== sanity-lnet test 212: Check discovery refcount loss bug (LU-14627) ========================================================== 23:33:55 (1783136035) Cleaning up LNet Writer error: failed to resolve Netlink family id unloading modules via unload_modules_local on: 'oleg123-server' oleg123-server: oleg123-server.virtnet: executing unload_modules_local oleg123-server: oleg123-server: LNET unconfigure error 22: Invalid argument modules unloaded. /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1048: echo: write error: Device or resource busy Loading modules from /home/green/git/lustre-release/lustre detected 4 online CPUs by sysfs MODOPTS_LIBCFS= Force libcfs to create 2 CPU partitions ../libcfs/libcfs/libcfs options: 'cpu_npartitions=2' error: set_param: setting /sys/kernel/debug/lnet/subsystem_debug=+neterror +net +nettrace +malloc: Invalid argument error: set_param: setting 'subsystem_debug'='+neterror +net +nettrace +malloc': Invalid argument /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet configure -a oleg123-server: Writer error: failed to resolve Netlink family id oleg123-server: opening /dev/lnet failed: No such file or directory oleg123-server: hint: the kernel modules may not be loaded oleg123-server: IOC_LIBCFS_GET_NI error 2: No such file or directory pdsh@oleg123-client: oleg123-server: ssh exited with exit code 1 oleg123-server: oleg123-server.virtnet: executing load_lnet oleg123-server: Loading modules from /home/green/git/lustre-release/lustre oleg123-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1048: echo: write error: Device or resource busy oleg123-server: detected 4 online CPUs by sysfs oleg123-server: MODOPTS_LIBCFS= oleg123-server: Force libcfs to create 2 CPU partitions Initial discovery /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover --force 192.168.201.123@tcp discover: - primary nid: 192.168.201.123@tcp Multi-Rail: true peer_ni: - nid: 192.168.201.123@tcp discover: - primary nid: 192.168.201.23@tcp Multi-Rail: true peer_ni: - nid: 192.168.201.23@tcp Fail local discover ping to set LNET_PEER_REDISCOVER flag /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s *@tcp -d *@tcp -r 1 -e local_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover --force 192.168.201.123@tcp manage: - discover: errno: -5 descr: ! 'failed to discover 192.168.201.123@tcp: Input/output error' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop del -a /home/green/git/lustre-release/lustre/utils/lctl net_delay add -s *@tcp -d 192.168.201.123@tcp -r 1 -m GET -l 3 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s *@tcp -d 192.168.201.123@tcp -r 1 -m GET -e local_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault delay add -s *@tcp -d 192.168.201.123@tcp -r 1 -m PUT -l 6 Force oleg123-client.virtnet to discover 192.168.201.123@tcp (in background) Force oleg123-server to discover 192.168.201.23@tcp /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover --force 192.168.201.123@tcp discover: - primary nid: 192.168.201.23@tcp Multi-Rail: true peer_ni: - nid: 192.168.201.23@tcp Wait for 69441 manage: - discover: errno: -5 descr: ! 'failed to discover 192.168.201.123@tcp: Input/output error' Finished wait on 69441 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault delay del -a /home/green/git/lustre-release/lustre/utils/lctl net_drop del -a Writer error: failed to resolve Netlink family id unloading modules via unload_modules_local on: 'oleg123-server' oleg123-server: oleg123-server.virtnet: executing unload_modules_local oleg123-server: modules unloaded. oleg123-server: oleg123-server.virtnet: executing unload_modules_local oleg123-server: oleg123-server: LNET unconfigure error 22: Invalid argument pdsh@oleg123-client: oleg123-server: ssh exited with exit code 2 pdsh@oleg123-client: oleg123-client: ssh exited with exit code 2 pdsh@oleg123-client: oleg123-client: ssh exited with exit code 2 pdsh@oleg123-client: oleg123-server: ssh exited with exit code 2