[Mauiusers] Re: maui + LoadLeveler 3.3

Jan-Frode Myklebust mykleb at no.ibm.com
Thu Dec 8 13:57:19 MST 2005


On Thu, Dec 08, 2005 at 09:53:05AM +0100, Jan-Frode Myklebust wrote:
> 
> 	job is deferred.  Reason:  RMFailure  (job start failed with rc -7 (ERROR:    API internal error occurred

Ooops, -7 seems to mean LL_CONTROL_AUTH_ERR according to the llapi.h. So
I obviously had not allowed the maui runner access to admin LL. Fixed
this now, but before I was able to run a job, maui segfaulted with the
following backtrace:

#0  0x000000000049d0a2 in MJobUpdateResourceCache (J=0x25ae000, SIndex=0) at MJob.c:1732
1732          NPCount = J->ReqHList[0].N->CRes.Procs;
(gdb) where
#0  0x000000000049d0a2 in MJobUpdateResourceCache (J=0x25ae000, SIndex=0) at MJob.c:1732
#1  0x000000000049cea6 in MJobGetProcCount (J=0x25ae000) at MJob.c:1644
#2  0x000000000049ec3d in MJobBuildCL (J=0x25ae000) at MJob.c:2667
#3  0x000000000049d7ff in MJobSetQOS (J=0x25ae000, Q=0x116f360, Mode=0) at MJob.c:1992
#4  0x00000000004c98da in MRMJobPostLoad (J=0x25ae000, TaskList=0x7fbffec5f0, R=0x142eee0) at MRM.c:3766
#5  0x000000000042062f in MLLJobLoad (J=0x25ae000, LLJob=0x2596370, LLStep=0x2596aa0, JobName=0x7fbffeeb30 "mgnt01.463.0",
    R=0x142eee0) at LLI.c:1868
#6  0x0000000000420e16 in MLLJobProcess (LLJob=0x2596370, LLStep=0x2596aa0, LLUsage=0x0,
    RMJID=0x2495600 "mgnt01.ibmno.test.ub.no.463.0", R=0x142eee0, Status=0) at LLI.c:2163
#7  0x00000000004214b2 in MLLWorkloadQuery (R=0x142eee0, JCount=0x7fbffef294, SC=0x0) at LLI.c:2525
#8  0x0000000000484a8b in __MUTFunc (V=0x7fbffef0d0) at MUtil.c:4715
#9  0x00000000004849f8 in MUThread (F=0x4211e5 <MLLWorkloadQuery>, TimeOut=9, RC=0x7fbffef298, ACount=3, Lock=0x0) at MUtil.c:4688
#10 0x00000000004c45a4 in MRMWorkloadQuery (WCount=0x7fbffef6e4, SC=0x0) at MRM.c:595
#11 0x00000000004c3f2a in MRMGetInfo () at MRM.c:364
#12 0x000000000043f168 in MSchedProcessJobs (OldDay=0x7fbffff790 "", GlobalSQ=0x7fbfffb790, GlobalHQ=0x7fbfff7790) at MSched.c:6802
#13 0x00000000004034d8 in main (ArgC=2, ArgV=0x7fbffff8b8) at Server.c:165


Any ideas ?


BTW: this is maui 3.2.6p13.


  -jf


More information about the mauiusers mailing list