24小时热门版块排行榜    

CyRhmU.jpeg
查看: 1926  |  回复: 6
当前只显示满足指定条件的回帖,点击这里查看本话题的所有回帖

wnryc

新虫 (初入文坛)

[交流] 【求助】跑vasp时, mpich2运行有时有问题已有4人参与

Hi, All

我在RHEL 5.4; mpich2-1.2.1p1;pgi-9.0.1;双核Xeon E5504 (intel CPU)环境下跑并行的vasp。有些作业,能够正常并行计算(使用命令:mpiexec -n 8 vasp.pgi >out& 或者mpiexec -n 8 vasp.pgi   out&,有些作业却不能运行(我安装mpich2, pgi.9.0.1没有问题),这时程序读了INCAR,POTCAR,POSCAR和KPOINTS文件后,屏幕提示如下的错误:
----------------------------------------------------------------------
running on    8 nodes
distr:  one band on    1 nodes,    8 groups
vasp.4.6.21  23Feb03 complex
POSCAR found :  3 types and   30 ions
LDA part: xc-table for Ceperly-Alder, Vosko type interpolation para-ferro
POSCAR, INCAR and KPOINTS ok, starting setup
WARNING: wrap around errors must be expected
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
FFT: planning ...            2
reading WAVECAR
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
WARNING: random wavefunctions but no delay for mixing, default for NELMDL
entering main loop
       N       E                     dE             d eps       ncg     rms          rms(c)
rank 6 in job 36  qltang1_54199   caused collective abort of all ranks
  exit status of rank 6: killed by signal 9
rank 3 in job 36  qltang1_54199   caused collective abort of all ranks
  exit status of rank 3: killed by signal 9
----------------------------------------------------------
不知道这是什么原因。苦恼了很久,特请大家帮忙解决下,谢谢!
回复此楼

» 猜你喜欢

» 本主题相关价值贴推荐,对您同样有帮助:

Dr.Qian-LinTang
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖

wnryc

新虫 (初入文坛)


xiaohunhun(金币+1):等着解答,你金币真的少的惨烈,呵呵 2010-06-16 20:32:05
从报错信息看,不是mpiexec (or mpirun)命令的问题,因该是mpich里面有问题,请各楼主帮忙啊!
Dr.Qian-LinTang
5楼2010-06-16 09:37:55
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖
查看全部 7 个回答

gump_813276

铜虫 (小有名气)

★ ★
小木虫(金币+0.5):给个红包,谢谢回帖交流
aylayl08(金币+1):谢谢讨论 2010-08-01 07:57:38
mpiexec -n 8 vasp.pgi   out&
你确定 试试mpiexec -n 8 vasp.pgi  &> out&
2楼2010-06-15 19:34:54
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖

wnryc

新虫 (初入文坛)

命令确实是mpiexec -n 8 vasp.pgi   out&或mpiexec -n 8 vasp.pgi  >out&

我按照你的:mpiexec -n 8 vasp.pgi  &> out&,结果也出现同样的报错信息:
--------------------------------------------
[qltang@qltang1 pgi]$ vi out
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
mpiexec_qltang1 (handle_stdin_input 1089): stdin problem; if pgm is run in background, redirect from /dev/null
mpiexec_qltang1 (handle_stdin_input 1090):     e.g.: mpiexec -n 4 a.out < /dev/null &
WARNING: random wavefunctions but no delay for mixing, default for NELMDL
entering main loop
       N       E                     dE             d eps       ncg     rms          rms(c)
Assertion failed in file /opt/software/tmp/mpich2-1.2.1p1/src/mpid/ch3/channels/nemesis/nemesis/include/mpid_nem_inline.h at line 728: local_rank < MPID_nem_mem_region.num_local
internal ABORT - process 1
rank 5 in job 44  qltang1_54199   caused collective abort of all ranks
  exit status of rank 5: killed by signal 11
rank 1 in job 44  qltang1_54199   caused collective abort of all ranks
  exit status of rank 1: return code 1
------------------------------------------------------------

我注意到报错信息里有这样一句话:“Assertion failed in file /opt/software/tmp/mpich2-1.2.1p1/src/mpid/ch3/channels/nemesis/nemesis/include/mpid_nem_inline.h at line 728: local_rank < MPID_nem_mem_region.num_local”。不知道mpich2为什么有时会出现这样的错误?

请达人指教,谢谢!
Dr.Qian-LinTang
3楼2010-06-15 20:27:34
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖

jghe

金虫 (著名写手)

★ ★
小木虫(金币+0.5):给个红包,谢谢回帖交流
aylayl08(金币+1):谢谢提示 2010-08-01 07:57:52
你的命令的确挺怪的
我用的是 mpirun -np 8 vasp>vasp.out&
4楼2010-06-15 22:19:39
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖
普通表情 高级回复(可上传附件)
信息提示
请填处理意见