Pangolin boosts blockchain speed and reliability with secure parallel commits
Pangolin: Efficient DAG-based BFT State-Machine Replication with TEE-Accelerated Commitment
Distributed, Parallel, and Cluster Computing
Summary
Many computer systems that must agree on a shared sequence of actions use special protocols to avoid errors or attacks; these protocols can be slow or complicated. The authors propose Pangolin, a new system that allows multiple parts to work in parallel to speed up agreement while still being secure and reliable. Pangolin uses a secure hardware feature to reduce communication steps and speed up confirming decisions, and it includes better ways to manage memory and handle client requests. Overall, Pangolin performs faster than comparable systems without relying on strict timing rules that might fail in distributed networks.
What this means in practice
- •For blockchain system developers: Build faster and more reliable consensus layers that handle faults efficiently with low communication overhead using secure hardware support.
- •For distributed database engineers: Implement scalable replicated state machines that maintain consistency and responsiveness even in highly asynchronous or geo-distributed environments.
Authors
Paul Franke-Bergmann, Maya Kuhlmann, Alexander Heß, Marc Leinweber, Rüdiger Kapitza, Hannes Hartenstein, Franz J. Hauck, Christian Berger
Abstract
Currently many Byzantine fault-tolerant (BFT) protocols use directed acyclic graphs (DAGs) to let replicas propose blocks of requests in parallel for improved throughput. Yet, the existing DAG-based designs mainly consider the atomic-broadcast layer: They typically do not describe an efficient client interaction layer, their garbage collection is either unspecified or relies on trusted external storage, and the lowest-latency designs rely on timing assumptions that may be violated in geo-distributed deployments. In this paper, we propose the Pangolin protocol: It introduces a novel low-latency DAG-based atomic broadcast layer and completes it into an efficient state-machine replication (SMR) framework. To preserve system throughput, clients issue requests to a single replica and verify replies efficiently via compact execution proofs. Furthermore, Pangolin introduces a new garbage-collection scheme for DAGs which bounds memory usage even under full asynchrony. Pangolin leverages trusted execution environments to tolerate f Byzantine faults with only n >= 2f + 1 replicas and accelerates vertex commitments significantly: Broadcasting certified vertices requires only a single communication step, and commit rules are refined to commit both frequently and early without revealing the coin-elected anchor. This way, Pangolin overtakes the fastest partially synchronous DAG protocols while being live under asynchrony: In our evaluation, Pangolin achieves an average 1.27x (up to 1.52x) latency speedup over Mysticeti.