<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Site Reliability Engineering</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Site Reliability Engineering feed</description>
    <item>
      <title>How Google Traced GKE API Timeouts to a Linux Kernel TCP Bug</title>
      <link>https://www.infoq.com/news/2026/11/gke-kernel-network-bug/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Site+Reliability+Engineering</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/11/gke-kernel-network-bug/en/headerimage/generatedHeaderImage-1794082671635.jpg"/&gt;&lt;p&gt;Google recently detailed how three interacting bugs across Google Kubernetes Engine (GKE), Private Service Connect, and the Linux kernel caused intermittent Kubernetes API connectivity failures, blocking around 800 developers from deploying to production.&lt;/p&gt; &lt;i&gt;By Renato Losio&lt;/i&gt;</description>
      <category>TCP</category>
      <category>Linux</category>
      <category>Networking</category>
      <category>Infrastructure</category>
      <category>Site Reliability Engineering</category>
      <category>Kubernetes</category>
      <category>Google Cloud</category>
      <category>DevOps</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Sat, 21 Nov 2026 09:44:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/11/gke-kernel-network-bug/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Site+Reliability+Engineering</guid>
      <dc:creator>Renato Losio</dc:creator>
      <dc:date>2026-11-21T09:44:00Z</dc:date>
      <dc:identifier>/news/2026/11/gke-kernel-network-bug/en</dc:identifier>
    </item>
    <item>
      <title>Article: Building Reliability into the Cloud: Observability as the Control Plane for Multi-Region Failover</title>
      <link>https://www.infoq.com/articles/observability-control-plane-failover/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Site+Reliability+Engineering</link>
      <description>&lt;img src="https://res.infoq.com/articles/observability-control-plane-failover/en/headerimage/header-1795002929606.jpg"/&gt;&lt;p&gt;Cloud SLAs promise uptime statistically, not absolutely. This article shows how to treat observability as a control plane that detects regional degradation, triggers automated failover, and confirms recovery rather than paging a human. Covers active-active architecture, DNS TTL pitfalls, composite Prometheus alerting, Route 53 weighted routing, and confirmation loops backed by a real S3 outage.&lt;/p&gt; &lt;i&gt;By Saurabh Ahuja&lt;/i&gt;</description>
      <category>Routing</category>
      <category>Cloud</category>
      <category>Architecture</category>
      <category>Cloud Computing</category>
      <category>Observability</category>
      <category>Site Reliability Engineering</category>
      <category>DevOps</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>article</category>
      <pubDate>Fri, 20 Nov 2026 09:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/articles/observability-control-plane-failover/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Site+Reliability+Engineering</guid>
      <dc:creator>Saurabh Ahuja</dc:creator>
      <dc:date>2026-11-20T09:00:00Z</dc:date>
      <dc:identifier>/articles/observability-control-plane-failover/en</dc:identifier>
    </item>
    <item>
      <title>Ten Years On, Google Updates the SRE Book for the AI Era</title>
      <link>https://www.infoq.com/news/2026/11/google-sre-book-ai-era/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Site+Reliability+Engineering</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/11/google-sre-book-ai-era/en/headerimage/generatedHeaderImage-1794674690062.jpg"/&gt;&lt;p&gt;Google has announced a completely rewritten second edition of Site Reliability Engineering: How Google Runs Production Systems, ten years after the original book was published by O'Reilly Media. The update reframes SRE around modern cloud architectures, platform engineering and AI workloads, while retaining the discipline's original emphasis on applying software engineering to operations.&lt;/p&gt; &lt;i&gt;By Matt Saunders&lt;/i&gt;</description>
      <category>Metrics</category>
      <category>Google</category>
      <category>Observability</category>
      <category>Site Reliability Engineering</category>
      <category>Service Level Objectives</category>
      <category>DevOps</category>
      <category>news</category>
      <pubDate>Tue, 17 Nov 2026 09:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/11/google-sre-book-ai-era/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Site+Reliability+Engineering</guid>
      <dc:creator>Matt Saunders</dc:creator>
      <dc:date>2026-11-17T09:00:00Z</dc:date>
      <dc:identifier>/news/2026/11/google-sre-book-ai-era/en</dc:identifier>
    </item>
  </channel>
</rss>
