00000400:00000001:3.0F:1631581081.819065:0:15644:0:(module.c:70:libcfs_ioctl()) Process entered 00000400:00000001:3.0:1631581081.819067:0:15644:0:(linux-module.c:113:libcfs_ioctl_getdata()) Process entered 00000400:00000010:3.0:1631581081.819068:0:15644:0:(linux-module.c:136:libcfs_ioctl_getdata()) alloc '(*hdr_pp)': 152 at ffff88e705eeee40 (tot 84626244). 00000400:00000001:3.0:1631581081.819069:0:15644:0:(linux-module.c:143:libcfs_ioctl_getdata()) Process leaving (rc=0 : 0 : 0) 00000400:00000001:3.0:1631581081.819070:0:15644:0:(linux-module.c:91:libcfs_ioctl_data_adjust()) Process entered 00000400:00000001:3.0:1631581081.819071:0:15644:0:(linux-module.c:105:libcfs_ioctl_data_adjust()) Process leaving (rc=0 : 0 : 0) 00000400:00000080:3.0:1631581081.819071:0:15644:0:(module.c:91:libcfs_ioctl()) libcfs ioctl cmd 3221775648 00000001:00000001:3.0:1631581081.819072:0:15644:0:(debug.c:509:libcfs_debug_mark_buffer()) ************************************************** 00000001:02000400:3.0:1631581081.819072:0:15644:0:(debug.c:510:libcfs_debug_mark_buffer()) DEBUG MARKER: MOUNTING /rds-d6 00000001:00000001:3.0:1631581081.819075:0:15644:0:(debug.c:511:libcfs_debug_mark_buffer()) ************************************************** 00000400:00000010:3.0:1631581081.819076:0:15644:0:(module.c:118:libcfs_ioctl()) kfreed 'hdr': 152 at ffff88e705eeee40 (tot 84626092). 00000400:00000001:3.0:1631581081.819077:0:15644:0:(module.c:119:libcfs_ioctl()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:3.0:1631581081.822814:0:15646:0:(obd_mount.c:1536:lustre_fill_super()) Process entered 00000020:01200004:3.0:1631581081.822815:0:15646:0:(obd_mount.c:1538:lustre_fill_super()) VFS Op: sb ffff88e70606a000 00000020:00000001:3.0:1631581081.822816:0:15646:0:(obd_mount.c:569:lustre_init_lsi()) Process entered 00000020:00000010:3.0:1631581081.822817:0:15646:0:(obd_mount.c:571:lustre_init_lsi()) kmalloced '(lsi)': 1048 at ffff88e70606d800. 00000020:00000010:3.0:1631581081.822818:0:15646:0:(obd_mount.c:574:lustre_init_lsi()) kmalloced '(lsi->lsi_lmd)': 104 at ffff89163bc31180. 00000020:00000001:3.0:1631581081.822818:0:15646:0:(obd_mount.c:592:lustre_init_lsi()) Process leaving (rc=18446613124552775680 : -130949156775936 : ffff88e70606d800) 00000020:00000001:3.0:1631581081.822864:0:15646:0:(obd_mount.c:1257:lmd_parse()) Process entered 00000020:00000010:3.0:1631581081.822865:0:15646:0:(obd_mount.c:1275:lmd_parse()) kmalloced '(lmd->lmd_params)': 4096 at ffff891628cdf000. 00000020:00000010:3.0:1631581081.822868:0:15646:0:(obd_mount.c:1456:lmd_parse()) kmalloced '(lmd->lmd_profile)': 14 at ffff89163b0f7670. 00000020:00000010:3.0:1631581081.822869:0:15646:0:(obd_mount.c:1491:lmd_parse()) kmalloced '(lmd->lmd_dev)': 44 at ffff89163b14d000. 00000020:00000010:3.0:1631581081.822870:0:15646:0:(obd_mount.c:1504:lmd_parse()) kmalloced '(lmd->lmd_opts)': 17 at ffff891624bf3240. 00000020:01000004:3.0:1631581081.822870:0:15646:0:(obd_mount.c:926:lmd_print()) mount data: 00000020:01000004:3.0:1631581081.822871:0:15646:0:(obd_mount.c:928:lmd_print()) profile: rds-d6-client 00000020:01000004:3.0:1631581081.822871:0:15646:0:(obd_mount.c:929:lmd_print()) device: 10.44.241.1@o2ib2:10.44.241.2@o2ib2:/rds-d6 00000020:01000004:3.0:1631581081.822872:0:15646:0:(obd_mount.c:930:lmd_print()) flags: 2 00000020:01000004:3.0:1631581081.822872:0:15646:0:(obd_mount.c:933:lmd_print()) options: flock,user_xattr 00000020:00000001:3.0:1631581081.822872:0:15646:0:(obd_mount.c:1513:lmd_parse()) Process leaving (rc=0 : 0 : 0) 00000020:01000004:3.0:1631581081.822873:0:15646:0:(obd_mount.c:1563:lustre_fill_super()) Mounting client rds-d6-client 00000020:00000001:3.0:1631581081.822874:0:15646:0:(obd_mount.c:230:lustre_start_mgc()) Process entered 00000400:00000200:5.0F:1631581082.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150390:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150392:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150393:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150395:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150397:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150398:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150400:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581082.150403:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581082.150403:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2f30 (tot 84626108). 00000400:00000010:5.0:1631581082.150405:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0a9000 (tot 84626388). 00000400:00000010:5.0:1631581082.150406:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a330. 00000400:00000010:5.0:1631581082.150408:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0aec00 (tot 84626828). 00000400:00000010:5.0:1631581082.150409:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d106c0 (tot 84626876). 00000400:00000200:5.0:1631581082.150411:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581082.150413:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581082.150415:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581082.150418:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581082.150420:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581082.150423:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581082.150425:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581082.150426:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581082.150433:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1F:1631581082.150489:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581082.150500:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581082.150540:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581082.150562:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000400:00000200:3.0:1631581082.150565:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:3.0:1631581082.150567:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093ac800 (tot 84627316). 00000800:00000200:27.0F:1631581082.150569:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:3.0:1631581082.150570:0:5978:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:3.0:1631581082.150572:0:5978:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:3.0:1631581082.150575:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581082.150577:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:3.0:1631581082.150579:0:5978:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000800:00000200:27.0:1631581082.150586:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000800:00000200:1.0F:1631581082.150587:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:27.0:1631581082.150588:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:3.0:1631581082.150588:0:5978:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000200:27.0:1631581082.150590:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000800:00000200:3.0:1631581082.150590:0:5978:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:1.0:1631581082.150590:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000200:27.0:1631581082.150591:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:27.0:1631581082.150592:0:5979:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000800:00000200:3.0:1631581082.150593:0:5978:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000400:00000010:27.0:1631581082.150594:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0aec00 (tot 84626876). 00000800:00000200:3.0:1631581082.150594:0:5978:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581082.150594:0:5978:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:27.0:1631581082.150595:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:3.0:1631581082.150600:0:5978:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:3.0:1631581082.150601:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581082.150608:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581082.150613:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581082.150618:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581082.150630:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581082.150630:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:27.0:1631581082.150631:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:27.0:1631581082.150631:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:27.0:1631581082.150633:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000200:1.0:1631581082.150634:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000010:1.0:1631581082.150635:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c13fa00 (tot 84627316). 00000400:00000010:27.0:1631581082.150639:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093ac800 (tot 84626876). 00000800:00000200:3.0:1631581082.150639:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581082.150640:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:3.0:1631581082.150641:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:1.0:1631581082.150643:0:5980:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x6655 00000400:00000200:1.0:1631581082.150644:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:1.0:1631581082.150645:0:5980:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:1.0:1631581082.150646:0:5980:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2f30 (tot 84626860). 00000400:00000010:1.0:1631581082.150648:0:5980:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0a9000 (tot 84626580). 00000400:00000200:1.0:1631581082.150649:0:5980:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a330 00000400:00000010:1.0:1631581082.150649:0:5980:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a330. 00000400:00000010:1.0:1631581082.150651:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c13fa00 (tot 84626140). 00000800:00000200:1.0:1631581082.150652:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581082.150653:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:1.0:1631581082.150653:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581083.150381:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150383:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150385:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150390:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150391:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150393:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581083.150394:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581083.150395:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2f20 (tot 84626156). 00000400:00000010:5.0:1631581083.150396:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0a9e00 (tot 84626436). 00000400:00000010:5.0:1631581083.150397:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a2a8. 00000400:00000010:5.0:1631581083.150399:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0ad800 (tot 84626876). 00000400:00000010:5.0:1631581083.150399:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10d80 (tot 84626924). 00000400:00000200:5.0:1631581083.150401:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581083.150403:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581083.150404:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581083.150407:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581083.150409:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581083.150412:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581083.150413:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581083.150414:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581083.150419:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581083.150477:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581083.150485:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581083.150543:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581083.150548:0:5979:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:31.0F:1631581083.150551:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:27.0:1631581083.150551:0:5979:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:27.0:1631581083.150552:0:5979:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff8916391a0800 (tot 84627364). 00000400:00000200:27.0:1631581083.150555:0:5979:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000800:00000200:31.0:1631581083.150556:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:27.0:1631581083.150557:0:5979:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000400:00000200:31.0:1631581083.150558:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:27.0:1631581083.150559:0:5979:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:27.0:1631581083.150560:0:5979:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:27.0:1631581083.150562:0:5979:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:31.0:1631581083.150571:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:27.0:1631581083.150571:0:5979:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000200:31.0:1631581083.150572:0:5981:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:31.0:1631581083.150573:0:5981:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000800:00000200:27.0:1631581083.150573:0:5979:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000400:00000010:31.0:1631581083.150575:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0ad800 (tot 84626924). 00000800:00000200:27.0:1631581083.150575:0:5979:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:31.0:1631581083.150576:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581083.150576:0:5979:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:31.0:1631581083.150577:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (133)-- 00000800:00000200:27.0:1631581083.150577:0:5979:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (133)++ 00000800:00000200:31.0:1631581083.150578:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:27.0:1631581083.150582:0:5979:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:27.0:1631581083.150599:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581083.150602:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581083.150608:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581083.150614:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581083.150631:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581083.150632:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:27.0:1631581083.150634:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:1.0:1631581083.150634:0:5980:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000800:00000200:31.0:1631581083.150635:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:3.0:1631581083.150635:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000200:1.0:1631581083.150635:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000010:3.0:1631581083.150637:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093ace00 (tot 84627364). 