preallocation as an option

XMLWordPrintableJSON

    • Type: Improvement
    • Resolution: Done
    • Priority: Major - P3
    • None
    • Affects Version/s: None
    • Component/s: Performance
    • None
    • Environment:
      Solaris ZFS others copy on write file systems
    • None
    • None
    • None
    • None
    • None
    • None
    • None

      Preallocation kill performance on ZFS. It makes only bigger fragmentation, there is any performance benefits using pre allocation on ZFS, BTRFS ...
      Before "fragmentation crash" MongoDB on compressed ZFS file system works 20%-30% faster than on UFS (reads).

      I've tested it on Solaris, with 40G of RAM, 8CPU, 2.1T ZFS/UFS filesystem

      1.8T of logs, 8 370 000 000 rows, seq writes and random reads

            Assignee:
            Eliot Horowitz (Inactive)
            Reporter:
            Tomasz Drobiszewski
            Votes:
            0 Vote for this issue
            Watchers:
            0 Start watching this issue

              Created:
              Updated:
              Resolved: