netty5/microbench
Nick Hill 2791f0fefa Avoid use of global AtomicLong for ScheduledFutureTask ids (#9599)
Motivation

Currently a static AtomicLong is used to allocate a unique id whenever a
task is scheduled to any event loop. This could be a source of
contention if delayed tasks are scheduled at a high frequency and can be
easily avoided by having a non-volatile id counter per queue.

Modifications

- Replace static AtomicLong ScheduledFutureTask#nextTaskId with a long
field in AbstractScheduledExecutorService
- Set ScheduledFutureTask#id based on this when adding the task to the
queue (in event loop) instead of at construction time
- Add simple benchmark

Result

Less contention / cache-miss possibility when scheduling future tasks

Before:

Benchmark      (num)   Mode  Cnt    Score    Error  Units
scheduleLots  100000  thrpt   20  346.008 ± 21.931  ops/s

Benchmark      (num)   Mode  Cnt    Score    Error  Units
scheduleLots  100000  thrpt   20  654.824 ± 22.064  ops/s
2019-09-25 07:34:25 +02:00
..
src/main Avoid use of global AtomicLong for ScheduledFutureTask ids (#9599) 2019-09-25 07:34:25 +02:00
pom.xml [maven-release-plugin] prepare for next development iteration 2019-09-12 16:09:55 +00:00
README.md Change the netty.io homepage scheme(http -> https) (#9344) 2019-07-09 21:09:42 +02:00

Microbenchmark tests

See our wiki page.