00000400:00000200:1.0:1631581083.150637:0:5980:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000200:3.0:1631581083.150640:0:5978:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x665d 00000400:00000010:1.0:1631581083.150640:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff8916391a0800 (tot 84626924). 00000800:00000200:1.0:1631581083.150641:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:3.0:1631581083.150642:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:3.0:1631581083.150643:0:5978:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:3.0:1631581083.150644:0:5978:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2f20 (tot 84626908). 00000400:00000010:3.0:1631581083.150645:0:5978:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0a9e00 (tot 84626628). 00000400:00000200:3.0:1631581083.150646:0:5978:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a2a8 00000400:00000010:3.0:1631581083.150647:0:5978:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a2a8. 00000400:00000010:3.0:1631581083.150648:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093ace00 (tot 84626188). 00000800:00000200:3.0:1631581083.150649:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581083.150650:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:3.0:1631581083.150651:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581084.150380:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150382:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150384:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150385:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150387:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150392:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581084.150393:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581084.150394:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2f10 (tot 84626204). 00000400:00000010:5.0:1631581084.150395:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0ade00 (tot 84626484). 00000400:00000010:5.0:1631581084.150396:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a220. 00000400:00000010:5.0:1631581084.150397:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0aba00 (tot 84626924). 00000400:00000010:5.0:1631581084.150398:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10cc0 (tot 84626972). 00000400:00000200:5.0:1631581084.150399:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581084.150401:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581084.150403:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581084.150406:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581084.150408:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581084.150410:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581084.150412:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581084.150413:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581084.150418:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581084.150475:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581084.150483:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581084.150542:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581084.150546:0:5979:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:31.0:1631581084.150550:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:27.0:1631581084.150550:0:5979:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:27.0:1631581084.150552:0:5979:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff8916391a2800 (tot 84627412). 00000800:00000200:31.0:1631581084.150554:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:27.0:1631581084.150554:0:5979:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:31.0:1631581084.150555:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:27.0:1631581084.150557:0:5979:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000400:00000200:31.0:1631581084.150558:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000800:00000200:27.0:1631581084.150559:0:5979:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:27.0:1631581084.150560:0:5979:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:27.0:1631581084.150569:0:5979:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:31.0:1631581084.150570:0:5981:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:31.0:1631581084.150571:0:5981:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:27.0:1631581084.150574:0:5979:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000010:31.0:1631581084.150575:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0aba00 (tot 84626972). 00000800:00000200:27.0:1631581084.150576:0:5979:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:31.0:1631581084.150577:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:31.0:1631581084.150578:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:31.0:1631581084.150578:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:27.0:1631581084.150578:0:5979:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:27.0:1631581084.150579:0:5979:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581084.150580:0:5979:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:27.0:1631581084.150601:0:5979:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:27.0:1631581084.150602:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581084.150609:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581084.150613:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:31.0:1631581084.150618:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581084.150631:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:31.0:1631581084.150632:0:5981:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000400:00000200:31.0:1631581084.150634:0:5981:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000800:00000200:27.0:1631581084.150634:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:27.0:1631581084.150634:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:1.0:1631581084.150635:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000010:31.0:1631581084.150636:0:5981:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff891636ebdc00 (tot 84627412). 00000400:00000200:27.0:1631581084.150636:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000800:00000200:1.0:1631581084.150637:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:31.0:1631581084.150638:0:5981:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x6665 00000400:00000010:27.0:1631581084.150638:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff8916391a2800 (tot 84626972). 00000800:00000200:27.0:1631581084.150639:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:31.0:1631581084.150640:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:31.0:1631581084.150641:0:5981:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:31.0:1631581084.150641:0:5981:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2f10 (tot 84626956). 00000400:00000010:31.0:1631581084.150642:0:5981:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0ade00 (tot 84626676). 00000400:00000200:31.0:1631581084.150643:0:5981:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a220 00000400:00000010:31.0:1631581084.150644:0:5981:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a220. 00000400:00000010:31.0:1631581084.150645:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff891636ebdc00 (tot 84626236). 00000800:00000200:31.0:1631581084.150646:0:5981:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581084.150647:0:5981:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:31.0:1631581084.150648:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581085.150379:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150381:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150383:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150384:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150387:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150390:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581085.150392:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581085.150392:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2f00 (tot 84626252). 00000400:00000010:5.0:1631581085.150393:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0ada00 (tot 84626532). 00000400:00000010:5.0:1631581085.150395:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a198. 00000400:00000010:5.0:1631581085.150396:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0ab400 (tot 84626972). 00000400:00000010:5.0:1631581085.150397:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10f00 (tot 84627020). 00000400:00000200:5.0:1631581085.150399:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581085.150400:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581085.150402:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581085.150405:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581085.150407:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581085.150409:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581085.150410:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581085.150411:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581085.150417:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581085.150458:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581085.150462:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581085.150530:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581085.150534:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:1.0:1631581085.150535:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:3.0:1631581085.150537:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:3.0:1631581085.150539:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093ace00 (tot 84627460). 00000800:00000200:1.0:1631581085.150539:0:5980:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:3.0:1631581085.150541:0:5978:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:1.0:1631581085.150541:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:3.0:1631581085.150544:0:5978:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000400:00000200:1.0:1631581085.150544:0:5980:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000800:00000200:3.0:1631581085.150546:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000400:00000200:1.0:1631581085.150546:0:5980:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000800:00000200:3.0:1631581085.150547:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:3.0:1631581085.150557:0:5978:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:1.0:1631581085.150558:0:5980:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:3.0:1631581085.150561:0:5978:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000800:00000200:3.0:1631581085.150563:0:5978:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000400:00000010:1.0:1631581085.150563:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0ab400 (tot 84627020). 00000800:00000200:1.0:1631581085.150565:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:3.0:1631581085.150566:0:5978:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:1.0:1631581085.150566:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:1.0:1631581085.150566:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:3.0:1631581085.150567:0:5978:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581085.150568:0:5978:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581085.150589:0:5978:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:3.0:1631581085.150590:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581085.150591:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581085.150594:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581085.150605:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581085.150607:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581085.150607:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000400:00000200:1.0:1631581085.150610:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000010:1.0:1631581085.150611:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c13fa00 (tot 84627460). 00000400:00000200:1.0:1631581085.150614:0:5980:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x666d 00000400:00000200:1.0:1631581085.150616:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:1.0:1631581085.150617:0:5980:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:1.0:1631581085.150617:0:5980:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2f00 (tot 84627444). 00000400:00000010:1.0:1631581085.150618:0:5980:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0ada00 (tot 84627164). 00000800:00000200:31.0:1631581085.150619:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000800:00000200:27.0:1631581085.150619:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000200:1.0:1631581085.150619:0:5980:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a198 00000400:00000200:31.0:1631581085.150620:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000010:1.0:1631581085.150620:0:5980:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a198. 00000800:00000200:3.0:1631581085.150621:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000010:1.0:1631581085.150621:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c13fa00 (tot 84626724). 00000800:00000200:1.0:1631581085.150622:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000400:00000200:31.0:1631581085.150623:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000800:00000200:1.0:1631581085.150623:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:1.0:1631581085.150623:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000010:31.0:1631581085.150625:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093ace00 (tot 84626284). 