lkml.org 
[lkml]   [1999]   [Jul]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: (disk/cpu) kernel performance problem


    On Mon, 26 Jul 1999, Mark Lord wrote:

    > Gerald Aigner wrote:
    > ..
    > > Looking into the problem I found that reading large data blocks from
    > > two IDE disks with the read(2) library/system call consumes about 45%
    > > of the available CPU time when reading roughly 30 Mbytes/sec.
    > ...
    >
    > Percentage of CPU time is not a useful measurement.
    > Think about it.. if I/O were infinitely fast, then CPU usage
    > would be 100%, since the CPU would never have to wait.
    >
    > If disk I/O were infinitely slow, CPU usage would be 0%,
    > but that's not a Good Thing, is it..
    >
    45% is the amount of time the kernel spends in loading data from disk.

    The lower this value the more time is available for other
    threads/applications on the same system therefore increasing overall
    system utilization.

    -Gerald


    -
    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/

    \
     
     \ /
      Last update: 2005-03-22 13:53    [W:0.020 / U:59.700 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site