Tandem Capacity Model (TCM) Manual

1 Introduction
TCM is a workstation-based capacity planning tool for NonStop systems. Capacity planners can
use TCM to estimate future system performance from current data.
The TCM system is modeled in terms of transactions so that the results can be readily understood
by a wide audience. TCM uses data from the Measure product, a performance monitoring product
that runs on the HP NonStop system. Because Measure does not instrument transactions, TCM
helps you convert Measure data into transaction-oriented data. TCM then uses the
transaction-oriented data to predict performance for changing workloads and configurations.
TCM does the following:
• Estimates the amount of hardware required to meet current and projected business needs
• Predicts the performance of user applications
• Forecasts the maximum capacity of your current systems
TCM and Related Products
TCM works with the Measure and MeasTCM HP products. TCM uses data collected by Measure
on the NonStop host system and summarized by MeasTCM. For detailed information about Measure,
consult the Measure Reference Manual. For detailed information about how to use MeasTCM, see
Chapter 3: “Using MeasTCM”.
TCM includes MeasTCM and the workstation-based TCM software. For a complete list of the
hardware and software required to run TCM, see the SOFTDOC file.
Functions and Features
You can use TCM to:
• Translate process-oriented performance data from MeasTCM into transaction-oriented
performance data.
This process, known as workload apportionment, is a major aspect of capacity planning for
HP NonStop systems.
• Predict the following usage:
Number of CPUs◦
◦ Number of logical disk volumes
◦ Average and percentile host response times for OLTP transactions and average response
times for batch transactions
◦ Online CPU utilization for both single-core and multi-core processors
◦ Disk utilization
• Archive and organize historical performance data.
This feature helps the capacity planner in many crucial activities, such as model validation,
sample selection, and trend analysis.
• Predict future transaction throughput based on historical information.
• Answer what-if questions regarding apportioned baseline data; estimated throughputs; host
response times; and the number of processors, disks, or both for various user-defined scenarios.
• Generate charts to aid in decision making and the presentation of capacity management
alternatives and recommendations.
18 Introduction