High CPU = Poor disk I/O on Svr2003?

From: Joe Pochedley (joepochedley_at_NAMFG.COM)
Date: 10/06/04

  • Next message: Tim Johnson: "Re: [Full-Disclosure] RE: Disclosure policy in Re: RealPlayer vulnerabilities"
    Date:         Wed, 6 Oct 2004 12:05:51 -0400
    To: NTBUGTRAQ@LISTSERV.NTBUGTRAQ.COM
    
    

     
    Russ,

    I know this isn't a very "technical" posting, but wondering if you can
    pass it along because it's somewhat disturbing and confusing.

    On Windows Server 2003:

    Given a process running at low priority consuming 100% processor time,
    any normal (or higher) priority process will have very slow disk access.

    The process in question is SETI running priority level 4. While this
    low priority process is running, any disk I/O is less than half its
    normal speed, sometimes disk I/O drops as much as 80%.

    This occurs on Windows Server 2003 but not on anything previous. We
    have tested on multiple Svr 2003 machines with different disk
    configurations (IDE and SCSI, Hardware RAID and stand alone disks) and
    have the same results on each. Performance settings on all machines
    were set to adjust Processor Scheduling and Memory usage for "Programs"
    though changing this setting didn't have any affect. Windows XP, 2000
    and NT do not exhibit this behavior.

    Can anyone else verify this? Shouldn't the scheduler be releasing CPU
    time for the low priority apps to disk I/O processes that need the
    time? What is wrong with Server 2003?

    Thanks.

    Joe Pochedley

    --
    NTBugtraq Editor's Note:
    Want to reply to the person who sent this message? This list is configured such that just hitting reply is going to result in the message coming to the list, not to the individual who sent the message. This was done to help reduce the number of Out of Office messages posters received. So if you want to send a reply just to the poster, you'll have to copy their email address out of the message and place it in your TO: field.
    --
    

  • Next message: Tim Johnson: "Re: [Full-Disclosure] RE: Disclosure policy in Re: RealPlayer vulnerabilities"