Hello,
[1.971778] [ cut here ]
[1.971960] WARNING: CPU: 1 PID: 6 at mm/page_alloc.c:2497
__alloc_pages_nodemask+0x1b9/0x693()
[1.972246] Modules linked in: sd_mod ahci
[1.972604] CPU: 1 PID: 6 Comm: kworker/u8:0 Not tainted
3.14.0-rc8-next-20140327-dbg
ci
> [1.972604] CPU: 1 PID: 6 Comm: kworker/u8:0 Not tainted
> 3.14.0-rc8-next-20140327-dbg-dirty #202
> [1.972890] Hardware name: Acer Aspire 5741G/Aspire 5741G
> , BIOS V1.20 02/08/2011
> [1.973182] Workqueue: events_unbound async_run_entry_fn
&
Hi,
I have these messages logged on 2 different servers (one production, one
stand-by) when using recent vanilla kernels.
I have found references to these logs, but this was supposedly
introduced in the 2.6.31 kernel.
However, running kernel 2.6.32.61, this message does not appear. It
appear
_alloc_pages_nodemask+0x1b9/0x693()
> > [1.972246] Modules linked in: sd_mod ahci
> > [1.972604] CPU: 1 PID: 6 Comm: kworker/u8:0 Not tainted
> > 3.14.0-rc8-next-20140327-dbg-dirty #202
> > [1.972890] Hardware name: Acer Aspire 5741G/Aspire
> >
On Tue, Dec 10, 2013 at 12:05:11PM +0100, Hannes Reinecke wrote:
> Obsolete; either use 'max_lun' if the host supports only a
> limited number of LUNs or BLIST_NOLUN if the target has
> problems addressing more than one LUN.
Looks good,
Reviewed-by: Christoph Hellwig
Btw, I noticed the SuSE tre
On Tue, Dec 10, 2013 at 12:05:12PM +0100, Hannes Reinecke wrote:
> Sequential scan for more than 256 LUNs is very fragile as
> LUNs might not be numbered sequentially after that point.
>
> SAM revisions later than SCSI-3 impose a structure on
> LUNs larger than 256, making LUN numbers between 256
On Tue, Dec 10, 2013 at 12:05:14PM +0100, Hannes Reinecke wrote:
> The SCSI standard defines 64-bit values for LUNs, and large arrays
> employing large or hierarchical LUN numbers become more and more
> common.
>
> So update the linux SCSI stack to use 64-bit LUN numbers.
Looks good,
Reviewed-by
On Tue, Dec 10, 2013 at 12:05:15PM +0100, Hannes Reinecke wrote:
> Now that we're using 64-bit LUNs internally we need to increase
> the size of max_luns to 64 bits, too.
>
> Signed-off-by: Hannes Reinecke
Looks good,
Reviewed-by: Christoph Hellwig
--
To unsubscribe from this list: send the li
_alloc_pages_nodemask+0x1b9/0x693()
> > [1.972246] Modules linked in: sd_mod ahci
> > [1.972604] CPU: 1 PID: 6 Comm: kworker/u8:0 Not tainted
> > 3.14.0-rc8-next-20140327-dbg-dirty #202
> > [1.972890] Hardware name: Acer Aspire 5741G/Aspire
> >
On Tue, 2014-03-25 at 16:36 +0100, Paolo Bonzini wrote:
> Il 25/03/2014 16:31, Christoph Hellwig ha scritto:
> > Paolo,
> >
> > do you have a virtio_scsi tree to picks this up in? We now have all
> > the infrastructure for it in James' tree.
>
> I don't, I usually just give my Acked-by and James
Move control of the prep_fn back from the ULDs into the scsi layer. Besides
cleaning up the code and removing the only use of the unprep_fn
requeuest_queue method this also prepares for usinng blk-mq, which doesn't
have equivalent functionality to the prep_fn method and requires the driver
to prov
Various patches from the scsi multiqueue development that make sense on their
own.
--
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.kernel.org/majordomo-info.html
Simply the I/O completion logic by folding scsi_end_request into its only
caller. There is a single site to either requeue the command or move on
to the next one instead of of the previous convoluted logic.
