Logo
Sign in

Apache Pegasus is a distributed key-value storage system designed for high performance, strong consistency, and horizontal scalability. It bridges the gap between in-memory systems like Redis and persistent stores like HBase, offering reliable data replication, automatic load balancing, and efficient cross-datacenter data migration.

Vendor

Vendor

The Apache Software Foundation

Company Website

Company Website

geo_faces.png
pegasus-ttl.png
Product details

Apache Pegasus

Apache Pegasus is a distributed key-value storage system designed to be horizontally scalable, strongly consistent, and high-performance. It fills the gap between in-memory systems like Redis and large-scale stores like HBase by offering persistent storage with low latency and robust consistency guarantees. Written entirely in C++, Pegasus uses RocksDB as its underlying engine and relies on the PacificA consensus protocol for replication and fault tolerance.

Features

  • Strong consistency via PacificA consensus protocol
  • Hash-based partitioning for horizontal scalability
  • Three-way replication for data durability
  • Automatic load balancing across ReplicaServers
  • Cold backup and restore using local or distributed filesystems
  • Eventually-consistent intra-datacenter replication (duplication)
  • Online partition splitting for dynamic scaling
  • Simple and well-defined APIs for client integration

Capabilities

  • Supports high-throughput read/write operations with low latency
  • Enables safe and fast data migration between data centers
  • Provides fault-tolerant storage with multi-level data safety
  • Facilitates real-time analytics through Pegasus-Spark integration
  • Offers operational flexibility with rebalance and snapshot tools
  • Compatible with distributed environments and cloud-native architectures

Benefits

  • Bridges the performance-consistency gap between Redis and HBase
  • Enhances system reliability with robust replication and backup
  • Reduces operational complexity through built-in automation
  • Improves scalability and availability for large-scale applications
  • Supports both online and offline data processing scenarios
  • Backed by the Apache Software Foundation for open governance