. It is not an option for kernel? > > > > No, because many devices do not implement SCSI ATA

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 06:43 AM, Johannes Thumshirn wrote: > Hi all, > > I'd like to attend LSF/MM and would like to discuss polling for block drivers. > > Currently there is blk-iopoll but it is neither as widely used as NAPI in the > networking field and accoring to Sagi's findings in [1] performance

Re: Advanced Format SAT devices show incorrect physical block size

On Tue, 10 Jan 2017, Dainius Masiliūnas wrote: > On Tue, Jan 10, 2017 at 9:00 PM, Alan Stern wrote: > > It is used for preventing the kernel from issuing a READ CAPACITY(16) > > command to the device. Normally the kernel would do this if the reply > > to READ

[PATCH RFC] sas: convert to bsg-lib

Convert the SAS transport class over to using bsg-lib instead of doing "raw" bsg access. Signed-off-by: Johannes Thumshirn --- drivers/scsi/scsi_transport_sas.c | 41 +++ 1 file changed, 16 insertions(+), 25 deletions(-) diff --git

Re: [LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

On 01/11/2017 02:43 PM, Johannes Thumshirn wrote: > Hi all, > > I'd like to attend LSF/MM and would like to discuss polling for block drivers. > > Currently there is blk-iopoll but it is neither as widely used as NAPI in the > networking field and accoring to Sagi's findings in [1] performance

[LSF/MM TOPIC][LSF/MM ATTEND] NAPI polling for block drivers

Hi all, I'd like to attend LSF/MM and would like to discuss polling for block drivers. Currently there is blk-iopoll but it is neither as widely used as NAPI in the networking field and accoring to Sagi's findings in [1] performance with polling is not on par with IRQ usage. On LSF/MM I'd like

Re: Advanced Format SAT devices show incorrect physical block size

On Tuesday 10 January 2017 15:29:23 Alan Stern wrote: > > Tom Yan wrote that smartctl/hdparm "works" because they use the SCSI ATA > > PASSTHROUGH command. It is not an option for kernel? > > No, because many devices do not implement SCSI ATA PASSTHROUGH. > (Consider devices whose underlying

Re: Advanced Format SAT devices show incorrect physical block size

On Tuesday 10 January 2017 14:12:25 James Bottomley wrote: > On Tue, 2017-01-10 at 16:00 -0500, Alan Stern wrote: > > In theory, I suppose we could change the kernel so that it would > > default to READ CAPACITY(16) for devices that report a SCSI level >= > > 3, or something along those lines.

Re: [PATCH] qla4xxx: remove two unused MSI-X related #defines

On Wed, Jan 11, 2017 at 02:26:52PM +0100, Christoph Hellwig wrote: > Spotted while preparing qla2xxx changes as the symbols exist in both > drivers (sigh..). > > Signed-off-by: Christoph Hellwig > --- Looks good, Reviewed-by: Johannes Thumshirn -- Johannes

[PATCH] qla4xxx: remove two unused MSI-X related #defines

Spotted while preparing qla2xxx changes as the symbols exist in both drivers (sigh..). Signed-off-by: Christoph Hellwig --- drivers/scsi/qla4xxx/ql4_def.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index

[PATCH] preview - block layer help to detect sequential IO

Objective of this patch is - To move code used in bcache module in block layer which is used to find IO stream. Reference code @drivers/md/bcache/request.c check_should_bypass(). This is a high level patch for review and understand if it is worth to follow ? As of now bcache module use this

[PATCH] lpfc: avoid double free of resource identifiers

From: Roberto Sassu Set variables initialized in lpfc_sli4_alloc_resource_identifiers() to NULL if an error occurred. Otherwise, lpfc_sli4_driver_resource_unset() attempts to free the memory again. Signed-off-by: Roberto Sassu Signed-off-by: Johannes Thumshirn

[LSF/MM TOPIC][LSF/MM ATTEND] multipath redesign

Hi all, I'd like to attend LSF/MM this year, and would like to discuss a redesign of the multipath handling. With recent kernels we've got quite some functionality required for multipathing already implemented, making some design decisions of the original multipath-tools implementation quite

Re: [LFS/MM TOPIC][LFS/MM ATTEND]: - Storage Stack and Driver Testing methodology.

On 01/11/2017 10:24 AM, Christoph Hellwig wrote: > On Wed, Jan 11, 2017 at 10:19:45AM +0100, Johannes Thumshirn wrote: >> Well, something I was thinking about but didn't find enough time to actually >> implement is making a xfstestes like test suite written using sg3_utils for >> SCSI. > >

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On 01/11/2017 10:01 AM, Christoph Hellwig wrote: > On Wed, Jan 11, 2017 at 09:59:17AM +0100, Hannes Reinecke wrote: >> I'd advocate to discuss this at LSF. >> Now that Mike moved the bio-based mpath stuff back in things got even >> more complex. > > Yeah. If we'd _only_ have bio based support it

Re: [PATCH v1] scsi: ufs: fix arguments order some trace calls

On 11/01/17 00:48, Subhash Jadavani wrote: > Colin Ian King reported that with > commit 7ff5ab473633 ("scsi: ufs: add tracing support") static analysis > is reporting that we may have swapped arguments on calls to: > trace_ufshcd_runtime_resume, >

Re: [LFS/MM TOPIC][LFS/MM ATTEND]: - Storage Stack and Driver Testing methodology.

On Wed, Jan 11, 2017 at 10:19:45AM +0100, Johannes Thumshirn wrote: > Well, something I was thinking about but didn't find enough time to actually > implement is making a xfstestes like test suite written using sg3_utils for > SCSI. Ronnie's libiscsi testsuite can use SG_IO for a new years now:

Re: [LFS/MM TOPIC][LFS/MM ATTEND]: - Storage Stack and Driver Testing methodology.

On Tue, Jan 10, 2017 at 10:40:53PM +, Chaitanya Kulkarni wrote: > Resending it at as a plain text. > > From: Chaitanya Kulkarni > Sent: Tuesday, January 10, 2017 2:37 PM > To: lsf...@lists.linux-foundation.org > Cc: linux-fsde...@vger.kernel.org; linux-bl...@vger.kernel.org; >

Re: [PATCH] libsas: fix \"sysfs group not found\" warnings at port teardown time

On 11/01/2017 06:29, seeteena wrote: Hi All, Let me know if this patch is accepted in Upsteam? let me know the commit id If it is the patch I think it is then it is not upstream (https://patchwork.kernel.org/patch/6450731/). I did propose a patch at the end of last year which fixed the

Re: [PATCH] scsi: qedi: select UIO

On 11/01/17 9:40 AM, "Martin K. Petersen" wrote: >> "Ewan" == Ewan D Milne writes: > >Ewan> Randy posted a similar patch back in December but I don't think >Ewan> there was ever a reply to Christoph's question about why qedi >Ewan> depends on

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Wed, Jan 11, 2017 at 09:59:17AM +0100, Hannes Reinecke wrote: > I'd advocate to discuss this at LSF. > Now that Mike moved the bio-based mpath stuff back in things got even > more complex. Yeah. If we'd _only_ have bio based support it would simplify things a lot, but as a third parallel path

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Wed, Jan 11, 2017 at 09:56:01AM +0100, Johannes Thumshirn wrote: > I'll dig it up and RFC post it. It's currently untested though as I > currently don't have a SMP capable SAS HBA here. > > Do you have an mptXsas available? Unfortunately not. But I think Hannes has, he has recently played

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On 01/11/2017 09:45 AM, Christoph Hellwig wrote: > On Wed, Jan 11, 2017 at 09:42:44AM +0100, Johannes Thumshirn wrote: >> On Tue, Jan 10, 2017 at 04:06:19PM +0100, Christoph Hellwig wrote: >>> Simply the boilerplate code needed for bsg nodes a bit. >>> >>> Signed-off-by: Christoph Hellwig

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Wed, Jan 11, 2017 at 09:45:12AM +0100, Christoph Hellwig wrote: > On Wed, Jan 11, 2017 at 09:42:44AM +0100, Johannes Thumshirn wrote: > > On Tue, Jan 10, 2017 at 04:06:19PM +0100, Christoph Hellwig wrote: > > > Simply the boilerplate code needed for bsg nodes a bit. > > > > > > Signed-off-by:

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Wed, Jan 11, 2017 at 09:42:44AM +0100, Johannes Thumshirn wrote: > On Tue, Jan 10, 2017 at 04:06:19PM +0100, Christoph Hellwig wrote: > > Simply the boilerplate code needed for bsg nodes a bit. > > > > Signed-off-by: Christoph Hellwig > > --- > > that reminds me of posting my

Re: [PATCH 01/15] virtio_blk: avoid DMA to stack for the sense buffer

On Wed, Jan 11, 2017 at 09:26:46AM +0100, Johannes Thumshirn wrote: > Isn't that one already queued in Jens' tree? Yes, it's now queued up. Patch 2 was submitted as well and should hopefully go into the next 4.10 RC. -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the

Re: [PATCH 14/15] block/bsg: move queue creation into bsg_setup_queue

On Tue, Jan 10, 2017 at 04:06:19PM +0100, Christoph Hellwig wrote: > Simply the boilerplate code needed for bsg nodes a bit. > > Signed-off-by: Christoph Hellwig > --- that reminds me of posting my SAS bsg-lib patch... Anyways looks good, Reviewed-by: Johannes Thumshirn

Re: [PATCH 01/15] virtio_blk: avoid DMA to stack for the sense buffer

On Tue, Jan 10, 2017 at 04:06:06PM +0100, Christoph Hellwig wrote: > Most users of BLOCK_PC requests allocate the sense buffer on the stack, > so to avoid DMA to the stack copy them to a field in the heap allocated > virtblk_req structure. Without that any attempt at SCSI passthrough I/O, >