== sanity-lnet test 206: Check no health or resends for single-rail remote failures ========================================================== 22:20:41 (1788834041) Cleaning up LNet LNET unconfigure error 22: Invalid argument unloading modules via unload_modules_local on: 'oleg412-server' oleg412-server: oleg412-server.virtnet: executing unload_modules_local oleg412-server: kmemleak disabled oleg412-server: LNET unconfigure error 22: Invalid argument modules unloaded. 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' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet configure -a oleg412-server: Writer error: failed to resolve Netlink family id oleg412-server: opening /dev/lnet failed: No such file or directory oleg412-server: hint: the kernel modules may not be loaded oleg412-server: IOC_LIBCFS_GET_NI error 2: No such file or directory pdsh@oleg412-client: oleg412-server: ssh exited with exit code 1 oleg412-server: oleg412-server.virtnet: executing load_lnet oleg412-server: kmemleak disabled oleg412-server: Loading modules from /home/green/git/lustre-release/lustre oleg412-server: detected 4 online CPUs by sysfs oleg412-server: MODOPTS_LIBCFS= oleg412-server: Force libcfs to create 2 CPU partitions /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover 192.168.204.112@tcp discover: - primary nid: 192.168.204.112@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.112@tcp net: - net type: lo local NI(s): - nid: 0@lo status: up - net type: tcp local NI(s): - nid: 192.168.204.12@tcp status: up interfaces: 0: ens2 - primary nid: 192.168.204.112@tcp - nid: 192.168.204.112@tcp health stats: health value: 1000 debug=+net Simulate remote_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.12@tcp -d 192.168.204.112@tcp -m GET -e remote_dropped -r 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.12@tcp -d 192.168.204.12@tcp -m GET -e remote_dropped -r 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping 192.168.204.112@tcp manage: - ping: errno: -5 descr: ! 'failed to ping 192.168.204.112@tcp: Input/output error' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set numa_range 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set max_interfaces 4096 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set discovery 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set drop_asym_route 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set retry_count 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set transaction_timeout 150 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set health_sensitivity 100 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_interval 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set router_sensitivity 100 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set response_tracking 3 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_limit 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set max_recovery_ping_interval 900 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --health 1000 --all /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net set --health 1000 --all /home/green/git/lustre-release/lustre/utils/lctl net_drop del -a Check that no resends took place Check that local NI health is unchanged Check that remote NI health is unchanged Simulate remote_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.12@tcp -d 192.168.204.112@tcp -m GET -e remote_error -r 1 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.12@tcp -d 192.168.204.12@tcp -m GET -e remote_error -r 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping 192.168.204.112@tcp manage: - ping: errno: -5 descr: ! 'failed to ping 192.168.204.112@tcp: Input/output error' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set numa_range 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set max_interfaces 4096 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set discovery 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set drop_asym_route 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set retry_count 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set transaction_timeout 150 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set health_sensitivity 100 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_interval 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set router_sensitivity 100 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set response_tracking 3 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_limit 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set max_recovery_ping_interval 900 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --health 1000 --all /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net set --health 1000 --all /home/green/git/lustre-release/lustre/utils/lctl net_drop del -a Check that no resends took place Check that local NI health is unchanged Check that remote NI health is unchanged Simulate remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.12@tcp -d 192.168.204.112@tcp -m GET -e remote_timeout -r 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.12@tcp -d 192.168.204.12@tcp -m GET -e remote_timeout -r 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping 192.168.204.112@tcp manage: - ping: errno: -5 descr: ! 'failed to ping 192.168.204.112@tcp: Input/output error' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set numa_range 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set max_interfaces 4096 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set discovery 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set drop_asym_route 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set retry_count 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set transaction_timeout 150 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set health_sensitivity 100 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_interval 1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set router_sensitivity 100 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set response_tracking 3 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_limit 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set max_recovery_ping_interval 900 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --health 1000 --all /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net set --health 1000 --all /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop del -a Check that no resends took place Check that local NI health is unchanged Check that remote NI health is unchanged Writer error: failed to resolve Netlink family id unloading modules via unload_modules_local on: 'oleg412-server' oleg412-server: oleg412-server.virtnet: executing unload_modules_local oleg412-server: kmemleak disabled modules unloaded. oleg412-server: oleg412-server.virtnet: executing unload_modules_local oleg412-server: kmemleak disabled oleg412-server: LNET unconfigure error 22: Invalid argument pdsh@oleg412-client: oleg412-client: ssh exited with exit code 2 pdsh@oleg412-client: oleg412-server: ssh exited with exit code 2 pdsh@oleg412-client: oleg412-server: ssh exited with exit code 2 pdsh@oleg412-client: oleg412-client: ssh exited with exit code 2