Hi Joe, all
I ran into some issues on a roach 1 where the 10 gbe buffer would fill up and overflow before i had run tap_start (if I recall correctly). In that case, no data would ever be transmitted, and I had to add a software register to the overflow port to see this was the case. Executing tap_start before enabling my logic to send data fixed this.
This could be the problem, when the buffers in the 10Ge core overflow, bad things happen. The internal state machine gets into a bad state and data packets do not happen. We try to prevent this at all costs. The 1Ge yellow block (as far as I am aware) is based on the 10Ge one so the same rules apply.
Regards Andrew
