This topic contains 1 reply, has 1 voice, and was last updated by  dfbdteam3 1 year, 6 months ago.

Viewing 2 posts - 1 through 2 (of 2 total)
  • Author
    Posts
  • #4698

    dfbdteam3
    Moderator

    What are the slots?
    how many types or slots are there?
    What are the issues with the slot based mechanism ?

    why it was removed from Hadoop 2 ?

    #4699

    dfbdteam3
    Moderator

    Each Map Reduce Jobs are split into task and Task tracker runs each task on a fixed number of map and reduce slots inside a data node based on a static configuration.

    In Hadoop 1.0 we need to specify in mapred-site.xml the following parameter to Configure the number of map slots and reduce slots

    mapreduce.tasktracker.map.tasks.maximum
    mapreduce.tasktracker.reduce.tasks.maximum

    The Following are the problem with Slot

    • Slots are wasted, anytime the cluster workload does not fit the static configuration.
    • In a slot-based model makes it hard for non-MapReduce applications to be scheduled appropriately.
    • Jobs never leave their original slots and cannot be move to free slots.

    For more details about MapReduce Jobs, please refer: MapReduce Tutorial

Viewing 2 posts - 1 through 2 (of 2 total)

You must be logged in to reply to this topic.