Signed-off-by: Christoph Hellwig
---
drivers/scsi/scsi_lib.c | 114 +---
Instead of trying to guess when we have a BIDI buffer in scsi_release_buffers
add a function to explicitly free the BIDI ressoures in the one place that
handles them. This avoids needing a special __scsi_release_buffers for the
case where we already have freed the request as well.
Signed-off-by:
Signed-off-by: Christoph Hellwig
---
drivers/scsi/scsi_error.c |6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 771c16b..b989d31 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2294,6 +2294,12 @@ sc
stuck in IO poll for a long time. In such cases driver
did not rearm which could lead to unprocessed eq.Change
sched iopoll once then check for valid bit of eqe from
eq in be_iopoll.
Signed-off-by: Minh Tran
Signed-off-by: John Soni Jose
Signed-off-by: Jayamohan Kallickal
---
drivers/scsi/
Getting WRB for MCCQ posting was done before looking if tag is
available or not. This lead to increase phba->ctrl.mcc_obj.q.used
variable and the WARN_ON message was coming from wrb_from_mccq().
Moved getting wrb from mccq after checking for the tag.
In wrb_from_mccq(), memset is done before
Even before probe for function was completed, iSCSI Daemon had initiated login
to target while OS was coming up. The targets which had node.startup=automatic,
login process was initiated.Since function specific initialization was still in
progress this lead to kernel panic.
The reson was MCCQ
This patch fixes lack of support for interrupt moderation.
This moderates the coalescing based on the rate of IO Completion
Signed-off-by: Minh Tran
Signed-off-by: John Soni Jose
Signed-off-by: Jayamohan Kallickal
---
drivers/scsi/be2iscsi/be.h | 11
drivers/scsi/be2iscsi
This patchset updates be2iscsi driver to 10.2.218.0
These patches are based on pending branch of scsi.git.
I had earlier sent patches 1, 2, and 3 which I would like to
withdraw.
0001 - Fix retreving MCCQ_WRB in non-embedded Mbox
0002 - Relinquishing control after 512 CQE
0003 - Fix MCCQ posti
SKH-R adapter, TCP Window Size/Scale parameters are passed
in TCP Connection Offload Mbx Command.
Signed-off-by: Minh Tran
Signed-off-by: John Soni Jose
Signed-off-by: Jayamohan Kallickal
---
drivers/scsi/be2iscsi/be_cmds.h | 20
drivers/scsi/be2iscsi/be_iscsi.c | 19 +--
dri
Bump driver version
Signed-off-by: John Soni Jose
Signed-off-by: Jayamohan Kallickal
---
drivers/scsi/be2iscsi/be_main.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/scsi/be2iscsi/be_main.h b/drivers/scsi/be2iscsi/be_main.h
index b3716e3..43f0b38 100644
--
Hi, hope the week is going well for everyone.
There appears to be evidence that VMware has an issue with exact SCSI
standards compliance when it comes to handling corner cases with SCSI
reservation requests. It appears as if Dell is pushing firmware hot
fixes for the EqualLogic controllers to wor
2014-03-27 19:21 GMT+01:00 Dr. Greg Wettstein :
> Hi, hope the week is going well for everyone.
>
> There appears to be evidence that VMware has an issue with exact SCSI
> standards compliance when it comes to handling corner cases with SCSI
> reservation requests. It appears as if Dell is pushing
Removing the host_lock from the I/O submission path gives a huge
scalability improvement.
Signed-off-by: Matthew Wilcox
---
drivers/scsi/mpt2sas/mpt2sas_scsih.c | 9 +++--
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
b/drivers/scsi/mpt2s
The mpt3sas_scsih_issue_tm() function does not use the 'serial_number'
argument passed to it. Removing it removes the last vestiges of the
scsi_cmnd's serial_number field from this driver.
Signed-off-by: Matthew Wilcox
---
drivers/scsi/mpt3sas/mpt3sas_base.h | 2 +-
drivers/scsi/mpt3sas/mpt3s
Reusing a smid quickly means it's still cache-hot. This yields a small
but noticable performance improvement in a well-known database benchmark.
This improvement is already present in the mpt3sas driver.
