Re: [Condor-users] MPI jobs can not be run on Condor 6.8

Mailing List Archives Authenticated access	UW Madison Computer Sciences Department Computer Systems Lab

Date: Wed, 11 Mar 2009 16:50:25 +0800 (CST)

From: tracy_luofengji <tracy_luofengji@xxxxxxx>

Subject: Re: [Condor-users] MPI jobs can not be run on Condor 6.8

Dear Zhao Kun,

Thanks for you help. I forgot to uncomment some sentences in the condor_config.local, and now the MPI jobs can be executed. But now the problem is, all the mpi jobs stay in the state "running" all the time, and never finish or return. I have spent several hours on it, but I can not find the reason.

Any help will be appraciated.

Regards,

Tracy

在2009-03-11 12:33:43，zhaokun <zhaokun@xxxxxxxxxxxxx> 写道： >Dear tracy_luofengji, > > > In submit file, remove 3 lines. Make sure mp1script and helloworld can be found in your working machine. > >>>>should_transfer_files?=?yes >>>>when_to_transfer_output?=?on_exit >>>>transfer_input_files?=?/usr/local/helloworld > > > > > > Thanks. >　　　　　　　Zhaokun > Beijing Hotsim Technology Co.,Ltd > zhaokun@xxxxxxxxxxxxx >　　　　　　　　　　2009-03-11 >=======From 2009-03-11 11:45:17 ======= > >>Dear Zhao Kun, >> >>Hello, thanks for your help. I have tested it again following your suggestion. Only one sentence like "job has been submitted..." in the log file, and no information in the output file and the error file. >> >>I have already used condor_status and condor_q -analyze before. The status of my worker node kept "Unclaimed" and the result of "condor_q -analyze" just told me:"1 job is rejected by unknown reasons". >> >>Do you have any suggestions? Any help will be appreciated. >> >>Thanks! >>Tracy >> >> >> >> >>在2009-03-11?11:37:22，zhaokun?<zhaokun@xxxxxxxxxxxxx>?写道： >>>Dear?tracy_luofengji, >>> >>> Please?add?following?lines?in?your?submit?file >>>???? >>> Log?=?test.log >>> Output?=?test.out >>> Error?=??test.err >>> >>>????you?may?find?what?happens?in?log?file?and?output?file?after?job?submited. >>> >>>? "condor_status"?and?"condor_q?-ana"?will?help?you?to?get?more?info. >>> >>> >>> >>> >>> >>> >>> >>> Thanks. >>>　　　　　　　Zhaokun >>> ???Beijing?Hotsim?Technology?Co.,Ltd >>> ???zhaokun@xxxxxxxxxxxxx >>>　　　　　　　　　　2009-03-11 >>>=======From?2009-03-11?11:29:21?======= >>> >>>>Dear?all, >>>>I?used?Condor?6.8?and?mpich-1.2.7.?I?tested?it?on?2?nodes:?one?acts?as?master?and?the?other?acts?as?worker.?On?the?worker?node,?I?copied?the?content?of?the?file?$CONDOR_HOME/etc/examples/condor_config.local.dedicated.resource?to?the?file?/home/condor/condor_config.local,?and?changed?the?dedicated?schedular?to: >>>>? >>>>DedicatedScheduler?=?"DedicatedScheduler@xxxxxxxxxxxxxxxxxxxxx" >>>>? >>>>Then?on?the?master?node,?I?created?a?submission?file?as?following: >>>> >>>>universe?=?parallel >>>>executable?=?/usr/local/mp1script >>>>arguments?=?/usr/local/helloworld >>>>machine_count?=?1 >>>>should_transfer_files?=?yes >>>>when_to_transfer_output?=?on_exit >>>>transfer_input_files?=?/usr/local/helloworld >>>>queue >>>>? >>>>When?I?submitted?the?job?to?condor,?the?job?always?kept?idle,?so?I?want?to?know?the?reason?for?it. >>>>? >>>>Thanks! >>>>Regards, >>>>Tracy >>>>_______________________________________________ >>>>Condor-users?mailing?list >>>>To?unsubscribe,?send?a?message?to?condor-users-request@xxxxxxxxxxx?with?a >>>>subject:?Unsubscribe >>>>You?can?also?unsubscribe?by?visiting >>>>https://lists.cs.wisc.edu/mailman/listinfo/condor-users >>>> >>>>The?archives?can?be?found?at:? >>>>https://lists.cs.wisc.edu/archive/condor-users/ >>>> >>> >>>=?=?=?=?=?=?=?=?=?=?=?=?=?=?=?=?=?=?=?= >>>_______________________________________________ >>>Condor-users?mailing?list >>>To?unsubscribe,?send?a?message?to?condor-users-request@xxxxxxxxxxx?with?a >>>subject:?Unsubscribe >>>You?can?also?unsubscribe?by?visiting >>>https://lists.cs.wisc.edu/mailman/listinfo/condor-users >>> >>>The?archives?can?be?found?at:? >>>https://lists.cs.wisc.edu/archive/condor-users/ >> >>_______________________________________________ >>Condor-users mailing list >>To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a >>subject: Unsubscribe >>You can also unsubscribe by visiting >>https://lists.cs.wisc.edu/mailman/listinfo/condor-users >> >>The archives can be found at: >>https://lists.cs.wisc.edu/archive/condor-users/ >> > >= = = = = = = = = = = = = = = = = = = = >_______________________________________________ >Condor-users mailing list >To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a >subject: Unsubscribe >You can also unsubscribe by visiting >https://lists.cs.wisc.edu/mailman/listinfo/condor-users > >The archives can be found at: >https://lists.cs.wisc.edu/archive/condor-users/

Mailing List Archives

Authenticated access

Re: [Condor-users] MPI jobs can not be run on Condor 6.8