== sanity-lnet test 211: Remote NI recovery checks ======= 22:58:15 (1735099095) /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet unconfigure /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet configure /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net add --net tcp --if eth0 default via 192.168.202.254 dev eth0 192.168.202.0/24 dev eth0 proto kernel scope link src 192.168.202.47 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net add --net tcp1 --if eth0 default via 192.168.202.254 dev eth0 192.168.202.0/24 dev eth0 proto kernel scope link src 192.168.202.47 default via 192.168.202.254 dev eth0 192.168.202.0/24 dev eth0 proto kernel scope link src 192.168.202.47 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover 192.168.202.47@tcp discover: - primary nid: 192.168.202.47@tcp Multi-Rail: true peer_ni: - nid: 192.168.202.47@tcp - nid: 192.168.202.47@tcp1 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_limit 10 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --nid 192.168.202.47@tcp --health 0 -p recovery queue should have 192.168.202.47@tcp /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl debug recovery -p Peer NI recovery: nid-0: 192.168.202.47@tcp -p recovery queue should be empty Waiting 20s for '0' Updated after 16s: want '0' got '0' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl debug recovery -p Check ping counts: - nid: 192.168.202.47@tcp ping_count: 0 - nid: 192.168.202.47@tcp1 ping_count: 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set recovery_limit 0 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --nid 192.168.202.47@tcp --health 500 -p recovery queue should have 192.168.202.47@tcp /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl debug recovery -p Peer NI recovery: nid-0: 192.168.202.47@tcp -p recovery queue should be empty Waiting 20s for '0' Updated after 6s: want '0' got '0' /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl debug recovery -p /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet unconfigure /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl lnet configure /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net add --net tcp --if eth0 default via 192.168.202.254 dev eth0 192.168.202.0/24 dev eth0 proto kernel scope link src 192.168.202.47 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl net add --net tcp1 --if eth0 default via 192.168.202.254 dev eth0 192.168.202.0/24 dev eth0 proto kernel scope link src 192.168.202.47 default via 192.168.202.254 dev eth0 192.168.202.0/24 dev eth0 proto kernel scope link src 192.168.202.47 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl discover 192.168.202.47@tcp discover: - primary nid: 192.168.202.47@tcp Multi-Rail: true peer_ni: - nid: 192.168.202.47@tcp - nid: 192.168.202.47@tcp1 /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 4 /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl peer set --nid 192.168.202.47@tcp --health 0 Check ping counts: Waiting 4s for '1' - nid: 192.168.202.47@tcp ping_count: 1 - nid: 192.168.202.47@tcp1 ping_count: 0 -p recovery queue should have 192.168.202.47@tcp /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl debug recovery -p Peer NI recovery: nid-0: 192.168.202.47@tcp Check ping counts: Waiting 14s for '4' Waiting 4s for '4' Updated after 11s: want '4' got '4' - nid: 192.168.202.47@tcp ping_count: 4 - nid: 192.168.202.47@tcp1 ping_count: 0 -p recovery queue should have 192.168.202.47@tcp /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl debug recovery -p Peer NI recovery: nid-0: 192.168.202.47@tcp /home/green/git/lustre-release/lustre/../lnet/utils/lnetctl set max_recovery_ping_interval 900 pdsh@oleg247-client: oleg247-server: ssh exited with exit code 2 pdsh@oleg247-client: oleg247-server: ssh exited with exit code 2