MPI跨节点运行：Fatal error in PMPI_Barrier: Unknown error class, error stack:

 问题：

在运行跨节点的MPI程序时，在没有使用同步函数（MPI_Barrier()）时，程序可以正常运行，加入同步函数后，会出现下面的错误：

Fatal error in PMPI_Barrier: Unknown error class, error stack:
PMPI_Barrier(289).....................: MPI_Barrier(comm=MPI_COMM_WORLD) failed
PMPI_Barrier(275).....................: 
MPIR_Barrier_impl(175)................: 
MPIR_Barrier_intra_auto(110)..........: 
MPIR_Barrier_intra_smp(43)............: 
MPIR_Barrier_impl(175)................: 
MPIR_Barrier_intra_auto(110)..........: 
MPIR_Barrier_intra_dissemination(49)..: 
MPIDU_Complete_posted_with_error(1137): Process failed
MPIR_Barrier_intra_smp(59)............: 
MPIR_Bcast_impl(310)..................: 
MPIR_Bcast_intra_auto(223)............: 
MPIR_Bcast_intra_binomial(182)........: Failure during collective
Fatal error in PMPI_Barrier: Unknown error class, error stack:
PMPI_Barrier(289).............: MPI_Barrier(comm=MPI_COMM_WORLD) failed
PMPI_Barrier(275).............: 
MPIR_Barrier_impl(175)........: 
MPIR_Barrier_intra_auto(110)..: 
MPIR_Barrier_intra_smp(59)....: 
MPIR_Bcast_impl(310)..........: 
MPIR_Bcast_intra_auto(223)....: 
MPIR_Bcast_intra_binomial(182): Failure during collective
Fatal error in PMPI_Barrier: Unknown error class, error stack:
PMPI_Barrier(289).............: MPI_Barrier(comm=MPI_COMM_WORLD) failed
PMPI_Barrier(275).............: 
MPIR_Barrier_impl(175)........: 
MPIR_Barrier_intra_auto(110)..: 
MPIR_Barrier_intra_smp(59)....: 
MPIR_Bcast_impl(310)..........: 
MPIR_Bcast_intra_auto(223)....: 
MPIR_Bcast_intra_binomial(182): Failure during collective

解决：

1、使用的节点运行说明文件为：

node1:3
node2:3
node3:3

2、将运行说明文件的节点名，修改为IP地址时，程序正常运行

10.10.1.12:3
10.10.1.56:3
10.10.1.23:3

3、那么应该是host文件出现了问题：

127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4 node1
::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
10.10.1.12:node1
10.10.1.56:node2
10.10.1.23:node3

4、在host文件中，127.0.0.1 后面添加了node1，那么其他节点尝试连接node1时可能会连接到本地主机。将node1删除，其他节点出现类似情况也要进行修改，程序即可正常运行。

127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
10.10.1.12:node1
10.10.1.56:node2
10.10.1.23:node3