mrbear 发表于 2016-12-9 11:08:19

FairScheduler in hadoop mapreduce

  as i reviewed the book,it saied:
  a.it 's goal is to let each userfairly share the cluster resources
  b.jobs are placed in pools,and each user has their own pool.
  c.u can set the priorify of a pool ,so
  d.this Scheduler supports preemption
  first ,i thought,if i run a client to submit two SEQUENCEjobs,if i use FAIR sheduler,
  1.whether the results will be out of order as the jobs are Faired?
  2.sinc they are faired,so whether it wil be lead to definite-loop as it faire resources fluently?(for example,one of our national policys is "一部分人先富起来,最終实现共同富裕".
页: [1]
查看完整版本: FairScheduler in hadoop mapreduce