|
|
| Line 1: |
Line 1: |
| | These terms do not state a common model for time measurements. I believe it is relatively well-established | | These terms do not state a common model for time measurements. I believe it is relatively well-established |
| | that the following events and time periods are of interest when measuring realtime performance: | | that the following events and time periods are of interest when measuring realtime performance: |
| − |
| |
| − | == Events ==
| |
| − | * A - hardware interrupt assertion
| |
| − | ** This is the time when the hardware interrupt line for an event is raised
| |
| − | * B - Interrupt service routine starts execution
| |
| − | * C - Process starts execution
| |
| − | * D - Result is received from processing the event
| |
| − |
| |
| − | == Time Periods ==
| |
| − | Real time performance is often expressed in terms of the maximum, minimum and average duration
| |
| − | for certain time periods defined by the events above.
| |
| − |
| |
| − | Here are some common terms, expressed relative to those events:
| |
| − | ; Interrupt latency : The time from A to B
| |
| − | ; Scheduling latency : The time from B to C (this is sometimes referred to as the time from A to C)
| |
| − | ; Processing time : The time from C to D
| |
| − | ; Response latency : The time from A to D
| |
| − |
| |
| − | Often, these or similar terms are used with less accuracy to describe the closest
| |
| − | approximation one can get to these, with a particular test framework and instrumentation set.
| |
| − |
| |
| − | For example, Response latency may be reported as "response time", and refer to the time from
| |
| − | when a host program records the time, previous to transmitting a piece of data which will cause
| |
| − | an interrupt on the target machine, to the time when a host program records the time after
| |
| − | receiving some signal from the target that processing is completed. Of course, time is taken
| |
| − | in the operations of recording time, tranmissing data, and detecting signals on the host machine.
| |
| − | But it may be that timing these individual operations at a finer granularity requires
| |
| − | instrumentation or hardware support not reasonably available for a test.
| |
These terms do not state a common model for time measurements. I believe it is relatively well-established
that the following events and time periods are of interest when measuring realtime performance:
