Forums

Can an RTOS guarantee that interrupt latency will never exceed a predefined maximum?

Started by NewToFPGA January 19, 2008
Do we need to configure Interrupt rate limiting on the processor per
application basis? If so, can I configure it on only selective
interrupts?
NewToFPGA wrote:
> Do we need to configure Interrupt rate limiting on the processor per > application basis? If so, can I configure it on only selective > interrupts?
If a device supports it properly, it can be always be enabled. If the amount of traffic is low, the device won't delay the interrupts (low latency/bandwidth). Only if the interrupt rate is going up, and there is still FIFO space available, the interrupt rate will be limited, which trades off higher latency for higher bandwidth. Consult the documentation of any devices capable of interrupt rate limiting for exact details of this option.

NewToFPGA wrote:
> Can an RTOS guarantee that interrupt latency will never exceed a > predefined maximum? if so, where do we define this value in the > programming?
No. But, It can be done by careful design of your system by you. Karthik Balaguru