analyze_stage
Diagnose a Spark stage by examining shuffle, skew, spill, and GC metrics, slowest tasks, anti-patterns, and query-plan details to pinpoint performance bottlenecks.
Instructions
Deep-dive one Spark stage of a run: shuffle/skew/spill/GC numbers, slowest tasks, anti-patterns and a detailed analysis of the stage's query plan.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"run_id": "<run_id>",
"stage_id": "<stage_id>"
},
"name": "analyze_stage"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | No | ||
| run_id | Yes | ||
| stage_id | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||