Roland,
Could you please review (and hopefully apply) the following patch series I
submitted
on Dec 17, 2009? These are really small patches.
The series seems to have fallen between the cracks.
Thanks!
-Jack
[PATCH 0/2] fix SRQ WQE buffer initialization in liblmx4 and in mlx4_ib
On Wednesday 03 February 2010 23:35, Roland Dreier wrote:
2. In closing/deallocating xrc domains, it is not an error if
ib_dealloc_xrcd returns busy.
This simply means that there are other user processes still using that
xrc domain.
The current process still needs to clean up
V2:
update the documentation
update the changelog
fix the checking code in udp
This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports,
it can be used like ip_local_port_range, but this is used to
reserve ports for third-party applications which use fixed
port numbers within
Mike Christie wrote:
What prevents the problem this code was handling from coming up now? Are
you now preallocating enough resources, or are you returning
-ENOMEM/-ENOBUFS from the init_task/xmit_task callouts so the scsi layer
is now requeueing the IO?
Basically before/after this change we
Or Gerlitz wrote:
Simplify and shrink the logic/code used for the send descriptors.
Changes include removal of struct iser_dto which is unnecessary
abstraction, use struct iser_regd_buf only for handling SCSI commands,
use dma_sync instead of dma_map/unmap, etc.
it turns out that bunch of
change the nes driver to return -ENOMEM on SQ/RQ overflow in the
manner done by other rdma hw drivers (e.g cxgb3, ehca, mlx4, mthca)
Signed-off-by: Or Gerlitz ogerl...@voltaire.com
Index: linux-2.6.33-rc4/drivers/infiniband/hw/nes/nes_verbs.c
After converting cl_status_t from enum to int,
no need to do this casting any more.
Signed-off-by: Yevgeny Kliteynik klit...@dev.mellanox.co.il
---
Note: this patch replaces the following patch:
[PATCH v3] opensm/complib/cl_passivelock.h: some casting issues
Check whether the loading is needed in the state mgr.
Signed-off-by: Yevgeny Kliteynik klit...@dev.mellanox.co.il
---
Changes since v2: cosmetics and copyright
opensm/opensm/osm_sa.c|8 +---
opensm/opensm/osm_state_mgr.c | 13 -
2 files changed, 9 insertions(+),
On Tue, Feb 2, 2010 at 7:45 PM, Ira Weiny wei...@llnl.gov wrote:
Sasha,
Following up on our thread regarding having multiple outstanding SMP's in
libibnetdisc.
These 2 patches implement that as well as add a function to set the max
outstanding the lib will use.
I left the default here
Bart Van Assche wrote:
Sounds really interesting. Do you have numbers available about how
much these patches improve throughput or decrease latency ?
Yes, generally speaking after the patches the initiator peaks to about 300-400K
IOPS
with latency under such load being 20-30us and before the
On Wed, Feb 3, 2010 at 5:39 AM, Sasha Khapyorsky sas...@voltaire.com wrote:
From: Slava Strebkov sla...@voltaire.com
Proposed new algorithm for calculation of root switch for multicast
spanning tree. Only edge switches(those connected to hosts or routers)
and switches - multicast members
Fix some commentary typos
Remove osm_ from static routine names
Signed-off-by: Hal Rosenstock hal.rosenst...@gmail.com
---
diff --git a/opensm/opensm/osm_mcast_mgr.c b/opensm/opensm/osm_mcast_mgr.c
index 19d0593..37ff120 100644
--- a/opensm/opensm/osm_mcast_mgr.c
+++
change the nes driver to return -ENOMEM on SQ/RQ overflow in the
manner done by other rdma hw drivers (e.g cxgb3, ehca, mlx4, mthca)
It should be consistent. Thanks for the patch.
Signed-off-by: Or Gerlitz ogerl...@voltaire.com
Acked-by: Chien Tung chien.tin.t...@intel.com
Chien
--
To
On 02/04/2010 05:21 AM, Or Gerlitz wrote:
[PATCH V2 08/9] ib/iser: move to use libiscsi passthrough mode
The libiscsi passthrough mode invokes the transport xmit calls directly
without first going through an internal queue as done in the other mode
which uses a queue and a xmitworker thread.
Subject: [PATCH] Wrong handling of MC create and delete traps
For these traps the GID in the data details is the MGID and
not the source port gid.
So the SM should check that subscriber port has the pkey of the MC group.
There was also an error in comparing the subnet prefix and guid due to
From: Octavian Purdila opurd...@ixiacom.com
Date: Thu, 4 Feb 2010 20:15:51 +0200
int inet_is_reserved_local_port(int port)
{
if (test_bit(port, reserved_ports))
return 1;
return 0;
}
In theory it might be slower because of the reserved_ports bitmap will have a
On Thu, Feb 4, 2010 at 1:00 PM, Ira Weiny wei...@llnl.gov wrote:
On Thu, 4 Feb 2010 09:19:39 -0500
Hal Rosenstock hal.rosenst...@gmail.com wrote:
On Tue, Feb 2, 2010 at 7:45 PM, Ira Weiny wei...@llnl.gov wrote:
Sasha,
Following up on our thread regarding having multiple outstanding SMP's
On 09:27 Thu 04 Feb , Hal Rosenstock wrote:
Fix some commentary typos
Remove osm_ from static routine names
Signed-off-by: Hal Rosenstock hal.rosenst...@gmail.com
Applied. Thanks.
