AIX: I/O Tuning Parameters

I/O Tuning Parameters:

    1. numfsbufs (vmtune –b) specifies the number of file system buffer
      structures. This value is critical asVMM will put a process on the wait list
      if there are insufficient free buffer structures.

 

  1. Run vmtune –a (pre 5.2) vmstat –v (5.2 & >) and monitor
    fsbufwaitcnt. This is incremented each time an I/O operation has to wait for
    file system buffer structures.
  2. A general technique is to double the numfsbufs value (up to a maximum of
    512) until fsbufwaitcount no longer increases. This value, as it is dynamic,
    should be re-executed on boot prior to any mount all command.
  3. hd_pbuf_cnt (vmtune –B) determines the number of pbufs assigned to LVM.
    pbufs are pinned memory buffers used to hold pending I/O requests.
  4. Again, examine vmtune –a and review the psbufwaitcnt. If increasing,
    multiply the current hd_pbuf_cnt by 2 until psbufwaitcnt stops incrementing.
  5. Because the hd_pbuf_cnt can only be reduced via a reboot (this is
    pinned memory) – be frugal when increasing this value.

I/O Tuning :

  1. Over 35% I/O wait should be investigated.
  2. Oracle databases like async I/O, DB2 & Sybase do not care (a good
    place to start would be AIO PARMS of
  3. MINSERVERS = 80 MAXSERVERS = 200 MAXREQUESTS = 8192)
  4. Recent technology disks will support higher ltg numbers
  5. lvmstat (must be enabled prior to usage) provides detailed information for
    I/O contention
  6. filemon is an excellent I/O tool (trace – ensure you turn it off)
  7. numfsbufs and hd_pbuf_cnt adjusted to reduce wait counts in vmtune or
    vmstat -v

Leave a Reply

Your email address will not be published. Required fields are marked *

CAPTCHA * Time limit is exhausted. Please reload the CAPTCHA.

This site uses Akismet to reduce spam. Learn how your comment data is processed.