What value did you set for this new command? Did you look at the cmds in
orte/mca/odls/odls_types.h to ensure you weren't using a duplicate value?
On Mar 8, 2011, at 6:15 AM, Hugo Meyer wrote:
> Hello @ll.
>
> I've got a problem in a communication between the
> v_protocol_receiver_component.c and the orted_comm.c.
>
> In the mca_vprotocol_receiver_component_init i've added a request that is
> received correctly by the orte_daemon_process_commands but when i try to
> reply to the sender i get the next error:
>
> [clus1:15593] [ 0] /lib64/libpthread.so.0 [0x2aaaabb03d40]
> [clus1:15593] [ 1]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0
> [0x2aaaaad760db]
> [clus1:15593] [ 2]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0
> [0x2aaaaad75aa4]
> [clus1:15593] [ 3]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/openmpi/mca_errmgr_orted.so
> [0x2aaaae2d2fdd]
> [clus1:15593] [ 4]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0(orte_odls_base_notify_iof_complete+0x1da)
> [0x2aaaaad42cb0]
> [clus1:15593] [ 5]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0(orte_daemon_process_commands+0x1068)
> [0x2aaaaad19ca6]
> [clus1:15593] [ 6]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0(orte_daemon_cmd_processor+0x81b)
> [0x2aaaaad18a55]
> [clus1:15593] [ 7]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0
> [0x2aaaaad9710e]
> [clus1:15593] [ 8]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0
> [0x2aaaaad974bb]
> [clus1:15593] [ 9]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0(opal_event_loop+0x1a)
> [0x2aaaaad972ad]
> [clus1:15593] [10]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0(opal_event_dispatch+0xe)
> [0x2aaaaad97166]
> [clus1:15593] [11]
> /home/hmeyer/desarrollo/radic-ompi/binarios/lib/libopen-rte.so.0(orte_daemon+0x2322)
> [0x2aaaaad17556]
> [clus1:15593] [12] /home/hmeyer/desarrollo/radic-ompi/binarios/bin/orted
> [0x4008a3]
> [clus1:15593] [13] /lib64/libc.so.6(__libc_start_main+0xf4) [0x2aaaabd2d8a4]
> [clus1:15593] [14] /home/hmeyer/desarrollo/radic-ompi/binarios/bin/orted
> [0x400799]
> [clus1:15593] *** End of error message ***
>
> The code that i've added at the v_protocol_receiver_component.c is (in bold
> the recv command that fails):
>
> int mca_vprotocol_receiver_request_protector(void) {
> orte_daemon_cmd_flag_t command;
> opal_buffer_t *buffer = NULL;
> int n = 1;
>
> command = ORTE_DAEMON_REQUEST_PROTECTOR_CMD;
>
> buffer = OBJ_NEW(opal_buffer_t);
> opal_dss.pack(buffer, &command, 1, ORTE_DAEMON_CMD);
>
> orte_rml.send_buffer(ORTE_PROC_MY_DAEMON, buffer, ORTE_RML_TAG_DAEMON, 0);
>
> orte_rml.recv_buffer(ORTE_PROC_MY_DAEMON, buffer,
> ORTE_DAEMON_REQUEST_PROTECTOR_CMD, 0);
> opal_dss.unpack(buffer, &mca_vprotocol_receiver.protector.jobid, &n,
> OPAL_UINT32);
> opal_dss.unpack(buffer, &mca_vprotocol_receiver.protector.vpid, &n,
> OPAL_UINT32);
>
> orte_process_info.protector.jobid =
> mca_vprotocol_receiver.protector.jobid;
> orte_process_info.protector.vpid = mca_vprotocol_receiver.protector.vpid;
>
> OBJ_RELEASE(buffer);
>
> return OMPI_SUCCESS;
>
> The code that i've added at the orted_comm.c is (in bold the send command
> that fails):
>
> case ORTE_DAEMON_REQUEST_PROTECTOR_CMD:
> if (orte_debug_daemons_flag) {
> opal_output(0, "%s orted_recv: received request protector from
> local proc %s",
> ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
> ORTE_NAME_PRINT(sender));
> }
> /* Define the protector */
> protector = (uint32_t)ORTE_PROC_MY_NAME->vpid + 1;
> if (protector >= (uint32_t)orte_process_info.num_procs) {
> protector = 0;
> }
>
> /* Pack the protector data */
> answer = OBJ_NEW(opal_buffer_t);
>
> if (ORTE_SUCCESS != (ret = opal_dss.pack(answer,
> &ORTE_PROC_MY_NAME->jobid, 1, OPAL_UINT32))) {
> ORTE_ERROR_LOG(ret);
> OBJ_RELEASE(answer);
> goto CLEANUP;
> }
> if (ORTE_SUCCESS != (ret = opal_dss.pack(answer, &protector, 1,
> OPAL_UINT32))) {
> ORTE_ERROR_LOG(ret);
> OBJ_RELEASE(answer);
> goto CLEANUP;
> }
> if (orte_debug_daemons_flag) {
> opal_output(0, "EL PROTECTOR ASIGNADO para %s ES: %d\n",
> ORTE_NAME_PRINT(sender), protector);
> }
>
> /* Send the protector data */
> if (0 > orte_rml.send_buffer(sender, answer,
> ORTE_DAEMON_REQUEST_PROTECTOR_CMD, 0)) {
> ORTE_ERROR_LOG(ORTE_ERR_COMM_FAILURE);
> ret = ORTE_ERR_COMM_FAILURE;
> OBJ_RELEASE(answer);
> goto CLEANUP;
> }
> OBJ_RELEASE(answer);
>
> I assume by testing that the error is in the bolded section, maybe because
> i'am missing some sentence when i try to communicate, or maybe this
> communication cannot be done. Any help will be appreciated.
>
> Thanks a lot.
>
> Hugo Meyer
>
> _______________________________________________
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel
