Sharding and HTTP/2 Connection Reuse Revisited: Why Are There Still Redundant Connections?

TL;DR

Despite HTTP/2's multiplexing capabilities, many websites still open redundant connections mainly due to domain sharding and DNS load balancing, impacting performance and hindering innovation.

Contribution

This paper measures the prevalence of redundant HTTP connections and analyzes their causes, highlighting persistent issues despite HTTP/2's design goals.

Findings

36%-72% of websites cause redundant connections

Major causes include domain sharding and DNS load balancing

Redundant connections remain prevalent despite HTTP/2 adoption

Abstract

HTTP/2 and HTTP/3 avoid concurrent connections but instead multiplex requests over a single connection. Besides enabling new features, this reduces overhead and enables fair bandwidth sharing. Redundant connections should hence be a story of the past with HTTP/2. However, they still exist, potentially hindering innovation and performance. Thus, we measure their spread and analyze their causes in this paper. We find that 36% - 72% of the 6.24M HTTP Archive and 78% of the Alexa Top 100k websites cause Chromium-based webbrowsers to open superfluous connections. We mainly attribute these to domain sharding, despite HTTP/2 efforts to revert it, and DNS load balancing, but also the Fetch Standard.