Announcement

Collapse
No announcement yet.

What are the optimum values for the different performance counters

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • What are the optimum values for the different performance counters

    Hi..

    Just to fire in a quick question.

    I had gone through the article Performance Monitoring the Easy Way from this site.
    It majorly relates to Windows 2008 Server.

    My question to the forum is that just as Joequerty mentioned that the optimum metric level for the Avg. Disk Queue length is 2 per spindle.

    Can anyone let me know the optimum values for the different performance counters.. Any article that I can find them on?

    Regards

  • #2
    Re: What are the optimum values for the different performance counters

    Some get a mention in the various Windows Server courses but since a lot depends on your specific hardware, there are no absolute values. I think also, you'll find Joe's value was "less than 2 per spindle"

    Best recommendation is to "benchmark" your servers by logging critical counters for the Processor, Memory, Disk Subsystem and Network performance objects and use this as a starting point. Make sure you pick up a variety of conditions to give a benchmark reflecting different uses of your infrastructure.
    Tom Jones
    MCT, MCSE (2000:Security & 2003), MCSA:Security & Messaging, MCDBA, MCDST, MCITP(EA, EMA, SA, EDA, ES, CS), MCTS, MCP, Sec+
    PhD, MSc, FIAP, MIITT
    IT Trainer / Consultant
    Ossian Ltd
    Scotland

    ** Remember to give credit where credit is due and leave reputation points where appropriate **

    Comment


    • #3
      Re: What are the optimum values for the different performance counters

      Right, sorry. I meant to say less than two per spindle. So again, for a three drive array you want AVG. Queue Length less than 6. Occassional spikes above 6 are not indicitive of a problem unless they are continuous and consistent.

      Comment


      • #4
        Re: What are the optimum values for the different performance counters

        No apology necessary, Joe -- thats exactly what you DID say here, didnt you?
        http://forums.petri.com/showthread.php?t=34853
        Last edited by Ossian; 4th April 2009, 17:19.
        Tom Jones
        MCT, MCSE (2000:Security & 2003), MCSA:Security & Messaging, MCDBA, MCDST, MCITP(EA, EMA, SA, EDA, ES, CS), MCTS, MCP, Sec+
        PhD, MSc, FIAP, MIITT
        IT Trainer / Consultant
        Ossian Ltd
        Scotland

        ** Remember to give credit where credit is due and leave reputation points where appropriate **

        Comment


        • #5
          Re: What are the optimum values for the different performance counters

          There is a lot of confusion about Avg Disk Queue counter. Bottom line: do not trust it. When you have RAIDs or controller cache involved, the counter is more confusing than useful.

          Much better counters are: Physical Disk\Avg. Disk sec Read and Physical Disk\Avg. Disk sec Write

          1ms - 15ms - healthy
          15ms-25ms - warning - up to you to decide whether the performance is acceptable)
          26ms or more - Critical - the disk is working too hard

          SQL and Exchange have some specific thresholds that can be found on technet/msdn
          Guy Teverovsky
          "Smith & Wesson - the original point and click interface"

          Comment

          Working...
          X