Lei, HUANG
da14ee21cf
* fix(mito2): look up row group stats by parquet leaf index for nested columns On flat-format tables a logical column can expand to multiple parquet leaf columns (e.g. a JSON2 struct stores the remainder and one leaf per promoted path). ParquetFlat used the logical column index in the SST schema directly as the leaf index when reading row group statistics, so min/max/null stats of every column after a nested column were read from wrong leaves. When the misplaced leaf held order-compatible statistics (e.g. a small Int64 JSON path vs. the timestamp window predicate), min-max pruning dropped whole row groups by mistake. SWCS compaction reads inputs with a time window predicate, so it silently lost all rows of such files; plain queries with time-range predicates were affected as well. Map each column to its first parquet leaf column and report NoStats for columns with multiple leaves, which makes pruning conservative for them. Add a unit test and a sqlness regression case that reproduces the data loss on the unfixed binary. Signed-off-by: Lei, HUANG <ratuthomm@gmail.com> * fix(mito2): skip nested root stats and correct SWCS regression baseline Signed-off-by: Lei, HUANG <ratuthomm@gmail.com> * fix(mito2): resolve statistics leaves for primary-key SST readers Resolve scalar roots against the actual Parquet schema in shared statistics helpers, covering both flat and primary-key readers. Remove flat-side translation to avoid mapping twice and align encoded primary-key statistics as well. Cover dense flat, legacy dense and sparse layouts with statistics and time-pruning regressions. Signed-off-by: Lei, HUANG <ratuthomm@gmail.com> * test(mito2): distinguish known null counts from unknown statistics Assert validity before reading timestamp null counts and add a nullable scalar after the nested root with a known nonzero count. Exercise the assertions for flat and primary-key SST layouts. Signed-off-by: Lei, HUANG <ratuthomm@gmail.com> * test(mito2): check JSON2 time pruning before SWCS compaction Query the first time window immediately after FLUSH to cover predicate reads on flush-written SSTs independently of compaction outputs. Regenerate the sqlness expectation and retain the post-compaction checks. Signed-off-by: Lei, HUANG <ratuthomm@gmail.com> * test(mito2): validate all business columns after JSON2 SWCS Expand the final regression query to all eight business columns so the generated expectation verifies complete rows, including tags and scalar fields, after repeated compaction. Signed-off-by: Lei, HUANG <ratuthomm@gmail.com> --------- Signed-off-by: Lei, HUANG <ratuthomm@gmail.com> (cherry picked from commit743261f05e) Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com> (cherry picked from commit113db823e8) Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com>
One database for metrics, logs, and traces
replacing Prometheus, Loki, and Elasticsearch
The unified OpenTelemetry backend — with SQL + PromQL on object storage.
- Introduction
- Overview
- Features
- How GreptimeDB Compares
- Architecture
- Try GreptimeDB
- Getting Started
- Build From Source
- Tools & Extensions
- Project Status
- Community
- License
- Commercial Support
- Contributing
- Acknowledgement
Introduction
GreptimeDB is an open-source observability database built for Observability 2.0 — treating metrics, logs, and traces as one unified data model (wide events) instead of three separate pillars.
Use it as the single OpenTelemetry backend — replacing Prometheus, Loki, and Elasticsearch with one database built on object storage. Query with SQL and PromQL, scale without pain, cut costs up to 50×.
Overview
A quick overview of what GreptimeDB ingests, how it connects to other systems, and what its distributed engine lets you do.
Features
| Feature | Description |
|---|---|
| Observability 2.0 native | Logs, metrics, and traces in one engine with SQL + PromQL. Native OpenTelemetry, Prometheus remote write, and Jaeger. Migrate one signal at a time, or use as a single backend. |
| Elastic compute-storage separation | Scale reads independently with horizontal replicas. Serve high-concurrency workloads from dashboards, alerting, and AI agents — without resharding or data migration. |
| Sub-second on PB–EB-scale data | Columnar engine with fulltext, inverted, and skipping indexes. Written in Rust. Designed for high-concurrency point queries, not just analytical scans. |
| 50× lower cost | Object storage (S3, GCS, Azure Blob) as primary storage, with a tiered cache (memory + local disk) to keep writes and queries fast. |
Perfect for:
- Replacing Prometheus + Loki + Elasticsearch with a single observability backend
- Scaling past Prometheus — high cardinality, long-term storage, no Thanos/Mimir overhead
- AI/agent workloads — store GenAI telemetry (OTel GenAI conventions), and serve high-concurrency reads from SRE/developer agents via horizontal read replicas
- Cutting observability costs with object storage (up to 50× savings on traces, 30% on logs)
- Edge-to-cloud observability with unified APIs on resource-constrained devices
Why Observability 2.0? Three separate databases for metrics, logs, and traces means three storage layers, three query languages, and three sets of dashboards. GreptimeDB stores all three as timestamped wide events in one columnar engine — JOIN across signals in SQL, run one stack instead of three, and ingest AI agent telemetry the same way. Read more: Observability 2.0 and the Database for It.
Learn more in Why GreptimeDB.