00000800:00000200:31.0:1631581085.150626:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:5.0:1631581086.150378:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150381:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150382:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150384:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150385:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150387:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581086.150391:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581086.150392:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2ef0 (tot 84626300). 00000400:00000010:5.0:1631581086.150393:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0ab200 (tot 84626580). 00000400:00000010:5.0:1631581086.150394:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a110. 00000400:00000010:5.0:1631581086.150395:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0a9800 (tot 84627020). 00000400:00000010:5.0:1631581086.150396:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10680 (tot 84627068). 00000400:00000200:5.0:1631581086.150397:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581086.150399:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581086.150402:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581086.150405:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581086.150407:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581086.150409:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581086.150410:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581086.150411:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581086.150417:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581086.150461:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581086.150477:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581086.150532:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581086.150537:0:5979:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:3.0:1631581086.150537:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:27.0:1631581086.150540:0:5979:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:27.0:1631581086.150541:0:5979:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff8916391a2800 (tot 84627508). 00000800:00000200:3.0:1631581086.150541:0:5978:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:3.0:1631581086.150542:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:27.0:1631581086.150543:0:5979:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:27.0:1631581086.150554:0:5979:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:27.0:1631581086.150556:0:5979:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000400:00000200:3.0:1631581086.150556:0:5978:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000800:00000200:27.0:1631581086.150557:0:5979:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:3.0:1631581086.150557:0:5978:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:3.0:1631581086.150558:0:5978:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:27.0:1631581086.150559:0:5979:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:27.0:1631581086.150563:0:5979:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000800:00000200:27.0:1631581086.150582:0:5979:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000400:00000010:3.0:1631581086.150582:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0a9800 (tot 84627068). 00000800:00000200:3.0:1631581086.150583:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581086.150584:0:5979:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:3.0:1631581086.150584:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:3.0:1631581086.150584:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:27.0:1631581086.150585:0:5979:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581086.150586:0:5979:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:27.0:1631581086.150591:0:5979:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:27.0:1631581086.150592:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581086.150595:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581086.150597:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581086.150601:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581086.150612:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:31.0:1631581086.150614:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000400:00000200:3.0:1631581086.150615:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000010:3.0:1631581086.150616:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093aea00 (tot 84627508). 00000800:00000200:31.0:1631581086.150617:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:31.0:1631581086.150618:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:1.0:1631581086.150618:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000200:3.0:1631581086.150619:0:5978:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x6675 00000800:00000200:1.0:1631581086.150620:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:31.0:1631581086.150621:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000200:3.0:1631581086.150621:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:3.0:1631581086.150621:0:5978:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:3.0:1631581086.150622:0:5978:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2ef0 (tot 84627492). 00000400:00000010:31.0:1631581086.150623:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff8916391a2800 (tot 84627052). 00000400:00000010:3.0:1631581086.150623:0:5978:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0ab200 (tot 84626772). 00000800:00000200:31.0:1631581086.150624:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:3.0:1631581086.150625:0:5978:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a110 00000400:00000010:3.0:1631581086.150625:0:5978:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a110. 00000400:00000010:3.0:1631581086.150626:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093aea00 (tot 84626332). 00000800:00000200:3.0:1631581086.150627:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581086.150628:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:3.0:1631581086.150629:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581087.150384:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150391:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150392:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150394:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150395:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581087.150397:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581087.150398:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2ee0 (tot 84626348). 00000400:00000010:5.0:1631581087.150399:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0adc00 (tot 84626628). 00000400:00000010:5.0:1631581087.150400:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a088. 00000400:00000010:5.0:1631581087.150401:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0af000 (tot 84627068). 00000400:00000010:5.0:1631581087.150402:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10dc0 (tot 84627116). 00000400:00000200:5.0:1631581087.150403:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581087.150405:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581087.150407:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581087.150410:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581087.150412:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581087.150415:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581087.150417:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581087.150418:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581087.150423:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581087.150481:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581087.150489:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581087.150498:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581087.150503:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000400:00000200:1.0:1631581087.150507:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:1.0:1631581087.150508:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c138e00 (tot 84627556). 00000400:00000200:1.0:1631581087.150511:0:5980:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:1.0:1631581087.150513:0:5980:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:1.0:1631581087.150515:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581087.150516:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:1.0:1631581087.150518:0:5980:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:1.0:1631581087.150523:0:5980:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000800:00000200:1.0:1631581087.150525:0:5980:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:1.0:1631581087.150544:0:5980:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:27.0:1631581087.150545:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000800:00000200:1.0:1631581087.150545:0:5980:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581087.150546:0:5980:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (133)++ 00000800:00000200:27.0:1631581087.150548:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:27.0:1631581087.150549:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:1.0:1631581087.150550:0:5980:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (134)-- 00000800:00000200:1.0:1631581087.150551:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (133)-- 00000400:00000200:27.0:1631581087.150552:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000800:00000200:1.0:1631581087.150552:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:31.0:1631581087.150553:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:27.0:1631581087.150553:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000800:00000200:1.0:1631581087.150553:0:5980:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:1.0:1631581087.150553:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:27.0:1631581087.150554:0:5979:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:1.0:1631581087.150555:0:5980:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000010:27.0:1631581087.150556:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0af000 (tot 84627116). 00000800:00000200:31.0:1631581087.150557:0:5981:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:27.0:1631581087.150557:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (133)-- 00000800:00000200:27.0:1631581087.150558:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000010:1.0:1631581087.150558:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c138e00 (tot 84626676). 00000800:00000200:27.0:1631581087.150559:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:1.0:1631581087.150559:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:31.0:1631581087.150572:0:5981:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000010:31.0:1631581087.150573:0:5981:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff891636ebdc00 (tot 84627116). 00000400:00000200:31.0:1631581087.150576:0:5981:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x667d 00000400:00000200:31.0:1631581087.150578:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:31.0:1631581087.150578:0:5981:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:31.0:1631581087.150579:0:5981:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2ee0 (tot 84627100). 00000400:00000010:31.0:1631581087.150580:0:5981:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0adc00 (tot 84626820). 00000400:00000200:31.0:1631581087.150581:0:5981:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a088 00000400:00000010:31.0:1631581087.150582:0:5981:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a088. 00000400:00000010:31.0:1631581087.150583:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff891636ebdc00 (tot 84626380). 00000800:00000200:31.0:1631581087.150584:0:5981:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581087.150585:0:5981:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:31.0:1631581087.150585:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581088.150381:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150383:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150385:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150390:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150392:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581088.150394:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581088.150394:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2ed0 (tot 84626396). 00000400:00000010:5.0:1631581088.150395:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0ae800 (tot 84626676). 00000400:00000010:5.0:1631581088.150396:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a000. 00000400:00000010:5.0:1631581088.150398:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0ab800 (tot 84627116). 00000400:00000010:5.0:1631581088.150398:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10ac0 (tot 84627164). 00000400:00000200:5.0:1631581088.150400:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581088.150402:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581088.150403:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581088.150406:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581088.150408:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581088.150411:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581088.150412:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581088.150413:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581088.150418:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581088.150486:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581088.150494:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581088.150553:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581088.150558:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:27.0:1631581088.150561:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:1.0:1631581088.150562:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:1.0:1631581088.150563:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c138e00 (tot 84627604). 