Hi, please clarify this, In lazy scheduling that spark had implemented, it is given that tasks are sorted when a slot becomes free at a node and the job with least tasks is scheduled first or made to wait maximum till time D if locality of data is not there. My question is, doesnt this result in jobs with large number of tasks getting starved?...If not, then how?
-- *Sai Prasanna. AN* *II M.Tech (CS), SSSIHL* *Entire water in the ocean can never sink a ship, Unless it gets inside.All the pressures of life can never hurt you, Unless you let them in.*
