How I may help
Email me!

Metrics

This page attempts to reconcile the different types and names of metrics gathered to measure computer system performance.

This is a companion page to my pages on Monitoring, Diagnostics, Profiling, Tuning, and Testing computer performance using Perfmon, LoadRunner, and other products.

 

Site Map List all pages on this site 
About this site About this site 
Go to first topic Go to Bottom of this page

Metrics for measuring computer performance

Set screen Aspects of Metrics

Go to Top of this page.
Previous topic this page
Next topic this page

Set screen System Metrics

    Both Mercury Deep Diagnostics and Mercury Profiler monitor these metrics:

  • CPU: Percentage utilization of the CPU. Note that the current release of Deep Diagnostics supports only a single CPU.
  • Memory: The percentage of memory in use.
  • Virtual Memory: The percent of virtual memory in use.
  • Context Switches per Second: How many times per second the operating system switches threads.

  • Page Ins per Second: The number of operating system pages being brought into the system per second.
  • Page Outs per Second: The number of operating system pages being swapped out of the system per second.

  • Swap Ins per Second: The number of pages read from swap space per second. (This does not apply to Windows systems.)
  • Swap Outs per Second: The number of pages written to swap space per second. (This does not apply to Windows systems.)

  • Disk Bytes per Second: The number of bytes being transferred to/from the disk per second.
  • Disk I/O per Second: The total number of transfer operations to and from the disk per second.

    Additionally, Deep Diagnostics measures:

  • Network Throughput: The number of bytes transmitted per second between any two systems running Deep Diagnostics Agents.
  • Network Bytes per Second: The number of bytes being transferred to/from the network per second.
  • Network I/O per Second: The total number of transfer operations to and from the network per second.
  • Network Latency: latency clock The elapsed time of a single call between two systems running Deep Diagnostics Agents (in milliseconds).

  • BEAJMX: Allows the monitoring of BEA WebLogic (6.1 or later) via the Java Management eXtensions (JMX). To collect these metrics, you must installed the support for JMX on the System Under Test.

  • CPU Time — the time that a given method invocation spends actually executing on the processor, including the time spent on the CPU for child calls.
  • Exclusive CPU Time excludes time spent on the CPU for child calls.

    These are available only after the property use.cpu.timestamps in the capture.properties file within the probe's /etc directory is set to "true" (from "false" by default) to capture per-thread CPU timings.

  • Latency latency clock is the wall-clock time from the time of the method start to the time of the method finish, for all methods.
  • Avg. Latency is the mean Latency calculated by dividing total Latency by the number of calls.

  • Throughput
  • Allocation
  • Deallocation
  • Live Object
 

CPU Utilization percentage Memory percentage Virtual Memory percentage Context Switches per second Page Ins per second Page Outs per second Disk I/O Operations per second Disk Bytes per second Network I/O Operations per second Network Bytes per second Network Network Latency - The elapsed time of a single call between two systems running Deep Diagnostics Agents (in milliseconds). Network Throughput - number of bytes transmitted per second between any two systems running Deep Diagnostics Agents.
Go to Top of this page.
Previous topic this page
Next topic this page

Set screen Tier Metrics

    JMS (Java Message Services) for asynchronous communications.

    The Java WAR file packaging JSP web front ends running in a web server...

    The Java EAR file packaging service components running in Java applications server...

 

Clients
Go to Top of this page.
Previous topic this page
Next topic this page

Set screen Java JVM Heap Metrics

  • JVM
    • JVM
      • Downtime
    • JVM Heap Used: The amount of heap in use for the application's VM. (This is applicable only to an instrumented application.)
    • JVM Heap Total: The total heap size of the application's VM. (This is applicable only to an instrumented application.)
    • JVM Heap Free: The amount of free heap space in the application’s VM. (This is applicable only to an instrumented application.)

Go to Top of this page.
Previous topic this page
Next topic this page

Set screen Java Platform Metrics

  • Classes
    • Classes Currently Loaded — several thousands.
    • Classes Loaded — several thousands.
    • Classes Unloaded
  • GC
    • GC Collections/sec
    • GC Time Spent in Collections
  • Threads
    • Threds Created/sec
    • Threds Current Count
    • Threds Current Daemon Count — a subset of the above.

Go to Top of this page.
Previous topic this page
Next topic this page

Set screen Web Server Metrics

    The default apache.cfg needs to be modified to included the following metrics beyond the default:

    Type Counter Name Description Notes
    - Uptime Apache Uptime (Apache) Uptime of the Apache server. Default
    CPU Utilization CPULoad Apache CPU Usage (Apache) Percentage of time the CPU is utilized by the Apache server.
    Resource Utilization BusyServers #Busy Servers (Apache) Number of servers in Busy state
    Resources Available IdleServers #Idle Servers (Apache) Number of servers in Idle state.
    Capacity Total Accesses Hits/sec (Apache) The rate of HTTP requests accessing the web server.
    - Total kBytes KBytes Sent/sec (Apache) The rate at which data bytes are sent from the Web server.
    - BytesPerReq Apache Average Bytes Per request (Apache) Average Bytes Per request of the Apache server. Default
    - BytesPerSec Apache Bytes Per Second (Apache) Bytes Per Second of the Apache server. Default
    - ReqPerSec Apache Requests Per Second (Apache) Requests Per Second of the Apache server. Default

Go to Top of this page.
Previous topic this page
Next topic this page

Set screen Mercury Diagnostics Sever Metrics

    A probe installed on the Mercury Diagnostics Server has this to show within its Profiler "Metrics" tab:

    • Online Cache
      • Active Nodes
      • Tree Aggregation Time
      • Trend Aggregation Time
    • Aggregator
      • Aggregated Txns/sec
      • Transactions Queued
    • Instance Trees
      • Avg. Trees Selected/sec
      • Max. Trees Selected/sec
      • Min. Trees Selected/sec
      • Total Trees Selected/sec
      • Trees Serialized/sec
    • Memory
      • Buffer Maps/s
      • Buffer Unmaps/s
      • Current Mapped Buffers
      • Heap Buffer Space
      • Mapped Buffer Space
    • Event Listener
      • Bytes/sec
      • Events/sec
      • Reads/sec
      • Total Buffer Full Count
    • Correlator
      • Data Blocs/sec
      • Fragments/sec
      • Transactions/sec
    • Persistence
      • Dirty Page %
      • Persistence Queries
      • Query Cache Hit %
      • Query Prefetch Populated Per Query
    • Symbol Table
      • Meta Reads From Disk/sec
      • Meta Writes To Disk/sec
      • Pathed Reads From Disk/sec
      • Pathed Writes To Disk/sec
      • Read Collisions/sec
      • Read Hits/sec
      • Reads From Disk/sec
      • Write Collisions/sec
      • Writes/sec
    • Query
      • Total Query Time

Go to Top of this page.
Previous topic this page
Next topic this page
IBM WebSphere PMI