librdma_cm: client example failed

librdma_cm: client example failed

[joel vennin]

Hi,

I've downloaded the latest version of librdma_cm 1.0.12.

I got unexpected segfault (hum, usually segfault is not really expected .. ;)

On the same server I execute the rdma_server and rdma_client. The
first is waiting incoming message. The second one segfault. This is
the backtrace of the rdma_client:
#0  0x00007f3de011482d in ?? () from /usr/lib/libmlx4-rdmav2.so
#1  0x00007f3de011640e in ?? () from /usr/lib/libmlx4-rdmav2.so
#2  0x00007f3de0a94244 in __ibv_modify_qp (qp=0x2458d40, attr=0x0,
attr_mask=57) at src/verbs.c:474
#3  0x00007f3de0c9b292 in ucma_init_conn_qp (id_priv=0x24590d0,
qp=0x2458d40) at src/cma.c:1060
#4  0x00007f3de0c9b3a3 in rdma_create_qp (id=0x24590d0, pd=<value
optimized out>, qp_init_attr=0x7fff973aa090) at src/cma.c:1203
#5  0x00007f3de0c9d6a9 in rdma_create_ep (id=0x601650, res=0x2458650,
pd=0x0, qp_init_attr=0x7fff973aa090) at src/cma.c:2153
#6  0x0000000000400bae in run () at examples/rdma_client.c:67
#7  0x0000000000400fcf in main (argc=1, argv=0x7fff973aa288) at
examples/rdma_client.c:131


The IB chipset is the following one:
04:00.0 InfiniBand: Mellanox Technologies MT26428 [ConnectX IB QDR,
PCIe 2.0 5GT/s] (rev a0)

Kernel use:
Linux 2.6.32.7.v01 #1 SMP Wed Feb 3 15:45:37 CET 2010 x86_64 GNU/Linux

libibverbs: 1.1.2
libmlx4: 1.0

Any help will be appreciated,

Thank you

Joel
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

RE: librdma_cm: client example failed

[Hefty, Sean]

> On the same server I execute the rdma_server and rdma_client. The
> first is waiting incoming message. The second one segfault. This is
> the backtrace of the rdma_client:
> #0  0x00007f3de011482d in ?? () from /usr/lib/libmlx4-rdmav2.so
> #1  0x00007f3de011640e in ?? () from /usr/lib/libmlx4-rdmav2.so
> #2  0x00007f3de0a94244 in __ibv_modify_qp (qp=0x2458d40, attr=0x0,
> attr_mask=57) at src/verbs.c:474

The attr parameter doesn't look right.  ucma_init_conn_qp calls ibv_modify_qp using an &attr parameter from the stack.  The attr_mask looks like it could be correct.

Can you try updating the libmlx4 library and see if you get the same resuls?

- Sean
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html