Re: How does disk caching work?

From: Uwe Doering (gemini_at_geminix.org)
Date: 04/20/04

  • Next message: Q?=Igor ShmuklerQ=20?=: "Re[2]: How does disk caching work?"
    Date: Tue, 20 Apr 2004 07:45:33 +0200
    To: freebsd-performance@freebsd.org
    
    

    Jim C. Nasby wrote:
    > Thanks very much for all your help. Only remaining question I have is:
    > is there something we can monitor to gauge what impact (if any) changes
    > to these settings have? Will changes to hi|lowrunningspace just result
    > in increased KB/s or TPS write performance in gstat? How can we tell if
    > we've advanced it too much?

    I don't know of any simple means of monitoring the effect, short of
    doing your own benchmark tests. If these variables are too low you will
    notice that the write throughput suffers during peak read demand.
    That's when we started to examine the kernel sources and found the reason.

    To be on the safe side, don't make 'vfs.hirunningspace' larger than a
    fraction of the overall disk i/o buffer space (derived from
    'kern.nbuf'), and also not larger than the buffer space in the disk
    controller.

    'vfs.lorunningspace' is used to implement a hysteresis and should be 1/2
    or 3/4 of 'vfs.hirunningspace'.

    > Likewise, what can we measure regarding nbuf? If I'm understanding
    > things correctly, runningspace comes out of nbuf, so obviously it needs
    > to be greater than that, but what symptoms will we see if it's set too
    > low?

    Maybe just bad performance due to the complete flushing of the disk i/o
    buffers (remember that meta data is cached in there), maybe system
    lockup. Can't tell. Just make sure that these variables stay smaller
    than the disk i/o buffer cache, and you won't have to bother with the
    consequences of overdoing it.

        Uwe

    -- 
    Uwe Doering         |  EscapeBox - Managed On-Demand UNIX Servers
    gemini@geminix.org  |  http://www.escapebox.net
    _______________________________________________
    freebsd-performance@freebsd.org mailing list
    http://lists.freebsd.org/mailman/listinfo/freebsd-performance
    To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org"
    

  • Next message: Q?=Igor ShmuklerQ=20?=: "Re[2]: How does disk caching work?"

    Relevant Pages

    • Re: How reduce read/write from HD
      ... Disk I/O is keyed to processes and services running on the ... The overall performance of the drive matters, access time, the ... monitor Disk I/O in real-time. ...
      (microsoft.public.windowsxp.general)
    • Re: MONITOR
      ... > DISK I/O if Possible, and Number of users during a specified time ... I am not familiar with MONITOR. ... > I need to have this done on a daily basis so I can produce daily, ...
      (comp.os.vms)
    • MONITOR
      ... I need to put together a MONITOR job. ... DISK I/O if Possible, and Number of users during a specified time during ... I need to have this done on a daily basis so I can produce daily, ...
      (comp.os.vms)
    • Re: Im giving up computers if this is the future.
      ... monitor to do disk i/o in VS3100's could only understand 31-bit byte ... offsets, and thus whatever was being booted had to be in the first 2 gigs of ... With ultrix or BSD or mach or whatnot, that wasn't an issue, but VMS ...
      (comp.os.vms)