<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Benchmark on Matheus Oliveira</title><link>https://blog.omatheusmesmo.dev/en/tags/benchmark/</link><description>Recent content in Benchmark on Matheus Oliveira</description><image><title>Matheus Oliveira</title><url>https://blog.omatheusmesmo.dev/images/duke.svg</url><link>https://blog.omatheusmesmo.dev/images/duke.svg</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Sun, 08 Nov 2026 10:00:00 -0300</lastBuildDate><atom:link href="https://blog.omatheusmesmo.dev/en/tags/benchmark/index.xml" rel="self" type="application/rss+xml"/><item><title>Inside the Quarkus reactive core, part 4: reactive or virtual threads in Quarkus 4</title><link>https://blog.omatheusmesmo.dev/en/posts/quarkus-4-reactive-or-virtual-threads/</link><pubDate>Sun, 08 Nov 2026 10:00:00 -0300</pubDate><guid>https://blog.omatheusmesmo.dev/en/posts/quarkus-4-reactive-or-virtual-threads/</guid><description>Reactive or virtual threads in Quarkus 4: why event loops are not carriers, what Java 21, Jackson 3, Vert.x 5 and Netty 4.2 change, Little&amp;#39;s law applied to the Quarkus default pools, an open-model benchmark of the three models on Quarkus 4.0.0.Beta1 and 3.40.1, why reactive and virtual threads collapse past the REST Client connection pool while workers hold, a pinning audit per integration and a decision table.</description></item></channel></rss>