PigPaxos: Devouring the Communication Bottlenecks in Distributed Consensus

  title={PigPaxos: Devouring the Communication Bottlenecks in Distributed Consensus},
  author={Aleksey Charapko and Ailidani Ailijiang and Murat Demirbas},
  journal={Proceedings of the 2021 International Conference on Management of Data},
Strongly consistent replication helps keep application logic simple and provides significant benefits for correctness and manageability. Unfortunately, the adoption of strongly-consistent replication protocols has been curbed due to their limited scalability and performance. To alleviate the leader bottleneck in strongly-consistent replication protocols, we introduce Pig, an in-protocol communication aggregation and piggybacking technique. Pig employs randomly selected nodes from follower… 

Devouring the Leader Bottleneck in BFT Consensus

This work introduces Stratus, a robust shared mempool protocol that decouples transaction distribution from consensus in BFT consensus, and provides easy-to-use APIs so that other BFT systems suffering from leader bottlenecks can use it.

Scalable but wasteful: current state of replication in the cloud

This work proposes a new metric to measure the efficiency of consensus protocols and shows that using this metric, for example, the optimized EPaxo protocol is less efficient than the unoptimized Multi-Paxos protocol, and demonstrates that Multi- Paxos can achieve 2$\times higher throughput than EPaxos in a fixed-budget resource setting that is typical of the cloud.

Scaling Blockchain Consensus via a Robust Shared Mempool

Stratus is a robust shared mempool protocol that decouples transaction distribution from consensus in BFT consensus, to have replicas disseminate transactions in a distributed manner and have the leader only propose transaction ids.

Fault-Tolerant Replication with Pull-Based Consensus in MongoDB

The design and implementation of strongly consistent replication in MongoDB is presented, how this consensus protocol works, how MongoDB integrates it with the rest of the replication system, and the extensions of the replicated protocol that support the authors' rich feature set are described.

Mandator and Sporades: Robust Wide-Area Consensus with Efficient Request Dissemination

The combination of Mandator and Sporades (Mandator-Sporades) provides a robust and high-performing state machine replication system that outperforms Mandator-PXos, Multi-Paxos, and EPaxos in the face of targeted distributed denial-of-service attacks.

Nezha: Deployable and High-Performance Consensus Using Synchronized Clocks

This paper presents a high-performance consensus protocol, Nezha, designed for single-cloud-region environments, which can be deployed by cloud tenants without any support from their cloud provider, and compares it with Multi-Paxos, Fast Paxos, Raft, a NOPaxos version the authors optimized for the cloud, and 2 recent protocols, Domino and TOQ-based EPaxos that use synchronized clocks.

Bottlenecks in Blockchain Consensus Protocols

  • S. AlqahtaniM. Demirbas
  • Computer Science
    2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS)
  • 2021
This paper studies the performance and the scalability of prominent consensus protocols, namely PBFT, Tendermint, HotStuff, and Streamlet, both analytically via load formulas and practically via implementation and evaluation and identifies the bottlenecks.

Automatic Compartmentalization of Distributed Protocols

  • Computer Science
  • 2022
As systems scale and distributed protocols become the bottlenecks, scalable variants have emerged, but these protocols are highly specialized to specific workloads, complicating the challenge of choosing the right protocol for every different environment.

Baxos: Backing off for Robust and Efficient Consensus

This work proposes Baxos, a new resilient consensus protocol that leverages a random exponential backoff scheme as a replacement for leader election in consensus algorithms and offers more robustness to liveness and performance downgrade attacks than leader-based consensus protocols.

Scaling Replicated State Machines with Compartmentalization [Technical Report]

The first comprehensive technique to eliminate state machine replication bottlenecks is introduced, and it is demonstrated how to compartmentalize MultiPaxos to increase its throughput by 6× on a write-only workload and 16x on a mixed read-write workload.



Dissecting the Performance of Strongly-Consistent Replication Protocols

This work presents an analytic modeling of the protocols using queuing theory and shows simulations under varying controlled parameters to cross-validate the analytic model, and presents empirical results from the prototyping and evaluation framework, Paxi.

Canopus: A Scalable and Massively Parallel Consensus Protocol

Canopus is proposed, a highly-parallel consensus protocol that is 'plug-compatible' with ZooKeeper, which exploits modern data center network topology, parallelism, and consensus semantics to achieve scalability with respect to the number of participants and throughput.

Revisiting consensus protocols through wait-free parallelization

This paper proposes a protocol-agnostic approach to improve the design of primary backup consensus protocols and presents coordination-free techniques to order operations across parallel instances, deal with instance failures, and assign clients to specific instances.

Optimistic replication

This article identifies key challenges facing optimistic replication systems---ordering operations, detecting and resolving conflicts, propagating changes efficiently, and bounding replica divergence---and provides a comprehensive survey of techniques developed for addressing these challenges.

HotStuff: BFT Consensus with Linearity and Responsiveness

HotStuff is the first partially synchronous BFT replication protocol exhibiting these combined properties, and its simplicity enables it to be further pipelined and simplified into a practical, concise protocol for building large-scale replication services.

ZooKeeper: Wait-free Coordination for Internet-scale Systems

ZooKeeper provides a per client guarantee of FIFO execution of requests and linearizability for all requests that change the ZooKeeper state to enable the implementation of a high performance processing pipeline with read requests being satisfied by local servers.

PaxosStore: High-availability Storage Made Practical in WeChat

A layered design of the Paxos-based storage protocol stack is proposed, where PaxosLog, the key data structure used in the protocol, is devised to bridge the programming-oriented consistent read/write to the storage-oriented Paxos procedure.

DPaxos: Managing Data Closer to Users for Low-Latency and Mobile Applications

The main objective of DPaxos is to reduce the latency of serving user requests, recovering from failures, and reacting to mobility, and achieves these objectives by a few proposed changes to the traditional Paxos protocol.

WPaxos: Wide Area Network Flexible Consensus

The dynamic partitioning of the object-space and emphasis on zone-local commits allow WPaxos to significantly outperform both partitioned Paxos deployments and leaderless Paxos approaches.

ResilientDB: Global Scale Resilient Blockchain Fabric

It is shown that GeoBFT is not only sound and provides great scalability, but also outperforms state-of-the-art consensus protocols by a factor of six in geo-scale deployments.