00000800:00000200:27.0:1631581088.150565:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:27.0:1631581088.150566:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:1.0:1631581088.150566:0:5980:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:1.0:1631581088.150568:0:5980:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:1.0:1631581088.150577:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581088.150578:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:27.0:1631581088.150579:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:1.0:1631581088.150580:0:5980:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:27.0:1631581088.150581:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:27.0:1631581088.150582:0:5979:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:1.0:1631581088.150585:0:5980:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000010:27.0:1631581088.150586:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0ab800 (tot 84627164). 00000800:00000200:1.0:1631581088.150587:0:5980:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:27.0:1631581088.150588:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581088.150589:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:27.0:1631581088.150589:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:1.0:1631581088.150589:0:5980:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:1.0:1631581088.150590:0:5980:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581088.150591:0:5980:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581088.150612:0:5980:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:1.0:1631581088.150613:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581088.150621:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581088.150625:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581088.150629:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581088.150638:0:5979:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:1.0:1631581088.150638:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581088.150640:0:5980:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000800:00000200:31.0:1631581088.150641:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000200:27.0:1631581088.150641:0:5979:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000200:1.0:1631581088.150641:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000010:27.0:1631581088.150642:0:5979:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff8916391a7800 (tot 84627604). 00000800:00000200:31.0:1631581088.150643:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:1.0:1631581088.150643:0:5980:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000200:27.0:1631581088.150645:0:5979:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x6685 00000400:00000010:1.0:1631581088.150645:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c138e00 (tot 84627164). 00000800:00000200:1.0:1631581088.150646:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:27.0:1631581088.150647:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:27.0:1631581088.150648:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:27.0:1631581088.150649:0:5979:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2ed0 (tot 84627148). 00000400:00000010:27.0:1631581088.150650:0:5979:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0ae800 (tot 84626868). 00000400:00000200:27.0:1631581088.150651:0:5979:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a000 00000400:00000010:27.0:1631581088.150652:0:5979:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a000. 00000400:00000010:27.0:1631581088.150653:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff8916391a7800 (tot 84626428). 00000800:00000200:27.0:1631581088.150654:0:5979:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581088.150655:0:5979:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581088.150656:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000020:00000001:1.0:1631581088.499688:0:12487:0:(genops.c:1886:obd_stale_export_get()) Process entered 00000020:00000001:1.0:1631581088.499689:0:12487:0:(genops.c:1900:obd_stale_export_get()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:1.0:1631581088.499691:0:12487:0:(genops.c:1886:obd_stale_export_get()) Process entered 00000020:00000001:1.0:1631581088.499691:0:12487:0:(genops.c:1900:obd_stale_export_get()) Process leaving (rc=0 : 0 : 0) 00000400:00000200:5.0:1631581089.150382:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150384:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150391:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150392:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150393:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581089.150395:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581089.150396:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2ec0 (tot 84626444). 00000400:00000010:5.0:1631581089.150397:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0aa000 (tot 84626724). 00000400:00000010:5.0:1631581089.150398:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a550. 00000400:00000010:5.0:1631581089.150399:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0aac00 (tot 84627164). 00000400:00000010:5.0:1631581089.150400:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10d40 (tot 84627212). 00000400:00000200:5.0:1631581089.150401:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581089.150403:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581089.150405:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581089.150408:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581089.150410:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581089.150412:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581089.150414:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581089.150414:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581089.150420:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581089.150477:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581089.150485:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581089.150536:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581089.150539:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000800:00000200:31.0:1631581089.150541:0:5981:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:3.0:1631581089.150554:0:5978:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:31.0:1631581089.150555:0:5981:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000200:3.0:1631581089.150555:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000010:31.0:1631581089.150557:0:5981:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff891636ebdc00 (tot 84627652). 00000400:00000200:3.0:1631581089.150557:0:5978:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:31.0:1631581089.150559:0:5981:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:3.0:1631581089.150559:0:5978:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:3.0:1631581089.150560:0:5978:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000010:3.0:1631581089.150561:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0aac00 (tot 84627212). 00000400:00000200:31.0:1631581089.150562:0:5981:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:3.0:1631581089.150562:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:31.0:1631581089.150563:0:5981:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581089.150563:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:31.0:1631581089.150564:0:5981:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (132)-- 00000800:00000200:3.0:1631581089.150564:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:31.0:1631581089.150566:0:5981:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:31.0:1631581089.150571:0:5981:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000800:00000200:31.0:1631581089.150573:0:5981:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:31.0:1631581089.150575:0:5981:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:31.0:1631581089.150576:0:5981:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:31.0:1631581089.150576:0:5981:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:31.0:1631581089.150597:0:5981:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:31.0:1631581089.150598:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581089.150606:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581089.150610:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581089.150614:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581089.150630:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581089.150630:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:31.0:1631581089.150632:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:31.0:1631581089.150633:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:27.0:1631581089.150633:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000200:3.0:1631581089.150633:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000800:00000200:27.0:1631581089.150634:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000010:3.0:1631581089.150634:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093aea00 (tot 84627652). 00000400:00000200:31.0:1631581089.150635:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000010:31.0:1631581089.150636:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff891636ebdc00 (tot 84627212). 00000800:00000200:31.0:1631581089.150637:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:3.0:1631581089.150637:0:5978:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x668d 00000400:00000200:3.0:1631581089.150638:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:3.0:1631581089.150639:0:5978:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:3.0:1631581089.150640:0:5978:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2ec0 (tot 84627196). 00000400:00000010:3.0:1631581089.150641:0:5978:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0aa000 (tot 84626916). 00000400:00000200:3.0:1631581089.150642:0:5978:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a550 00000400:00000010:3.0:1631581089.150642:0:5978:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a550. 00000400:00000010:3.0:1631581089.150643:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093aea00 (tot 84626476). 00000800:00000200:3.0:1631581089.150644:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581089.150645:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:3.0:1631581089.150646:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581090.150379:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150381:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150383:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150384:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150385:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150390:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581090.150392:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581090.150393:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2eb0 (tot 84626492). 00000400:00000010:5.0:1631581090.150394:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0a8a00 (tot 84626772). 00000400:00000010:5.0:1631581090.150395:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a4c8. 00000400:00000010:5.0:1631581090.150396:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0a9a00 (tot 84627212). 00000400:00000010:5.0:1631581090.150397:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10c00 (tot 84627260). 00000400:00000200:5.0:1631581090.150398:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581090.150400:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581090.150402:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581090.150405:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581090.150407:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581090.150409:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581090.150410:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581090.150411:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581090.150416:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581090.150474:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581090.150482:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581090.150542:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581090.150547:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:27.0:1631581090.150549:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:1.0:1631581090.150550:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:1.0:1631581090.150551:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c13fa00 (tot 84627700). 00000800:00000200:27.0:1631581090.150553:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:1.0:1631581090.150554:0:5980:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:27.0:1631581090.150555:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:1.0:1631581090.150556:0:5980:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000400:00000200:27.0:1631581090.150558:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000800:00000200:1.0:1631581090.150558:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581090.150560:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:1.0:1631581090.150569:0:5980:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:27.0:1631581090.150570:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:27.0:1631581090.150571:0:5979:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:1.0:1631581090.150574:0:5980:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000010:27.0:1631581090.150576:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0a9a00 (tot 84627260). 