Luke Gorrie

Have been having a look at how to integrate `intel_mp` with the `core.worker` module. I hope it would be straightforward to replace the shell code for running Snabb processes with...

@wingo I wonder actually whether the YANG support would be suitable even for such simple cases as test suite programs? The `intel_mp` tests run a few related programs and need...

@wingo Neat :) So would it be reasonable for one Snabb process to provide configuration to another by constructing the value as a Lua object and serializing that to a...

@javierguerragiraldez Thanks for playing along :) How about if we break this down into smaller sub-questions? 1. Do we need side-traces? (How come everything can't be a root trace?) 1....

I dived into the code and I have some thoughts on this one: > Can side traces have loops? Yes and no. The answer depends on how we define the...

(This line of thought also matches with the explanation that @corsix gave a ways back: https://github.com/LuaJIT/LuaJIT/issues/208#issuecomment-236399378.)

I want to propose a new answer: The main difference between a root trace and a side trace is that a root trace has an empty snapshot 0 whereas a...

More highly relevant code is [`lj_snap.c:lj_snap_replay()`](https://github.com/raptorjit/raptorjit/blob/master/src/lj_snap.c#L430) that sets up the special snapshot 0 to inherit from a parent trace. Reading now...

@raj2569 You read my mind! :-) I have actually been thinking about the implications of having a word size that accommodates all the major datatypes in networking, the largest common...

@szbnwer I usually use Linus's distributed development model for big changes. Rewriting the VM in C would be done on a branch. This branch could be used to experiment with...