Random Notes
  • Introduction
  • Reading list
  • Theory
    • Index
      • Impossibility of Distributed Consensus with One Faulty Process
      • Time, Clocks, and the Ordering of Events in a Distributed System
      • Using Reasoning About Knowledge to analyze Distributed Systems
      • CAP Twelve Years Later: How the “Rules” Have Changed
      • A Note on Distributed Computing
  • Operating System
    • Index
  • Storage
    • Index
      • Tachyon: Reliable, Memory Speed Storage for Cluster Computing Frameworks
      • Exploiting Commutativity For Practical Fast Replication
      • Don’t Settle for Eventual: Scalable Causal Consistency for Wide-Area Storage with COPS
      • Building Consistent Transactions with Inconsistent Replication
      • Managing Update Conflicts in Bayou, a Weakly Connected Replicated Storage System
      • Spanner: Google's Globally-Distributed Database
      • Bigtable: A Distributed Storage System for Structured Data
      • The Google File System
      • Dynamo: Amazon’s Highly Available Key-value Store
      • Chord: A Scalable Peer-to-peer Lookup Service for Internet Applications
      • Replicated Data Consistency Explained Through Baseball
      • Session Guarantees for Weakly Consistent Replicated Data
      • Flat Datacenter Storage
      • Small Cache, Big Effect: Provable Load Balancing forRandomly Partitioned Cluster Services
      • DistCache: provable load balancing for large-scale storage systems with distributed caching
      • Short Summaries
  • Coordination
    • Index
      • Logical Physical Clocks and Consistent Snapshots in Globally Distributed Databases
      • Paxos made simple
      • ZooKeeper: Wait-free coordination for Internet-scale systems
      • Just Say NO to Paxos Overhead: Replacing Consensus with Network Ordering
      • Keeping CALM: When Distributed Consistency is Easy
      • In Search of an Understandable Consensus Algorithm
      • A comprehensive study of Convergent and Commutative Replicated Data Types
  • Fault Tolerance
    • Index
      • The Mystery Machine: End-to-end Performance Analysis of Large-scale Internet Services
      • Gray Failure: The Achilles’ Heel of Cloud-Scale Systems
      • Capturing and Enhancing In Situ System Observability for Failure Detection
      • Check before You Change: Preventing Correlated Failures in Service Updates
      • Efficient Scalable Thread-Safety-Violation Detection
      • REPT: Reverse Debugging of Failures in Deployed Software
      • Redundancy Does Not Imply Fault Tolerance
      • Fixed It For You:Protocol Repair Using Lineage Graphs
      • The Good, the Bad, and the Differences: Better Network Diagnostics with Differential Provenance
      • Lineage-driven Fault Injection
      • Short Summaries
  • Cloud Computing
    • Index
      • Improving MapReduce Performance in Heterogeneous Environments
      • CLARINET: WAN-Aware Optimization for Analytics Queries
      • MapReduce: Simplified Data Processing on Large Clusters
      • Dryad: Distributed Data-Parallel Programs from Sequential Building Blocks
      • Resource Management
      • Apache Hadoop YARN: Yet Another Resource Negotiator
      • Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center
      • Dominant Resource Fairness: Fair Allocation of Multiple Resource Types
      • Large-scale cluster management at Google with Borg
      • MapReduce Online
      • Delay Scheduling: A Simple Technique for Achieving Locality and Fairness in Cluster Scheduling
      • Reining in the Outliers in Map-Reduce Clusters using Mantri
      • Effective Straggler Mitigation: Attack of the Clones
      • Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing
      • Discretized Streams: Fault-Tolerant Streaming Computation at Scale
      • Sparrow: Distributed, Low Latency Scheduling
      • Making Sense of Performance in Data Analytics Framework
      • Monotasks: Architecting for Performance Clarity in Data Analytics Frameworks
      • Drizzle: Fast and Adaptable Stream Processing at Scale
      • Naiad: A Timely Dataflow System
      • The Dataflow Model:A Practical Approach to Balancing Correctness, Latency, and Cost in Massive-Scale
      • Interruptible Tasks:Treating Memory Pressure AsInterrupts for Highly Scalable Data-Parallel Program
      • PACMan: Coordinated Memory Caching for Parallel Jobs
      • Multi-Resource Packing for Cluster Schedulers
      • Other interesting papers
  • Systems for ML
    • Index
      • A Berkeley View of Systems Challenges for AI
      • Tiresias: A GPU Cluster Managerfor Distributed Deep Learning
      • Gandiva: Introspective Cluster Scheduling for Deep Learning
      • Workshop papers
      • Hidden Technical Debt in Machine Learning Systems
      • Inference Systems
      • Parameter Servers and AllReduce
      • Federated Learning at Scale - Part I
      • Federated Learning at Scale - Part II
      • Learning From Non-IID data
      • Ray: A Distributed Framework for Emerging AI Applications
      • PipeDream: Generalized Pipeline Parallelism for DNN Training
      • DeepXplore: Automated Whitebox Testingof Deep Learning Systems
      • Distributed Machine Learning Misc.
  • ML for Systems
    • Index
      • Short Summaries
  • Machine Learning
    • Index
      • Deep Learning with Differential Privacy
      • Accelerating Deep Learning via Importance Sampling
      • A Few Useful Things to Know About Machine Learning
  • Video Analytics
    • Index
      • Scaling Video Analytics on Constrained Edge Nodes
      • Focus: Querying Large Video Datasets with Low Latency and Low Cost
      • NoScope: Optimizing Neural Network Queriesover Video at Scale
      • Live Video Analytics at Scale with Approximation and Delay-Tolerance
      • Chameleon: Scalable Adaptation of Video Analytics
      • End-to-end Learning of Action Detection from Frame Glimpses in Videos
      • Short Summaries
  • Networking
    • Index
      • Salsify: Low-Latency Network Video through Tighter Integration between a Video Codec and a Transport
      • Learning in situ: a randomized experiment in video streaming
      • Short Summaries
  • Serverless
    • Index
      • Serverless Computing: One Step Forward, Two Steps Back
      • Encoding, Fast and Slow: Low-Latency Video Processing Using Thousands of Tiny Threads
      • SAND: Towards High-Performance Serverless Computing
      • Pocket: Elastic Ephemeral Storage for Serverless Analytics
      • Fault-tolerant and Transactional Stateful Serverless Workflows
  • Resource Disaggregation
    • Index
  • Edge Computing
    • Index
  • Security/Privacy
    • Index
      • Differential Privacy
      • Honeycrisp: Large-Scale Differentially Private Aggregation Without a Trusted Core
      • Short Summaries
  • Misc.
    • Index
      • Rate Limiting
      • Load Balancing
      • Consistency Models in Distributed System
      • Managing Complexity
      • System Design
      • Deep Dive into the Spark Scheduler
      • The Actor Model
      • Python Global Interpreter Lock
      • About Research and PhD
Powered by GitBook
On this page
  • TL;DR:
  • Summary:
  • Note:
  • Related Links:

