In _scsih_probe, delay the call to scsi_add_host until the host has been
fully set up.
Otherwise, the default .can_queue value of 1 causes scsi-mq to set the block
layer request queue size to its minimum size, resulting in awful performance.
In _scsih_probe error handling, call mpt3sas_base_deta
In _scsih_probe, delay the call to scsi_add_host until the host has been
fully set up.
Otherwise, the default .can_queue value of 1 causes scsi-mq to set the block
layer request queue size to its minimum size, resulting in awful performance.
In _scsih_probe error handling, call mpt3sas_base_deta
On 07/12/2014 06:48 PM, K. Y. Srinivasan wrote:
Correctly set SRB flags for all valid I/O directions. Some IHV drivers on the
Windows host require this. The host validates the command and SRB flags
prior to passing the command down to native driver stack.
Signed-off-by: K. Y. Srinivasan
Cc:
--
On 07/12/2014 06:48 PM, K. Y. Srinivasan wrote:
On some Windows hosts on FC SANs, TEST_UNIT_READY can return SRB_STATUS_ERROR.
Correctly handle this. Note that there is sufficient sense information to
support scsi error handling even in this case.
In this version of the patch I have addressed co
On 07/12/2014 06:48 PM, K. Y. Srinivasan wrote:
Going forward it is possible that some of the commands that are not currently
implemented will be implemented on future Windows hosts. Even if they are not
implemented, we are told the host will corrrectly handle unsupported
commands (by returning a
On 07/12/2014 06:48 PM, K. Y. Srinivasan wrote:
Based on the negotiated VMBUS protocol version, we adjust the size of the
storage
protocol messages. The two sizes we currently handle are pre-win8 and post-win8.
In WS2012 R2, we are negotiating higher VMBUS protocol version than the win8
version.
On 07/12/2014 06:48 PM, K. Y. Srinivasan wrote:
On Azure, we have seen instances of unbounded I/O latencies. To deal with
this issue, implement handler that can reset the timeout. Note that the
host gaurantees that it will respond to each command that has been issued.
Signed-off-by: K. Y. Srini
On 07/12/2014 06:48 PM, K. Y. Srinivasan wrote:
Hyper-V hosts can support multiple targets and multiple channels and larger
number of
LUNs per target. Update the code to reflect this. With this patch we can
correctly
enumerate all the paths in a multi-path storage environment.
In this version
On 07/12/2014 06:48 PM, K. Y. Srinivasan wrote:
Set cmd_per_lun to reflect value supported by the Host.
In this version of the patch I have addressed comments from
Christoph Hellwig
Signed-off-by: K. Y. Srinivasan
Cc:
---
drivers/scsi/storvsc_drv.c |2 +-
1 files changed, 1 insertions(
> -Original Message-
> From: driverdev-devel-boun...@linuxdriverproject.org [mailto:driverdev-
> devel-boun...@linuxdriverproject.org] On Behalf Of KY Srinivasan
> Sent: Sunday, July 13, 2014 7:38 PM
> To: Martin K. Petersen
> Cc: linux-scsi@vger.kernel.org; jasow...@redhat.com; linux-
>
> -Original Message-
> From: KY Srinivasan
> Sent: Sunday, July 13, 2014 11:50 AM
> To: 'Martin K. Petersen'
> Cc: h...@infradead.org; James Bottomley; linux-ker...@vger.kernel.org;
> de...@linuxdriverproject.org; a...@canonical.com; sta...@vger.kernel.org;
> linux-scsi@vger.kernel.org; o
> -Original Message-
> From: linux-scsi-ow...@vger.kernel.org [mailto:linux-scsi-
> ow...@vger.kernel.org] On Behalf Of Douglas Gilbert
> Sent: Monday, 07 July, 2014 8:31 AM
> To: SCSI development list
> Subject: [PATCH v2] scsi_debug: support scsi-mq, queues and locks
>
> Resend, looks
> -Original Message-
> From: Christoph Hellwig [mailto:h...@infradead.org]
> Sent: Sunday, July 13, 2014 2:51 AM
> To: KY Srinivasan
> Cc: jasow...@redhat.com; a...@canonical.com; linux-
> ker...@vger.kernel.org; de...@linuxdriverproject.org; oher...@suse.com;
> jbottom...@parallels.com;
> -Original Message-
> From: Martin K. Petersen [mailto:martin.peter...@oracle.com]
> Sent: Sunday, July 13, 2014 5:59 AM
> To: KY Srinivasan
> Cc: h...@infradead.org; James Bottomley; linux-ker...@vger.kernel.org;
> de...@linuxdriverproject.org; a...@canonical.com; sta...@vger.kernel.org
> -Original Message-
> From: linux-scsi-ow...@vger.kernel.org [mailto:linux-scsi-
> ow...@vger.kernel.org] On Behalf Of Elliott, Robert (Server Storage)
> Sent: Saturday, July 12, 2014 6:20 PM
> To: Benjamin LaHaise
> Cc: Christoph Hellwig; Jeff Moyer; Jens Axboe; dgilb...@interlog.com;
>
> -Original Message-
> From: linux-scsi-ow...@vger.kernel.org [mailto:linux-scsi-
> ow...@vger.kernel.org] On Behalf Of Martin K. Petersen
...
