Erro ao submeter job paralelo

marianaandrade
(usa Ubuntu)

Enviado em 13/05/2015 - 09:23h

Prezados,
Tento submeter um job na fila paralelo, ele fica um tempo na área de execução, mas logo vai para os jobs pendentes com a seguinte mensagem de erro:

"scheduling info: (collecting of scheduler job information is turned off)
error for job 1500: can't get password entry for user "xxx". Either the user does not exist or NIS error!"

Obs.: Onde está "xxx" é o nome do meu usuário. Uso SGE para trabalhar com filas.

Alguém tem alguma ideia de como resolver isso?

Atenciosamente,
Mariana.

marianaandrade
(usa Ubuntu)

Enviado em 11/06/2015 - 09:18h

Coloquei o schedd_job_info = true

E agora tenho essas mensagens aqui:

queue instance "all.q@n12" dropped because it is temporarily not available
queue instance "all.q@n13" dropped because it is temporarily not available
queue instance "all.q@n14" dropped because it is temporarily not available
queue instance "paralelo@n12" dropped because it is temporarily not available
queue instance "paralelo@n13" dropped because it is temporarily not available
queue instance "serial@n14" dropped because it is temporarily not available

Job is in error state

Error for job 1563: can't get password entry for user "xxx". Either the user does not exist or NIS

error!

Jobs can not run because queue instance is not contained in its hard queue list
1558

Jobs can not run because available slots combined under PE are not in range of job
1558


cannot run in queue "all.q" because it is not contained in its hard queue list (-q)
cannot run in queue "serial" because it is not contained in its hard queue list (-q)
cannot run in PE "mpi" because it only offers 96 slots


Alguém pode ajudar por favor?