Signed-off-by: Matthew Wilcox
---
drivers/scsi/mpt2sas/mpt2sas_base.c | 8
1 file
The host lock is a serious scalability problem on 2-socket and larger
systems which are doing a lot of I/O. Before removing the temporary
usgae of DEF_SCSI_QCMD, we need to remove all uses of serial_number.
An unrelated performance issue is that reusing the most recent
driver-specific data struct
Removing the host_lock from the I/O submission path gives a huge
scalability improvement.
Signed-off-by: Matthew Wilcox
---
drivers/message/fusion/mptfc.c| 12 +---
drivers/message/fusion/mptsas.c | 10 --
drivers/message/fusion/mptscsih.c | 8 +++-
drivers/message/fus
Removing the host_lock from the I/O submission path gives a huge
scalability improvement.
Signed-off-by: Matthew Wilcox
---
drivers/scsi/mpt3sas/mpt3sas_scsih.c | 9 +++--
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
b/drivers/scsi/mpt3s
The mpt2sas_scsih_issue_tm() function does not use the 'serial_number'
argument passed to it. Removing it removes the last vestiges of the
scsi_cmnd's serial_number field from this driver.
Signed-off-by: Matthew Wilcox
---
drivers/scsi/mpt2sas/mpt2sas_base.h | 2 +-
drivers/scsi/mpt2sas/mpt2s
Reusing a msg frame quickly means it's still cache-hot. This yields
a small but noticable performance improvement in a well-known database
benchmark. This improvement is already present in the mpt3sas driver.
Signed-off-by: Matthew Wilcox
---
drivers/message/fusion/mptbase.c | 2 +-
1 file cha
Hello Krishna Gudipati,
The patch 51e569aa1f0c: "[SCSI] bfa: Added support to obtain SFP
info." from Jun 24, 2011, leads to the following static checker
warning:
drivers/scsi/bfa/bfa_ioc.c:3668 bfa_cb_sfp_state_query()
warn: add curly braces?
drivers/scsi/bfa/bfa_ioc.c
3659 st
On Fri, Mar 28, 2014 at 02:05:14AM +0300, Dan Carpenter wrote:
> Hello Krishna Gudipati,
>
> The patch 51e569aa1f0c: "[SCSI] bfa: Added support to obtain SFP
> info." from Jun 24, 2011, leads to the following static checker
> warning:
>
> drivers/scsi/bfa/bfa_ioc.c:3668 bfa_cb_sfp_state_que
On 03/27/2014 09:39 AM, Jayamohan Kallickal wrote:
> Even before probe for function was completed, iSCSI Daemon had initiated
> login
> to target while OS was coming up. The targets which had
> node.startup=automatic,
> login process was initiated.Since function specific initialization was sti
On 02/24/2014 07:06 PM, vikas.chaudh...@qlogic.com wrote:
> From: Tej Parkash
>
> Problem:
> iSCSI stop_firmware mailbox command is not completing outstanding IO.
>
What about qla4xxx_hw_reset? I saw the comment in
qla4_8xxx_stop_firmware saying what you wrote above, but for the old
qla4xxx_is
Hi Mike,
qla4xxx_hw_reset is specific to ISP4032, which does not come in same block,
there is check of ISP80XX (exclude ISP4032) before we enter this block.
Let me know if any other concern.
Thanks
Tej
From: Mike Christie [micha...@cs.wisc.edu]
Sent: Fri
On Mar 27, 9:22pm, Tommy Apel wrote:
} Subject: Re: [Scst-devel] OSS target - VMware SCSI reservation bug conform
Good morning, hope the end of the week is going well for everyone.
> 2014-03-27 19:21 GMT+01:00 Dr. Greg Wettstein :
> > Hi, hope the week is going well for everyone.
> >
> > There a
Hi,
> During kexec boot we call ibmvscsi_release_crq_queue() to tear down
> the old CRQ from the previous kernel. ibmvscsi_release_crq_queue()
> does this by calling H_FREE_CRQ. The hypervisor breaks this work
> down so as limit the time spent in any one hcall, so we have to loop
> until complete
39 matches
Mail list logo