00000800:00000200:1.0:1631581090.150576:0:5980:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:27.0:1631581090.150577:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581090.150578:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:27.0:1631581090.150578:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:1.0:1631581090.150578:0:5980:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:1.0:1631581090.150579:0:5980:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581090.150580:0:5980:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581090.150602:0:5980:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:1.0:1631581090.150602:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581090.150610:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581090.150614:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581090.150619:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581090.150630:0:5979:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:1.0:1631581090.150630:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000400:00000200:27.0:1631581090.150633:0:5979:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000800:00000200:1.0:1631581090.150633:0:5980:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:1.0:1631581090.150633:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:31.0:1631581090.150634:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000010:27.0:1631581090.150634:0:5979:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff8916391a7800 (tot 84627700). 00000400:00000200:1.0:1631581090.150635:0:5980:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000800:00000200:31.0:1631581090.150636:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:27.0:1631581090.150637:0:5979:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x6695 00000400:00000010:1.0:1631581090.150637:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c13fa00 (tot 84627260). 00000800:00000200:1.0:1631581090.150638:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:27.0:1631581090.150639:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:27.0:1631581090.150639:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:27.0:1631581090.150640:0:5979:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2eb0 (tot 84627244). 00000400:00000010:27.0:1631581090.150641:0:5979:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0a8a00 (tot 84626964). 00000400:00000200:27.0:1631581090.150642:0:5979:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a4c8 00000400:00000010:27.0:1631581090.150643:0:5979:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a4c8. 00000400:00000010:27.0:1631581090.150644:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff8916391a7800 (tot 84626524). 00000800:00000200:27.0:1631581090.150645:0:5979:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581090.150647:0:5979:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581090.150647:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581091.150379:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150381:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150383:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150384:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150387:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150390:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581091.150392:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581091.150393:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2ea0 (tot 84626540). 00000400:00000010:5.0:1631581091.150394:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0aaa00 (tot 84626820). 00000400:00000010:5.0:1631581091.150395:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a660. 00000400:00000010:5.0:1631581091.150396:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0af600 (tot 84627260). 00000400:00000010:5.0:1631581091.150397:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10500 (tot 84627308). 00000400:00000200:5.0:1631581091.150399:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581091.150400:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581091.150402:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581091.150405:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581091.150407:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581091.150410:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581091.150411:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581091.150412:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581091.150417:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581091.150475:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581091.150483:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581091.150542:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581091.150547:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:31.0:1631581091.150550:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:3.0:1631581091.150551:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:3.0:1631581091.150553:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093aea00 (tot 84627748). 00000800:00000200:31.0:1631581091.150554:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:31.0:1631581091.150555:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:3.0:1631581091.150555:0:5978:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:3.0:1631581091.150558:0:5978:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:3.0:1631581091.150567:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581091.150568:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:31.0:1631581091.150569:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:31.0:1631581091.150570:0:5981:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:3.0:1631581091.150570:0:5978:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:31.0:1631581091.150571:0:5981:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:3.0:1631581091.150574:0:5978:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000010:31.0:1631581091.150576:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0af600 (tot 84627308). 00000800:00000200:3.0:1631581091.150576:0:5978:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:31.0:1631581091.150577:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:31.0:1631581091.150578:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:3.0:1631581091.150578:0:5978:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:31.0:1631581091.150579:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:3.0:1631581091.150579:0:5978:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581091.150580:0:5978:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581091.150601:0:5978:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:3.0:1631581091.150602:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581091.150610:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581091.150614:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:31.0:1631581091.150619:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581091.150628:0:5981:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:3.0:1631581091.150628:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581091.150630:0:5978:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:3.0:1631581091.150630:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:31.0:1631581091.150631:0:5981:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000800:00000200:27.0:1631581091.150631:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000010:31.0:1631581091.150632:0:5981:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff891636ebdc00 (tot 84627748). 00000800:00000200:27.0:1631581091.150632:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:3.0:1631581091.150632:0:5978:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000010:3.0:1631581091.150634:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093aea00 (tot 84627308). 00000400:00000200:31.0:1631581091.150635:0:5981:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x669d 00000800:00000200:3.0:1631581091.150635:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:31.0:1631581091.150636:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:31.0:1631581091.150637:0:5981:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:31.0:1631581091.150638:0:5981:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2ea0 (tot 84627292). 00000400:00000010:31.0:1631581091.150638:0:5981:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0aaa00 (tot 84627012). 00000400:00000200:31.0:1631581091.150639:0:5981:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a660 00000400:00000010:31.0:1631581091.150640:0:5981:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a660. 00000400:00000010:31.0:1631581091.150641:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff891636ebdc00 (tot 84626572). 00000800:00000200:31.0:1631581091.150642:0:5981:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581091.150643:0:5981:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:31.0:1631581091.150643:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581092.150381:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150383:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150385:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150386:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150388:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150389:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150390:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150392:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581092.150393:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581092.150394:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2e90 (tot 84626588). 00000400:00000010:5.0:1631581092.150395:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0ae200 (tot 84626868). 00000400:00000010:5.0:1631581092.150396:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a5d8. 00000400:00000010:5.0:1631581092.150398:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0a9200 (tot 84627308). 00000400:00000010:5.0:1631581092.150399:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10340 (tot 84627356). 00000400:00000200:5.0:1631581092.150401:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581092.150403:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581092.150404:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581092.150407:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581092.150409:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581092.150412:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581092.150413:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581092.150414:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581092.150419:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581092.150476:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581092.150483:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581092.150489:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581092.150494:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000400:00000200:1.0:1631581092.150497:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:1.0:1631581092.150498:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c138e00 (tot 84627796). 00000400:00000200:1.0:1631581092.150501:0:5980:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:1.0:1631581092.150503:0:5980:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:1.0:1631581092.150505:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581092.150522:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:1.0:1631581092.150524:0:5980:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:1.0:1631581092.150528:0:5980:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000800:00000200:1.0:1631581092.150531:0:5980:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:1.0:1631581092.150544:0:5980:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:1.0:1631581092.150545:0:5980:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581092.150546:0:5980:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (133)++ 00000800:00000200:27.0:1631581092.150547:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000800:00000200:1.0:1631581092.150549:0:5980:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (134)-- 00000800:00000200:27.0:1631581092.150550:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000800:00000200:1.0:1631581092.150550:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (133)-- 00000800:00000200:1.0:1631581092.150550:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000400:00000200:27.0:1631581092.150551:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:1.0:1631581092.150551:0:5980:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:1.0:1631581092.150552:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:27.0:1631581092.150554:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:1.0:1631581092.150554:0:5980:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000200:27.0:1631581092.150555:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000800:00000200:3.0:1631581092.150555:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000010:1.0:1631581092.150555:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c138e00 (tot 84627356). 00000400:00000200:27.0:1631581092.150556:0:5979:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000800:00000200:1.0:1631581092.150557:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000010:27.0:1631581092.150558:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0a9200 (tot 84626916). 00000800:00000200:1.0:1631581092.150558:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000800:00000200:27.0:1631581092.150559:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:3.0:1631581092.150559:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:1.0:1631581092.150559:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (133)-- 00000400:00000200:3.0:1631581092.150573:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000010:3.0:1631581092.150575:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093aea00 (tot 84627356). 00000400:00000200:3.0:1631581092.150578:0:5978:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x66a5 00000400:00000200:3.0:1631581092.150580:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:3.0:1631581092.150580:0:5978:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:3.0:1631581092.150581:0:5978:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2e90 (tot 84627340). 00000400:00000010:3.0:1631581092.150582:0:5978:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0ae200 (tot 84627060). 00000400:00000200:3.0:1631581092.150583:0:5978:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a5d8 00000400:00000010:3.0:1631581092.150584:0:5978:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a5d8. 00000400:00000010:3.0:1631581092.150585:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093aea00 (tot 84626620). 