Philippe Gerum wrote:
Jim Cromie wrote:
cycletest now has decent options passed in.
I havent given any thought to exposing options thru xeno-test's
Instead, Im thinking of adding statistics, ala latency.
for that, Im also pondering a new -g 100 option to group the tests
ie given: -g 100 -l 1000 -v
it would compute statistics on 10 sets of 100 cycles, and report 10
Again, this is notional, comments/feedback needed.
This would be mainly useful for running different test scenarii - i.e.
one per cycle? - I guess. But then, would not we have problems
interpreting the results, since different testcases might lead to
unrelated data sets? IOW, how would we use such data sets?
Several observations led me to this idea.
- in normal mode, the prog rewrites the same display line over and over
it plays-back oddly when you more/cat the file.
- with -v, it prints successive lines, but less info per line (no avg)
which makes sense, since the avg is at the bottom.
- 1000 lines of output is a boat-load, each is individually
uninteresting / almost same as others.
with latency, each line/second of the output contains the average of
10,000 samples of 100uS measures IIRC, and the inner min,max,avg tell us
about the high-frequency jitter,etc in the processes.
Then the multiple samples tell us something about the low-freq jitter.
IOW, we get a glimpse into the ergodicity of the noise
(I say that, pretending I _understand_ ergodicity)
Whether it applies / makes sense here, Im not at all sure.
:-) Ya gotta try this - simple, but highly addictive. A sport we can
I hope thats everything for now,
it needs a good shakedown, and I need a beer.
Eh, I hope you had it by now, otherwise, you must be so damn
Xenomai-core mailing list