On Tue, 2015-08-04 at 12:09 -0600, Jason Gunthorpe wrote:
On Mon, Aug 03, 2015 at 11:33:51AM -0700, Bart Van Assche wrote:
Bart, do you know what hardware this workaround is for?
I hope the HW vendors can comment on this. Sorry but I'm not sure which HCA
models and/or firmware versions
On Fri, 2015-05-29 at 09:05 -0400, Doug Ledford wrote:
It's been over two weeks and no response from either Dave or Alex. I
have filed a ticket to have them removed from the maintainers list.
Sorry, thought I replied to this earlier -- I'm fine with it, I
unfortunately don't have time to keep
On Tue, 2014-07-08 at 15:49 +0200, Bart Van Assche wrote:
Thanks for digging up this information and also for sharing it.
Sure thing; it's a bummer that something in the email must have tickled
vger's taboo filters...
This is interesting. What I noticed is that the in the SRP target
driver
On Wed, 2014-07-09 at 15:57 +0200, Bart Van Assche wrote:
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1644,10 +1644,14 @@ static void srp_process_rsp(struct srp_target_port
*target, struct srp_rsp *rsp)
On Thu, 2014-07-03 at 15:47 +0200, Bart Van Assche wrote:
- if (rsp-flags (SRP_RSP_FLAG_DOOVER | SRP_RSP_FLAG_DOUNDER))
- scsi_set_resid(scmnd,
be32_to_cpu(rsp-data_out_res_cnt));
- else if (rsp-flags (SRP_RSP_FLAG_DIOVER |
-removal-and-multipa.patch
0003-IB-srp-Fix-residual-handling.patch
0004-IB-srp-Use-P_Key-cache-for-P_Key-lookups.patch
0005-IB-srp-Optimize-completion-queue-polling.patch
All except the last can be
Acked-by: David Dillow d...@thedillows.org
or feel free to s/Acked/Reviewed/
--
To unsubscribe from
[Apologies if you get this twice, mailer crashed during the first send]
On Thu, 2014-07-03 at 15:48 +0200, Bart Van Assche wrote:
Reduce completion queue lock contention by polling for multiple
work completions at once. Limit the number of poll cycles per
completion notification to preserve
On Thu, 2014-07-03 at 15:48 +0200, Bart Van Assche wrote:
Reduce completion queue lock contention by polling for multiple
work completions at once. Limit the number of poll cycles per
completion notification to preserve fairness if multiple verbs
applications use the same port or if multiple
On Wed, 2014-02-26 at 14:16 +0100, Bart Van Assche wrote:
On 02/26/14 07:32, David Dillow wrote:
On Tue, 2014-02-25 at 11:33 +0100, Bart Van Assche wrote:
Do you really think it is essential to introduce a
new flag in the block layer for the purpose of suppressing transport
layer error
On Tue, 2014-02-25 at 11:33 +0100, Bart Van Assche wrote:
Do you really think it is essential to introduce a
new flag in the block layer for the purpose of suppressing transport
layer error messages and to add support for that flag in the block
core and in the SCSI mid-layer ? To me it seems a
On Mon, 2014-02-24 at 20:58 +0100, Bart Van Assche wrote:
On 02/22/14 06:41, David Dillow wrote:
I didn't suggest that -- I'm saying add a common functionality to turn
on/off the message printing for commands that failed due to a dead
transport. If it is useful for SRP initiators
On Fri, 2014-02-21 at 10:23 +0100, Bart Van Assche wrote:
On 02/21/14 04:55, David Dillow wrote:
While I can see the utility for slow consoles, this should probably be
done in the SCSI lib, with a separate flag for indicating it is a
failure due to transport issues. That would allow
On Thu, 2014-02-20 at 11:52 +0100, Bart Van Assche wrote:
Do not log SCSI command failures that are the result of a transport
layer failure, a SCSI abort or SCSI reset. This patch is a slightly
modified version of a patch posted by Sebastian Riemer in March 2013
(see also
with that of the FC
transport layer.
* Fix a rare race condition triggered by path failover.
* Document the rport state transitions.
For all three,
Acked-by: David Dillow dillo...@ornl.gov
Thanks Bart!
