Re: GC thread performance

[Hans Åberg]

> On 3 Dec 2017, at 23:15, Arne Babenhauserheide <address@hidden> wrote:
> 
> Hans Åberg <address@hidden> writes:
> 
>> I see the the expected behavior when turing off the GC altogether,
>> using malloc and free without cleanup: I third of the time on one
>> thread, decreasing up to hardware concurrency.
> 
> I also saw that - I think we tracked it down to the GC heuristics
> miscalculating when to run and running either too often or too seldomly.

I looked at the GC interface for way to make collections more rare, but could 
not find that.

> I think we didn't get to actually fixing the underlying issue, though we
> found that it should be possible.

The GC mailing list server is down, and has been that for some time it seems, 
so it is unclear about the state of the package.