<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Wsl on Luther Monson</title>
    <link>https://luth.io/tags/wsl/</link>
    <description>Recent content in Wsl on Luther Monson</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Thu, 20 Aug 2026 20:45:00 -0700</lastBuildDate>
    <atom:link href="https://luth.io/tags/wsl/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>My Benchmark Was 4x Wrong Because of WSL</title>
      <link>https://luth.io/blog/2026/08/benchmark-4x-wrong-wsl-drvfs-cwd/</link>
      <pubDate>Thu, 20 Aug 2026 20:45:00 -0700</pubDate>
      <guid>https://luth.io/blog/2026/08/benchmark-4x-wrong-wsl-drvfs-cwd/</guid>
      <description>&lt;p&gt;I do most of my benchmarking on a Windows box in WSL2. It&amp;rsquo;s the machine on my desk with 32 threads and 62 GB of RAM.&#xA;Everybody who does that learns the first rule early: don&amp;rsquo;t put your data on &lt;code&gt;/mnt/c&lt;/code&gt;. DrvFs is the 9p-backed mount that&#xA;exposes the Windows drives inside WSL, and it&amp;rsquo;s slow for file-heavy work. So the databases, the docroot and the build&#xA;output all live on the WSL ext4 disk. My scaling harness for &lt;a href=&#34;https://github.com/ephpm/ephpm&#34;&gt;ePHPm&lt;/a&gt; even says so in&#xA;capital letters in its README.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