--
Dave Dillow
National Center for Computational Science
Oak Ridge National Laboratory
(865
On Thu, 2013-10-31 at 10:02 -0700, Bart Van Assche wrote:
On 31/10/2013 9:21, Or Gerlitz wrote:
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -104,7 +104,7 @@ static ssize_t state_show(struct ib_port *p, struct
port_attribute *unused,
return
On Sat, 2013-10-26 at 14:29 +0200, Bart Van Assche wrote:
The changes since the previous version of this patch series are as follows
(see also http://thread.gmane.org/gmane.linux.drivers.rdma/17693):
- Renamed the can_queue parameter into queue_size.
- Corrected the title of the introductory
-freeing-Scsi_H.patch
0002-IB-srp-Avoid-offlining-operational-SCSI-devices.patch
0003-IB-srp-Report-receive-errors-correctly.patch
Acked-by: David Dillow dillo...@ornl.gov
for all three. Thanks Bart!
--
Dave Dillow
National Center for Computational Science
Oak Ridge National Laboratory
(865
On Thu, 2013-10-10 at 14:19 +0200, Bart Van Assche wrote:
@@ -2267,6 +2310,7 @@ static const match_table_t srp_opt_tokens = {
{ SRP_OPT_SG_TABLESIZE, sg_tablesize=%u },
{ SRP_OPT_COMP_VECTOR, comp_vector=%u},
{ SRP_OPT_TL_RETRY_COUNT,
it possible to figure out which SCSI host corresponds to which
SRP initiator port by making the SGID (source GID) available in sysfs.
Many of these already have it, but for patches 1-10:
Acked-by: David Dillow dillo...@ornl.gov
--
Dave Dillow
National Center for Computational Science
Oak Ridge
On Sat, 2013-10-19 at 18:13 +0200, Bart Van Assche wrote:
Since it takes some work to figure out the state transitions from the
source code, I have tried to draw a diagram representing all state
transitions. I have attached that diagram to this e-mail. That diagram
probably will make it
On Wed, 2013-10-09 at 09:28 -0400, Hal Rosenstock wrote:
From strace:
poll([{fd=0, events=POLLIN}], 1, 1000) = 1 ([{fd=0, revents=POLLIN}])
read(0, , 4096) = 0
poll([{fd=0, events=POLLIN}], 1, 1000) = 1 ([{fd=0, revents=POLLIN}])
read(0, , 4096)
On Mon, 2013-09-16 at 16:25 +0200, Bart Van Assche wrote:
On 09/12/13 00:16, David Dillow wrote:
On Tue, 2013-09-10 at 19:44 +0200, Bart Van Assche wrote:
If this name was not yet in use in any interface that is visible in user
space, I would agree that we should come up with a better name
On Mon, 2013-09-09 at 14:12 +0200, Jack Wang wrote:
On 08/28/2013 10:19 AM, Jack Wang wrote:
Hi,
Below patch is new version which address comments from Bart.
Hi Roland,
Could you included this in your tree or do you need me resend it?
Acked-by: David Dillow dillo...@ornl.gov
I
, tl_retry_count=%u },
+ { SRP_OPT_CAN_QUEUE,can_queue=%d },
I'm pretty much OK with the patch, but since we're stuck with it going
forward, I'd like to have a better externally visible name here --
queue_depth? max_queue? queue_size?
Otherwise,
Acked-by: David
as requested by Dave Dillow.
- Fixed a race between transport layer failure handling and device
removal. This issue was reported by Vu Pham.
For patches 1-6,
Acked-by: David Dillow dillo...@ornl.gov
--
Dave Dillow
National Center for Computational Science
Oak Ridge National Laboratory
(865) 241-6602
On Tue, 2013-08-20 at 17:55 +0200, Bart Van Assche wrote:
On 08/20/13 17:34, Sagi Grimberg wrote:
Question,
If srp now will allow larger queues while using a single global FMR pool
of size 1024, isn't it more likely now that in stress environment srp
will run out of FMRs to handle IO
: David Dillow dillo...@ornl.gov
Cc: Roland Dreier rol...@purestorage.com
Cc: Vu Pham v...@mellanox.com
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo info
On Thu, 2013-07-04 at 10:01 +0200, Bart Van Assche wrote:
On 07/03/13 20:57, David Dillow wrote:
And I'm getting the strong sense that the answer to my question about
fast_io_fail_tmo = 0 when dev_loss_tmo is that we should not allow that
combination, even if it doesn't break the kernel
...@profitbricks.com
Signed-off-by: Bart Van Assche bvanass...@acm.org
Acked-by: David Dillow dillo...@ornl.gov
I don't believe I ack'd this; I don't want the callers doing the result
shift, do it in srp_finish_req().
