Page 1 of 2 12 LastLast
Results 1 to 10 of 16

Thread: Btrfs Picks Up Snappy Compression Support

  1. #1
    Join Date
    Jan 2007
    Posts
    14,837

    Default Btrfs Picks Up Snappy Compression Support

    Phoronix: Btrfs Picks Up Snappy Compression Support

    New patches have been published for the Btrfs file-system that implement support for Google's Snappy compression algorithm, which promises to deliver better performance beyond LZO compression...

    http://www.phoronix.com/vr.php?view=MTA0MjQ

  2. #2
    Join Date
    May 2010
    Posts
    36

    Default

    Just a positive comment about the article itself:

    - it doesn't contain personal opinions
    - it properly quotes and links to claims of others
    - it actually reads like news
    - isn't riddled with a metric ton of links to other phoronix articles

    When comparing this to todays FBSD9 article... is that written by the same Michael? More of this news reporting quality please.

  3. #3

    Default

    Quote Originally Posted by dhewg View Post
    When comparing this to todays FBSD9 article... is that written by the same Michael? More of this news reporting quality please.
    Just a matter of being awake for less than an hour at that time so not entirely burned out and while coffee is fresh in me.... (and that FreeBSD 9.0 article was written in comparison after like 16 hours of work yesterday and while having already written two articles and like 6 or 7 news posts.)
    Last edited by Michael; 01-13-2012 at 11:29 AM.

  4. #4

    Default

    Quote Originally Posted by dhewg View Post
    Just a positive comment about the article itself:

    - it doesn't contain personal opinions
    - it properly quotes and links to claims of others
    - it actually reads like news
    - isn't riddled with a metric ton of links to other phoronix articles

    When comparing this to todays FBSD9 article... is that written by the same Michael? More of this news reporting quality please.
    Fully agree.

    Quote Originally Posted by Michael View Post
    Just a matter of being awake for less than an hour at that time so not entirely burned out and while coffee is fresh in me.... (and that FreeBSD 9.0 article was written in comparison after like 16 hours of work yesterday and while having already written two articles and like 6 or 7 news posts.)
    Maybe you should sleep an hour more, and instead of churning out a mass of questionable content publish less, but well-written posts.

  5. #5

    Default

    Quote Originally Posted by AnonymousCoward View Post
    Maybe you should sleep an hour more, and instead of churning out a mass of questionable content publish less, but well-written posts.
    Not economical at this point...

  6. #6
    Join Date
    Jan 2009
    Posts
    80

    Default

    How good is PTS at benchmarking transparent filesystem compression? What kind of data is written to/read from disk when it does its thing? Text? Random? Multimedia? Straight zeroes? A mixture of all of the above?
    Last edited by loonyphoenix; 01-13-2012 at 12:30 PM.

  7. #7
    Join Date
    Dec 2009
    Posts
    29

    Default

    Quote Originally Posted by loonyphoenix View Post
    How good is PTS at benchmarking transparent filesystem compression? What kind of data is written to/read from disk when it does its thing? Text? Random? Multimedia? Straight zeroes? A mixture of all of the above?
    Yeah it would be nice to have a real world type of benchmark. Anandtech analyzed it a while ago, and it's a large portion of 4K reads and writes, and then sequential data, all interleaved.

    http://www.anandtech.com/show/5272/o...b-ssd-review/4

    Only 42% of all operations are sequential, the rest range from pseudo to fully random (with most falling in the pseudo-random category). Average queue depth is 4.625 IOs, with 59% of operations taking place in an IO queue of 1.

  8. #8
    Join Date
    Aug 2007
    Posts
    6,633

    Default

    I do not get why btrfs gets lots of mostly useless features when not even the really performance relevant issues are solved. It can not be that dpkg needs ages because of a fucked up fsync implementaion. such hacks like eatmydata do not work for chroot anyway...

  9. #9
    Join Date
    Jan 2012
    Posts
    151

    Default

    Quote Originally Posted by dhewg View Post
    Just a positive comment about the article itself:

    - it doesn't contain personal opinions
    - it properly quotes and links to claims of others
    - it actually reads like news
    - isn't riddled with a metric ton of links to other phoronix articles

    When comparing this to todays FBSD9 article... is that written by the same Michael? More of this news reporting quality please.
    Quote Originally Posted by Michael View Post
    Just a matter of being awake for less than an hour at that time so not entirely burned out and while coffee is fresh in me.... (and that FreeBSD 9.0 article was written in comparison after like 16 hours of work yesterday and while having already written two articles and like 6 or 7 news posts.)
    Quote Originally Posted by anonymouscoward View Post
    Maybe you should sleep an hour more, and instead of churning out a mass of questionable content publish less, but well-written posts.
    +1; less articles + better journalism >> many articles + poor journalism

  10. #10

    Default

    Quote Originally Posted by FourDMusic View Post
    +1; less articles + better journalism >> many articles + poor journalism
    I've already said less articles is not viable in a business sense.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •