Re: Very low disk performance on 5.x

From: Arne (arne_woerner_at_yahoo.com)
Date: 05/02/05

  • Next message: David Gilbert: "Re: 64bit CPUs" 
    Date: Mon, 2 May 2005 07:14:56 -0700 (PDT)
To: Allen <bsdlists@rfnj.org>

    --- Allen <bsdlists@rfnj.org> wrote:
    > Also you should keep in mind, there could simply be some really
    > goofy
    > controller option enabled, that forces the RAID5 to behave in a
    > "degraded"
    > state for reads -- forcing it to read up all the other disks in
    > the stripe
    > and calculate the XOR again, to make sure the data it read off
    > the disk
    > matches the checksum. It's rare, but I've seen it before, and
    > it will
    > cause exactly this sort of RAID5 performance inversion. Since
    > the XOR is
    > recalculated on every write and requires only reading up one
    > sector on a
    > different disk, options that do the above will result in read
    > scores
    > drastically lower than writes to the same array.
    >
    Isn't that compensated by the cache? I mean:
    We would just
    1. read all the blocks, that correspond to the block, that is
    requested,
    2. put them all into the cache
    3. check the parity bits (XOR should be very fast; especially in
    comparison to the disc read times)
    4. keep them in the cache (some kind of read ahead...)
    5. send the requested block to the driver

    -Arne

    __________________________________________________
    Do You Yahoo!?
    Tired of spam? Yahoo! Mail has the best spam protection around
    http://mail.yahoo.com
    _______________________________________________
    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: David Gilbert: "Re: 64bit CPUs"

    Relevant Pages

    • md: md6_raid5 crash 2.6.20
      ... the drives in the raid5 array starting giving read errors. ... Note I'm using PATA drives on with a promise IDE controller (using the ... CPU: L2 Cache: 512K ... SCSI device sda: 312581808 512-byte hdwr sectors ...
      (Linux-Kernel)
    • Re: [RFC][PATCH 000 of 3] MD Acceleration and the ADMA interface: Introduction
      ... acceleration, pre-emptible xor. ... To date these patches only cover raid5 ... The ADMA interface should support a PIO ...
      (Linux-Kernel)
    • Re: Very low disk performance on 5.x
      ... >>I presume you would only compare read to write performance on a RAID5 ... >>device which has battery backed cache. ... results in marginally improved write speeds, ... to make sure the data it read off the disk ...
      (freebsd-performance)
    • Re: Storage performance questions
      ... >> There seem to be a rumour floating around that RAID5 is just as fast as ... >> RAID0 on the above storage systems. ... This goes against every benchmark I ... > cache, not after it gets destaged to disk. ...
      (comp.unix.solaris)
    • Re: Storage performance questions
      ... > There seem to be a rumour floating around that RAID5 is just as fast as ... > ever seen on RAID controllers. ... cache, not after it gets destaged to disk. ...
      (comp.unix.solaris)