platoneko / databend

An elastic and reliable Modern Cloud Data Warehouse, offers Blazing Fast Query and combines Elasticity, Simplicity, Low cost of the Cloud, built to make the Data Cloud easy

A Modern Cloud Data Warehouse with the Elasticity and Performance both on Object Storage

Website | Roadmap | Documentation

• What is Databend?
• Design Overview
  • Meta Service Layer
  • Compute Layer
  • Storage Layer
• Getting Started
• Roadmap

What is Databend?

Databend is an open source elastic and scalable Modern Cloud Data Warehouse.

Databend is multi-cluster, shared data architecture, disaggregates compute resource scaling from storage resources, offers blazing fast query and combines elasticity, simplicity, low cost of the cloud, built to make the Data Cloud easy.

• Elastic

  • Storage and compute resources can be scaled up/down on your demand

• Serverless

  • You don’t have to think about servers, you pay only for what you actually used

• User-Friendly

  • ANSI SQL compliant, MySQL/ClickHouse/REST API

• Security

  • All data files and network traffic in Databend is encrypted end-to-end

Design Overview

Databend is inspired by ClickHouse and its computing model is based on apache-arrow.

Databend consists of three components: meta service layer, and the decoupled compute and storage layers.

Meta Service Layer

The meta service is a layer to service multiple tenants. In current implementation, the meta service has components:

• Metadata - Which manages all metadata of databases, tables, clusters, the transaction, etc.
• Administration Which stores user info, user management, access control information, usage statistics, etc.
• Security Which performs authorization and authentication to protect the privacy of users' data.

Compute Layer

The compute layer is the clusters that running computing workloads, each cluster have many nodes, each node has components:

• Planner - Builds execution plan from the user's SQL statement.
• Optimizer - Optimizer rules like predicate push down or pruning of unused columns.
• Processors - Vectorized Execution Engine, which is build by planner instructions.
• Cache - Caching Data and Indexes based on the version.

Many clusters can attach the same database, so they can serve the query in parallel by different users.

Storage Layer

Databend stores data in an efficient, columnar format as Parquet files. For efficient pruning, Databend also creates indexes for each Parquet file to speed up the queries.

Getting Started

• Databend Docs
• Databend Deploy
• Databend Develop
• Databend Contributing
• Databend Performance
• Databend Weekly

Roadmap

Databend is currently in Alpha and is not ready to be used in production, Roadmap 2022

License

Databend is licensed under Apache 2.0.

Acknowledgement

Document Hosting