Dear All,
I must say first that I am new to Infiniband so maybe I am just making some
stupid mistakes. I have installed OFED-1.5-rc1 on OpenSUSE 11.1 (we need
gcc4.3). The installer expects libstdc++4.2 but it is libstdc++4.3
on the system, so after changing this in the installer everything
On Thu, Oct 29, 2009 at 12:10 PM, Gheorghe Ardelean
ardel...@ww.uni-erlangen.de wrote:
I must say first that I am new to Infiniband so maybe I am just making some
stupid mistakes. I have installed OFED-1.5-rc1 on OpenSUSE 11.1 (we need
gcc4.3). The installer expects libstdc++4.2 but it is
I'm having an issue with using the available distro OFED package.
This was with Ubuntu 9.04:
node:~$ sudo ibv_devinfo
mlx4: There is a mismatch between the kernel and the userspace
libraries: Kernel does not support XRC. Exiting.
Failed to open device
This was using the
Bart,
It appears that it has.
node:~$ aptitude search libmlx4
i A libmlx4-1 - A userspace driver for Mellanox
ConnectX I
p libmlx4-1-dbg - Debugging symbols for the
libmlx4 driver
p libmlx4-dev - Development files for the
node:~$ sudo ibv_devinfo
mlx4: There is a mismatch between the kernel and the userspace
libraries: Kernel does not support XRC. Exiting.
Failed to open device
It seems you are using the default Ubuntu kernel but a libmlx4 package
from somewhere else. If you are using the OFED-patched
Chris Worley, on 10/28/2009 09:47 PM wrote:
It appears that SRP tries to coalesce and fragment initiator I/O
requests into 64KB packets, as that looks to be the size requested
to/from the device on the target side (and the I/O scheduler is
disabled on the target).
Is there a way to control
On 19:48 Fri 23 Oct , Hal Rosenstock wrote:
Heap memory consumption by the unicast and multicast routing tables can be
reduced.
This patch is analagous to the previous patch doing this for the unicast
routing tables (LFTs).
Using valgrind --tool=massif (for heap profiling), there
Set switch's mcast table max_mlid_ho as actually configured mlid for the
switch instead of a value extended to MFT block size aligned. This makes
mlid handling checks to be more reliable.
Signed-off-by: Sasha Khapyorsky sas...@voltaire.com
---
opensm/opensm/osm_mcast_tbl.c |5 +++--
1 files
Rename 'ibnd_scan' variable to shorter 'scan' to highlight its local
feature.
Signed-off-by: Sasha Khapyorsky sas...@voltaire.com
---
infiniband-diags/libibnetdisc/src/chassis.c | 52
infiniband-diags/libibnetdisc/src/ibnetdisc.c | 40 +-
2 files
Cleanups: kill not needed braces, castings, consolidate flows.
Signed-off-by: Sasha Khapyorsky sas...@voltaire.com
---
infiniband-diags/libibnetdisc/src/chassis.c | 117 -
infiniband-diags/libibnetdisc/src/ibnetdisc.c | 90 +--
2 files changed, 99
Merge some obviously repeated code in optional counters processing
functions.
Signed-off-by: Sasha Khapyorsky sas...@voltaire.com
---
infiniband-diags/src/perfquery.c | 91 --
1 files changed, 29 insertions(+), 62 deletions(-)
diff --git
Hi Ira,
Thanks for reporting.
On 15:44 Thu 29 Oct , Ira Weiny wrote:
OpenSM $ mlid_ho 49152; p_tbl-max_mlid_ho 49152
mlid_ho 49154; p_tbl-max_mlid_ho 49153
opensm: osm_mcast_tbl.c:107: osm_mcast_tbl_set: Assertion `mlid_ho =
p_tbl-max_mlid_ho' failed.
Aborted (core dumped)
Small
Export rdma_set_ib_paths to user space to allow applications to
manually set the IB path used for connections. This allows
alternative ways for a user space application or library to obtain
path record information, including retrieving path information
from cached data, avoiding direct
On 09:18 Tue 04 Aug , Hal Rosenstock wrote:
Implementation description would be very useful.
What does initial support mean?
Signed-off-by: Hal Rosenstock hal.rosenst...@gmail.com
---
diff --git a/opensm/include/opensm/osm_subnet.h
b/opensm/include/opensm/osm_subnet.h
index
On 10:05 Sat 24 Oct , Hal Rosenstock wrote:
As part of this change, transaction timeouts (and retries) are per
umad agent (supplied at osm_vendor_bind).
Old ABI is supported without these bind parameters.
Signed-off-by: Hal Rosenstock hal.rosenst...@gmail.com
---
diff --git
On 09:43 Thu 22 Oct , Hal Rosenstock wrote:
This define controls an array in the OpenSM umad vendor layer. Moving
this define to the vendor layer aids in Windows porting. See thread
which ends with:
http://lists.openfabrics.org/pipermail/ofw/2009-October/005819.html
Signed-off-by: Hal
16 matches
Mail list logo