Re: 2120S poor performance

From: Michael E.Conlen (meconlen_at_obfuscated.net)
Date: 12/09/04

  • Next message: Darcy Buskermolen: "Re: Memory problems:-(" 
    Date: Thu, 9 Dec 2004 14:51:49 -0500

    On Dec 9, 2004, at 12:49 PM, Jin Guojun [VFFS] wrote:

    > I do not remember where the original problem of 2120s was posted.
    > The read in RAID 5 mode is 40-56 MB/s, where write rate is 5-13 MB/s.
    > The most problem is at writing to RAID, average around 8 MB/s.
    > SCSI buses self is Okay because doing multiple R/W without RAID
    > can get maximum disk I/O. Soft RAID, like Vinum, also slows down
    > disk array performance. SO, it sounds like that RAID design has
    > big overhead to kill the performance.
    >
    > dd if=/dev/aacd0s1b of=/dev/null bs=128k count=20000
    > dev/null bs=128k count=20000
    > 20000+0 records in
    > 20000+0 records out
    > 2621440000 bytes transferred in 61.651078 secs (42520587 bytes/sec)
    >
    > Adaptec guy told me that this is a design issue. One older model,
    > which may be out of market, is performing better, but I would not
    > expect a large difference as soft RAID do not give better performance.

    Poorly implemented RAID-5 will often times incur a read operation for
    every write so that it can calculate the checksum value. Some
    implementations will identify when an entire stripe is being written
    and avoid it when possible.

    Try tuning the FS so that the blocks in the FS match up with the stripe
    size in the controller. I believe this will force every write to be a
    stripe. 

    --
Michael Conlen
meconlen@obfuscated.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: Darcy Buskermolen: "Re: Memory problems:-("

    Relevant Pages

    • Re: New PCI IDE controller or new mainboard - advice needed
      ... Currently '\Program Files' is a junction that points to a folder on a RAID ... Installing to stripe will also allow windows to start faster and all I/O ... When I purchased the two new IDE disks 2 months ago, ...
      (microsoft.public.windowsxp.hardware)
    • Re: Poor raid 1 performance?
      ... I basically assumed a 1-sector stripe ... > Or that the stripe size is lower than available free cache on the RAID ... > delivered to the main system by the RAID controller, ... interface mismatch between drives and host interface. ...
      (comp.sys.ibm.pc.hardware.storage)
    • Re: Oracle IO tuning tips/practices on Windows
      ... I would think that direct attached scsi raid with relatively new ... would read a full stripe. ... to combine the 2 databases into 1 'reporting' database. ...
      (comp.databases.oracle.server)
    • Re: Fibre Channel Storage - Access by multiple hosts
      ... disksuite to provide the stripe as the software RAID would probably be too ... I see the hardware external RAID controller as they ... > all of our JBODs with EMC's disk arrays with hot swapable disks. ...
      (comp.unix.solaris)
    • Re: Stripe sizing and maxcontig
      ... I've been reading up a lot recently on filesystem tuning, and stripe ... RAID controllers) and are looking at moving our databases over onto it ... It is likely different parts of the database may be ... I'm better off setting the stripe size to (number of disks * ...
      (comp.unix.solaris)