HI,
I am not able to measure the interrupt latency with the tm_basic module.
First: I run the tm_basic on my NIOS II demo board It gives me all the informations except the interrupt latency it is normal at this point.
Second: I added the 2 options with the ecos config tools CYGVAR_KERNEL_COUNTERS_CLOCK_LATENCY & CYGVAR_KERNEL_COUNTERS_CLOCK_DSR_LATENCY)
I also added the definition of HAL_CLOCK_LATENCY() in the hal_intr.h module# ifdef CYGVAR_KERNEL_COUNTERS_CLOCK_LATENCY # define HAL_CLOCK_LATENCY( _pvalue_ ) HAL_CLOCK_READ( _pvalue_ )# endif
Now when I run the tm_basic, the program stops after the printout of
Reading the hardware clock takes 78 'ticks' overhead
... this value will be factored out of all other measurements
It blocks in the loop :
// Try and measure how long the clock interrupt handling takes
for (i = 0; i < nsamples; i++) {
tick0 = cyg_current_time();
while (true) {
tick1 = cyg_current_time();
if (tick0 != tick1) break;
}
HAL_CLOCK_READ(&tv[i]);
}
The tick1 doesn’t increase
The RealTimeClock::isr runs but the dsr is not working.
Am I wrong in this procedure ?
Thanks for your advice.
