turbPipePeriodic/.cache/libturbPipe.so: cannot map zero-fill pages

[AdwardAllan]

nrspre turbPipe 1 # done

nrsmpi turbPipe 1 # error

using OCCA_CACHE_DIR: /home/lxj/.local/nekrs/examples/turbPipePeriodic/.cache/occa/

building udf ... done
building nek ... done

/home/lxj/.local/nekrs/examples/turbPipePeriodic/.cache/libturbPipe.so: cannot map zero-fill pages

Primary job terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.

---

mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

Process name: [[46131,1],0]
Exit code: 1

[MalachiTimothyPhillips]

It looks to me as if you may be running out of memory. Are you able to provide additional information regarding your system, such as the output of nvidia-smi? What backend are you targeting (e.g., Serial, CUDA)? Could you capture the stdout + stderr into a logfile and attach here?

[AdwardAllan]

Hi Malachi I have run successfully in examples/eddy , so I think it’s surely out of memory in examples/turbpipePeriodic. The error.txt is attached . Could you provide more details or documents about this perfect tools, I’m so interesting in this Solver but there is only information of Nek5000 . 从 Windows 版邮件<https://go.microsoft.com/fwlink/?LinkId=550986>发送

…

________________________________ 发件人: Malachi ***@***.***> 发送时间: Tuesday, August 24, 2021 11:13:51 AM 收件人: Nek5000/nekRS ***@***.***> 抄送: 李新俊 ***@***.***>; Author ***@***.***> 主题: Re: [Nek5000/nekRS] turbPipePeriodic/.cache/libturbPipe.so: cannot map zero-fill pages (#372) It looks to me as if you may be running out of memory. Are you able to provide additional information regarding your system, such as the output of nvidia-smi? What backend are you targeting (e.g., Serial, CUDA)? Could you capture the stdout + stderr into a logfile and attach here? ― You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#372 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AP3V4D2FQNRTHGRBHI55T4TT6ME67ANCNFSM5CVZOAUQ>.

__ ____ _____ ____ ___ / /__ / __ \/ ___/ / __ \ / _ \ / //_// /_/ /\__ \ / / / // __// ,< / _, _/___/ / /_/ /_/ \___//_/|_|/_/ |_|/____/ COPYRIGHT (c) 2019-2020 UCHICAGO ARGONNE, LLC Version: 20.0 MPI tasks: 2 using OCCA_CACHE_DIR: /home/lxj/nekRS/examples/turbPipePeriodic/.cache/occa/ building udf ... done building nek ... done /home/lxj/nekRS/examples/turbPipePeriodic/.cache/libturbPipe.so: cannot map zero-fill pages /home/lxj/nekRS/examples/turbPipePeriodic/.cache/libturbPipe.so: cannot map zero-fill pages -------------------------------------------------------------------------- Primary job terminated normally, but 1 process returned a non-zero exit code. Per user-direction, the job has been aborted. -------------------------------------------------------------------------- -------------------------------------------------------------------------- mpirun detected that one or more processes exited with non-zero status, thus causing the job to be terminated. The first process to do so was: Process name: [[55307,1],0] Exit code: 1

[stgeke]

Can you please use the discussion form here on GitHub for things like that.
btw: Looks like you used v20.0 which is quite old. Can you try again using the latest release.