Hi, Alex Thanks for your suggestion. I did some tests this weekend and found that may be intel mpi's or vasp's issue. When I ran another version of vasp which compiled with intel mpi 2017 the error disappeared. Then,I switched to the original version of vasp,errors occured.
Alex Zarochentsev <zamena...@gmail.com> 于2020年7月10日周五 下午5:01写道: > Hello, > > > On Fri, Jul 10, 2020 at 11:28 AM 肖正刚 <guru.nov...@gmail.com> wrote: > >> Hi all, >> >> We run lustre 2.12.2(both server&clients) on CentOS 7.6, we hits getcwd >> error when ran vasp. >> Error message: >> forrtl: severe (121): Cannot access current working directory for unit 7, >> file "Unknown" >> Image PC Routine Line >> Source >> vasp_std 0000000000D1CAC9 Unknown Unknown >> Unknown >> vasp_std 0000000000D36DCF Unknown Unknown >> Unknown >> vasp_std 00000000007B2620 Unknown Unknown >> Unknown >> vasp_std 000000000086E57A Unknown Unknown >> Unknown >> vasp_std 0000000000935DB1 Unknown Unknown >> Unknown >> vasp_std 0000000000AEE62D Unknown Unknown >> Unknown >> vasp_std 0000000000BA6239 Unknown Unknown >> Unknown >> vasp_std 000000000040921E Unknown Unknown >> Unknown >> libc-2.17.so 00002B7D2ABBA3D5 __libc_start_main Unknown >> Unknown >> vasp_std 0000000000409129 Unknown Unknown >> Unknown >> >> I can not find any errors about lustre in that client. >> Any more , in mds&oss I can't find any errors about that client. >> >> Any suggestions? >> > > > similar to > https://jira.whamcloud.com/browse/LU-12997 ? > the first comment in LU-12997 says it is a kernel bug. > > Thanks, > Zam. > >> >> _______________________________________________ >> lustre-discuss mailing list >> lustre-discuss@lists.lustre.org >> http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org >> >
_______________________________________________ lustre-discuss mailing list lustre-discuss@lists.lustre.org http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org