Was this helpful?

  1. Coordination
  2. Index

In Search of an Understandable Consensus Algorithm

https://web.stanford.edu/~ouster/cgi-bin/papers/raft-atc14

PreviousKeeping CALM: When Distributed Consistency is EasyNextA comprehensive study of Convergent and Commutative Replicated Data Types

Last updated 5 years ago

Was this helpful?

TL;DR:

Raft is a consensus algorithm that is designed to be easy to understand. It's equivalent to Paxos in fault-tolerance and performance.

Summary:

This paper introduces Raft, a consensus algorithm that is designed to be more understandable and practical than Paxos. It is similar to Paxos in efficiency and fault-tolerance(both algorithms operate in non-Byzantine, asynchronous model).

Before Raft, there already exist several consensus protocols(e.g., Paxos, view-stamped replication). However, as we know, Paxos is notoriously difficult to understand. Although the algorithm itself is not very complicated, the question I always ask when I study Paxos is: Why does it work? Besides, the Paxos algorithm introduced by Lamport is somewhat incomplete. For example, it doesn’t address the “Dueling Proposers” problem and the cluster membership management. The original version of Paxos(called Synod) is also inefficient since it needs two rounds to choose a single value.

The overall goal of Raft is same as multi-Paxos, which is to replicate a log of commands across a collection of computers. The techniques used by the authors include problem decomposition and reducing state space(“handle multiple problems with single mechanism”). The main difference between Paxos and Raft is that Raft will select one server to act as a leader and that server will be responsible for replicating the logs. The leader election of Raft is similar to the prepare phase of Paxos. Raft adds some restrictions on which server can be elected. Specifically, servers with incomplete logs are not eligible to become a leader.

After it elects a leader, the leader starts accepting command from the clients and appends the command to its log. Like the proposers in Paxos, the leader in Raft will send RPCs to all followers and declares victory when it gets the response from a majority of followers.

Note:

1. Raft uses Terms to identify obsolete information(e.g., old leaders). Each term starts with a leader election and has at most one leader(some terms may have no leader)

2.I think the leader election in Raft is somewhat different from the leader election algorithm(e.g., Bully algorithm). The leader election in Raft guarantees that only one leader is elected per term, but may fail due to timeouts in multiple followers, which means it may violate termination. In contrast, the other leader election algorithm solves “weak agreement” where it may not satisfy agreement(There might exist two leaders at the same time), but it always terminates.

Related Links: