RFR: Non-cancellable mark loops should have sensible stride

[Roman Kennke]

Am 05.07.2018 um 09:41 schrieb Aleksey Shipilev:
> On 07/05/2018 09:38 AM, Roman Kennke wrote:
>> It looks ok. But why did we do it in the first place? It looks like this
>> was done on purpose. But it also seems illogical. Can you hg annotate it
>> and see how that happened?
> 
> We did this to match the old code while refactoring mark_loop. Our intent was to compile down the
> strided marking loop to the same "process one element, check for termination" shape we used to have.
> But that is nonsensical, and performance data shows it really does not make sense.
> 

Yes, makes sense. Please push that change.

Thanks, Roman