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body
On Tue, 2013-07-02 at 13:18 -0600, Jason Gunthorpe wrote:
On Mon, Jul 01, 2013 at 07:26:05AM -0400, David Dillow wrote:
You assume independent failures, which is suspect -- many times these
are data-dependent, or so I tend to think. Jason, do you have any
insight on this (overall) topic you
count from 2
back to 7]
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wed, 2013-07-03 at 16:45 +0200, Bart Van Assche wrote:
Having it in the caller has the
advantage that the compiler can optimize the shift operation out because
the number that is being shifted left is a constant.
srp_finish_req() is likely to be inlined, so the compiler will be able
to
On Wed, 2013-07-03 at 10:57 -0400, David Dillow wrote:
On Wed, 2013-07-03 at 16:45 +0200, Bart Van Assche wrote:
Having it in the caller has the
advantage that the compiler can optimize the shift operation out because
the number that is being shifted left is a constant.
srp_finish_req
On Wed, 2013-07-03 at 14:54 +0200, Bart Van Assche wrote:
+int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo)
+{
+ return (fast_io_fail_tmo 0 || dev_loss_tmo 0 ||
+ fast_io_fail_tmo dev_loss_tmo)
+ fast_io_fail_tmo = SCSI_DEVICE_BLOCK_MAX_TIMEOUT
+
On Wed, 2013-07-03 at 18:00 +0200, Bart Van Assche wrote:
On 07/03/13 17:14, David Dillow wrote:
On Wed, 2013-07-03 at 14:54 +0200, Bart Van Assche wrote:
+int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo)
+{
+ return (fast_io_fail_tmo 0 || dev_loss_tmo 0
On Wed, 2013-07-03 at 20:24 +0200, Bart Van Assche wrote:
On 07/03/13 19:27, David Dillow wrote:
On Wed, 2013-07-03 at 18:00 +0200, Bart Van Assche wrote:
The combination of dev_loss_tmo off and reconnect_delay 0 worked fine
in my tests. An I/O failure was detected shortly after the cable
On Mon, 2013-07-01 at 10:18 +0200, Bart Van Assche wrote:
On 06/30/13 23:48, David Dillow wrote:
On Fri, 2013-06-28 at 14:58 +0200, Bart Van Assche wrote:
From: Vu Pham vuhu...@mellanox.com
Allow the InfiniBand RC retry count to be configured by the user
as an option in the target login
On Mon, 2013-07-01 at 09:01 +0200, Bart Van Assche wrote:
On 06/30/13 23:05, David Dillow wrote:
On Fri, 2013-06-28 at 14:53 +0200, Bart Van Assche wrote:
+int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo)
+{
+ return (fast_io_fail_tmo 0 || dev_loss_tmo 0
On Fri, 2013-06-28 at 14:48 +0200, Bart Van Assche wrote:
Avoid that srp_claim_command() can claim a command while
I think you meant srp_claim_req() ?
srp_queuecommand() is still busy queueing the same command.
Found this via source reading.
The main issue seems to be a broken, possibly
and recreating an rport via sysfs.
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
accepted,
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
.
Signed-off-by: Bart Van Assche bvanass...@acm.org
Cc: Roland Dreier rol...@purestorage.com
Cc: James Bottomley jbottom...@parallels.com
Cc: David Dillow dillo...@ornl.gov
Cc: Vu Pham v...@mellanox.com
Cc: Sebastian Riemer sebastian.rie...@profitbricks.com
---
Documentation/ABI/stable/sysfs
that the SCSI
error handler skips the srp_reset_host() call after a transport
layer error.
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo info at http
On Fri, 2013-06-28 at 14:49 +0200, Bart Van Assche wrote:
If reconnecting failed we know that no command completion will
be received anymore. Hence let the SCSI error handler fail such
commands immediately.
