<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Fault Tolerance - News</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Fault Tolerance News feed</description>
    <item>
      <title>Meta’s ZGateway Cuts ZippyDB Connections 19x While Handling 1B+ Operations per Second</title>
      <link>https://www.infoq.com/news/2026/09/meta-zgateway-zippydb-proxy/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Fault+Tolerance-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/09/meta-zgateway-zippydb-proxy/en/headerimage/generatedHeaderImage-1789253966189.jpg"/&gt;&lt;p&gt;Meta has introduced ZGateway, a stateless proxy for ZippyDB that centralizes connection management, traffic routing, caching, load balancing, and admission control. The gateway handles more than 1 billion operations per second and about 40% of ZippyDB traffic, while Meta’s model estimates a 19x reduction in persistent connections.&lt;/p&gt; &lt;i&gt;By Leela Kumili&lt;/i&gt;</description>
      <category>Scalability</category>
      <category>Caching</category>
      <category>Database</category>
      <category>multi-region</category>
      <category>Load Balancing</category>
      <category>Service Mesh</category>
      <category>Key-Value Store</category>
      <category>Availability</category>
      <category>Fault Tolerance</category>
      <category>Distributed Systems</category>
      <category>Routing</category>
      <category>Architecture &amp; Design</category>
      <category>Development</category>
      <category>news</category>
      <pubDate>Mon, 28 Sep 2026 13:55:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/09/meta-zgateway-zippydb-proxy/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Fault+Tolerance-news</guid>
      <dc:creator>Leela Kumili</dc:creator>
      <dc:date>2026-09-28T13:55:00Z</dc:date>
      <dc:identifier>/news/2026/09/meta-zgateway-zippydb-proxy/en</dc:identifier>
    </item>
    <item>
      <title>Uber Redesigns M3DB Sharding with Subclusters to Limit Failure Impact</title>
      <link>https://www.infoq.com/news/2026/09/uber-m3db-subcluster-sharding/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Fault+Tolerance-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/09/uber-m3db-subcluster-sharding/en/headerimage/generatedHeaderImage-1788717337142.jpg"/&gt;&lt;p&gt;Uber has redesigned shard placement in M3DB with fixed size subclusters to limit the impact of node failures, maintenance, and cluster scaling. The approach bounds shard dependencies, preserves replica isolation, and uses a greedy algorithm to select shard migrations while avoiding a separate rebalancing pass and unnecessary data movement.&lt;/p&gt; &lt;i&gt;By Leela Kumili&lt;/i&gt;</description>
      <category>Database</category>
      <category>Database Replication</category>
      <category>Load Balancing</category>
      <category>Sharding</category>
      <category>Availability</category>
      <category>Distributed Systems</category>
      <category>Clusters</category>
      <category>Scalability</category>
      <category>Time Series Data</category>
      <category>Open Source</category>
      <category>Uber</category>
      <category>Microservices</category>
      <category>Algorithms</category>
      <category>Fault Tolerance</category>
      <category>DevOps</category>
      <category>Architecture &amp; Design</category>
      <category>Development</category>
      <category>news</category>
      <pubDate>Mon, 21 Sep 2026 14:37:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/09/uber-m3db-subcluster-sharding/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Fault+Tolerance-news</guid>
      <dc:creator>Leela Kumili</dc:creator>
      <dc:date>2026-09-21T14:37:00Z</dc:date>
      <dc:identifier>/news/2026/09/uber-m3db-subcluster-sharding/en</dc:identifier>
    </item>
    <item>
      <title>AWS Cannot Restore Data Held Only in Damaged Middle East Availability Zones</title>
      <link>https://www.infoq.com/news/2026/09/aws-middle-east-data-loss/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Fault+Tolerance-news</link>
      <description>&lt;img src="https://www.infoq.com/styles/static/images/logo/logo_bigger.jpg"/&gt;&lt;p&gt;AWS has told customers it cannot restore resources and data hosted exclusively in the mec1-az2 availability zone in the UAE, or exclusively in the Bahrain region, after damage during the conflict with Iran. The company says the Bahrain damage spanned multiple availability zones and exceeded what its regional and multi-AZ services are designed to withstand.&lt;/p&gt; &lt;i&gt;By Steef-Jan Wiggers&lt;/i&gt;</description>
      <category>Cloud</category>
      <category>AWS</category>
      <category>Reliability</category>
      <category>Compliance</category>
      <category>Fault Tolerance</category>
      <category>Infrastructure</category>
      <category>Architecture</category>
      <category>DevOps</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Mon, 21 Sep 2026 08:43:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/09/aws-middle-east-data-loss/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Fault+Tolerance-news</guid>
      <dc:creator>Steef-Jan Wiggers</dc:creator>
      <dc:date>2026-09-21T08:43:00Z</dc:date>
      <dc:identifier>/news/2026/09/aws-middle-east-data-loss/en</dc:identifier>
    </item>
  </channel>
</rss>
