[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[HTCondor-users] about condor negotiator



Dear all,
    we used condor in the local cluster, and devided resource into different groups.
    But we have a negotiation problem:
        Some jobs in schedd stay idle for a long time, but lots of slots in collector are in idle.
        however, these idle jobs are netotiated to running in the machines  when some new jobs are submitted into schedd
   
    Our groups configuration as follow:     
        GROUP_NAMES = cms, juno, physics, higgs, dyw, hxmt
        GROUP_QUOTA_DYNAMIC_cms = 1.0
        GROUP_QUOTA_DYNAMIC_juno = 1.0
        GROUP_QUOTA_DYNAMIC_higgs = 1.0
        GROUP_QUOTA_DYNAMIC_physics = 1.0
        GROUP_QUOTA_DYNAMIC_dyw = 1.0
        GROUP_QUOTA_DYNAMIC_hxmt = 1.0
        GROUP_ACCEPT_SURPLUS = true
    
        we don't want the quota limits the number of slots used by every group, so we set dynamic quota. 
       Are there some wrong configurations  lead the negotiation problem?  Thanks for help.

Best regards,
Jiang Xiaowei

NAME:Jiang Xiaowei
MAIL:jiangxw@xxxxxxxxxxxxxxx
TEL:010 8823 6024
DEPARTMENT:Computing Center of IHEP