[Mauiusers] Maui just dies

[Gerson Galang]

Hi Troy,

Not sure how detailed the log you want so I just set my loglevel to 9 to 
give your a better idea on what's happening.

Cheers,
Gerson

08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,SRCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,SRCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 INFO:     SRCFG[0] set to FLAGS=OWNERPREEMPT
08/28 15:43:11 MSRProcessConfig(SR,FLAGS=OWNERPREEMPT)
08/28 15:43:11 MUGetIndex(FLAGS,ValList,0)
08/28 15:43:11 MUCmpFromString(=OWNERPREEMPT,Size)
08/28 15:43:11 MUGetIndex(OWNERPREEMPT,ValList,0)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,SRCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,SRCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 INFO:     SRCFG[0] set to CLASSLIST=parallel,batch
08/28 15:43:11 MSRProcessConfig(SR,CLASSLIST=parallel,batch)
08/28 15:43:11 MUGetIndex(CLASSLIST,ValList,0)
08/28 15:43:11 MUCmpFromString(=parallel,batch,Size)
08/28 15:43:11 MACLLoadConfig(ACL,==parallel,batch,1,CLASS)
08/28 15:43:11 MUCmpFromString(=parallel,Size)
08/28 15:43:11 INFO:     ACL[0] loaded with CLASS parallel (Affinity: 2)
08/28 15:43:11 MUCmpFromString(batch,Size)
08/28 15:43:11 INFO:     ACL[1] loaded with CLASS batch (Affinity: 2)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,SRCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,SRCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 INFO:     SRCFG[0] set to PRIORITY=20
08/28 15:43:11 MSRProcessConfig(SR,PRIORITY=20)
08/28 15:43:11 MUGetIndex(PRIORITY,ValList,0)
08/28 15:43:11 MUCmpFromString(=20,Size)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,SRCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,SRCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,RMCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,RMCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 INFO:     RMCFG[0] set to TYPE=PBS
08/28 15:43:11 MRMAdd(RMName,RP)
08/28 15:43:11 MCPRestore(RM,base,Optr)
08/28 15:43:11 INFO:     no checkpoint entry for object 'RM 
            base '
08/28 15:43:11 INFO:     RM base added
08/28 15:43:11 MUGetIndex(TYPE,ValList,0)
08/28 15:43:11 MUGetIndex(PBS,ValList,0)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,RMCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,RMCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 INFO:     RMCFG[0] set to SUSPENDSIG=suspend
08/28 15:43:11 MUGetIndex(SUSPENDSIG,ValList,0)
08/28 15:43:11 MRMSetAttr(base,14,Value,2)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,RMCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,RMCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,AMCFG,,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,AMCFG,,Index,Value,1024,SymTable)
08/28 15:43:11 MNodeLoadConfig(GLOBAL,NULL)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,NODECFG,GLOBAL,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,NODECFG,GLOBAL,Index,Value,1024,SymTable)
08/28 15:43:11 MNodeLoadConfig(DEFAULT,NULL)
08/28 15:43:11 MCfgGetSVal(Buf,CurPtr,NODECFG,DEFAULT,Index,Value,SymTable)
08/28 15:43:11 MCfgGetVal(Buf,NODECFG,DEFAULT,Index,Value,1024,SymTable)
08/28 15:43:11 ServerProcessArgs(1,ArgV,0)
08/28 15:43:11 
MUGetOpt(1,ArgV,a:Ab:B:c:C:dD:f:hH:i:j:l:m:n:N:p:P:r:s:v?-:,OptArg)
08/28 15:43:11 ServerDemonize()
08/28 15:43:11 INFO:     child process in background
08/28 15:43:11 ServerAuthenticate()
08/28 15:43:11 MFULock(/var/spool/maui/,/var/spool/maui/maui.pid)
08/28 15:43:11 INFO:     parent is exiting


Troy Baer wrote:
> On Thu, 2004-08-26 at 23:18, Gerson Galang wrote:
> 
>>I've been testing maui-3.2.6 patch7 thoroughly by sending lots of jobs 
>>on the server (torque) just to see how maui will schedule the jobs I 
>>have in the queue. One thing that I've noticed is that after 
>>running/suspending/resuming the jobs I have in the queue, the maui 
>>scheduler just suddenly dies. i know that the scheduler died because my 
>>jobs which are supposed to run and resume just sits there in the queue 
>>doing nothing. Doing a ps -aux also won't show the maui process that 
>>I've started. Is this a known issue of maui3.2.6p7?
> 
> 
> What are the last entries in maui.log?  It's hard to say what might be
> going wrong without that information.
> 
> 	--Troy