[openib-general] ping problem with ammasso cards(iWARP interface)

Steve Wise swise at opengridcomputing.com
Mon Jul 10 13:40:03 PDT 2006


Hey guys,

I lost this thread for a day due to a mailer problem, but I just noticed
something screwy with the iwarp branch.  I accidentally checked in
config.h and config.h.in for librdma.  

I'm wondering if that's causing problems?

maybe nuke those files, redo autogen/configure/make/make install and see
if that helps?


Steve.



On Fri, 2006-07-07 at 15:21 -0700, Ravinandan Arakali wrote:
> Pradipta,
> Following is the output from gdb after core dump. I have also copy-pasted
> the gdb output on client system.
> 
> Attached is the dmesg output when krping test is run in verbose mode.
> The ping data on the sender(client) seems okay. The content is shifted
> forward by one character for each packet. On receiver, after receiving ping
> pkt 9, it seems to jump to pkt no. 1935. Not sure if it's because messages
> can be lost during writing to /var/log/messages ?
> 
> -----------------------------------------
> (gdb) run -s -vV -C100 -d -a 0.0.0.0 -p 9999
> Starting program:
> /tmp/ib/src/userspace/librdmacm/examples/.libs/rping -s -vV -C100 -d -a
> 0.0.0.0 -p 9999
> [Thread debugging using libthread_db enabled]
> [New Thread -1210054992 (LWP 3668)]
> ipaddr (0.0.0.0)
> port 9999
> created cm_id 0x804e6e0
> [New Thread -1210057824 (LWP 3671)]
> rdma_bind_addr successful
> rdma_listen
> cma_event type 4 cma_id 0x804e968 (child)
> child cma 0x804e968
> 
> Program received signal SIGSEGV, Segmentation fault.
> [Switching to Thread -1210054992 (LWP 3668)]
> rping_setup_qp (cb=0x0, cm_id=0x804e968) at examples/rping.c:514
> 514             cb->pd = ibv_alloc_pd(cm_id->verbs);
> (gdb) bt
> #0  rping_setup_qp (cb=0x0, cm_id=0x804e968) at examples/rping.c:514
> #1  0x0804a716 in main (argc=9, argv=Cannot access memory at address 0x6
> ) at examples/rping.c:767
> (gdb)
> 
> ---------------------------------
> (gdb) run -c -vV -C100 -d  -a 17.2.2.102 -p 9999
> Starting program:
> /tmp/ib/src/userspace/librdmacm/examples/.libs/rping -c -vV -C100 -d  -a
> 17.2.2.102 -p 9999
> [Thread debugging using libthread_db enabled]
> [New Thread 47388824908032 (LWP 4620)]
> ipaddr (17.2.2.102)
> port 9999
> created cm_id 0x506b00
> [New Thread 1082132800 (LWP 4623)]
> cma_event type 0 cma_id 0x506b00 (parent)
> cma_event type 2 cma_id 0x506b00 (parent)
> rdma_resolve_addr - rdma_resolve_route successful
> created pd 0x506e60
> created channel 0x506e80
> created cq 0x506ea0
> created qp 0x506f40
> rping_setup_buffers called on cb 0x505010
> allocated & registered buffers...
> [New Thread 1090525504 (LWP 4624)]
> cq_thread started.
> 
> 
> -----Original Message-----
> From: Pradipta Kumar Banerjee [mailto:bpradip at in.ibm.com]
> Sent: Friday, July 07, 2006 1:29 PM
> To: Ravinandan Arakali
> Cc: bpradip at in.ibm.com; openib-general at openib.org
> Subject: Re: [openib-general] ping problem with ammasso cards(iWARP
> interface)
> 
> 
> Ravinandan Arakali wrote:
> > Attached are the outputs when rping and krping are run.
> > The dmesg output when krping is run is quite verbose.
> > Hopefully, you can throw some light by looking at it.
> > The rping server core dumped as soon as the client was run.
> 
> Ravi,
>   Use the following for krping. You will be able to see the ping data using
> dmesg.
> 
> echo "server,port=9999,addr=17.2.2.102,validate,verbose" > /proc/krping
> echo "client,port=9999,addr=17.2.2.102,validate,verbose" > /proc/krping
> 
> As for the rping, can u run rping under gdb (gdb
> librdmacm/example/.libs/rping)
> and send the backtrace on segfault.
> 
> Thanks,
> Pradipta
> >
> > Thanks,
> > Ravi
> >
> >
> >> To unsubscribe, please visit
> http://openib.org/mailman/listinfo/openib-general
> _______________________________________________
> openib-general mailing list
> openib-general at openib.org
> http://openib.org/mailman/listinfo/openib-general
> 
> To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general





More information about the general mailing list