Minimize blocking time on Rev 3 nRF51822

RE: Minimize blocking time on Rev 3 nRF51822

ovrebekk — Wed, 18 Nov 2015 10:35:45 GMT

"So if I advertise with very little data and send very little during a connection, all of my times will stay far below max?"

Yes, I would expect so.

You can not have 2 GPIOTE channels controlling the same output pin, that is correct. We fixed this problem in the nRF52 series by introducing separate SET and CLEAR tasks for each GPIOTE channel.

RE: Minimize blocking time on Rev 3 nRF51822

Nikolaus Wittenstein — Tue, 17 Nov 2015 19:42:55 GMT

Luckily I don't have that much data to send, so hopefully I'll be good on that front!

I was mostly curious because the max time is highest at the end of a connection event. It wasn't clear to me if that time changed based on how much data was sent (vs. e.g. the 290μs after sending a packet). So if I advertise with very little data and send very little during a connection, all of my times will stay far below max?

I may just have to try the GPIO toggling, unless I can figure out some way to gate a PWM using the PPI. Turns out you can't have two different GPIOTE blocks controlling the same output pin??

Thanks!

RE: Minimize blocking time on Rev 3 nRF51822

ovrebekk — Tue, 17 Nov 2015 10:17:39 GMT

The short answer is to try to send as little data as possible ;)

The worst case numbers in the SDS typically occur if you are sending 6 packets per connection event (which is the maximum for the S110). If you don't send anything, or only send a single packet per connection event, the interrupt times will be much shorter.

Exactly how long the interrupts are depends on many factors, and isn't specified in detail, but if you have a scope available you could do some measurements on your own. Simply use the old trick where you toggle a GPIO quickly in the main loop, and observe on the scope how long the pauses in the toggling is.

Regards
Torbjørn