<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Scaling on Sai Ram&#39;s Blog</title>
    <link>https://sairam.dev/categories/scaling/</link>
    <description>Recent content in Scaling on Sai Ram&#39;s Blog</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <copyright>&amp;copy; 2020. All rights reserved.</copyright>
    <lastBuildDate>Sat, 11 Mar 2017 23:00:00 +0530</lastBuildDate>
    
	<atom:link href="https://sairam.dev/categories/scaling/index.xml" rel="self" type="application/rss+xml" />
    
    
    <item>
      <title>How to scale requests to a single IP (DC)</title>
      <link>https://sairam.dev/post/2017-03-11-how-to-scale-ip-at-dc/</link>
      <pubDate>Sat, 11 Mar 2017 23:00:00 +0530</pubDate>
      
      <guid>https://sairam.dev/post/2017-03-11-how-to-scale-ip-at-dc/</guid>
      <description>Scaling app servers to nearly unlimited size is easy to explain but really hard in practice. It basically amounts to this:
 Balance requests using DNS anycast so you can spread load before it hits your servers Setup &amp;ldquo;Head End&amp;rdquo; machines with as large pipes as possible (40Gbps?) and load balance at the lowest layer you can. Balance at IP level using IPVS and direct server return. A single reasonable machine can handle a 40Gbps pipe&amp;hellip;.</description>
    </item>
    
  </channel>
</rss>