Re: 2.4.0test5-pre4-lowlat latencies benchmarked, 2.2.16+Ingo's LL patch = strange behaviour

From: Benno Senoner (sbenno@gardena.net)
Date: Tue Jul 25 2000 - 20:13:58 EDT

  • Next message: Borislav Deianov: "Re: synthetic parallel processing"

    On Wed, 26 Jul 2000, Mark Hahn wrote:
    > > Unfortunately during disk writes it performs still quite bad , about 50msec
    > > during disk writes.
    >
    > you still mean misconfigured (PIO) disk writes, right?

    for all my tests (past/present/future) assume
     EIDE DMA=on , unmask irq=on 32bit access=on

    I do not care about untuned , non-DMAed IDE disks, because these are not
    the typical machines of the power desktop multimedia machine.

    The user who wants low latencies is willing to buy non-flawed hardware.
    Bloating the kernel to deliver good latencies on old, slow polled devices etc is
    simply silly.

    Benno.

    -
    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 : Tue Jul 25 2000 - 19:23:38 EDT