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send
On Fri, 2013-06-28 at 14:54 +0200, Bart Van Assche wrote:
Finish all outstanding I/O requests after fast_io_fail_tmo expired,
which speeds up failover in a multipath setup. This patch is a
reworked version of a patch from Sebastian Riemer.
-static void srp_reset_req(struct srp_target_port
nit.
Assuming we accept patch 8,
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, 2013-06-28 at 14:55 +0200, Bart Van Assche wrote:
Start the reconnect timer, fast_io_fail timer and dev_loss timers
if a transport layer error occurs.
Assuming 8 is applied,
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma
On Fri, 2013-06-28 at 14:56 +0200, Bart Van Assche wrote:
From: Sebastian Riemer sebastian.rie...@profitbricks.com
Avoid that path failover in a multipath setup causes the SCSI layer
to generate kernel messages about SCSI command failures. This patch
speeds up SRP initiator operation
, configuring the completion
vector properly not only allows to reduce latency on an initiator
connected to multiple SRP targets but also allows to improve
throughput.
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body
On Fri, 2013-06-28 at 14:58 +0200, Bart Van Assche wrote:
From: Vu Pham vuhu...@mellanox.com
Allow the InfiniBand RC retry count to be configured by the user
as an option in the target login string. The transport layer
timeout in nanoseconds is computed as follows from the retry count:
On Fri, 2013-06-28 at 10:18 +0200, Bart Van Assche wrote:
On 06/27/13 23:24, David Dillow wrote:
Shouldn't there be some documentation about how to set this? What
happens when you try to set it on an HCA that doesn't support this how
does the user know what's wrong?
Hello Dave,
HCA
that the SCSI
error handler skips the srp_reset_host() call after a transport
layer error.
Acked-by: David Dillow dillo...@ornl.gov
--
Dave Dillow
National Center for Computational Science
Oak Ridge National Laboratory
(865) 241-6602 office
--
To unsubscribe from this list: send the line
On Wed, 2013-06-12 at 15:24 +0200, Bart Van Assche wrote:
The SRP initiator implements host reset by reconnecting to the SRP
target. That means that communication with the target is possible
as soon as host reset finished. Hence skip the host settle delay.
Acked-by: David Dillow dillo
On Wed, 2013-06-12 at 15:20 +0200, Bart Van Assche wrote:
If the add_one callback fails during driver load no resources are
allocated so there isn't a need to release any resources. Trying
to clean the resource may lead to the following kernel panic:
Acked-by: David Dillow dillo...@ornl.gov
On Wed, 2013-06-12 at 15:25 +0200, Bart Van Assche wrote:
An SRP target is required to maintain a single connection between
initiator and target. This means that if the 'add_target' attribute
is used to create a second connection to a target that the first
connection will be logged out and
On Wed, 2013-06-12 at 17:14 +0200, Bart Van Assche wrote:
Not sure how I missed that ... I will drop this version and replace it
with the proper fix.
I expect the merge window will be opening soon; I should be able to make
time on Sunday to review anything you post by then -- do you think the
to the indirect_command_descriptors, etc. Unless srp_daemon is patched,
this won't be usable without that. I'm not tied to this position, though
-- we should be moving in the direction of more control via the login
string.
Otherwise,
Acked-by: David Dillow dillo...@ornl.gov
--
Dave Dillow
National Center
On Wed, 2013-06-12 at 15:35 +0200, Bart Van Assche wrote:
Several InfiniBand HCA's allow to configure the completion vector
per queue pair. This allows to spread the workload created by IB
completion interrupts over multiple MSI-X vectors and hence over
multiple CPU cores. In other words,
On Fri, 2013-02-15 at 10:39 +0100, Bart Van Assche wrote:
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c
b/drivers/infiniband/ulp/srp/ib_srp.c
index 8a7eb9f..b34752d 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -734,6 +734,7 @@ static int
On Mon, 2013-01-07 at 06:34 -0500, Bart Van Assche wrote:
Sorry but this patch looks wrong to me, and that because of the
following reasons:
- A root cause analysis is missing. It has been mentioned in the patch
description that device_del() did hang but an analysis of why that
hang
On Thu, 2012-12-20 at 09:13 +0100, Bart Van Assche wrote:
On 12/19/12 19:04, David Dillow wrote:
On Wed, 2012-12-19 at 15:21 +0100, Bart Van Assche wrote:
The connection state must be initialized before srp_connect_target()
is invoked. Drop the assignment in srp_add_target() since it occurs
On Thu, 2012-12-20 at 17:27 +0200, Or Gerlitz wrote:
On 20/12/2012 17:10, David Dillow wrote:
Works for me, ship it!
Dave, did you gave the patches a try?
This one looks to be an obvious fix, but I have not tested the others; I
have been relying on Bart, Alex, and yourself
On Wed, 2012-12-19 at 15:21 +0100, Bart Van Assche wrote:
The connection state must be initialized before srp_connect_target()
is invoked. Drop the assignment in srp_add_target() since it occurs
after srp_connect_target() and since scsi_host_alloc()
zero-initializes the Scsi_Host structure
On Wed, 2012-12-19 at 15:22 +0100, Bart Van Assche wrote:
Do not send a task management function if sending will fail anyway
because either there is no RDMA/RC connection or the QP is in the
error state.
Signed-off-by: Bart Van Assche bvanass...@acm.org
Acked-by: David Dillow dillo
or if reconnecting fails.
Signed-off-by: Bart Van Assche bvanass...@acm.org
It's not the cleanest way to handle this, but it is the simplest and
we're short on time.
Acked-by: David Dillow dillo...@ornl.gov
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body
On Fri, 2012-12-14 at 17:12 +0100, Bart Van Assche wrote:
Thanks for the quick reply. You might have missed Vu's message though.
Vu Pham reported that v1 of this patch did not fix the endless error
handling loop (see e.g.
On Fri, 2012-12-14 at 16:38 +0100, Bart Van Assche wrote:
If a SCSI command times out it is passed to the SCSI error
handler. The SCSI error handler will try to abort the command
that timed out. If aborting failed a device reset will be
attempted. If the device reset fails too a host reset
like that.
Acked-by: David Dillow d...@thedillows.org
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, 2012-12-14 at 17:12 +0100, Bart Van Assche wrote:
On 12/14/12 16:55, David Dillow wrote:
This is much more than your original patch that Alex claimed fixed his
issues; are you not merging two separate issues?
Also, there's no reason to invoke srp_send_tsk_mgmt() if we're
On Thu, 2012-11-29 at 12:21 -0800, Roland Dreier wrote:
On Mon, Nov 26, 2012 at 8:04 PM, David Dillow dillo...@ornl.gov wrote:
We can push it through James's tree if need be, but Bart's code is
pretty self-contained, and going through the SCSI tree will introduce
merge dependencies. It'd
On Mon, 2012-11-26 at 10:43 +0100, Bart Van Assche wrote:
On 11/26/12 05:44, David Dillow wrote:
From: Bart Van Assche bvanass...@acm.org
Some SCSI upper layer drivers, e.g. sd, issue SCSI commands from
inside scsi_remove_host() (see also the sd_shutdown() call in
sd_remove()). Make
On Mon, 2012-11-26 at 10:46 +0100, Bart Van Assche wrote:
On 11/26/12 05:44, David Dillow wrote:
The state of the target has several conditions that overlap, making it
easier to model as a bit-field of exceptional conditions rather than an
enum of all possible states.
Bart Van Assche
On Mon, 2012-11-26 at 23:15 +0400, James Bottomley wrote:
On Mon, 2012-11-26 at 10:50 -0800, Roland Dreier wrote:
- I think the srp_transport stuff should go through linux-scsi /
James B.
instead of my tree, esp. since it's shared with the IBM vscsi stuff
(I think)
- I see Bart had
On Mon, 2012-11-26 at 09:57 +0200, Or Gerlitz wrote:
On Mon, Nov 26, 2012 at 6:44 AM, David Dillow dillo...@ornl.gov wrote:
One may also pull this series from github:
git pull git://github.com/dillow/srp-initiator.git ha-merge-v1
Hi Dave,
The kernel maintainers file specifies
On Fri, 2012-11-23 at 16:07 +0100, Bart Van Assche wrote:
On 09/27/12 02:31, David Dillow wrote:
On Tue, 2012-09-25 at 17:05 +0200, Bart Van Assche wrote:
On 08/09/12 17:41, Bart Van Assche wrote:
[ ... ]
Hello Dave,
More than six weeks have elapsed since I posted version four
...@acm.org
[ adapted to new state tracking ]
Signed-off-by: David Dillow dillo...@ornl.gov
---
drivers/infiniband/ulp/srp/ib_srp.c | 11 ++-
1 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c
b/drivers/infiniband/ulp/srp/ib_srp.c
index 2951e1c
the state space.
