An Early Benchmark of Quality of Experience Between HTTP/2 and HTTP/3 using Lighthouse

Abstract

Google's QUIC (GQUIC) is an emerging transport protocol designed to reduce HTTP latency. Deployed across its platforms and positioned as an alternative to TCP+TLS, GQUIC is feature rich: offering reliable data transmission and secure communication. It addresses TCP+TLS's (i) Head of Line Blocking (HoLB), (ii) excessive round-trip times on connection establishment, and (iii) entrenchment. Efforts by the IETF are in progress to standardize the next generation of HTTP's (HTTP/3, or H3) delivery, with their own variant of QUIC. While performance benchmarks have been conducted between GQUIC and HTTP/2-over-TCP (H2), no such analysis to our knowledge has taken place between H2 and H3. In addition, past studies rely on Page Load Time as their main, if not only, metric. The purpose of this work is to benchmark the latest draft specification of H3 and dig further into a user's Quality of Experience (QoE) using Lighthouse: an open source (and metric diverse) auditing tool. Our findings show that, for one of H3's early implementations, H3 is consistently worse than H2 in terms of performance.

On Cross-Layer Interactions of QUIC, Encrypted DNS and HTTP/3: Design, Evaluation, and Dataset

“…Resource Multiplexing [48] HTTP Adaptive Streaming (HAS) over H3 [49] H3 with Lighthouse [50] H3 adoption and performance measurement [51][52][53] H3 over LEO satellites [21] H3 with IoT [54] compared to HTTP/2. While HTTP/3 semantics and highlevel features of HTTP/2 are kept intact, some core protocol aspects have been substantially reworked [57].…”

Web Privacy By Design: Evaluating Cross-layer Interactions of QUIC, DNS and H/3

“…Resource Multiplexing [48] HTTP Adaptive Streaming (HAS) over H3 [49] H3 with Lighthouse [50] H3 adoption and performance measurement [51][52][53] H3 over LEO satellites [21] H3 with IoT [54] C. HTTP3 protocol…”

Exploring Proxying QUIC and HTTP/3 for Satellite Communication

“…A large fraction of previous studies [40]- [43] examines the performance of Google's QUIC flavor (gQUIC) that differs in fundamental points, such as the cryptographic handshake, from the IETF specification of QUIC [44]. Recent web performance evaluations show that HTTP/3 using IETF QUIC does not necessarily perform better than HTTP/2, which builds upon TCP [45], [46]. Saif et al [45] find that TCP performs better except if loss is present.…”

“…Recent web performance evaluations show that HTTP/3 using IETF QUIC does not necessarily perform better than HTTP/2, which builds upon TCP [45], [46]. Saif et al [45] find that TCP performs better except if loss is present. In this case, QUIC's design shows its strength by reducing the impact of head-of-line blocking.…”