他的回复:
请问楼主问题解决了吗?我近期也遇到了类似的问题。 具体情况是:器群含多台主机,安装的是OpenMPI 4.0.3,操作系统是CentOS7.3.1611.网卡都是CX5网卡。主从节点是通过NFS共享相关文件。SSH互信已经配好,且没问题。环境变量也已同步。 问题是: 当主节点通过mpirun访问某一特定从节点的时候报错(添加-x PATH=$PATH -x LD_LIBRARY_PATH=$LD_LIBRARY_PATH也报错): [s77-3:19940] [[63847,0],0] ORTE_ERROR_LOG: Error in file base/plm_base_launch_support.c at line 1200 -------------------------------------------------------------------------- ORTE was unable to reliably start one or more daemons. This usually is caused by: (中间和楼主截图中内容一致,在此省去) * an inability to create a connection back to mpirun due to a lack of common network interfaces and/or no route found between them. Please check network connectivity (including firewalls and network routing requirements). 当主从节点互换后运行mpirun没问题;主节点访问其他从节点也都没问题。 目前猜测问题和“lack of authority to execute on one or more specified nodes. Please verify your allocation and authorities.”有关。 求助专家给予解答~