Scheduled Downtime
On Friday 21 April 2023 @ 5pm MT, this website will be down for maintenance and expected to return online the morning of 24 April 2023 at the latest

Mpirun stuck with no errors or interuptions

David Jones

New member
Hello, there,
I am new here.
I got a problem. After running 'mpirun -np 4 ./real.exe', it gets stuck. Four processes can be seen in command 'top', and there are no errors or interruptions, but it just gets stuck. But I tested 'mpirun -np 1 ./real.exe' or just './real.exe' can run normally. And before that I have checked the compilation of WRF and WPS. Have anyone ever encountered this situation?By the way, right now this is only running on one node, let alone running across nodes.
Anyone help? Thanks a lot.
 
Usually, they will ask you for the namelist.wps, namelist.input, and a copy of the error files to help. If it is running on one processor but not 4, that sounds like you compiled it to run serially rather than in parallel. (you can check this in configure.wps and configure.wrf) For more advanced advice, you will probably want to upload those files to your post.
 
Apologize and here are attach files. Just stuck with no errors or interruptions and in rsl.error.0000, 'forrtl: error (69): process interrupted (SIGINT)' means I ctrl+c and end the process.
 

Attachments

  • namelist.input
    3.7 KB · Views: 1
  • namelist.wps
    710 bytes · Views: 1
  • rsl.error.zip
    4.2 KB · Views: 1
  • rsl.out.zip
    3.5 KB · Views: 1
  • screen_shot.zip
    105.6 KB · Views: 1
Usually, they will ask you for the namelist.wps, namelist.input, and a copy of the error files to help. If it is running on one processor but not 4, that sounds like you compiled it to run serially rather than in parallel. (you can check this in configure.wps and configure.wrf) For more advanced advice, you will probably want to upload those files to your post.
Thanks for your reply. here are compiled screen_shot pic.
 

Attachments

  • compile_wps.jpg
    compile_wps.jpg
    69.3 KB · Views: 5
  • compile_wrf.jpg
    compile_wrf.jpg
    53.2 KB · Views: 5
Hi David,
The fact that you ARE getting rsl.* files printed out shows that you did compile with code for parallel processing. Since you're able to get real.exe to run with a single processor, can you use that output to move on to wrf.exe? If you experience the same issue with wrf.exe, please send the new rsl* files. Please also speak to a systems administrator at your institution to ensure you have everything set up properly, and that you are using the correct syntax/method for executing the wrf.exe command for multiple processes in your particular environment.
 
Top