> Also, this is not touched by the patch, but you're then doing:
>
> (*(__be32 *)(&cdb_ptr[i])) = cpu_to_be32(p_lba);
>
> What if this
> "Sreekanth" == Reddy, Sreekanth writes:
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 6ae109b..4a0728a 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -3865,7 +3865,8 @@ _scsih_setup_direct_io(
> "Christoph" == Christoph Hellwig writes:
Christoph> On Sun, Jul 13, 2014 at 10:52:53AM -0400, Douglas Gilbert wrote:
>> To make things clearer when referring to the WRITE SAME command I
>> would suggest "WRITE SAME(unmap)" for the case when its UNMAP field
>> is 1 (as I assume it is in this
> "Sreekanth" == Reddy, Sreekanth writes:
Sreekanth> Bump mpt2sas driver version to 17.100.00.00.
Reviewed-by: Martin K. Petersen
--
Martin K. Petersen Oracle Linux Engineering
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majord
> "Sreekanth" == Reddy, Sreekanth writes:
Sreekanth> Added code to send a SEP message that turns off the
Sreekanth> Predictive Failure LED when a drive is removed (if Predictive
Sreekanth> Failure LED was turned on).
Sreekanth> Added a new flag 'pfa_led_on' per device that tracks the
Sreekan
> "Sreekanth" == Reddy, Sreekanth writes:
Sreekanth> Copyright in driver sources is updated for year the 2014.
Reviewed-by: Martin K. Petersen
--
Martin K. Petersen Oracle Linux Engineering
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a mess
> "Sreekanth" == Reddy, Sreekanth writes:
Sreekanth> Below is the change set in MPI2 Rev Y specification and in
Sreekanth> 2.00.17 header files
Sreekanth> 1) Added SCSIStatusQualifier to SCSI IO Error Reply message.
Sreekanth> 2) Added ATA Security Freeze Lock to IO Unit Page 1 Flags
Sreekant
On Sun, Jul 13, 2014 at 10:52:53AM -0400, Douglas Gilbert wrote:
> To make things clearer when referring to the WRITE SAME command
> I would suggest "WRITE SAME(unmap)" for the case when its UNMAP
> field is 1 (as I assume it is in this case).
Actually it could be WRITE SAME (10) with or without u
> "Sreekanth" == Reddy, Sreekanth writes:
Sreekanth> Added driver module parameter max_msix_vectors. Using this
Sreekanth> module parameter the maximum number of MSI-X vectors could be
Sreekanth> set.
Sreekanth> The number of MSI-X vectors used would be the minimum of
Sreekanth> MSI-X vector
> "Sreekanth" == Reddy, Sreekanth writes:
Sreekanth> Added driver module parameter max_msix_vectors. Using this
Sreekanth> module parameter the maximum number of MSI-X vectors could be
Sreekanth> set.
Sreekanth> The number of MSI-X vectors used would be the minimum of
Sreekanth> MSI-X vector
On 14-07-13 10:35 AM, Martin K. Petersen wrote:
"Christoph" == Christoph Hellwig writes:
Christoph> Simplify handling of discard requests by setting up the
Christoph> command directly instead of initializing request fields and
Christoph> then calling scsi_setup_blk_pc_cmnd to propagate the
Chr
> "Christoph" == Christoph Hellwig writes:
Reviewed-by: Martin K. Petersen
--
Martin K. Petersen Oracle Linux Engineering
--
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 http://vger.
> "Christoph" == Christoph Hellwig writes:
Christoph> Factor out a function to initialize regular read/write
Christoph> commands and leave sd_init_command as a simple dispatcher to
Christoph> the different prepare routines.
Reviewed-by: Martin K. Petersen
--
Martin K. Petersen Oracle
> "Christoph" == Christoph Hellwig writes:
Christoph> Currently cmd->allowed is initialized from rq->retries for
Christoph> discard commands, but retries is always 0 for non-BLOCK_PC
Christoph> requests. Set it to the standard number of retries instead.
