Observability
Collecting and analyzing observability data to troubleshoot the system
openGemini
A time-series database for observability, focusing on the storage and analysis of massive data.
Features
High Performance
Store and query data quickly and efficiently with automatic partitioning, LSM-based storage techniques, and better data process engineering
High Scalability
Adopting MPP architecture, support distributed cluster deployment and can be flexibly expanded as business grows to meet higher load requirements
High Cardinality
A new high cardinality storage engine solves problems such as excessive index memory usage and low read and write performance
Observability
Metrics, Logs and Traces can be stored in openGeminiļ¼provide a basis for data association analysis
Low O&M Costs
Scure and stable, simple architecture, quick deployment and no third-party dependencies
Data Compression
Data is stored in column format, and different data types use dedicated data compression algorithms. The data compression ratio is as high as 15:1 or higher
Application Scenarios
Blog
Four steps to teach you to automatically export flame graphs
A good helper for operations engineers
openGemini: Batch Query Optimization
This article introduces what is batch query and the performance problems caused by serial execution of batch query. openGemini makes full use of the powerful concurrent processing capability of Go language to carry out concurrent transformation of serial query, and proposes an adaptive parallel query task scheduler to solve the performance problems of serial query.
openGemini Optimization Example: Query a Plan Template
Database performance tuning is a process that requires patience and perseverance. It is necessary to continuously analyze and optimize, find out potential performance problems, and take appropriate measures to optimize. Only through continuous efforts and practice can we really improve the performance of the database system and provide better support for the business. This article presents an example of how to optimize openGemini based on flame graph analysis, and also describes how to add a query template to help readers.
openGemini: Full-Text Index Parsing
This article introduces the function of openGemini full-text index, including the basic principle, index creation, full-text query and filtering. Compared with the traditional full-text index, the CLV dynamic segmentation algorithm adopted by openGemini has great advantages in the memory resource consumption and matching efficiency of inverted index.
Join Us
Community
Gemini is open source.Star our GitHub repo,follow us on Twitter,and join our developer community on Slack
GitHub
Twitter
SlackContribution
We look forward to working with more enterprises, universities and developers to jointly promote technological innovation