Transaction

jmetaB025f577cdcd1411ccbd9f803e265b0d98e70f2a9a4fc9bdeed977ab872050b44e9@6e310a0579acad2cd4035426f1abe6c508d443dd4241600efb7c245ddb21c7da atom.entrymetarss.netMQ<entry> <title type="text">What happens to latency if service time is cut in half</title> <id>https://pveentjer.github.io/misc/2022/04/18/service-time-cut-in-half.html</id> <updated>2024-06-18T06:26:16.640583Z</updated> <link href="https://pveentjer.github.io/misc/2022/04/18/service-time-cut-in-half.html"/> <author> <name>luu</name> <uri>https://news.ycombinator.com/user?id=luu</uri> </author> <content type="html">&lt;img src=&#34;https://pveentjer.github.io/assets/utilization_plot.png&#34; style=&#34;width: 220px; height: 232px;&#34; /&gt;&lt;br /&gt;The author discusses the impact of cutting service time in half on latency, using queuing theory formulas to calculate the arrival rate and latency. The results show a 11x improvement in latency, contradicting Martin Thompson&#39;s claim of a 20x improvement. &lt;a href=&#34;https://hackernews.betacat.io/#what-happens-to-latency-if-service-time-is-cut-in-half&#34; target=&#34;_blank&#34;&gt;[summary]&lt;/a&gt; &lt;a href=&#34;https://news.ycombinator.com/item?id=40714544&#34; target=&#34;_blank&#34;&gt;[comments]&lt;/a&gt;</content> </entry>