Reviewed-by: Martin K. Petersen
--
> "Christoph" == Christoph Hellwig writes:
Christoph> Currently cmd->allowed is initialized from rq->retries for
Christoph> write same commands, but retries is always 0 for non-BLOCK_PC
Christoph> requests. Set it to the standard number of retries instead.
Reviewed-by: Martin K. Petersen
> "Christoph" == Christoph Hellwig writes:
Christoph> Simplify handling of discard requests by setting up the
Christoph> command directly instead of initializing request fields and
Christoph> then calling scsi_setup_blk_pc_cmnd to propagate the
Christoph> information into the command.
Would
> "Christoph" == Christoph Hellwig writes:
Christoph> Simplify handling of write same requests by setting up the
Christoph> command directly instead of initializing request fields and
Christoph> then calling scsi_setup_blk_pc_cmnd to propagate the
Christoph> information into the command.
Rev
> "Christoph" == Christoph Hellwig writes:
Christoph> Simplify handling of flush requests by setting up the command
Christoph> directly instead of initializing request fields and then
Christoph> calling scsi_setup_blk_pc_cmnd to propagate the information
Christoph> into the command.
Looks go
> "Christoph" == Christoph Hellwig writes:
Could have a slightly more verbose patch description. Otherwise OK.
Reviewed-by: Martin K. Petersen
--
Martin K. Petersen Oracle Linux Engineering
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a mess
> "Christoph" == Christoph Hellwig writes:
Christoph> We should call the device handler prep_fn for all TYPE_FS
Christoph> requests, not just simple read/write calls that are handled
Christoph> by the disk driver.
Christoph> Restructure the common I/O code to call the prep_fn handler
Christo
> "Christoph" == Christoph Hellwig writes:
Christoph> scsi_init_io should only be called for requests that transfer
Christoph> data, so move the assert that a request has segments from the
Christoph> callers into scsi_init_io.
Reviewed-by: Martin K. Petersen
--
Martin K. Petersen Ora
On Sun, Jul 13, 2014 at 5:54 PM, Akinobu Mita wrote:
> If the controller doesn't support 64-bit addressing mode, it must not
> set the DMA mask to 64-bit. But it's unconditionally trying to set to
> 64-bit without checking 64-bit addressing support in the controller
> capabilities.
>
> It was cor
> "KY" == KY Srinivasan writes:
KY> Windows hosts do support UNMAP and set the field in the
KY> EVPD. However, since the host advertises SPC-2 compliance, Linux
KY> does not even query the VPD page.
>> If we want to enable UNMAP in this case I'd prefer a blacklist entry
>> than trying UNMAP
If the controller doesn't support 64-bit addressing mode, it must not
set the DMA mask to 64-bit. But it's unconditionally trying to set to
64-bit without checking 64-bit addressing support in the controller
capabilities.
It was correctly checked before commit 3b1d05807a9a68c6d0580e9248247a774a4d
On Fri, Jul 11, 2014 at 01:25:10PM -0700, Andi Kleen wrote:
> From: Andi Kleen
>
> These data structures are accessed by different CPUs and have some
> fields which are mostly read only and others which are frequently
> written. Separate some common ones into separate cache line
> to minimize fal
> "Christoph" == Christoph Hellwig writes:
Christoph> Sagi, can you send an update for the core-for-3.17 tree to
Christoph> pass a dma_direction or the scsi data buffer to
Christoph> scsi_transfer_length so we can make safe for bidi usage in
Christoph> the future?
I have cleaned this up in m
Sagi,
can you send an update for the core-for-3.17 tree to pass a
dma_direction or the scsi data buffer to scsi_transfer_length so we can
make safe for bidi usage in the future?
--
To unsubscribe from this list: send the line "unsubscribe linux-scsi" in
the body of a message to majord...@vger.ker
The series looks good to me, although I'll probably put the commit
message for the timer patch into the comment for the eh_timed_out
handler.
Can I get another set of reviews? I've seen Olaf has put them into the
SLES tree, so I'd expect he's done a review already?
--
To unsubscribe from this li
On Sat, Jul 12, 2014 at 03:51:47PM -0500, micha...@cs.wisc.edu wrote:
> The following patches were made over Chrisoph's scsi-queue drivers-for-3.17
> branch. They are some fixes to the get_host_stats code and new error code
> for when a iscsi ping times out.
The series looks fine to me, I'll merge
44 matches
Mail list logo