<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Kfunc on Mi&amp;Bee Blog</title><link>/en/tags/kfunc/</link><description>Recent content in Kfunc on Mi&amp;Bee Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>蓝宝石的傻话</managingEditor><lastBuildDate>Sat, 13 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="/en/tags/kfunc/rss.xml" rel="self" type="application/rss+xml"/><item><title>BPF OOM Kernel Patches Deep Dive: Custom OOM Policies with eBPF</title><link>/en/posts/telemetry/ebpf-oom-bpf-patches/</link><pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate><guid>/en/posts/telemetry/ebpf-oom-bpf-patches/</guid><description>&lt;p&gt;The previous articles showed how to use eBPF to observe OOM events. But we could only watch, not intervene. The kernel&amp;rsquo;s OOM Killer decides who lives and dies based on the &lt;code&gt;oom_badness()&lt;/code&gt; algorithm, with no user control.&lt;/p&gt;
&lt;p&gt;In 2025, Google engineer Roman Gushchin proposed the BPF OOM kernel patch series, aiming to let eBPF programs fully take over OOM handling policy. This is the biggest change to Linux memory management&amp;rsquo;s OOM subsystem in nearly two decades.&lt;/p&gt;</description></item></channel></rss>