Sasha
--
To unsubscribe from this list: send the line unsubscribe linux-rdma in
the body of a message to
In newly introduced MC group root switch calculation method as it is
now, sw-num_of_mcm field (number of MC group members connected to this
switch) is updated only once when switch is first visited (for some
reason it is under such 'if' block), as result it will always '1' or
'0', which is
On Thu, Feb 4, 2010 at 12:43 PM, Eli Dorfman (Voltaire)
dorfman@gmail.com wrote:
Subject: [PATCH] Wrong handling of MC create and delete traps
For these traps the GID in the data details is the MGID and
not the source port gid.
So the SM should check that subscriber port has the pkey of
From: Tetsuo Handa penguin-ker...@i-love.sakura.ne.jp
Date: Fri, 5 Feb 2010 06:45:28 +0900
Octavian Purdila wrote:
int inet_is_reserved_local_port(int port)
{
if (test_bit(port, reserved_ports))
return 1;
return 0;
}
Above check is exactly what I'm doing in the
OpenMPI uses rdma_bind_addr() to figure out which ip addresses are valid
for which IB devices. This logic is now broken. Regardless of whether
OpenMPI should use another method for determining which IP address
belong to which interfaces, we should probably rethink whether we're
breaking rdma-cm
Sean Hefty wrote:
But how can you determine _which_ rdma device should be used if and app
binds to 127.0.0.1? I think this is busted...
The code just picks the first rdma device available. To me, this is preferable
than simply disallowing the loopback device from working at all. I
Well then the rdma-cm needs to know which devices support hw loopback.
Cuz on a T3-only system, no hwloop...
The problem sounds like it's more than just whether 127.0.0.1 is usable. That
check may fix openmpi, but it sounds more like the app needs to know whether the
device can actually support
Sean Hefty wrote:
At first thought, we can extend enum ib_device_cap_flags to indicate if a device
supports loopback capabilities or not. The rdma_cm could then skip over such
devices when dealing with a loopback address.
This solution would work. Will you code it up?
Stevo
--
To
This solution would work. Will you code it up?
I can do that. I just want to make sure that we address the full scope of the
problem.
- Sean
--
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
Sean Hefty wrote:
Well then the rdma-cm needs to know which devices support hw loopback.
Cuz on a T3-only system, no hwloop...
The problem sounds like it's more than just whether 127.0.0.1 is usable. That
check may fix openmpi, but it sounds more like the app needs to know whether the
Hey Roland, are you ok with a device attribute to indicate hw-loopback
support?
Sigh, I guess so. Can we have the rdma-cm handle this somewhat
automagically, eg only choose devices that do handle loopback when
binding/connecting to 127.0.0.1? Or maybe can we put the handling of
this into
Roland Dreier wrote:
Hey Roland, are you ok with a device attribute to indicate hw-loopback
support?
Sigh, I guess so. Can we have the rdma-cm handle this somewhat
automagically, eg only choose devices that do handle loopback when
binding/connecting to 127.0.0.1?
That's the plan.
Or
On Thu, 4 Feb 2010 16:13:25 -0800
Ira Weiny wei...@llnl.gov wrote:
On Thu, 4 Feb 2010 15:01:32 -0500
Hal Rosenstock hal.rosenst...@gmail.com wrote:
On Thu, Feb 4, 2010 at 1:00 PM, Ira Weiny wei...@llnl.gov wrote:
On Thu, 4 Feb 2010 09:19:39 -0500
Hal Rosenstock
Tetsuo Handa wrote:
Hello.
Amerigo Wang wrote:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2b79377..d3e160a 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_timewait_death_row
Octavian Purdila wrote:
On Friday 05 February 2010 02:41:12 you wrote:
David Miller wrote:
Octavian Purdila wrote:
int inet_is_reserved_local_port(int port)
{
if (test_bit(port, reserved_ports))
return 1;
return 0;
}
Above check is exactly what I'm doing in
On Wed, Feb 3, 2010 at 5:30 AM, Amerigo Wang amw...@redhat.com wrote:
This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports,
it can be used like ip_local_port_range, but this is used to
reserve ports for third-party applications which use fixed
port numbers within
Bart Van Assche wrote:
On Wed, Feb 3, 2010 at 5:30 AM, Amerigo Wang amw...@redhat.com wrote:
This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports,
it can be used like ip_local_port_range, but this is used to
reserve ports for third-party applications which use fixed
port numbers
34 matches
Mail list logo