> (slowdowns because releasing/acquiring the GIL is not free, particularly when contended) 

Yes, it's relatively high.  We shouldn't release the GIL only for ~0.5ms.  That's why 1MB~ seems nice threshold.

>  If the threshold is too low then users can always choose not to use multi-threading (and in general one doesn't expect much from it in Python)

I don't like this idea.  We shouldn't force users to change their program from multi threaded to single threaded.  So we need to avoid large performance regression.


> but if the threshold is too high then users have no recourse. That being said, 65536 does still seem a bit low based on the results available.

But they can get the benefit when input is too large. 65536 seems "too low" to me.