Go GC: Solving the Latency Problem in Go 1.5

Re:Go GC: Solving the Latency Problem in Go 1.5 by MrBuddyCasino on Thursday July 09, 2015 @05:29AM (#9856925)

Also, Azul Systems solved that issue - the proprietary C4 GC has no pauses, and the heap can be huge, like hundreds of GB. If that tech would become common place, maybe this discussion would be obsolete. But I think C4 requires kernel support, and the first attempt to get a patch accepted didn't go well.

[ Parent | on HN ]

Re:Go GC: Solving the Latency Problem in Go 1.5 by osi on Thursday July 09, 2015 @08:54AM (#9857530)

To clarify, Azul's Zing does have pauses, but they optimized the crap out of them (the pauses are more time-to-safepoint rather than GC pauses). GC time wrt application stopped time is constant regardless of heap size.

(I'm an Azul customer and Zing user)

[ Parent | on HN ]

Re:Go GC: Solving the Latency Problem in Go 1.5 by MrBuddyCasino on Thursday July 09, 2015 @09:00AM (#9857552)

Thanks, the marketing implies its pause-less. What are typical application stop times?

[ Parent | on HN ]

Re:Go GC: Solving the Latency Problem in Go 1.5 by osi on Thursday July 09, 2015 @09:39AM (#9857765)

My mean pauses are a few hundred micros. Standard deviation is slightly more (300-500 micros), with a max of a millisecond or two.

[ Parent | on HN ]

Re:Go GC: Solving the Latency Problem in Go 1.5 by pcwalton on Thursday July 09, 2015 @01:01PM (#9859172)

Azul also sacrifices throughput over the HotSpot GC to achieve very low pause times—the overhead of a GC is not just in its pause times! There's no free lunch.

[ Parent | on HN ]