libfabric:core:core:fi_param_define_():223 registered var perf_cntr libfabric:core:core:fi_param_get_():272 variable perf_cntr= libfabric:core:core:fi_param_define_():223 registered var hook libfabric:core:core:fi_param_get_():272 variable hook= libfabric:core:core:fi_param_define_():223 registered var provider libfabric:core:core:fi_param_define_():223 registered var fork_unsafe libfabric:core:core:fi_param_define_():223 registered var universe_size libfabric:core:core:fi_param_get_():272 variable provider= libfabric:core:core:fi_param_define_():223 registered var provider_path libfabric:core:core:fi_param_get_():272 variable provider_path= libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:gni:fabric:__gnix_alps_init():275 [8510:1] lli put failed, ret=-1(Bad file descriptor) libfabric:gni:fabric:_gnix_nics_per_rank():672 [8510:1] __gnix_app_init() failed, ret=-5(Bad file descriptor) libfabric:gni:fabric:_gnix_nic_init():1407 [8510:1] _gnix_nics_per_rank failed: -5 libfabric:core:core:ofi_register_provider():200 registering provider: gni (1.1) libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:ofi_rxm:core:fi_param_define_():223 registered var buffer_size libfabric:ofi_rxm:core:fi_param_define_():223 registered var comp_per_progress libfabric:ofi_rxm:core:fi_param_define_():223 registered var sar_limit libfabric:ofi_rxm:core:fi_param_define_():223 registered var use_srx libfabric:ofi_rxm:core:fi_param_get_():272 variable buffer_size= libfabric:core:core:ofi_register_provider():200 registering provider: ofi_rxm (1.0) libfabric:core:core:ofi_register_provider():193 no provider structure or name libfabric:core:core:fi_param_define_():223 registered var rxd_enable libfabric:core:core:fi_param_get_():272 variable rxd_enable= libfabric:core:core:ofi_register_provider():200 registering provider: UDP (1.1) libfabric:sockets:core:fi_param_define_():223 registered var pe_waittime libfabric:sockets:core:fi_param_define_():223 registered var max_conn_retry libfabric:sockets:core:fi_param_define_():223 registered var def_conn_map_sz libfabric:sockets:core:fi_param_define_():223 registered var def_av_sz libfabric:sockets:core:fi_param_define_():223 registered var def_cq_sz libfabric:sockets:core:fi_param_define_():223 registered var def_eq_sz libfabric:sockets:core:fi_param_define_():223 registered var pe_affinity libfabric:sockets:core:fi_param_define_():223 registered var keepalive_enable libfabric:sockets:core:fi_param_define_():223 registered var keepalive_time libfabric:sockets:core:fi_param_define_():223 registered var keepalive_intvl libfabric:sockets:core:fi_param_define_():223 registered var keepalive_probes libfabric:sockets:core:fi_param_define_():223 registered var iface libfabric:sockets:core:fi_param_get_():272 variable iface= libfabric:core:core:ofi_register_provider():200 registering provider: sockets (2.0) libfabric:tcp:core:fi_param_define_():223 registered var iface libfabric:core:core:ofi_register_provider():200 registering provider: tcp (0.1) libfabric:gni:fabric:_gnix_ep_getinfo():455 [8510:1] libfabric:gni:fabric:_gnix_ep_getinfo():455 [8510:1] libfabric:gni:fabric:_gnix_ep_getinfo():455 [8510:1] libfabric:gni:fabric:__gnix_getinfo_resolve_node():415 [8510:1] node: (null) service: (null) libfabric:gni:fabric:__gnix_getinfo_resolve_node():420 [8510:1] src_pe: 0x315 src_port: 0x0 