0 views collected around this technical thread.
This article introduces JMH, explains why it outperforms simple loops or other tools, and provides step‑by‑step Maven setup, benchmark creation, execution, and advanced annotations such as @Warmup, @Fork, @Setup, Blackhole usage, and SpringBoot integration for accurate Java micro‑benchmarking.
This article introduces JMH, explains its key features, and presents microbenchmark results comparing thread‑exclusive, thread‑shared, Snowflake, UUID, and Snowflake‑algorithm GUID generation methods under various thread counts, accompanied by the full Java test code.
This article explains why simple timing is unreliable in Java due to JIT compilation, introduces the official JMH tool for microbenchmarking, outlines best‑practice tips, demonstrates how to set up a Maven project, write benchmark code, run tests, interpret results, and details each JMH annotation.
This article explains how to quickly benchmark Java code performance, introduces the JMH microbenchmarking tool, provides sample JMH benchmark code comparing System.currentTimeMillis() and System.nanoTime(), and presents the results showing nanoTime's superior throughput.
This article introduces Java Microbenchmark Harness (JMH), explains why warm‑up is necessary, details common annotations, shows how to set up a Maven project, provides a complete benchmark example comparing LinkedList iteration methods, and demonstrates how to run and interpret the results.
This article introduces JMH, the official Java microbenchmarking tool, explains why warm‑up is needed, shows how to build a Maven project, provides a complete LinkedList iteration benchmark example, demonstrates common JMH annotations, and outlines how to run and interpret benchmark results.
This article details the performance tuning of Vivo's Java-based push recommendation service, covering background challenges, measurement metrics, hotspot code and JVM GC optimizations, custom split utilities, map key improvements, off‑heap caching, and the resulting throughput and latency gains.
The Vivo Push recommendation service was dramatically accelerated by replacing regex‑based String.split with a custom utility, converting massive String‑key maps to long keys, and moving large caches off‑heap, which together cut latency by about 32%, boosted throughput roughly 45% and nearly doubled overall performance.
This article introduces Java Microbenchmark Harness (JMH), explains why warm‑up is needed, walks through project setup with Maven, demonstrates benchmark code for LinkedList iteration, details common JMH annotations, shows how to run and interpret results, and concludes with practical usage tips, while also mentioning a promotional book giveaway.
This article introduces Java Microbenchmark Harness (JMH), explains why warm‑up is needed, shows how to build a benchmark project with Maven, provides a complete LinkedList iteration benchmark example with all relevant JMH annotations, demonstrates execution commands, and interprets the resulting performance reports.
This article examines the performance of four Java integer-to-string conversion methods—Integer.toString, String.valueOf, a+"", and ""+a—by conducting raw loop tests and detailed JMH microbenchmarks, analyzing JVM warm-up, JIT, and OSR effects to reveal reliable measurement practices.
JMeter’s reported throughput can be misleading because it includes local processing time, especially when response validation such as regex extraction adds overhead, leading to significant underestimation of actual server load; the article demonstrates this with experiments and suggests micro‑benchmark corrections to obtain accurate results.
This article introduces JMH, explains how to add dependencies, write and run microbenchmarks for string concatenation, describes key annotations, highlights common pitfalls, and shows how to package, visualize, and integrate JMH benchmarks within Java projects.
The article explains how to conduct microbenchmark tests for API parameter signing, measures the overhead of signature generation, and demonstrates using a custom performance testing framework to isolate request processing time and improve throughput accuracy.
This article describes how Tubi’s engineering team built and optimized a real‑time recommendation backend, using ScalaMeter microbenchmarks and wrk2 load testing to measure latency, throughput and error rates, and demonstrates scaling the service across multiple machines with custom scripts.
This article shares Vipshop’s extensive Java performance‑optimization experience, introduces the open‑source VJTools project for profiling and troubleshooting, and presents practical insights on common pitfalls, reliable techniques, JIT fundamentals, micro‑benchmarking, useful tools, and real‑world case studies from Vipshop’s architecture.