Apache Spark History
Enables AI agents to connect with Apache Spark History Servers for intelligent job analysis and performance monitoring.
概要
Transform your Spark infrastructure monitoring with AI! This Model Context Protocol (MCP) server bridges AI agents with your existing Apache Spark infrastructure, allowing them to analyze job performance, identify bottlenecks, and provide intelligent insights from your Spark History Server data. It enables natural language queries for job details, performance metric analysis across applications, comparison of multiple jobs to identify regressions, investigation of failures with detailed error analysis, and generation of insights from historical execution data.
主な機能
- Query job details through natural language
- Analyze performance metrics across applications
- Compare multiple jobs to identify regressions
- Investigate failures with detailed error analysis
- Generate insights from historical execution data
- 71 GitHub stars
ユースケース
- Identify why an ETL job is running slower than usual by analyzing application metrics and generating optimization recommendations.
- Determine the root cause of a job failure by examining failed tasks, error messages, and executor logs.
- Compare today's batch job performance with yesterday's run to highlight configuration differences and identify performance deltas.