https://alimov.dev/tags/jmh/ Recent content in Jmh on alimov.dev Hugo en-us Tue, 07 Apr 2026 00:00:00 +0000 https://alimov.dev/posts/reactive-source-sink-benchmarking-backpressure-in-pulsar-pipelines/ Tue, 07 Apr 2026 00:00:00 +0000 https://alimov.dev/posts/reactive-source-sink-benchmarking-backpressure-in-pulsar-pipelines/ <h2 id="introduction">Introduction</h2> <p>Does wrapping a blocking Pulsar consumer in <code>Flux.generate</code> give you backpressure? Does adding backpressure cost you throughput?</p> <p>The first answer is no — wrapping blocking calls in Reactor operators creates something that looks reactive but behaves like a fire hose. The second answer is also no: a properly implemented reactive pipeline is <strong>dramatically faster</strong> than both alternatives. Our JMH benchmark shows the reactive approach hitting <strong>6.29 million messages/sec</strong> — 27x faster than the Flux-wrapped approach (232k msg/sec) and 24,800x faster than plain blocking (253 msg/sec). The reactive pipeline is faster because it does less work per message: no thread blocking, no <code>Mono.fromCallable</code> allocation, no <code>boundedElastic</code> scheduling overhead.</p>