Pioplat: A Scalable, Low-Cost Framework for Latency Reduction in Ethereum Blockchain

TL;DR

Pioplat addresses latency in permissionless blockchains by deploying a distributed cluster of relay nodes across continents alongside an instrumented full node to elastically reduce message latency without modifying the underlying protocol. It combines adaptive neighbor selection with a low-latency relay communication protocol (including UDP for small messages and complete-object forwarding) and data caches to minimize propagation delays for blocks and transactions. The authors provide a complete open-source implementation and present extensive evaluation showing substantial latency reductions (e.g., blocks by ≈$0.8$ s and transactions by ≈$0.92$ s) as relays are added, along with sustained improvements under different tunings and comparisons to Peri. The framework enables latency-sensitive use cases such as arbitrage and MEV extraction, offering a scalable, cost-efficient solution with practical deployment considerations and directions for future automatic tuning.

Abstract

As decentralized applications on permissionless blockchains are prevalent, more and more latency-sensitive usage scenarios emerged, where the lower the latency of sending and receiving messages, the better the chance of earning revenue. To reduce latency, we present Pioplat, a feasible, customizable, and low-cost latency reduction framework consisting of multiple relay nodes on different continents and at least one instrumented variant of a full node. The node selection strategy of Pioplat and the low-latency communication protocol offer an elastic way to reduce latency effectively. We demonstrate Pioplat's feasibility with an implementation running on five continents and show that Pioplat can significantly reduce the latency of receiving blocks/transactions and sending transactions, thus fulfilling the requirements of most latency-sensitive use cases. Furthermore, we provide the complete implementation of Pioplat to promote further research and allow people to apply the framework to more blockchain systems.

Figures (5)

• Figure 1: Overview of Pioplat system: relay nodes distributed across different continents are connected to each other via a low-latency communication protocol, and they are all connected to one (or more) instrumented variant full node to obtain the forkID and redirect data requests. Users of Pioplat reduce latency by simply connecting their full nodes to one or more relay nodes.
• Figure 2: When a Pioplat relay node receives a block or transaction body message never seen before from the blockchain p2p network, the relay node broadcasts the message to other relay nodes at first. The left figure depicts the expected scenario; The right figure depicts the redundant message transmission between relay nodes when multiple receive new messages simultaneously.
• Figure 3: The datagram format in communication between relay nodes. It consists header and a complete block or transaction object.
• Figure 4: The top graph shows the latency of receiving blocks comparison between Baseline and Pioplat; The bottom graph shows the trend of Pioplat latency with the addition of a relay node, where each vertical dotted line indicates the moment when a new relay node is connected.
• Figure 5: The top graph shows the latency of receiving blocks comparison between Peri and Pioplat; The bottom graph shows the timestamp difference of receiving transactions between Peri and Pioplat;