00000800:00000200:3.0:1631581092.150603:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581092.150604:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:3.0:1631581092.150604:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000020:00000001:14.0F:1631581092.210868:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=3872 : 3872 : f20) 00000020:00000001:14.0:1631581092.210874:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=77960 : 77960 : 13088) 00000020:00000001:14.0:1631581092.210876:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=68464 : 68464 : 10b70) 00000020:00000001:14.0:1631581092.210878:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=57213 : 57213 : df7d) 00000020:00000001:14.0:1631581092.210880:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709548912 : -2704 : fffffffffffff570) 00000020:00000001:14.0:1631581092.210883:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=45976 : 45976 : b398) 00000020:00000001:14.0:1631581092.210885:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=3048 : 3048 : be8) 00000020:00000001:14.0:1631581092.210887:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=83716 : 83716 : 14704) 00000020:00000001:14.0:1631581092.210889:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=8112 : 8112 : 1fb0) 00000020:00000001:14.0:1631581092.210891:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709549642 : -1974 : fffffffffffff84a) 00000020:00000001:14.0:1631581092.210893:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=3736 : 3736 : e98) 00000020:00000001:14.0:1631581092.210895:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709547695 : -3921 : fffffffffffff0af) 00000020:00000001:14.0:1631581092.210897:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709543720 : -7896 : ffffffffffffe128) 00000020:00000001:14.0:1631581092.210899:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=7092 : 7092 : 1bb4) 00000020:00000001:14.0:1631581092.210901:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709548136 : -3480 : fffffffffffff268) 00000020:00000001:14.0:1631581092.210903:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709519572 : -32044 : ffffffffffff82d4) 00000020:00000001:14.0:1631581092.210905:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=31178 : 31178 : 79ca) 00000020:00000001:14.0:1631581092.210907:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550264 : -1352 : fffffffffffffab8) 00000020:00000001:14.0:1631581092.210909:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709548912 : -2704 : fffffffffffff570) 00000020:00000001:14.0:1631581092.210911:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709529510 : -22106 : ffffffffffffa9a6) 00000020:00000001:14.0:1631581092.210913:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709529542 : -22074 : ffffffffffffa9c6) 00000020:00000001:14.0:1631581092.210915:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=1885032 : 1885032 : 1cc368) 00000020:00000001:14.0:1631581092.210917:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550264 : -1352 : fffffffffffffab8) 00000020:00000001:14.0:1631581092.210919:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550964 : -652 : fffffffffffffd74) 00000020:00000001:14.0:1631581092.210921:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550264 : -1352 : fffffffffffffab8) 00000020:00000001:14.0:1631581092.210923:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550264 : -1352 : fffffffffffffab8) 00000020:00000001:14.0:1631581092.210925:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210927:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550264 : -1352 : fffffffffffffab8) 00000020:00000001:14.0:1631581092.210929:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=197880 : 197880 : 304f8) 00000020:00000001:14.0:1631581092.210932:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550264 : -1352 : fffffffffffffab8) 00000020:00000001:14.0:1631581092.210934:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709536704 : -14912 : ffffffffffffc5c0) 00000020:00000001:14.0:1631581092.210936:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=18446744073709550264 : -1352 : fffffffffffffab8) 00000020:00000001:14.0:1631581092.210938:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210940:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210941:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210943:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210945:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210946:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210948:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210950:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210951:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210953:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210955:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210957:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210958:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210960:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210962:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210963:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210965:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210967:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210968:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210970:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210972:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210973:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210975:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210977:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210979:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210980:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210982:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210984:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210985:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210987:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210989:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210991:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210993:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210994:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210996:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210998:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.210999:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211001:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211003:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211004:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211006:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211008:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211010:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211011:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211013:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211015:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211016:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211018:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211020:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211021:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211023:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211025:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211026:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211028:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211030:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211032:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211033:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211035:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211037:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211038:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211040:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211042:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211043:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211045:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211047:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211049:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211051:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211052:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211054:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211056:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211057:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211059:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211061:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211063:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211064:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211066:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211068:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211069:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211071:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211073:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211074:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211076:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211078:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211079:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211081:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211083:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211085:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211086:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211088:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211090:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211091:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211093:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211095:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211096:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211098:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211100:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211101:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211114:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211115:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211116:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211116:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211117:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211117:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211117:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211118:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211118:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211119:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211119:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211120:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211120:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211121:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211121:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211122:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211122:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211123:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211123:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211123:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211124:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211124:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211125:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211125:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211126:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211126:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211127:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211127:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211128:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211128:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211128:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211129:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211129:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211130:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211130:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211131:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211132:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211132:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211132:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211133:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211133:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211134:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211134:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211135:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211135:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211136:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211136:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211137:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211137:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211138:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211138:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211138:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211139:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211139:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211140:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211140:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211141:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211141:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211142:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211142:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211143:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211143:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211144:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211144:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211144:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211145:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211145:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211146:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211146:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211147:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211148:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211148:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