Pauseless GC is a thing, and has been thoroughly studied for decades. It’s not even hard to implement. The problem is that a naive implementation of such a GC makes so many sacrifices in other areas—memory usage, throughput—that it’s undesirable in practice.
-
-
Also Azul C4/Shenandoah boosterism. These are awesome systems, but they are suitable only for a minority of applications.
-
Can you explain why?
@giltene preaches that when asked to choose between throughput and latency,@AzulSystems choose excellent engineering and took both.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.