Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] openib segfaults with Torque
From: Fischer, Greg A. (fischega_at_[hidden])
Date: 2014-06-10 14:53:58


Yes, this fails on all nodes on the system, except for the head node.

The uptime of the system isn't significant. Maybe 1 week, and it's received basically no use.

-----Original Message-----
From: Nathan Hjelm [mailto:hjelmn_at_[hidden]]
Sent: Tuesday, June 10, 2014 2:49 PM
To: Fischer, Greg A.
Cc: Open MPI Users
Subject: Re: [OMPI users] openib segfaults with Torque

Well, thats interesting. The output shows that ibv_create_cq is failing. Strange since an identical call had just succeeded (udcm creates two completion queues). Some questions that might indicate where the failure might be:

Does this fail on any other node in your system?

How long has the node been up?

-Nathan Hjelm
Application Readiness, HPC-5, LANL

On Tue, Jun 10, 2014 at 02:06:54PM -0400, Fischer, Greg A. wrote:
> Jeff/Nathan,
>
> I ran the following with my debug build of OpenMPI 1.8.1 - after opening a terminal on a compute node with "qsub -l nodes 2 -I":
>
> mpirun -mca btl openib,self -mca btl_base_verbose 100 -np 2 ring_c &>
> output.txt
>
> Output and backtrace are attached. Let me know if I can provide anything else.
>
> Thanks for looking into this,
> Greg
>
> -----Original Message-----
> From: users [mailto:users-bounces_at_[hidden]] On Behalf Of Jeff
> Squyres (jsquyres)
> Sent: Tuesday, June 10, 2014 10:31 AM
> To: Nathan Hjelm
> Cc: Open MPI Users
> Subject: Re: [OMPI users] openib segfaults with Torque
>
> Greg:
>
> Can you run with "--mca btl_base_verbose 100" on your debug build so that we can get some additional output to see why UDCM is failing to setup properly?
>
>
>
> On Jun 10, 2014, at 10:25 AM, Nathan Hjelm <hjelmn_at_[hidden]> wrote:
>
> > On Tue, Jun 10, 2014 at 12:10:28AM +0000, Jeff Squyres (jsquyres) wrote:
> >> I seem to recall that you have an IB-based cluster, right?
> >>
> >> From a *very quick* glance at the code, it looks like this might be a simple incorrect-finalization issue. That is:
> >>
> >> - you run the job on a single server
> >> - openib disqualifies itself because you're running on a single
> >> server
> >> - openib then goes to finalize/close itself
> >> - but openib didn't fully initialize itself (because it
> >> disqualified itself early in the initialization process), and
> >> something in the finalization process didn't take that into account
> >>
> >> Nathan -- is that anywhere close to correct?
> >
> > Nope. udcm_module_finalize is being called because there was an
> > error setting up the udcm state. See btl_openib_connect_udcm.c:476.
> > The opal_list_t destructor is getting an assert failure. Probably
> > because the constructor wasn't called. I can rearrange the
> > constructors to be called first but there appears to be a deeper
> > issue with the user's
> > system: udcm_module_init should not be failing! It creates a couple
> > of CQs, allocates a small number of registered bufferes and starts
> > monitoring the fd for the completion channel. All these things are
> > also done in the setup of the openib btl itself. Keep in mind that
> > the openib btl will not disqualify itself when running single server.
> > Openib may be used to communicate on node and is needed for the dynamics case.
> >
> > The user might try adding -mca btl_base_verbose 100 to shed some
> > light on what the real issue is.
> >
> > BTW, I no longer monitor the user mailing list. If something needs
> > my attention forward it to me directly.
> >
> > -Nathan
>
>
> --
> Jeff Squyres
> jsquyres_at_[hidden]
> For corporate legal information go to:
> http://www.cisco.com/web/about/doing_business/legal/cri/
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users
>
>

