Type: Posts; User: rogerdpack; Keyword(s):

Search: Search took 0.09 seconds.

  1. compiler optimization

    (Sorry I didn't read too closely if it already does this, and didn't look in the source to check). Anyway one thought is "is this using gcc -march=native"? and another might be to use gcc's profile...
  2. apparently they're waiting for an impending patch...

    apparently they're waiting for an impending patch to the kernel to add lz4 "natively" so that they can just leverage that instead of their own version of lz4. Hopefully soon :)
  3. not merged

    I believe the lz4 stuff was never merged is that right?
  4. compression

    As a note, might be nice to mention that btrfs + compression can still be faster, in your benchmarks, viz:
Results 1 to 4 of 4