AutoFlow: Hotspot-Aware, Dynamic Load Balancing for Distributed Stream Processing

TL;DR

AutoFlow is a system that dynamically balances load in distributed stream processing by monitoring hotspots and migrating states, improving performance without significant latency overhead.

Contribution

AutoFlow introduces a centralized scheduler with hotspot-aware algorithms and efficient state migration for dynamic load balancing in streaming dataflows.

Findings

Achieves effective load balancing in skewed workloads

Maintains low latency overhead during rebalancing

Supports implicit barriers and time-window load measurement

Abstract

Stream applications are widely deployed on the cloud. While modern distributed streaming systems like Flink and Spark Streaming can schedule and execute them efficiently, streaming dataflows are often dynamically changing, which may cause computation imbalance and backpressure. We introduce AutoFlow, an automatic, hotspot-aware dynamic load balance system for streaming dataflows. It incorporates a centralized scheduler which monitors the load balance in the entire dataflow dynamically and implements state migrations correspondingly. The scheduler achieves these two tasks using a simple asynchronous distributed control message mechanism and a hotspot-diminishing algorithm. The timing mechanism supports implicit barriers and a highly efficient state-migration without global barriers or pauses to operators. It also supports a time-window based load-balance measurement and feeds them to the hotspot-diminishing algorithm without user interference. We implemented AutoFlow on top of Ray, an actor-based distributed execution framework. Our evaluation based on various streaming benchmark dataset shows that AutoFlow achieves good load-balance and incurs a low latency overhead in highly data-skew workload.