OpenMPI设置集群环境
2016-08-17 08:48
288 查看
OpenMPI设置集群环境
安装准备
首先准备两个机器,比如 host1 和 host2,设置这两个机器可以互相免密钥登录(Linux SSH 免密码登录)修改两个机器的/etc/hosts文件,加入两个机器的信息,比如:
172.17.0.2 test1 172.17.0.3 test2
安装openmpi
下载
$ wget -c https://www.open-mpi.org/software/ompi/v1.10/downloads/openmpi-1.10.3.tar.gz[/code]安装
$ tar zxvf openmpi-1.10.3.tar.gz $ cd openmpi-1.10.3 $ ./configure --prefix=/opt/openmpi $ make $ sudo make install设置环境PATH和LD_LIBRARY_PATH
手动运行下面的命令$ export PATH=$PATH:/opt/openmpi/bin $ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/openmpi/lib/
并且将其写入~/.bashrc文件中,这样mpiexec在远程机器上运行的时候就会自动source环境了。PATH=$PATH:/opt/openmpi/bin LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/openmpi/lib/ export PATH LD_LIBRARY_PATH测试
$ cd examples (源代码目录) $ make $ mpirun -np 10 hello_c $ mpirun -np 10 ring_c $ mpirun -np 3 printenv在集群中运行mpi作业
首先创建一个集群机器列表,并指定每个机器的slots数,比如文件名hostfile,内如如下:test1 slots=2 test2 slots=2
运行mpi作业$ mpiexec --hostfile hosts -np 4 hello_c Hello, world, I am 1 of 4, (Open MPI v1.10.3, package: Open MPI jhadmin@test1 Distribution, ident: 1.10.3, repo rev: v1.10.2-251-g9acf492, Jun 14, 2016, 124) Hello, world, I am 0 of 4, (Open MPI v1.10.3, package: Open MPI jhadmin@test1 Distribution, ident: 1.10.3, repo rev: v1.10.2-251-g9acf492, Jun 14, 2016, 124) Hello, world, I am 2 of 4, (Open MPI v1.10.3, package: Open MPI jhadmin@test2 Distribution, ident: 1.10.3, repo rev: v1.10.2-251-g9acf492, Jun 14, 2016, 124) Hello, world, I am 3 of 4, (Open MPI v1.10.3, package: Open MPI jhadmin@test2 Distribution, ident: 1.10.3, repo rev: v1.10.2-251-g9acf492, Jun 14, 2016, 124)问题及说明
如果在运行命令“mpiexec –hostfile hosts -np 4 hello_c”出现下面错误的时候bash: orted: command not found -------------------------------------------------------------------------- ORTE was unable to reliably start one or more daemons. This usually is caused by: * not finding the required libraries and/or binaries on one or more nodes. Please check your PATH and LD_LIBRARY_PATH settings, or configure OMPI with --enable-orterun-prefix-by-default * lack of authority to execute on one or more specified nodes. Please verify your allocation and authorities. * the inability to write startup files into /tmp (--tmpdir/orte_tmpdir_base). Please check with your sys admin to determine the correct location to use. * compilation of the orted with dynamic libraries when static are required (e.g., on Cray). Please check your configure cmd line and consider using one of the contrib/platform definitions for your system type. * 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). --------------------------------------------------------------------------
可以使用下面命令来查看是不是环境变量没有设置对,开始我就是环境变量 PATH 和 LD_LIBRARY_PATH 设置有问题,才出现上面的错误。mpiexec --hostfile hosts -np 4 printenv
检查~/.bashrc文件,指定正确的路径即可。
转载请以链接形式标明本文链接
本文链接:http://blog.csdn.net/kongxx/article/details/52227572
相关文章推荐
- Hadoop集群_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- VMWare虚拟机环境下的Linux服务器集群 - 使用LVS+Heartbeat+Ldirectord (1)VMWare虚拟机设置
- Hadoop集群_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群 -Eclipse开发环境设置
- 集群环境ssh免密码登录设置
- Hadoop集群_2_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- 集群环境ssh免密码登录设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Hadoop集群(第7期)_Eclipse开发环境设置
- Ubuntu系统下的Hadoop集群(7)_设置Linux环境变量的方法和区别
- hadoop2.6.2集群环境搭建在经过几天的环境搭建,终于搭建成功,其中对于hadoop的具体设置倒是没有碰到很多问题,反而在hadoop各节点之间的通信遇到了问题,而且还反复了很多遍,光虚拟机就重