> Core was generated by `ring_c'.
> Program terminated with signal 6, Aborted.
> #0 0x00007f8b6ae1cb55 in raise () from /lib64/libc.so.6
> #0 0x00007f8b6ae1cb55 in raise () from /lib64/libc.so.6
> #1 0x00007f8b6ae1e0c5 in abort () from /lib64/libc.so.6
> #2 0x00007f8b6ae15a10 in __assert_fail () from /lib64/libc.so.6
> #3 0x00007f8b664b684b in udcm_module_finalize (btl=0x717060,
> cpc=0x7190c0) at
> ../../../../../openmpi-1.8.1/ompi/mca/btl/openib/connect/btl_openib_co
> nnect_udcm.c:734
> #4 0x00007f8b664b5474 in udcm_component_query (btl=0x717060,
> cpc=0x718a48) at
> ../../../../../openmpi-1.8.1/ompi/mca/btl/openib/connect/btl_openib_co
> nnect_udcm.c:476
> #5 0x00007f8b664ae316 in
> ompi_btl_openib_connect_base_select_for_local_port (btl=0x717060) at
> ../../../../../openmpi-1.8.1/ompi/mca/btl/openib/connect/btl_openib_co
> nnect_base.c:273
> #6 0x00007f8b66497817 in btl_openib_component_init (num_btl_modules=0x7fffe34cebe0, enable_progress_threads=false, enable_mpi_threads=false)
> at
> ../../../../../openmpi-1.8.1/ompi/mca/btl/openib/btl_openib_component.
> c:2703
> #7 0x00007f8b6b43fa5e in mca_btl_base_select
> (enable_progress_threads=false, enable_mpi_threads=false) at
> ../../../../openmpi-1.8.1/ompi/mca/btl/base/btl_base_select.c:108
> #8 0x00007f8b666d9d42 in mca_bml_r2_component_init (priority=0x7fffe34cecb4, enable_progress_threads=false, enable_mpi_threads=false)
> at
> ../../../../../openmpi-1.8.1/ompi/mca/bml/r2/bml_r2_component.c:88
> #9 0x00007f8b6b43ed1b in mca_bml_base_init
> (enable_progress_threads=false, enable_mpi_threads=false) at
> ../../../../openmpi-1.8.1/ompi/mca/bml/base/bml_base_init.c:69
> #10 0x00007f8b655ff739 in mca_pml_ob1_component_init (priority=0x7fffe34cedf0, enable_progress_threads=false, enable_mpi_threads=false)
> at
> ../../../../../openmpi-1.8.1/ompi/mca/pml/ob1/pml_ob1_component.c:271
> #11 0x00007f8b6b4659b2 in mca_pml_base_select
> (enable_progress_threads=false, enable_mpi_threads=false) at
> ../../../../openmpi-1.8.1/ompi/mca/pml/base/pml_base_select.c:128
> #12 0x00007f8b6b3d233c in ompi_mpi_init (argc=1, argv=0x7fffe34cf0e8,
> requested=0, provided=0x7fffe34cef98) at
> ../../openmpi-1.8.1/ompi/runtime/ompi_mpi_init.c:604
> #13 0x00007f8b6b407386 in PMPI_Init (argc=0x7fffe34cefec,
> argv=0x7fffe34cefe0) at pinit.c:84
> #14 0x000000000040096f in main (argc=1, argv=0x7fffe34cf0e8) at
> ring_c.c:19
>

