KeyDB is an in-memory database that supports various data structures and offers on-disk persistence, enabling high throughput of over 1 million operations per second with submillisecond latency. It provides high availability through active-replica nodes and scalable architecture, addressing the need for fast and reliable data access in applications with heavy workloads.
Funding
$1.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
CTTFounders
Product
Problem
Redis, while performant, can be limited by its single-threaded architecture, especially when handling heavy workloads. This can lead to bottlenecks and underutilization of modern multi-core processors, impacting overall throughput and latency. Traditional Redis setups also require complex configurations for high availability and active replication.
Solution
KeyDB is a multithreaded fork of Redis designed to overcome single-threaded limitations and maximize performance on modern hardware. It maintains full compatibility with the Redis protocol, modules, and scripts, serving as a drop-in replacement for existing Redis deployments. KeyDB's multithreaded architecture enables significantly higher throughput and lower latency by concurrently handling network I/O and query parsing. KeyDB also offers features like active-replication for simplified hot-spare failover, FLASH storage, and subkey expires. Its MVCC architecture allows non-blocking queries such as KEYS and SCAN, preventing performance degradation during large operations.
Target Audience
KeyDB is designed for developers and organizations that require a high-performance, scalable, and Redis-compatible in-memory database solution, particularly those dealing with heavy workloads and seeking to maximize hardware utilization.
Features
- Multithreaded architecture for concurrent network I/O and query processing
- MVCC (Multi-Version Concurrency Control) for non-blocking queries like KEYS and SCAN
- Active-Replication for simplified hot-spare failover and distributed writes
- Support for Redis protocol, modules, and scripts, ensuring drop-in compatibility
- FLASH storage option for utilizing SSDs as a memory extension
- Subkey EXPIREs for expiring members within a set
- TLS encryption support with high throughput
- Configurable durability preferences for RDB and AOF persistence
- Ability to dump and load directly to AWS S3
- ModJS: Open source Javascript module to create custom commands