Urgent.News

What's breaking now, across thousands of outlets.

Tech

We rewrote LF Edge eKuiper in Rust: 425k eps, 8MB RAM, 13ms boot (vs Flink, Go eKuiper & Benthos)

Over at I-Dacs Labs , we run high-throughput telemetry pipelines on edge devices (Raspberry Pis, Advantech gateways, and embedded x86/ARM boxes). We've been using LF Edge eKuiper for local stream processing (SQL filtering, sliding windows, and MQTT/Kafka sinks), but kept hitting the classic edge computing wall: JVM engines (Apache Flink) : Incredible throughput, but require >1 GB RAM and take 20+…

I-Dacs Labs has rewritten the LF Edge eKuiper engine from Java to Rust, a significant step forward for high-throughput telemetry pipelines on edge devices. Traditional JVM-based engines like Apache Flink require 1 GB RAM and take 20+ seconds to boot, while Go-based alternatives like Upstream eKuiper and Benthos, although lighter, suffer from tail latency jitter and packet loss under burst sensor loads.

By rewriting the engine in pure Rust, the team achieved an impressive 425,308 events per second with zero data loss and only 8-9 MB of idle RAM consumption. The Rust-based rekuiper boots in just 12.5-14.5 milliseconds, a stark contrast to the 1.2 seconds required by Go eKuiper and the 20 seconds needed for Apache Flink. Notably, rekuiper's lock-free stream bus and bounded actor queues for sinks eliminate runtime GC pauses, resulting in a highly efficient and reliable edge computing solution.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

More from Thursday 10 September →