== sanity-lnet test 233: Check for successful resends ==== 12:27:25 (1756312045) Cleaning up LNet 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: 'oleg413-server' oleg413-server: oleg413-server.virtnet: executing unload_modules_local oleg413-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy oleg413-server: LNET unconfigure error 22: Invalid argument oleg413-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 1034: echo: write error: Device or resource busy /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1035: 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 oleg413-server: Writer error: failed to resolve Netlink family id oleg413-server: opening /dev/lnet failed: No such file or directory oleg413-server: hint: the kernel modules may not be loaded oleg413-server: IOC_LIBCFS_GET_NI error 2: No such file or directory pdsh@oleg413-client: oleg413-server: ssh exited with exit code 1 oleg413-server: oleg413-server.virtnet: executing load_lnet oleg413-server: Loading modules from /home/green/git/lustre-release/lustre oleg413-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1034: echo: write error: Device or resource busy oleg413-server: /home/green/git/lustre-release/lustre/tests/test-framework.sh: line 1035: echo: write error: Device or resource busy oleg413-server: detected 4 online CPUs by sysfs oleg413-server: MODOPTS_LIBCFS= oleg413-server: Force libcfs to create 2 CPU partitions /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover 192.168.204.113@tcp discover: - primary nid: 192.168.204.113@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.113@tcp oleg413-server: oleg413-server.virtnet: executing lnet_if_list oleg413-server: oleg413-server.virtnet: executing /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net add --net tcp1 --if ens2 oleg413-server: default via 192.168.204.254 dev ens2 192.168.204.0/24 dev ens2 proto kernel scope link src 192.168.204.113 oleg413-server: default via 192.168.204.254 dev ens2 192.168.204.0/24 dev ens2 proto kernel scope link src 192.168.204.113 /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 192.168.204.13 default via 192.168.204.254 dev ens2 192.168.204.0/24 dev ens2 proto kernel scope link src 192.168.204.13 net: - net type: lo local NI(s): - nid: 0@lo status: up - net type: tcp local NI(s): - nid: 192.168.204.13@tcp status: up interfaces: 0: ens2 - net type: tcp1 local NI(s): - nid: 192.168.204.13@tcp1 status: up interfaces: 0: ens2 - primary nid: 192.168.204.113@tcp - nid: 192.168.204.113@tcp health stats: health value: 1000 - nid: 192.168.204.113@tcp1 health stats: health value: 1000 debug=+net Simulate intermittent local_interrupt /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp1 -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp1 -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp1 -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp1 -m GET -e local_interrupt -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping --source 192.168.204.13@tcp 192.168.204.113@tcp ping: - primary nid: 192.168.204.113@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.113@tcp - nid: 192.168.204.113@tcp1 /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 Check for 1 successful resend Simulate intermittent local_dropped /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp1 -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp1 -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp1 -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp1 -m GET -e local_dropped -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping --source 192.168.204.13@tcp 192.168.204.113@tcp ping: - primary nid: 192.168.204.113@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.113@tcp - nid: 192.168.204.113@tcp1 /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 Check for 1 successful resend Simulate intermittent local_aborted /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp1 -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp1 -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp1 -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp1 -m GET -e local_aborted -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping --source 192.168.204.13@tcp 192.168.204.113@tcp ping: - primary nid: 192.168.204.113@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.113@tcp - nid: 192.168.204.113@tcp1 /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 Check for 1 successful resend Simulate intermittent local_no_route /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp1 -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp1 -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp1 -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp1 -m GET -e local_no_route -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping --source 192.168.204.13@tcp 192.168.204.113@tcp ping: - primary nid: 192.168.204.113@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.113@tcp - nid: 192.168.204.113@tcp1 /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 Check for 1 successful resend Simulate intermittent local_timeout /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp1 -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp1 -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp1 -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp1 -m GET -e local_timeout -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping --source 192.168.204.13@tcp 192.168.204.113@tcp ping: - primary nid: 192.168.204.113@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.113@tcp - nid: 192.168.204.113@tcp1 /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 Check for 1 successful resend Simulate intermittent remote_dropped /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp -d 192.168.204.113@tcp1 -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl fault drop add -s 192.168.204.13@tcp -d 192.168.204.13@tcp1 -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.113@tcp1 -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/utils/lctl net_drop add -s 192.168.204.13@tcp1 -d 192.168.204.13@tcp1 -m GET -e remote_dropped -r 2 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl ping --source 192.168.204.13@tcp 192.168.204.113@tcp ping: - primary nid: 192.168.204.113@tcp Multi-Rail: true peer_ni: - nid: 192.168.204.113@tcp - nid: 192.168.204.113@tcp1 /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 Check for 1 successful resend oleg413-server: oleg413-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: 'oleg413-server' oleg413-server: oleg413-server.virtnet: executing unload_modules_local oleg413-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy oleg413-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 156: echo: write error: Device or resource busy modules unloaded. oleg413-server: oleg413-server.virtnet: executing unload_modules_local oleg413-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 114: echo: write error: Device or resource busy oleg413-server: LNET unconfigure error 22: Invalid argument oleg413-server: /home/green/git/lustre-release/lustre/scripts/lustre_rmmod: line 156: echo: write error: Device or resource busy pdsh@oleg413-client: oleg413-client: ssh exited with exit code 2 pdsh@oleg413-client: oleg413-server: ssh exited with exit code 2 pdsh@oleg413-client: oleg413-client: ssh exited with exit code 2 pdsh@oleg413-client: oleg413-server: ssh exited with exit code 2