参考:
https://blog.csdn.net/asdfaa/article/details/137884414
检查系统是否支持 IPv6,查看被禁用了
在启用 IPv6 之前,首先要确保您的系统支持 IPv6。要检查内核是否启用了 IPv6,可以运行以下命令:
cat /proc/sys/net/ipv6/conf/all/disable_ipv6
如果返回的结果为 0,则说明您的系统支持 IPv6。如果结果为 1,您需要启用 IPv6,然后重新检查。
检查下面两个服务。opensmd 没有启动,直接启动,然后用ibstat命令
systemctl status opensmd
systemctl status openibd
ibstat
cat /proc/sys/net/ipv6/conf/all/disable_ipv6
echo 1 >/proc/sys/net/ipv6/conf/all/disable_ipv6
一开始端口是down, 现在是active,然后就可以用了
root@gpumcw2:/home/mcw# ibstat CA 'mlx5_0' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cc36c System image GUID: 0x946dae03009cc36c Port 1: State: Initializing Physical state: LinkUp Rate: 200 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae03009cc36c Link layer: InfiniBand CA 'mlx5_1' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cc364 System image GUID: 0x946dae03009cc364 Port 1: State: Initializing Physical state: LinkUp Rate: 200 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae03009cc364 Link layer: InfiniBand CA 'mlx5_2' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae0300b00278 System image GUID: 0x946dae0300b00278 Port 1: State: Down Physical state: Polling Rate: 10 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae0300b00278 Link layer: InfiniBand CA 'mlx5_3' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae0300b00279 System image GUID: 0x946dae0300b00278 Port 1: State: Down Physical state: Polling Rate: 10 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae0300b00279 Link layer: InfiniBand CA 'mlx5_4' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cc374 System image GUID: 0x946dae03009cc374 Port 1: State: Initializing Physical state: LinkUp Rate: 200 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae03009cc374 Link layer: InfiniBand CA 'mlx5_5' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cef04 System image GUID: 0x946dae03009cef04 Port 1: State: Initializing Physical state: LinkUp Rate: 200 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae03009cef04 Link layer: InfiniBand root@gpumcw2:/home/mcw#
root@gpumcw2:/home/mcw# ibstat CA 'mlx5_0' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cc36c System image GUID: 0x946dae03009cc36c Port 1: State: Active Physical state: LinkUp Rate: 200 Base lid: 2 LMC: 0 SM lid: 2 Capability mask: 0xa651e84a Port GUID: 0x946dae03009cc36c Link layer: InfiniBand CA 'mlx5_1' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cc364 System image GUID: 0x946dae03009cc364 Port 1: State: Active Physical state: LinkUp Rate: 200 Base lid: 16 LMC: 0 SM lid: 2 Capability mask: 0xa651e848 Port GUID: 0x946dae03009cc364 Link layer: InfiniBand CA 'mlx5_2' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae0300b00278 System image GUID: 0x946dae0300b00278 Port 1: State: Down Physical state: Polling Rate: 10 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae0300b00278 Link layer: InfiniBand CA 'mlx5_3' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae0300b00279 System image GUID: 0x946dae0300b00278 Port 1: State: Down Physical state: Polling Rate: 10 Base lid: 65535 LMC: 0 SM lid: 0 Capability mask: 0xa651e848 Port GUID: 0x946dae0300b00279 Link layer: InfiniBand CA 'mlx5_4' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cc374 System image GUID: 0x946dae03009cc374 Port 1: State: Active Physical state: LinkUp Rate: 200 Base lid: 20 LMC: 0 SM lid: 2 Capability mask: 0xa651e848 Port GUID: 0x946dae03009cc374 Link layer: InfiniBand CA 'mlx5_5' CA type: MT4123 Number of ports: 1 Firmware version: 20.38.1002 Hardware version: 0 Node GUID: 0x946dae03009cef04 System image GUID: 0x946dae03009cef04 Port 1: State: Active Physical state: LinkUp Rate: 200 Base lid: 5 LMC: 0 SM lid: 2 Capability mask: 0xa651e848 Port GUID: 0x946dae03009cef04 Link layer: InfiniBand root@gpumcw2:/home/mcw#
另外一个机器上指定接口去ping没有用ipv6的这个接口的IP
root@gpumcw2:/home/mcw# ifconfig ibs13 ibs13: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 2044 inet 10.xx.xx.8 netmask 255.255.255.0 broadcast 10.110.10.255 inet6 fe80::966d:ae03:9c:c36c prefixlen 64 scopeid 0x20<link> unspec 00-00-08-0D-FE-80-00-00-00-00-00-00-00-00-00-00 txqueuelen 256 (UNSPEC) RX packets 2146 bytes 379613 (379.6 KB) RX errors 0 dropped 0 overruns 0 frame 0 TX packets 2151 bytes 278364 (278.3 KB) TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0 root@gpumcw2:/home/mcw# root@gpumcw2:/home/mcw# ping -I ibs13 10.xx.xx.8 PING 10.xx.xx.8 (10.xx.xx.8) from 10.110.10.1 ibs13: 56(84) bytes of data. 64 bytes from 10.xx.xx.8: icmp_seq=1 ttl=64 time=0.324 ms 64 bytes from 10.xx.xx.8: icmp_seq=2 ttl=64 time=0.103 ms ^C --- 10.xx.xx.8 ping statistics --- 2 packets transmitted, 2 received, 0% packet loss, time 1032ms rtt min/avg/max/mdev = 0.103/0.213/0.324/0.110 ms root@gpumcw2:/home/mcw#
没好之前lo状态
好了之后状态
标签:lid,InfiniBand,CA,开启,version,ipv6,gpu,GUID,Port From: https://www.cnblogs.com/machangwei-8/p/18162336