Skip to content 
About M3DB
M3DB is Uber's open-source, distributed time-series database designed for large-scale metrics storage and processing. Originally developed to power Uber's massive monitoring infrastructure, M3DB serves as Prometheus remote storage with 100% PromQL compatibility. It features a multi-component architecture including M3 Coordinator (Prometheus sidecar), M3 Query (distributed query engine), and M3 Aggregator (stream-based downsampling), all coordinated through etcd clustering. M3DB excels at handling billions of time series with proven production scalability.
GreptimeDB vs. M3DB
| Feature/Aspect | GreptimeDB | M3DB |
|---|---|---|
| Data Model | Unified Observability Database | Distributed Time-Series Database |
| Value Model | Multi-Value (supports complex data structures) | Single-Value (Prometheus metrics) |
| Multi-model Support | Metrics, Logs & Traces in one database | Metrics only (requires separate systems for logs/traces) |
| Query Languages | SQL & PromQL (dual interface) | PromQL (100% compatibility) & M3QL |
| Ingestion Protocols | SQL gRPC InfluxDB Line Protocol Prometheus Remote Storage OpenTelemetry Loki Push API Elasticsearch Bulk API HTTP API | Prometheus Remote Write M3 Coordinator API Carbon (Graphite) |
| Data Retention | Flexible TTL policies with tiered storage | Configurable retention with automatic expiration |
| Continuous Aggregation | Built-in SQL aggregation, Pipeline ETL engine & Flow streaming computation | M3 Aggregator with stream-based downsampling |
| Deployment Complexity | Single system deployment | Multi-component deployment (coordinator, query, aggregator) |
| Use Cases | Unified observability, real-time analytics, IoT monitoring, edge computing | Large-scale Prometheus monitoring, metrics aggregation |
| Architecture | Cloud-native distributed with compute-storage separation | Multi-component architecture (M3DB + M3 Coordinator + M3 Query + M3 Aggregator) |
| Storage Format | Apache Parquet (columnar, compressed) | M3TSZ compression (optimized Gorilla TSZ) |
| Storage Scalability | Object storage integration with unlimited capacity | Distributed storage with automatic sharding |
| High Availability | Native clustering with automatic failover | Multi-region deployment with quorum-based consistency |
| License | Apache 2.0 | Apache 2.0 |
| Written Language | Rust (memory safety, performance) | Go (ecosystem compatibility) |
| Deployment Options | Single-node, cluster, Kubernetes-native, edge-to-cloud with unified API | Multi-component deployment with etcd coordination |
| Operational Complexity | Single unified system with simplified Kubernetes operations | Complex multi-component operations |
Join our community
Get the latest updates and discuss with other users.