> [binf316:24591] mca: base: components_register: registering btl
> components [binf316:24591] mca: base: components_register: found
> loaded component openib [binf316:24592] mca: base:
> components_register: registering btl components [binf316:24592] mca:
> base: components_register: found loaded component openib
> [binf316:24591] mca: base: components_register: component openib
> register function successful [binf316:24591] mca: base:
> components_register: found loaded component self [binf316:24591] mca:
> base: components_register: component self register function successful
> [binf316:24591] mca: base: components_open: opening btl components
> [binf316:24591] mca: base: components_open: found loaded component
> openib [binf316:24591] mca: base: components_open: component openib
> open function successful [binf316:24591] mca: base: components_open:
> found loaded component self [binf316:24591] mca: base:
> components_open: component self open function successful
> [binf316:24592] mca: base: components_register: component openib
> register function successful [binf316:24592] mca: base:
> components_register: found loaded component self [binf316:24592] mca:
> base: components_register: component self register function successful
> [binf316:24592] mca: base: components_open: opening btl components
> [binf316:24592] mca: base: components_open: found loaded component
> openib [binf316:24592] mca: base: components_open: component openib
> open function successful [binf316:24592] mca: base: components_open:
> found loaded component self [binf316:24592] mca: base:
> components_open: component self open function successful
> [binf316:24591] select: initializing btl component openib
> [binf316:24592] select: initializing btl component openib
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_ip.c:364:add_rdma_addr] Adding addr 9.9.10.75
> (0x4b0a0909) subnet 0x9090000 as mlx4_0:1
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_ip.c:364:add_rdma_addr] Adding addr 9.9.10.75
> (0x4b0a0909) subnet 0x9090000 as mlx4_0:1
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:686:init_one_port] looking for mlx4_0:1 GID
> index 0
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:717:init_one_port] my IB subnet_id for HCA
> mlx4_0 port 1 is fe80000000000000
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1294:setup_qps] pp: rd_num is 256 rd_low is
> 192 rd_win 128 rd_rsv 4
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1339:setup_qps] srq: rd_num is 1024 rd_low is
> 1008 sd_max is 64 rd_max is 256 srq_limit is 48
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1339:setup_qps] srq: rd_num is 1024 rd_low is
> 1008 sd_max is 64 rd_max is 256 srq_limit is 48
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1339:setup_qps] srq: rd_num is 1024 rd_low is
> 1008 sd_max is 64 rd_max is 256 srq_limit is 48
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_rdmacm.c:1840:rdmacm_component_query]
> rdmacm_component_query
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_ip.c:132:mca_btl_openib_rdma_get_ipv4addr] Looking for
> mlx4_0:1 in IP address list
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_ip.c:141:mca_btl_openib_rdma_get_ipv4addr] FOUND:
> mlx4_0:1 is 9.9.10.75 (0x4b0a0909)
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_rdmacm.c:1750:ipaddrcheck] Found device
> mlx4_0:1 = IP address 9.9.10.75 (0x4b0a0909):51845
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_rdmacm.c:1776:ipaddrcheck] creating new
> server to listen on 9.9.10.75 (0x4b0a0909):51845 [binf316:24591]
> openib BTL: rdmacm CPC available for use on mlx4_0:1
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_udcm.c:542:udcm_module_init] created cpc
> module 0x719220 for btl 0x716ee0
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:686:init_one_port] looking for mlx4_0:1 GID
> index 0
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:717:init_one_port] my IB subnet_id for HCA
> mlx4_0 port 1 is fe80000000000000
> [binf316][[17980,1],0][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_udcm.c:565:udcm_module_init] error
> creating ud send completion queue
> ring_c: ../../../../../openmpi-1.8.1/ompi/mca/btl/openib/connect/btl_openib_connect_udcm.c:734: udcm_module_finalize: Assertion `((0xdeafbeedULL << 32) + 0xdeafbeedULL) == ((opal_object_t *) (&m->cm_recv_msg_queue))->obj_magic_id' failed.
> [binf316:24591] *** Process received signal *** [binf316:24591]
> Signal: Aborted (6) [binf316:24591] Signal code: (-6)
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1294:setup_qps] pp: rd_num is 256 rd_low is
> 192 rd_win 128 rd_rsv 4
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1339:setup_qps] srq: rd_num is 1024 rd_low is
> 1008 sd_max is 64 rd_max is 256 srq_limit is 48
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1339:setup_qps] srq: rd_num is 1024 rd_low is
> 1008 sd_max is 64 rd_max is 256 srq_limit is 48
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_component.c:1339:setup_qps] srq: rd_num is 1024 rd_low is
> 1008 sd_max is 64 rd_max is 256 srq_limit is 48
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_rdmacm.c:1840:rdmacm_component_query]
> rdmacm_component_query