211149:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211149:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211150:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211150:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211151:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211151:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211152:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211152:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211153:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211153:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211153:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211154:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211154:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211155:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211155:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211156:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211156:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211157:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211157:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211158:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211158:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211159:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211159:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211159:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211160:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211160:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211161:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211161:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211162:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211162:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211163:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211163:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211164:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211164:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211165:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211165:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211166:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211166:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211167:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211167:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211168:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211168:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211169:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211169:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211169:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211170:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211170:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211171:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211171:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211172:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211172:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211173:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211173:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211174:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000020:00000001:14.0:1631581092.211174:0:5380:0:(lprocfs_status.c:1775:lprocfs_read_helper()) Process leaving (rc=0 : 0 : 0) 00000100:00000040:14.0:1631581092.211175:0:5380:0:(pinger.c:317:ptlrpc_pinger_main()) next wakeup in 25 (6274) 00000400:00000200:5.0:1631581093.150397:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150405:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150411:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150416:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150420:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150425:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150440:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150441:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581093.150443:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581093.150444:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2e80 (tot 84626636). 00000400:00000010:5.0:1631581093.150445:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0ae200 (tot 84626916). 00000400:00000010:5.0:1631581093.150446:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a770. 00000400:00000010:5.0:1631581093.150447:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0a9200 (tot 84627356). 00000400:00000010:5.0:1631581093.150448:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10780 (tot 84627404). 00000400:00000200:5.0:1631581093.150449:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581093.150451:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581093.150453:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581093.150457:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581093.150459:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581093.150461:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581093.150462:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581093.150463:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581093.150468:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581093.150525:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581093.150533:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581093.150588:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581093.150593:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:27.0:1631581093.150596:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:1.0:1631581093.150597:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:1.0:1631581093.150598:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c138e00 (tot 84627844). 00000800:00000200:27.0:1631581093.150600:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:1.0:1631581093.150601:0:5980:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:27.0:1631581093.150602:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:1.0:1631581093.150603:0:5980:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:1.0:1631581093.150605:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581093.150606:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:27.0:1631581093.150615:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:1.0:1631581093.150615:0:5980:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:27.0:1631581093.150616:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:27.0:1631581093.150618:0:5979:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:1.0:1631581093.150619:0:5980:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000010:27.0:1631581093.150621:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0a9200 (tot 84627404). 00000800:00000200:1.0:1631581093.150621:0:5980:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:27.0:1631581093.150622:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581093.150623:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:27.0:1631581093.150624:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:1.0:1631581093.150624:0:5980:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:1.0:1631581093.150625:0:5980:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581093.150626:0:5980:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581093.150648:0:5980:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:1.0:1631581093.150648:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581093.150656:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581093.150660:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581093.150665:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581093.150675:0:5979:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:1.0:1631581093.150675:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000400:00000200:27.0:1631581093.150678:0:5979:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000800:00000200:1.0:1631581093.150678:0:5980:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:1.0:1631581093.150678:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:31.0:1631581093.150679:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000010:27.0:1631581093.150679:0:5979:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff8916391a7800 (tot 84627844). 00000800:00000200:31.0:1631581093.150680:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:1.0:1631581093.150680:0:5980:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000200:27.0:1631581093.150682:0:5979:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x66ad 00000400:00000010:1.0:1631581093.150682:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c138e00 (tot 84627404). 00000800:00000200:1.0:1631581093.150683:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:27.0:1631581093.150684:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:27.0:1631581093.150684:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:27.0:1631581093.150686:0:5979:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2e80 (tot 84627388). 00000400:00000010:27.0:1631581093.150686:0:5979:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0ae200 (tot 84627108). 00000400:00000200:27.0:1631581093.150687:0:5979:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a770 00000400:00000010:27.0:1631581093.150688:0:5979:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a770. 00000400:00000010:27.0:1631581093.150689:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff8916391a7800 (tot 84626668). 00000800:00000200:27.0:1631581093.150691:0:5979:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581093.150692:0:5979:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581093.150693:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581094.150396:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150404:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150410:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150415:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150420:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150425:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150430:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150434:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581094.150440:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581094.150442:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2e70 (tot 84626684). 00000400:00000010:5.0:1631581094.150446:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0aaa00 (tot 84626964). 00000400:00000010:5.0:1631581094.150449:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a6e8. 00000400:00000010:5.0:1631581094.150453:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0af600 (tot 84627404). 00000400:00000010:5.0:1631581094.150455:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10000 (tot 84627452). 00000400:00000200:5.0:1631581094.150461:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581094.150466:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581094.150472:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581094.150483:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581094.150490:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581094.150496:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581094.150500:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581094.150505:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581094.150516:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581094.150572:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581094.150580:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581094.150634:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581094.150646:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:31.0:1631581094.150653:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:3.0:1631581094.150656:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:3.0:1631581094.150660:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093aea00 (tot 84627892). 00000800:00000200:31.0:1631581094.150661:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:31.0:1631581094.150664:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:3.0:1631581094.150668:0:5978:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000400:00000200:31.0:1631581094.150672:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:31.0:1631581094.150675:0:5981:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:3.0:1631581094.150675:0:5978:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000400:00000200:31.0:1631581094.150679:0:5981:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000800:00000200:3.0:1631581094.150681:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000400:00000010:31.0:1631581094.150683:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0af600 (tot 84627452). 00000800:00000200:3.0:1631581094.150684:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:31.0:1631581094.150686:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:31.0:1631581094.150689:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:3.0:1631581094.150691:0:5978:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000800:00000200:31.0:1631581094.150692:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:3.0:1631581094.150705:0:5978:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000800:00000200:3.0:1631581094.150712:0:5978:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:3.0:1631581094.150719:0:5978:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:3.0:1631581094.150722:0:5978:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581094.150724:0:5978:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581094.150735:0:5978:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:3.0:1631581094.150737:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581094.150742:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581094.150747:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:1.0:1631581094.150765:0:5980:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:31.0:1631581094.150784:0:5981:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:1.0:1631581094.150785:0:5980:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:31.0:1631581094.150786:0:5981:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000400:00000200:31.0:1631581094.150787:0:5981:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000800:00000200:27.0:1631581094.150787:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000200:1.0:1631581094.150788:0:5980:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000200:31.0:1631581094.150789:0:5981:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000800:00000200:27.0:1631581094.150789:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000010:31.0:1631581094.150790:0:5981:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093aea00 (tot 84627452). 