[ewg] rping/rdma cm address resolution trouble

[Matthew Small]

I am having trouble running rping and was wondering if anyone had any
suggestions as to what is going wrong.  Here is my results from running
rping on two nodes in my cluster:

Server Node (192.168.122.253)-

$ rping -s -a 127.0.0.1 -p 12345 -v -d -C 5
   count 5
   created cm_id 0x508190
   rdma_bind_addr successful
   rdma_listen

Client Node-

$ rping -c -a 192.168.122.253 -p 12345 -v -d -C 5
   count 5
   created cm_id 0x505b40
   cma_event type 1 cma_id 0x505b40 (parent)
   cma event 1, error -2
   waiting for addr/route resolution state 1
   Segmentation fault
$

Things to note:
When I first tried this, I attempted to bind the server to it's IP address (
192.168.122.253) rather than the loopback and received an error from the
bind.   The  rping command works properly when I run the client and server
on the same node as long as the client specifies the loopback address and
not the nodes IP address.  Below I have included output from ifconfig.  I
have just recently started working with this infiniband setup so it may be
something I'm missing thats pretty obvious.

$ /sbin/ifconfig
eth0      Link encap:Ethernet
          inet addr:192.168.122.253  Bcast:192.168.255.255  Mask:255.255.0.0
          inet6 addr: fe80::219:b9ff:fee4:58f1/64 Scope:Link
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:3424250 errors:0 dropped:0 overruns:0 frame:0
          TX packets:961642 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:1000
          RX bytes:468558412 (446.8 MiB)  TX bytes:256364830 (244.4 MiB)
          Interrupt:169 Memory:f8000000-f8011100

eth1      Link encap:Ethernet
          inet addr:192.168.123.253  Bcast:192.168.123.255  Mask:
255.255.255.0
          inet6 addr: fe80::219:b9ff:fee4:58f3/64 Scope:Link
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:126893725 errors:0 dropped:241 overruns:0 frame:0
          TX packets:133000489 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:1000
          RX bytes:118522954308 (110.3 GiB)  TX bytes:129523439551 (120.6GiB)
          Interrupt:169 Memory:f4000000-f4011100

lo        Link encap:Local Loopback
          inet addr:127.0.0.1  Mask:255.0.0.0
          inet6 addr: ::1/128 Scope:Host
          UP LOOPBACK RUNNING  MTU:16436  Metric:1
          RX packets:2209361 errors:0 dropped:0 overruns:0 frame:0
          TX packets:2209361 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:0
          RX bytes:135356030 (129.0 MiB)  TX bytes:135356030 (129.0 MiB)

-Matt
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/ewg/attachments/20080214/9eac09d7/attachment.html>