VMware support requires the Perfmon log data to diagnose performance issues on Windows virtual machines. There is a large amount of possible counters and information that is gathered from Perfmon. This article provides information on the counters and data that VMware support requires to diagnose virtual machine performance issues.

To collect the required Perfmon log data in Windows XP/2000/2003:

1. Click Start > Programs > Administrative Tools > Performance.
2. Under Performance Logs and Alerts, right-click Counter Logs and click New Log Settings.
3. Enter a name for the log and then click OK.
4. Click the General tab and then click Add.
5. Add these objects and ensure to select all the counters for these objects:
    
   • Cache
   • Memory
   • Network Interface
   • Objects
   • Paging File
   • Physical Disk
   • Process
   • Processor
   • Redirector
   • Server
   • Server Work Queues
   • System
   • Thread
   • VM Processor
   • VM Memory
     
     Note: VM Processor and VM Memoryare optional counters and are not available in all environments.
      
6. In the Update Time section, depending on the frequency of problem occurrence, set the interval according to this table:
    

   Problem occurrence	Interval
   Weekly	15 minutes
   Daily	90 seconds
   Hourly	5 seconds

7. Click the Log Files tab.
8. Select Binary Circular File and set the Log File size limit to 200MB.
   
   Note: This size is required to gather sufficient history to see a trend.

To collect the required Perfmon log data in Windows 7, Windows Server 2008 R2, Windows 8, Windows 2012 and Windows Vista:

1. Click Start > Run, enter perfmon.exe, and click OK.
2. Go to the User Defined folder. Click New > Data Collector Set.
3. Enter a name for your Data Collector Set.
4. Select Create manually and click Next.
5. Go to Create Data Logs, select Performance Counter and then click Next.
6. Add these objects and ensure to select all the counters for these objects:
    
   • Cache
   • Memory
   • Network Interface
   • Objects
   • Paging File
   • Physical Disk
   • Process
   • Processor
   • Redirector
   • Server
   • Server work Queues
   • System
   • Thread
   • VM Processor
   • VM Memory
     
     Note: VM Processor and VM Memory are optional counters and are available in all environments.
      
7. Depending on the frequency of problem occurrence, set the interval according to this table:
    

   Problem occurrence	Interval
   Weekly	15 minutes
   Daily	90 seconds
   Hourly	5 seconds

    

    
8. Specify the location where you want to save the data.
9. To start the Data Collector Set immediately, select Start this data collector set now.
10. After the problem occurrence is captured in the logs, stop the Data Collector Set.
    
    To stop the Data Collector Set, right-click Data Collector Set under User Defined and click Stop.