This is a response to this issue:
https://discuss.ardupilot.org/t/gyro-problem-after-waypoint-log-analisys
The 2nd gyro went bad with a large offset. Then the first gyro was
marked unhealthy, forcing the EKF to switch to the 2nd gyro. That
resulted in a crash.
I think the SPI bus was getting bad transfers and the register check
code happened to get a bad transfer, thereby marking the first gyro
unhealthy
This change ensures we only fail the register check if two transfers
in a row are bad. This makes it much less likely that a noisy bus will
lead to an unhealthy gyro
bugobliterator
Andrew Tridgell
Lucas De Marchi