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_ip.c:132:mca_btl_openib_rdma_get_ipv4addr] Looking for
> mlx4_0:1 in IP address list
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/btl_openib_ip.c:141:mca_btl_openib_rdma_get_ipv4addr] FOUND:
> mlx4_0:1 is 9.9.10.75 (0x4b0a0909)
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_rdmacm.c:1750:ipaddrcheck] Found device
> mlx4_0:1 = IP address 9.9.10.75 (0x4b0a0909):57734
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_rdmacm.c:1776:ipaddrcheck] creating new
> server to listen on 9.9.10.75 (0x4b0a0909):57734 [binf316:24592]
> openib BTL: rdmacm CPC available for use on mlx4_0:1
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_udcm.c:542:udcm_module_init] created cpc
> module 0x7190c0 for btl 0x717060
> [binf316][[17980,1],1][../../../../../openmpi-1.8.1/ompi/mca/btl/openi
> b/connect/btl_openib_connect_udcm.c:565:udcm_module_init] error
> creating ud send completion queue
> ring_c: ../../../../../openmpi-1.8.1/ompi/mca/btl/openib/connect/btl_openib_connect_udcm.c:734: udcm_module_finalize: Assertion `((0xdeafbeedULL << 32) + 0xdeafbeedULL) == ((opal_object_t *) (&m->cm_recv_msg_queue))->obj_magic_id' failed.
> [binf316:24592] *** Process received signal *** [binf316:24592]
> Signal: Aborted (6) [binf316:24592] Signal code: (-6) [binf316:24591]
> [ 0] /lib64/libpthread.so.0(+0xf7c0)[0x7fb35959c7c0]
> [binf316:24591] [ 1] /lib64/libc.so.6(gsignal+0x35)[0x7fb359248b55]
> [binf316:24591] [ 2] /lib64/libc.so.6(abort+0x181)[0x7fb35924a131]
> [binf316:24591] [ 3]
> /lib64/libc.so.6(__assert_fail+0xf0)[0x7fb359241a10]
> [binf316:24591] [ 4]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(+0x3784b)[0x7fb3548e284b]
> [binf316:24591] [ 5]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(+0x36474)[0x7fb3548e1474]
> [binf316:24591] [ 6]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(ompi_btl_openib_connect_base_select_for_local_port+0x15b)[
> 0x7fb3548da316] [binf316:24591] [ 7]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(+0x18817)[0x7fb3548c3817]
> [binf316:24591] [ 8] [binf316:24592] [ 0]
> /lib64/libpthread.so.0(+0xf7c0)[0x7f8b6b1707c0]
> [binf316:24592] [ 1]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(mc
> a_btl_base_select+0x1b2)[0x7fb35986ba5e]
> [binf316:24591] [ 9] /lib64/libc.so.6(gsignal+0x35)[0x7f8b6ae1cb55]
> [binf316:24592] [ 2]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bm
> l_r2.so(mca_bml_r2_component_init+0x20)[0x7fb354b05d42]
> [binf316:24591] [10] /lib64/libc.so.6(abort+0x181)[0x7f8b6ae1e131]
> [binf316:24592] [ 3]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(mc
> a_bml_base_init+0xd6)[0x7fb35986ad1b]
> [binf316:24591] [11]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_pm
> l_ob1.so(+0x7739)[0x7fb353a2b739] [binf316:24591] [12]
> /lib64/libc.so.6(__assert_fail+0xf0)[0x7f8b6ae15a10]
> [binf316:24592] [ 4]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(+0x3784b)[0x7f8b664b684b]
> [binf316:24592] [ 5]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(+0x36474)[0x7f8b664b5474]
> [binf316:24592] [ 6]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(mc
> a_pml_base_select+0x26e)[0x7fb3598919b2]
> [binf316:24591] [13]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(ompi_btl_openib_connect_base_select_for_local_port+0x15b)[
> 0x7f8b664ae316] [binf316:24592] [ 7]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bt
> l_openib.so(+0x18817)[0x7f8b66497817]
> [binf316:24592] [ 8]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(om
> pi_mpi_init+0x5f6)[0x7fb3597fe33c]
> [binf316:24591] [14]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(mc
> a_btl_base_select+0x1b2)[0x7f8b6b43fa5e]
> [binf316:24592] [ 9]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_bm
> l_r2.so(mca_bml_r2_component_init+0x20)[0x7f8b666d9d42]
> [binf316:24592] [10]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(MP
> I_Init+0x17e)[0x7fb359833386]
> [binf316:24591] [15] ring_c[0x40096f]
> [binf316:24591] [16]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(mc
> a_bml_base_init+0xd6)[0x7f8b6b43ed1b]
> [binf316:24592] [11]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/openmpi/mca_pm
> l_ob1.so(+0x7739)[0x7f8b655ff739] [binf316:24592] [12]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(mc
> a_pml_base_select+0x26e)[0x7f8b6b4659b2]
> [binf316:24592] [13]
> /lib64/libc.so.6(__libc_start_main+0xe6)[0x7fb359234c36]
> [binf316:24591] [17] ring_c[0x400889]
> [binf316:24591] *** End of error message ***
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(om
> pi_mpi_init+0x5f6)[0x7f8b6b3d233c]
> [binf316:24592] [14]
> /xxxx/yyyy_ib/gcc-4.8.3/toolset/openmpi-1.8.1_debug/lib/libmpi.so.1(MP
> I_Init+0x17e)[0x7f8b6b407386]
> [binf316:24592] [15] ring_c[0x40096f]
> [binf316:24592] [16]
> /lib64/libc.so.6(__libc_start_main+0xe6)[0x7f8b6ae08c36]
> [binf316:24592] [17] ring_c[0x400889]
> [binf316:24592] *** End of error message ***
> ----------------------------------------------------------------------
> ---- mpirun noticed that process rank 0 with PID 24591 on node xxxx316
> exited on signal 6 (Aborted).
> ----------------------------------------------------------------------
> ----