OSI/TS Configuration and Management Manual

Performing Monitoring and Troubleshooting Guide
OSI/TS Configuration and Management Manual—424831-001
4-2
Why Measure Performance?
performance analysis concepts to identify potential sources of problems and areas that
need further investigation.
Why Measure Performance?
The level of performance of your OSI/TS subsystem directly affects the level of
performance of your entire system and your network and, ultimately, your company’s
ability to do business effectively.
Good performance is a large part of the value of your system to its users. If they feel
that the performance of your system is unsatisfactory, they may not use it effectively,
even if it correctly performs the required functions.
What to Measure
Performance is usually measured in terms of response time, job turnaround time, or
system throughput. The primary concern of a user sitting at a terminal is typically the
first two. The primary concern of the system manager is usually reliable and
satisfactory throughput.
General Sources of Performance Problems
In general, the CPU is the source of congestion for networks using LANs, and line speed
is the source of congestion for networks using X.25 WANs. This is due to the maximum
bandwidth capability on each type of network. The throughput on a LAN (measured in
either messages per second or bytes per second) can be much greater than on an X.25
network, which can cause the CPU to become the limiting factor in achieving higher
performance. The lower aggregate bandwidth on X.25 networks can cause saturation of
the line before another resource (such as the CPU) becomes congested.
Since subsystem resources are limited by the capacity of their various hardware and
software components, only a limited number of users or programs can make use of any
given resource at a given time. For example, only one application at a time can run
during each CPU cycle, and the order in which that application requires the necessary
resources is usually rigid. If a resource is not available, the application must wait until
the resource has been made available again.
In the Compaq environment, this situation is improved. There are multiple CPUs in a
Compaq system, and work can be spread among the CPUs to achieve some simultaneity
of processing. Even with multiple CPUs, however, some may be overloaded, while
others are not. This results in the same resource availability problem that occurs on
single-CPU systems. To aggravate the problem, other resources, such as disks or
communications lines, may be overutilized.
The actual users of your system resources are the system itself (control information) and
the applications running on the system. Competition for resources can lead to long
queues for the use of a particular resource. Congestion is typically due to the
overutilization of such resources as memory, CPU processing, disk processing, and
communications line capacity. To achieve a substantial improvement in your system
performance, you may need to distribute the workload by moving part of it to another