libfabric:ofi_rxm:core:ofi_check_info():997 Unsupported capabilities libfabric:ofi_rxm:core:ofi_check_info():998 Supported: FI_MSG, FI_RMA, FI_TAGGED, FI_READ, FI_WRITE, FI_RECV, FI_SEND, FI_REMOTE_READ, FI_REMOTE_WRITE, FI_MULTI_RECV, FI_LOCAL_COMM, FI_REMOTE_COMM, FI_SOURCE, FI_DIRECTED_RECV libfabric:ofi_rxm:core:ofi_check_info():998 Requested: FI_RMA, FI_ATOMIC, FI_RMA_EVENT libfabric:core:core:fi_getinfo_():712 fi_getinfo: provider ofi_rxm returned -61 (No data available) libfabric:UDP:core:ofi_check_ep_type():628 Unsupported endpoint type libfabric:UDP:core:ofi_check_ep_type():629 Supported: FI_EP_DGRAM libfabric:UDP:core:ofi_check_ep_type():629 Requested: FI_EP_RDM libfabric:core:core:fi_getinfo_():712 fi_getinfo: provider UDP returned -61 (No data available) libfabric:tcp:core:ofi_check_ep_type():628 Unsupported endpoint type libfabric:tcp:core:ofi_check_ep_type():629 Supported: FI_EP_MSG libfabric:tcp:core:ofi_check_ep_type():629 Requested: FI_EP_RDM libfabric:core:core:fi_getinfo_():712 fi_getinfo: provider tcp returned -61 (No data available) ____________________________FI_INFO DETAILS_______________________________ fi_info: caps: [ FI_RMA, FI_ATOMIC, FI_MULTI_RECV, FI_TRIGGER, FI_FENCE, FI_RMA_EVENT ] mode: [ ] addr_format: FI_ADDR_GNI src_addrlen: 48 dest_addrlen: 48 src_addr: fi_addr_gni://315 dest_addr: (null) handle: (null) fi_tx_attr: caps: [ FI_RMA, FI_ATOMIC, FI_MULTI_RECV, FI_TRIGGER, FI_FENCE, FI_RMA_EVENT ] mode: [ ] op_flags: [ FI_DELIVERY_COMPLETE ] msg_order: [ FI_ORDER_SAS, FI_ORDER_STRICT ] comp_order: [ ] inject_size: 16 size: 500 iov_limit: 8 rma_iov_limit: 1 fi_rx_attr: caps: [ FI_RMA, FI_ATOMIC, FI_MULTI_RECV, FI_TRIGGER, FI_FENCE, FI_RMA_EVENT ] mode: [ ] op_flags: [ ] msg_order: [ FI_ORDER_SAS, FI_ORDER_STRICT ] comp_order: [ ] total_buffered_recv: 0 size: 500 iov_limit: 8 fi_ep_attr: type: FI_EP_RDM protocol: FI_PROTO_GNI protocol_version: 0 max_msg_size: 4294967295 msg_prefix_size: 0 max_order_raw_size: 0 max_order_war_size: 0 max_order_waw_size: 0 mem_tag_format: 0x0000000000000000 tx_ctx_cnt: 1 rx_ctx_cnt: 1 auth_key_size: 0 fi_domain_attr: domain: 0x0 name: /sys/class/gni/kgni0 threading: FI_THREAD_DOMAIN control_progress: FI_PROGRESS_AUTO data_progress: FI_PROGRESS_AUTO resource_mgmt: FI_RM_ENABLED av_type: FI_AV_UNSPEC mr_mode: [ FI_MR_BASIC ] mr_key_size: 8 cq_data_size: 8 cq_cnt: 0 ep_cnt: -1 tx_ctx_cnt: 3 rx_ctx_cnt: 4 max_ep_tx_ctx: 128 max_ep_rx_ctx: 128 max_ep_stx_ctx: 0 max_ep_srx_ctx: 0 cntr_cnt: 0 mr_iov_limit: 1 caps: [ FI_REMOTE_COMM ] mode: [ ] auth_key_size: 0 max_err_data: 0 mr_cnt: 65535 fi_fabric_attr: name: gni prov_name: gni prov_version: 1.1 api_version: 1.6 libfabric:core:core:fi_fabric_():896 Opened fabric: gni libfabric:gni:domain:gnix_domain_open():579 [8510:1] libfabric:gni:fabric:gnix_domain_open():591 [8510:1] failed to find authorization key, creating new authorization key libfabric:gni:fabric:__gnix_alps_init():275 [8510:1] lli put failed, ret=-1(Bad file descriptor) libfabric:gni:fabric:gnixu_get_rdma_credentials():437 [8510:1] __gnix_app_init() failed, ret=-5(Bad file descriptor) libfabric:gni:domain:_gnix_auth_key_enable():345 [8510:1] pkey=00002aaa ptag=171 key_partition_size=0 key_offset=0 enabled libfabric:gni:domain:gnix_domain_open():597 [8510:1] authorization key=0x63b790 ptag 171 cookie 0x2aaa libfabric:gni:eq:gnix_eq_open():380 [8510:1] libfabric:gni:eq:gnix_verify_eq_attr():103 [8510:1] libfabric:gni:eq:gnix_eq_set_wait():76 [8510:1] libfabric:gni:eq:gnix_wait_open():536 [8510:1] libfabric:gni:eq:gnix_verify_wait_attr():367 [8510:1] libfabric:gni:eq:gnix_init_wait_obj():387 [8510:1] libfabric:gni:ep_ctrl:__gnix_wait_start_progress():175 [8510:1] libfabric:gni:ep_ctrl:__gnix_wait_start_progress():179 [8510:1] libfabric:gni:ep_ctrl:__gnix_wait_nic_prog_thread_fn():72 [8510:2] libfabric:gni:cq:gnix_cq_open():651 [8510:1] libfabric:gni:cq:verify_cq_attr():139 [8510:1] libfabric:gni:cq:gnix_cq_set_wait():192 [8510:1] libfabric:gni:cq:gnix_cntr_open():433 [8510:1] libfabric:gni:cq:__verify_cntr_attr():65 [8510:1] libfabric:gni:eq:gnix_cntr_set_wait():96 [8510:1] libfabric:gni:eq:gnix_wait_open():536 [8510:1] libfabric:gni:eq:gnix_verify_wait_attr():367 [8510:1] libfabric:gni:eq:gnix_init_wait_obj():387 [8510:1] libfabric:gni:ep_ctrl:__gnix_wait_start_progress():175 [8510:1] libfabric:gni:cq:gnix_cntr_open():433 [8510:1] libfabric:gni:cq:__verify_cntr_attr():65 [8510:1] libfabric:gni:eq:gnix_cntr_set_wait():96 [8510:1] libfabric:gni:eq:gnix_wait_open():536 [8510:1] libfabric:gni:eq:gnix_verify_wait_attr():367 [8510:1] libfabric:gni:eq:gnix_init_wait_obj():387 [8510:1] libfabric:gni:ep_ctrl:__gnix_wait_start_progress():175 [8510:1] libfabric:gni:cq:gnix_cntr_open():433 [8510:1] libfabric:gni:cq:__verify_cntr_attr():65 [8510:1] libfabric:gni:eq:gnix_cntr_set_wait():96 [8510:1] libfabric:gni:eq:gnix_wait_open():536 [8510:1] libfabric:gni:eq:gnix_verify_wait_attr():367 [8510:1] libfabric:gni:eq:gnix_init_wait_obj():387 [8510:1] libfabric:gni:ep_ctrl:__gnix_wait_start_progress():175 [8510:1] libfabric:gni:av:gnix_av_open():838 [8510:1] libfabric:gni:ep_ctrl:gnix_ep_open():2295 [8510:1] libfabric:gni:ep_ctrl:__init_tag_storages():2092 [8510:1] initializing tag storage, tag_type=1 libfabric:gni:ep_ctrl:_gnix_xpmem_handle_create():238 [8510:1] libfabric:gni:ep_ctrl:_gnix_cm_nic_alloc():609 [8510:1] libfabric:gni:fabric:_gnix_resolve_gni_ep_name():118 [8510:1] libfabric:gni:ep_ctrl:_gnix_cm_nic_alloc():628 [8510:1] creating cm_nic for 171/0x2aaa/1302529 libfabric:gni:ep_ctrl:gnix_nic_alloc():947 [8510:1] libfabric:gni:ep_ctrl:gnix_nic_alloc():1052 [8510:1] GNI_CdmAttach returned GNI_RC_INVALID_PARAM libfabric:gni:fabric:_gnix_dump_gni_res():729 [8510:1] Device Resources: dev res: MDD, avail: 4086 res: 409 held: 0 total: 4095 dev res: CQ, avail: 2038 res: 64 held: 0 total: 2047 dev res: FMA, avail: 125 res: 4 held: 0 total: 127 dev res: CE, avail: 4 res: 0 held: 0 total: 4 dev res: DLA, avail: 16384 res: 1024 held: 0 total: 16384 dev res: TCR, avail: 64730 res: 0 held: 0 total: 16 dev res: DVA, avail: 4398046511104 res: 1099511627776 held: 0 total: 4398046511104 libfabric:gni:fabric:_gnix_dump_gni_res():745 [8510:1] Job Resources: libfabric:gni:ep_ctrl:_gnix_cm_nic_alloc():649 [8510:1] gnix_nic_alloc returned Invalid argument libfabric:gni:ep_ctrl:_gnix_ep_nic_init():2188 [8510:1] _gnix_cm_nic_alloc returned Invalid argument libfabric:gni:ep_ctrl:gnix_ep_open():2404 [8510:1] _gnix_ep_nic_init returned -22 libfabric:gni:ep_ctrl:_gnix_xpmem_handle_destroy():315 [8510:1] libfabric:gni:ep_ctrl:__xpmem_hndl_destruct():103 [8510:1] libfabric:gni:ep_ctrl:__destruct_tag_storages():1595 [8510:1] destroying tag storage COMMS ERROR: fi_endpoint creation failed: Invalid argument