News for hackers. Stuff that matters.

A comment on Go GC: Prioritizing low latency and simplicity. Parent comment

Re:Go GC: Prioritizing low latency and simplicity by tedunangst on Monday August 31, 2015 @10:16PM (#10150321)
Throughput is a problem that solves itself. Wait a year and buy a new computer. :)

Not kidding, though, the latency hit from stop the world only gets worse scaling from 32 cores to 64. May as well call it "batch" GC. On the other hand, concurrent GC will keep the same latency but hopefully double throughput on such a machine.

[ Parent | on HN ]
Re:Go GC: Prioritizing low latency and simplicity by pcwalton on Monday August 31, 2015 @10:25PM (#10150348)
Unlikely. GC, especially non-generational GC, is a memory bound application with low arithmetic intensity and locality. The scaling will likely be sublinear, especially with that many CPUs.
[ Parent | on HN ]
Re:Go GC: Prioritizing low latency and simplicity by tedunangst on Monday August 31, 2015 @10:55PM (#10150457)
Yes, perhaps a poor assumption. But at what point will the scaling go negative? Even 25% more throughput (same latency) seems preferable to 100% more latency (same throughput). Is it fair to assume latency will be linear with the "server" GC?
[ Parent | on HN ]