How GreptimeDB Compares
| Capability | GreptimeDB | Prometheus / Thanos / Mimir | Grafana Loki | Elasticsearch |
|---|---|---|---|---|
| Data types | Metrics, logs, traces | Metrics only | Logs only | Logs, traces |
| Query language | SQL + PromQL | PromQL | LogQL | Query DSL |
| Storage | Native object storage (S3, etc.) | Local disk + object storage (Thanos/Mimir) | Object storage (chunks) | Local disk |
| Scaling | Compute-storage separation, stateless nodes | Federation / Thanos / Mimir — multi-component, ops heavy | Stateless + object storage | Shard-based, ops heavy |
| Cost efficiency | Up to 50× lower storage cost | High at scale | Moderate | High (inverted index overhead) |
| OpenTelemetry | Native (metrics + logs + traces) | Partial (metrics only) | Partial (logs only) | Via instrumentation |
Benchmarks:
Architecture
GreptimeDB can run in two modes:
- Standalone — single binary for development and small deployments.
- Distributed — four components, each independently scalable:
- Frontend — protocol entry (OTel, Prometheus, MySQL/PostgreSQL, gRPC, ingestion APIs for Elasticsearch/InfluxDB/Loki) and the distributed query engine. Stateless, scales horizontally.
- Datanode — region engine with WAL, memtable, SST, cache, compaction, and indexes. Persists data to object storage. Elastic.
- Metasrv — metadata, routing, repartitioning, autopilot, and security. Backed by a pluggable KV layer (etcd or RDS).
- Flownode (optional) — continuous flow computation (streaming and materialized views).
For deeper coverage, see the architecture doc or DeepWiki.
Try GreptimeDB
For AI agents — paste this prompt into your agent:
Read https://docs.greptime.com/SKILL.md and follow the instructions
to deploy, configure, ingest, and query GreptimeDB.
docker run -p 127.0.0.1:4000-4003:4000-4003 \
-v "$(pwd)/greptimedb_data:/greptimedb_data" \
--name greptime --rm \
greptime/greptimedb:latest standalone start \
--http-addr 0.0.0.0:4000 \
--rpc-bind-addr 0.0.0.0:4001 \
--mysql-addr 0.0.0.0:4002 \
--postgres-addr 0.0.0.0:4003
Dashboard: http://localhost:4000/dashboard
Read more in the full Install Guide.
Troubleshooting:
- Cannot connect to the database? Ensure that ports
4000,4001,4002, and4003are not blocked by a firewall or used by other services. - Failed to start? Check the container logs with
docker logs greptimefor further details.
Getting Started
Build From Source
Prerequisites:
- Rust toolchain — nightly, pinned by
rust-toolchain.toml - Protobuf compiler (>= 3.15)
- C/C++ building essentials:
gcc/g++/autoconfand the glibc dev package (libc6-devon Ubuntu,glibc-develon Fedora) - Python toolchain (optional, only for some test scripts)
Build and run:
make # build greptime binary
cargo run -- standalone start # start in standalone mode
Common dev commands:
make fmt # format Rust code
make clippy # lint (fails on warnings)
make test # unit + integration tests (uses cargo-nextest)
make sqlness-test # SQL regression tests
See the Contribution Guidelines for the full developer workflow.
Tools & Extensions
- Kubernetes: GreptimeDB Operator
- Helm Charts: Greptime Helm Charts
- Dashboard: Web UI
- gRPC Ingester: Go, Java, C++, Erlang, Rust, .NET
- Grafana Data Source: GreptimeDB Grafana data source plugin
- Grafana Dashboard: Official Dashboard for monitoring
Project Status
GreptimeDB is at v1.0 GA with stable APIs and regular releases. It runs in production at scale — OceanBase Cloud operates 80+ GreptimeDB clusters managing 300 TB of logs, cutting log storage cost by 60% after migrating from Grafana Loki. See more in case studies.
Read the v1.0 highlights and 2026 roadmap, or browse the version reference.
If GreptimeDB is useful to you, please star the repo.
Community
We invite you to engage and contribute!
License
GreptimeDB is an open-core project. Its core is licensed under the Apache License 2.0.
A small set of peripheral, enterprise-only features are gated behind the
enterprise Cargo feature (not built by default) and are governed by the
separate GreptimeDB Enterprise License. Source files under
that license carry an explicit Enterprise License header.
Commercial Support
Running GreptimeDB in your organization? We offer enterprise add-ons, services, training, and consulting. Contact us for details.
Contributing
- Read our Contribution Guidelines.
- Explore Internal Concepts and DeepWiki.
- Pick up a good first issue and join the #contributors Slack channel.
Acknowledgement
Special thanks to all contributors! See AUTHOR.md.
- Uses Apache Arrow™ (memory model)
- Apache Parquet™ (file storage)
- Apache DataFusion™ (query engine)
- Apache OpenDAL™ (data access abstraction)
All trademarks, logos, and brand names referenced in this README and in the Overview diagram are the property of their respective owners. Their use is for identification purposes only and does not imply endorsement or affiliation.