== sanity-lnet test 207: Check health and resends for multi-rail remote errors ========================================================== 12:21:50 (1752510110) Cleaning up LNet /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy LNET unconfigure error 22: Invalid argument /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 156: echo: write error: Device or resource busy unloading modules via unload_modules_local on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing unload_modules_local oleg424-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy oleg424-server: LNET unconfigure error 22: Invalid argument oleg424-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 156: echo: write error: Device or resource busy modules unloaded. /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1024: echo: write error: Device or resource busy /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1025: 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' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet configure -a oleg424-server: Writer error: failed to resolve Netlink family id oleg424-server: opening /dev/lnet failed: No such file or directory oleg424-server: hint: the kernel modules may not be loaded oleg424-server: IOC_LIBCFS_GET_NI error 2: No such file or directory pdsh@oleg424-client: oleg424-server: ssh exited with exit code 1 oleg424-server: oleg424-server.virtnet: executing load_lnet oleg424-server: Loading modules from /home/green/git/lustre-release/lustre oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1024: echo: write error: Device or resource busy oleg424-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1025: echo: write error: Device or resource busy oleg424-server: detected 4 online CPUs by sysfs oleg424-server: MODOPTS_LIBCFS= oleg424-server: Force libcfs to create 2 CPU partitions /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover 192.168.204.124@tcp discover: - primary nid: 192.168.204.124@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.124@tcp oleg424-server: oleg424-server.virtnet: executing lnet_if_list oleg424-server: oleg424-server.virtnet: executing /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net add --net tcp1 --if ens2 oleg424-server: default via 192.168.204.254 dev ens2 192.168.204.0/24 dev ens2 proto kernel scope link src 192.168.204.124 oleg424-server: default via 192.168.204.254 dev ens2 192.168.204.0/24 dev ens2 proto kernel scope link src 192.168.204.124 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet configure /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net add --net tcp1 --if ens2 default via 192.168.204.254 dev ens2 192.168.204.0/24 dev ens2 proto kernel scope link src 192.168.204.24 default via 192.168.204.254 dev ens2 192.168.204.0/24 dev ens2 proto kernel scope link src 192.168.204.24 net: - net type: lo local NI(s): - nid: 0@lo status: up - net type: tcp local NI(s): - nid: 192.168.204.24@tcp status: up interfaces: 0: ens2 - net type: tcp1 local NI(s): - nid: 192.168.204.24@tcp1 status: up interfaces: 0: ens2 - primary nid: 192.168.204.124@tcp - nid: 192.168.204.124@tcp health stats: health value: 1000 - nid: 192.168.204.124@tcp1 health stats: health value: 1000 debug=+net Simulate remote_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.124@tcp -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.124@tcp1 -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp -d 192.168.204.24@tcp -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp -d 192.168.204.24@tcp1 -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.124@tcp -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.124@tcp1 -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.24@tcp -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp1 -d 192.168.204.24@tcp1 -m GET -r 1 -e remote_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping 192.168.204.124@tcp manage: - ping: errno: -5 descr: ! 'failed to ping 192.168.204.124@tcp: Input/output error' /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 2 resends took place Check that local NI health is unchanged Check that remote NI health has been changed /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --health 1000 --all Simulate remote_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.124@tcp -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp -d 192.168.204.124@tcp1 -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.24@tcp -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.24@tcp1 -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.124@tcp -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.124@tcp1 -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp1 -d 192.168.204.24@tcp -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp1 -d 192.168.204.24@tcp1 -m GET -r 1 -e remote_error /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping 192.168.204.124@tcp manage: - ping: errno: -5 descr: ! 'failed to ping 192.168.204.124@tcp: Input/output error' /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 has been changed /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --health 1000 --all Simulate remote_timeout /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp -d 192.168.204.124@tcp -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.124@tcp1 -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.24@tcp -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp -d 192.168.204.24@tcp1 -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.124@tcp -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.124@tcp1 -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.24@tcp1 -d 192.168.204.24@tcp -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.24@tcp1 -d 192.168.204.24@tcp1 -m GET -r 1 -e remote_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping 192.168.204.124@tcp manage: - ping: errno: -5 descr: ! 'failed to ping 192.168.204.124@tcp: Input/output error' /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 has been changed /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --health 1000 --all oleg424-server: oleg424-server.virtnet: executing /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net del --net tcp1 --if ens2 Writer error: failed to resolve Netlink family id /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 156: echo: write error: Device or resource busy unloading modules via unload_modules_local on: 'oleg424-server' oleg424-server: oleg424-server.virtnet: executing unload_modules_local oleg424-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy oleg424-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 156: echo: write error: Device or resource busy modules unloaded. oleg424-server: oleg424-server.virtnet: executing unload_modules_local oleg424-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy oleg424-server: LNET unconfigure error 22: Invalid argument oleg424-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 156: echo: write error: Device or resource busy pdsh@oleg424-client: oleg424-client: ssh exited with exit code 2 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 2 pdsh@oleg424-client: oleg424-client: ssh exited with exit code 2 pdsh@oleg424-client: oleg424-server: ssh exited with exit code 2