00000400:00000010:1.0:1631581094.150790:0:5980:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c138e00 (tot 84627892). 00000800:00000200:31.0:1631581094.150791:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:1.0:1631581094.150793:0:5980:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x66b5 00000400:00000200:1.0:1631581094.150795:0:5980:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000400:00000200:1.0:1631581094.150796:0:5980:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:1.0:1631581094.150797:0:5980:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2e70 (tot 84627436). 00000400:00000010:1.0:1631581094.150798:0:5980:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0aaa00 (tot 84627156). 00000400:00000200:1.0:1631581094.150799:0:5980:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a6e8 00000400:00000010:1.0:1631581094.150800:0:5980:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a6e8. 00000400:00000010:1.0:1631581094.150801:0:5980:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c138e00 (tot 84626716). 00000800:00000200:1.0:1631581094.150802:0:5980:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:1.0:1631581094.150803:0:5980:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:1.0:1631581094.150803:0:5980:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000400:00000200:5.0:1631581095.150407:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.161@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581095.150415:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.162@o2ib1 60: deadline 0 ping_notsent 0 alive 0 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581095.150421:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.163@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581095.150426:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.164@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581095.150430:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.165@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581095.150435:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.166@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581095.150440:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.167@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000200:5.0:1631581095.150445:0:6010:0:(router.c:1102:lnet_ping_router_locked()) rtr 10.47.240.168@o2ib1 60: deadline 0 ping_notsent 0 alive 1 alive_count 1 lpni_ping_timestamp 6195 00000400:00000010:5.0:1631581095.150450:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10980 (tot 84626668). 00000400:00000010:5.0:1631581095.150454:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d100c0 (tot 84626620). 00000400:00000010:5.0:1631581095.150456:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10100 (tot 84626572). 00000400:00000010:5.0:1631581095.150458:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10e80 (tot 84626524). 00000400:00000010:5.0:1631581095.150460:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10f40 (tot 84626476). 00000400:00000010:5.0:1631581095.150462:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10e40 (tot 84626428). 00000400:00000010:5.0:1631581095.150464:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d104c0 (tot 84626380). 00000400:00000010:5.0:1631581095.150466:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d102c0 (tot 84626332). 00000400:00000010:5.0:1631581095.150468:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10380 (tot 84626284). 00000400:00000010:5.0:1631581095.150470:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10fc0 (tot 84626236). 00000400:00000010:5.0:1631581095.150472:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10a40 (tot 84626188). 00000400:00000010:5.0:1631581095.150474:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10c40 (tot 84626140). 00000400:00000010:5.0:1631581095.150476:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d106c0 (tot 84626092). 00000400:00000010:5.0:1631581095.150478:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10d80 (tot 84626044). 00000400:00000010:5.0:1631581095.150480:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10cc0 (tot 84625996). 00000400:00000010:5.0:1631581095.150482:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10f00 (tot 84625948). 00000400:00000010:5.0:1631581095.150484:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10680 (tot 84625900). 00000400:00000010:5.0:1631581095.150486:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10dc0 (tot 84625852). 00000400:00000010:5.0:1631581095.150489:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10ac0 (tot 84625804). 00000400:00000010:5.0:1631581095.150491:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10d40 (tot 84625756). 00000400:00000010:5.0:1631581095.150493:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10c00 (tot 84625708). 00000400:00000010:5.0:1631581095.150495:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10500 (tot 84625660). 00000400:00000010:5.0:1631581095.150497:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10340 (tot 84625612). 00000400:00000010:5.0:1631581095.150499:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10780 (tot 84625564). 00000400:00000010:5.0:1631581095.150501:0:6010:0:(lib-lnet.h:517:lnet_rspt_free()) kfreed 'rspt': 48 at ffff891636d10000 (tot 84625516). 00000400:00000200:5.0:1631581095.150505:0:6010:0:(lib-move.c:3071:lnet_recover_local_nis()) attempting to recover local ni: 10.47.1.195@o2ib1 00000400:00000010:5.0:1631581095.150507:0:6010:0:(lib-move.c:3078:lnet_recover_local_nis()) alloc '(ev_info)': 16 at ffff89162bbd2e60 (tot 84625532). 00000400:00000010:5.0:1631581095.150510:0:6010:0:(api-ni.c:1491:lnet_ping_buffer_alloc()) alloc '(pbuf)': 280 at ffff89163c0a8a00 (tot 84625812). 00000400:00000010:5.0:1631581095.150513:0:6010:0:(lib-lnet.h:239:lnet_md_alloc()) slab-alloced 'md' of size 136 at ffff891624a5a880. 00000400:00000010:5.0:1631581095.150516:0:6010:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff89163c0a9a00 (tot 84626252). 00000400:00000010:5.0:1631581095.150519:0:6010:0:(lib-lnet.h:507:lnet_rspt_alloc()) alloc '(rspt)': 48 at ffff891636d10000 (tot 84626300). 00000400:00000200:5.0:1631581095.150524:0:6010:0:(lib-move.c:4911:LNetGet()) LNetGet -> 12345-10.47.1.195@o2ib1 00000400:00000200:5.0:1631581095.150530:0:6010:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source ANY to NMR: 10.47.1.195@o2ib1 local destination 00000400:00000200:5.0:1631581095.150536:0:6010:0:(lib-move.c:1744:lnet_handle_send()) rspt_next_hop_nid = 10.47.1.195@o2ib1 00000400:00000200:5.0:1631581095.150546:0:6010:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : GET try# 0 00000800:00000200:5.0:1631581095.150553:0:6010:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 0 bytes in 0 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:5.0:1631581095.150560:0:6010:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:5.0:1631581095.150564:0:6010:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff891636de4a00] (130)++ 00000800:00000200:5.0:1631581095.150566:0:6010:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff891636de4a00] (131)++ 00000800:00000200:5.0:1631581095.150578:0:6010:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:22.1:1631581095.150634:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (130)++ 00000800:00000200:22.1:1631581095.150642:0:813:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (131)++ 00000800:00000200:3.0:1631581095.150697:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581095.150702:0:5978:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:27.0:1631581095.150705:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (132)++ 00000400:00000200:3.0:1631581095.150705:0:5978:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : GET - for me 00000400:00000010:3.0:1631581095.150706:0:5978:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff88e6093af800 (tot 84626740). 00000400:00000200:3.0:1631581095.150709:0:5978:0:(lib-ptl.c:571:lnet_ptl_match_md()) Request from 12345-10.47.1.195@o2ib1 of length 272 into portal 0 MB=0x8000000000000000 00000800:00000200:27.0:1631581095.150710:0:5979:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff891636de4a00] (133)-- 00000400:00000200:27.0:1631581095.150711:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000200:3.0:1631581095.150711:0:5978:0:(lib-ptl.c:200:lnet_try_match_md()) Incoming get index 0 from 12345-10.47.1.195@o2ib1 of length 48/272 into md 0x1 [1] + 0 00000800:00000200:3.0:1631581095.150713:0:5978:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581095.150714:0:5978:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff88e705da5200] (133)-- 00000400:00000200:3.0:1631581095.150723:0:5978:0:(lib-move.c:2484:lnet_handle_send_case_locked()) Source Specified: 10.47.1.195@o2ib1 to MR: 10.47.1.195@o2ib1 local destination 00000400:00000200:27.0:1631581095.150725:0:5979:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: GET: OK 00000400:00000200:27.0:1631581095.150726:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 5 status: 0 00000400:00000200:27.0:1631581095.150727:0:5979:0:(lib-move.c:3623:lnet_mt_event_handler()) 10.47.1.195@o2ib1 recovery message sent successfully:0 00000400:00000200:3.0:1631581095.150728:0:5978:0:(lib-move.c:1758:lnet_handle_send()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) -> 10.47.1.195@o2ib1(10.47.1.195@o2ib1:10.47.1.195@o2ib1) : REPLY try# 0 00000400:00000010:27.0:1631581095.150730:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff89163c0a9a00 (tot 84626300). 00000800:00000200:3.0:1631581095.150730:0:5978:0:(o2iblnd_cb.c:1683:kiblnd_send()) sending 48 bytes in 1 frags to 12345-10.47.1.195@o2ib1 00000800:00000200:27.0:1631581095.150731:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581095.150732:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:27.0:1631581095.150732:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- 00000800:00000200:3.0:1631581095.150733:0:5978:0:(o2iblnd.c:405:kiblnd_find_peer_locked()) got peer_ni [ffff89163819df00] -> 10.47.1.195@o2ib1 (3) version: 12 00000800:00000200:3.0:1631581095.150734:0:5978:0:(o2iblnd_cb.c:1563:kiblnd_launch_tx()) conn[ffff88e705da5200] (131)++ 00000800:00000200:3.0:1631581095.150734:0:5978:0:(o2iblnd_cb.c:1336:kiblnd_queue_tx_locked()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581095.150756:0:5978:0:(o2iblnd_cb.c:1569:kiblnd_launch_tx()) conn[ffff88e705da5200] (133)-- 00000800:00000200:3.0:1631581095.150757:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000800:00000200:22.1:1631581095.150764:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff891636de4a00] (130)++ 00000800:00000200:22.1:1631581095.150768:0:123:0:(o2iblnd_cb.c:3769:kiblnd_cq_completion()) conn[ffff88e705da5200] (131)++ 00000800:00000200:27.0:1631581095.150773:0:5979:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581095.150784:0:5979:0:(o2iblnd_cb.c:343:kiblnd_handle_rx()) Received d1[1] from 10.47.1.195@o2ib1 00000800:00000200:3.0:1631581095.150784:0:5978:0:(o2iblnd_cb.c:3891:kiblnd_scheduler()) conn[ffff88e705da5200] (132)++ 00000800:00000200:3.0:1631581095.150786:0:5978:0:(o2iblnd_cb.c:75:kiblnd_tx_done()) conn[ffff88e705da5200] (133)-- 00000800:00000200:31.0:1631581095.150787:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (132)-- 00000400:00000200:27.0:1631581095.150787:0:5979:0:(lib-move.c:4196:lnet_parse()) TRACE: 10.47.1.195@o2ib1(10.47.1.195@o2ib1) <- 10.47.1.195@o2ib1 : REPLY - for me 00000400:00000200:3.0:1631581095.150787:0:5978:0:(lib-msg.c:918:lnet_is_health_check()) health check = 1, status = 0, hstatus = 0 00000400:00000010:27.0:1631581095.150788:0:5979:0:(lib-lnet.h:490:lnet_msg_alloc()) alloc '(msg)': 440 at ffff8916391a7800 (tot 84626740). 00000800:00000200:31.0:1631581095.150789:0:5981:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (132)-- 00000400:00000200:3.0:1631581095.150789:0:5978:0:(lib-msg.c:803:lnet_health_check()) health check: 10.47.1.195@o2ib1->10.47.1.195@o2ib1: REPLY: OK 00000400:00000200:27.0:1631581095.150791:0:5979:0:(lib-move.c:3963:lnet_parse_reply()) 10.47.1.195@o2ib1: Reply from 12345-10.47.1.195@o2ib1 of length 48/48 into md 0x66bd 00000400:00000010:3.0:1631581095.150791:0:5978:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff88e6093af800 (tot 84626300). 00000400:00000200:27.0:1631581095.150792:0:5979:0:(lib-msg.c:918:lnet_is_health_check()) health check = 0, status = 0, hstatus = 0 00000800:00000200:3.0:1631581095.150792:0:5978:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff88e705da5200] (131)-- 00000400:00000200:27.0:1631581095.150793:0:5979:0:(lib-move.c:3609:lnet_mt_event_handler()) Received event: 3 status: 0 00000400:00000010:27.0:1631581095.150794:0:5979:0:(lib-move.c:3630:lnet_mt_event_handler()) kfreed 'ev_info': 16 at ffff89162bbd2e60 (tot 84626284). 00000400:00000010:27.0:1631581095.150795:0:5979:0:(api-ni.c:1504:lnet_ping_buffer_free()) kfreed 'pbuf': 280 at ffff89163c0a8a00 (tot 84626004). 00000400:00000200:27.0:1631581095.150795:0:5979:0:(lib-md.c:69:lnet_md_unlink()) Unlinking md ffff891624a5a880 00000400:00000010:27.0:1631581095.150796:0:5979:0:(lib-lnet.h:270:lnet_md_free()) slab-freed 'md' at ffff891624a5a880. 00000400:00000010:27.0:1631581095.150797:0:5979:0:(lib-lnet.h:500:lnet_msg_free()) kfreed 'msg': 440 at ffff8916391a7800 (tot 84625564). 00000800:00000200:27.0:1631581095.150798:0:5979:0:(o2iblnd_cb.c:205:kiblnd_post_rx()) conn[ffff891636de4a00] (131)++ 00000800:00000200:27.0:1631581095.150799:0:5979:0:(o2iblnd_cb.c:239:kiblnd_post_rx()) conn[ffff891636de4a00] (132)-- 00000800:00000200:27.0:1631581095.150800:0:5979:0:(o2iblnd_cb.c:3907:kiblnd_scheduler()) conn[ffff891636de4a00] (131)-- Debug log: 1373 lines, 1373 kept, 0 dropped, 0 bad.