Uploaded image for project: 'Hadoop Distributed Data Store'
  1. Hadoop Distributed Data Store
  2. HDDS-981

Block allocation should involve pipeline selection and then container selection

    XMLWordPrintableJSON

    Details

    • Type: Bug
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 0.4.0
    • Component/s: SCM
    • Labels:
      None
    • Target Version/s:

      Description

      Currently SCM maintains a list of preallocated containers and allocates blocks from these containers. This approach does not work well with dynamics of the cluster where new nodes are being added and pipelines are destroyed. New containers are not created until all the preallocated containers are exhausted.

      The Jira aims to establish a criteria in block allocation where first a pipeline is selected amongst the available pipelines and then a container is selected in that pipeline. In order to handle the dynamics of the cluster a fixed interval pipeline creator job can be launched which creates pipelines in the system.

        Attachments

        1. HDDS-981.001.patch
          64 kB
          Lokesh Jain
        2. HDDS-981.002.patch
          64 kB
          Lokesh Jain
        3. HDDS-981.003.patch
          72 kB
          Lokesh Jain
        4. HDDS-981.004.patch
          74 kB
          Lokesh Jain
        5. HDDS-981.005.patch
          97 kB
          Lokesh Jain
        6. HDDS-981.006.patch
          98 kB
          Lokesh Jain
        7. HDDS-981.007.patch
          98 kB
          Lokesh Jain
        8. HDDS-981.008.patch
          100 kB
          Lokesh Jain

          Activity

            People

            • Assignee:
              ljain Lokesh Jain
              Reporter:
              ljain Lokesh Jain
            • Votes:
              0 Vote for this issue
              Watchers:
              8 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved: