No announcement yet.

Tux3 File-System Works Out Faster Fsync Support

  • Filter
  • Time
  • Show
Clear All
new posts

  • #11
    Originally posted by danielbot View Post
    Incorrect, you will get long term fragmentation and run a bit slower, but still fast most probably. It actually takes a lot of churn to age a filesystem to the point where you notice it.
    "most probably" and "a filesystem" -- Did you test tux3 yourself? It seems you have no idea, what you are talking about: To quote one of the tux3 developers:

    Originally posted by Daniel Phillips
    In the full disclosure department, Tux3 is still not properly optimized in some areas. One of them is fragmentation: it is not very hard to make Tux3 slow down by running long tests. Our current allocation algorithm is completely naive - it just allocates the next available block and wraps at the top of volume. After a few wraps, it makes a big mess. So today we are not claiming victory in the benchmark department, we still have some work to do.

    Originally posted by danielbot View Post
    False. Benchmarks running on top of ram (tmpfs) are shown here:
    flock is about as fast on tux3 as on xfs ( XFS: 1.10s; Tux3: 1.07s) -- not much of a difference here. The dbench benchmarks are quite meaningless, as tux3 has no sane allocator. Benchmarking such stuff doesn't make sense before the algorithm is in place.

    Originally posted by danielbot View Post
    Far be it from me to know why somebody wants their filesystem to run slowly, but if XFS devs want it that way and can convince you that slow is actually good then more power to them.
    It's not slow on purpose, it's slow for empty disks. That's all. I'm very positive that once a proper allocator is used, the numbers are quite different. If not and the file system is stable, I'll happily use it
    Last edited by leidola; 05-11-2015, 09:43 AM.


    • #12
      We need this mainlined, so that more people can easily test it...