Needs-to-be-signed-off-by: Bart Van Assche bvanass...@acm.org
Signed-off-by: David Dillow dillo...@ornl.gov
---
drivers/infiniband/ulp/srp/ib_srp.c | 146 +--
drivers/infiniband/ulp/srp/ib_srp.h | 11 +--
2 files changed, 76 insertions(+), 81
From: Vu Pham v...@mellanox.com
From: Vu Pham v...@mellanox.com
Now that SRP recreates the CM id, QP, and CQ for each connection,
there is no need to wait for the timewait state to complete.
Signed-off-by: Vu Pham v...@mellanox.com
Signed-off-by: David Dillow dillo...@ornl.gov
---
drivers
Once we know we have an issue with the QP, there is no point trying to
send anything else down the pipe. This also allows us to consolidate
code in the SCSI EH path.
Needs-to-be-signed-off-by: Bart Van Assche bvanass...@acm.org
[ adapted to new state tracking code ]
Signed-off-by: David Dillow
srp_transport: Simplify attribute initialization code
srp_transport: Document sysfs attributes
IB/srp: Allow SRP disconnect through sysfs
David Dillow (2):
IB/srp: simplify state tracking
IB/srp: don't send anything on a bad QP
Ishai Rabinovitz (1):
IB/srp: destroy and recreate QP and CQs
on the new connection.
Signed-off-by: Ishai Rabinovitz is...@mellanox.co.il
Signed-off-by: Michael S. Tsirkin m...@mellanox.co.il
[ updated to current code from OFED, cleaned up commit message ]
Signed-off-by: David Dillow dillo...@ornl.gov
---
drivers/infiniband/ulp/srp/ib_srp.c | 66
From: David Dillow dillo...@ornl.gov
From: Bart Van Assche bvanass...@acm.org
Eliminate the private_rport_attrs[] array and the SETUP_*() macros
used to set up that array since the information in that array
duplicates the information in the static device attributes. Also,
verify whether
...@lab.ntt.co.jp
Cc: Robert Jennings r...@linux.vnet.ibm.com
Signed-off-by: Bart Van Assche bvanass...@acm.org
Signed-off-by: David Dillow dillo...@ornl.gov
---
Documentation/ABI/stable/sysfs-transport-srp |7 +++
drivers/infiniband/ulp/srp/ib_srp.c | 10 ++
drivers/scsi
From: Bart Van Assche bvanass...@acm.org
Enlarge the block layer timeout for disks such that it is above
the InfiniBand transport layer timeout.
Signed-off-by: Bart Van Assche bvanass...@acm.org
Signed-off-by: David Dillow dillo...@ornl.gov
---
drivers/infiniband/ulp/srp/ib_srp.c | 45
sure that any code reading the attribute array will see all
values written into that array.
Cc: FUJITA Tomonori fujita.tomon...@lab.ntt.co.jp
Cc: Robert Jennings r...@linux.vnet.ibm.com
Signed-off-by: Bart Van Assche bvanass...@acm.org
Signed-off-by: David Dillow dillo...@ornl.gov
---
drivers/scsi
From: Bart Van Assche bvanass...@acm.org
Document the sysfs attributes of the SRP initiator according
to the rules specified in Documentation/ABI/README.
Signed-off-by: Bart Van Assche bvanass...@acm.org
Signed-off-by: David Dillow dillo...@ornl.gov
---
Documentation/ABI/stable/sysfs-driver
From: Bart Van Assche bvanass...@acm.org
Cc: FUJITA Tomonori fujita.tomon...@lab.ntt.co.jp
Cc: Robert Jennings r...@linux.vnet.ibm.com
Signed-off-by: Bart Van Assche bvanass...@acm.org
Signed-off-by: David Dillow dillo...@ornl.gov
---
Documentation/ABI/stable/sysfs-transport-srp | 12
On Sun, 2012-11-25 at 23:44 -0500, David Dillow wrote:
From: David Dillow dillo...@ornl.gov
From: Bart Van Assche bvanass...@acm.org
Eliminate the private_rport_attrs[] array and the SETUP_*() macros
used to set up that array since the information in that array
duplicates the information
On Tue, 2012-09-25 at 17:05 +0200, Bart Van Assche wrote:
On 08/09/12 17:41, Bart Van Assche wrote:
[ ... ]
Hello Dave,
More than six weeks have elapsed since I posted version four of this
patch series. It would be appreciated if you could tell me when review
comments for this patch
On Fri, 2012-08-24 at 10:27 +, Bart Van Assche wrote:
srp_free_req() uses the scsi_cmnd structure contents to unmap
buffers, so we must invoke srp_free_req() before we release
ownership of that structure.
Signed-off-by: Bart Van Assche bvanass...@acm.org
Acked-by: David Dillow dillo
On Mon, 2012-09-17 at 15:50 -0400, Roland Dreier wrote:
On Mon, Sep 17, 2012 at 12:31 PM, David Dillow dillo...@ornl.gov wrote:
Roland, are you planning to apply this one and the one Bart has that
fixes the error handling (srp_aport)? I didn't see them in your pull
request.
Sorry, I
by calling scsi_done().
But otherwise
Acked-by: David Dillow dillo...@ornl.gov
[PATCH 2/2] ib_srp: Avoid that aborted requests cause I/O to hang
Acked-by: David Dillow dillo...@ornl.gov
--
Dave Dillow
National Center for Computational Science
Oak Ridge National Laboratory
(865) 241-6602 office
On Tue, 2012-05-29 at 17:07 -0400, Karandeep Chahal wrote:
Subject: [PATCH] Infiniband srp fast failover patch.
This conflicts with Bart's patches to improve failover; it will be much
better to use his approach to block the target rather than remove it
wholesale -- we could have lost
On Mon, 2012-05-21 at 17:49 +0200, Bernd Schubert wrote:
David, below is a first version to convert SRP_RQ_SHIFT into a new
module option srp_rq_size. I already tested it, but I also need to
re-read it myself.
Author: Bernd Schubert bernd.schub...@itwm.fraunhofer.de
Date: Mon May 21
On Wed, 2012-05-30 at 01:22 -0400, David Dillow wrote:
On Mon, 2012-05-21 at 17:49 +0200, Bernd Schubert wrote:
David, below is a first version to convert SRP_RQ_SHIFT into a new
module option srp_rq_size. I already tested it, but I also need to
re-read it myself.
Author: Bernd
On Sat, 2012-05-19 at 10:50 +, Bart Van Assche wrote:
On 04/30/12 15:11, David Dillow wrote:
On Sun, 2012-04-22 at 16:01 +, Bart Van Assche wrote:
On 03/29/12 16:59, Dave Dillow wrote:
I haven't chewed on the rest yet, but would like to see this one at
least in 3.4 if possible
On Wed, 2012-05-16 at 11:54 -0400, Bernd Schubert wrote:
2) Low SRP command queues. Is there a reason why
SRP_RQ_SHIFT/SRP_RQ_SIZE and their depend values such as SRP_RQ_SIZE are
so small?
That's a decision that has been around since the beginning of the driver
as far as I can tell. It looks
On Sun, 2012-04-22 at 16:01 +, Bart Van Assche wrote:
On 03/29/12 16:59, Dave Dillow wrote:
I haven't chewed on the rest yet, but would like to see this one at
least in 3.4 if possible.
If you have further comments about any of the patches in this series,
these are welcome. The 3.5
On Sun, 2012-03-04 at 17:05 +, Bart Van Assche wrote:
On 02/26/12 06:39, David Dillow wrote:
As I've previously said, this is better handled by user space and
you add additional failure cases when you try to retrofit a transport
ping into SRP.
Let's look at this from another point
On Sat, 2012-03-03 at 14:37 +, Bart Van Assche wrote:
On 02/26/12 06:32, David Dillow wrote:
On Sat, 2012-01-14 at 12:43 +, Bart Van Assche wrote:
Separate connection and host state. Only report QP errors while
connected. Only invoke ib_send_cm_dreq() from inside
1 - 100 of 264 matches
Mail list logo