我正在尝试运行一个简单的 MPI 程序(多个数组加法),它在我的 PC 中完美运行,但只是挂起或在集群中显示以下错误。
我正在使用 open mpi 和以下命令来执行
集群网络配置(主节点1)
MASTER
eth0 Link encap:Ethernet HWaddr 00:22:19:A4:52:74
inet addr:10.1.1.1 Bcast:10.1.255.255 Mask:255.255.0.0
inet6 addr: fe80::222:19ff:fea4:5274/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:16914 errors:0 dropped:0 overruns:0 frame:0
TX packets:7183 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:2050581 (1.9 MiB) TX bytes:981632 (958.6 KiB)
eth1 Link encap:Ethernet HWaddr 00:22:19:A4:52:76
inet addr:192.168.41.203 Bcast:192.168.41.255 Mask:255.255.255.0
inet6 addr: fe80::222:19ff:fea4:5276/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:701 errors:0 dropped:0 overruns:0 frame:0
TX packets:228 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:75457 (73.6 KiB) TX bytes:25295 (24.7 KiB)
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:88362 errors:0 dropped:0 overruns:0 frame:0
TX packets:88362 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:21529504 (20.5 MiB) TX bytes:21529504 (20.5 MiB)
peth0 Link encap:Ethernet HWaddr 00:22:19:A4:52:74
inet6 addr: fe80::222:19ff:fea4:5274/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:17175 errors:0 dropped:0 overruns:0 frame:0
TX packets:7257 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:2373869 (2.2 MiB) TX bytes:1020320 (996.4 KiB)
Interrupt:16 Memory:da000000-da012800
peth1 Link encap:Ethernet HWaddr 00:22:19:A4:52:76
inet6 addr: fe80::222:19ff:fea4:5276/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:1112 errors:0 dropped:0 overruns:0 frame:0
TX packets:302 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:168837 (164.8 KiB) TX bytes:33241 (32.4 KiB)
Interrupt:16 Memory:d6000000-d6012800
virbr0 Link encap:Ethernet HWaddr 52:54:00:E3:80:BC
inet addr:192.168.122.1 Bcast:192.168.122.255 Mask:255.255.255.0
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
NODE 1
eth0 Link encap:Ethernet HWaddr 00:22:19:53:42:C6
inet addr:10.1.255.253 Bcast:10.1.255.255 Mask:255.255.0.0
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:16559 errors:0 dropped:0 overruns:0 frame:0
TX packets:7299 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:1898811 (1.8 MiB) TX bytes:1056294 (1.0 MiB)
lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:25 errors:0 dropped:0 overruns:0 frame:0
TX packets:25 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:3114 (3.0 KiB) TX bytes:3114 (3.0 KiB)
peth0 Link encap:Ethernet HWaddr 00:22:19:53:42:C6
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:16913 errors:0 dropped:0 overruns:0 frame:0
TX packets:7276 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:2221627 (2.1 MiB) TX bytes:1076708 (1.0 MiB)
Interrupt:16 Memory:f8000000-f8012800
virbr0 Link encap:Ethernet HWaddr 52:54:00:E7:E5:FF
inet addr:192.168.122.1 Bcast:192.168.122.255 Mask:255.255.255.0
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
Error
mpirun -machinefile machine -np 4 ./query
error code:
[[22877,1],0][btl_tcp_endpoint.c:638:mca_btl_tcp_endpoint_complete_connect] connect() to 192.168.122.1 failed: Connection refused (111)
Code
#include <mpi.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define group MPI_COMM_WORLD
#define root 0
#define size 100
int main(int argc,char *argv[])
{
int no_tasks,task_id,i;
MPI_Init(&argc,&argv);
MPI_Comm_size(group,&no_tasks);
MPI_Comm_rank(group,&task_id);
int arr1[size],arr2[size],local1[size],local2[size];
if(task_id==root)
{
for(i=0;i<size;i++)
{
arr1[i]=arr2[i]=i;
}
}
MPI_Scatter(arr1,size/no_tasks,MPI_INT,local1,size/no_tasks,MPI_INT,root,group);
MPI_Scatter(arr2,size/no_tasks,MPI_INT,local2,size/no_tasks,MPI_INT,root,group);
for(i=0;i<size/no_tasks;i++)
{
local1[i]+=local2[i];
}
MPI_Gather(local1,size/no_tasks,MPI_INT,arr1,size/no_tasks,MPI_INT,root,group);
if(task_id==root)
{
printf("The Array Sum Is\n");
for(i=0;i<size;i++)
{
printf("%d ",arr1[i]);
}
}
MPI_Finalize();
return 0;
}