Re: designing fast, streaming disk i/o with mmap: help wanted

From: Bill Huey (billh@burn.ucsd.edu)
Date: Fri Mar 31 2000 - 22:32:56 EST

  • Next message: Bill Huey: "Re: designing fast, streaming disk i/o with mmap: help wanted"

    > Streaming playback of movies is nothing compared to the task of
    > multichannel recording. You have to simultaneously read/write N (with

    It was a comment about their overall technology, but if I'm easily
    tricked by crazy amounts of read-ahead then please correct my
    misunderstanding. (made mention of in a private mail.)
     
    > ultimately, i would rather assume that the underlying fs is not going
    > to help me, do the best job i can with the existing tools, and then if
    > an fs design is available to make things even faster, all the better.

    Yeah, I know. I don't particularly know the specifics of the/your problems being
    solved so I'm likely to be speaking out of my ass.

    Interleaving the tracks was certainly an option that I was thinking about at
    lunch, but this kind of thing is specific for a highly constrained set of
    disk read patterns. This would change of course for something that does
    alot of random access.

    Folks have done some reseach on the topic, but I don't know where you are in
    the problem space and I was suggesting that possibly have an in memory data
    structure describes the streams on the disk could be useful.

    It's certainly a hot topic and I'd love to have a bitch'n multitrack recorder,
    streaming sampler under Linux. ;-)

    bill
     
    > --p

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.rutgers.edu
    Please read the FAQ at http://www.tux.org/lkml/



    This archive was generated by hypermail 2b29 : Fri Mar 31 2000 - 22:36:33 EST