gcp-spark-observability
Monitors, inventories, and assesses Google Cloud Managed Service for Apache Spark (Dataproc Serverless and Dataproc on Compute Engine) environments, clusters, batches, jobs, sessions, metrics, logs, costs, and configurations across single and multiple regions. Use when listing active or historical Spark workloads, discovering failed batches or jobs, auditing multi-region fleet inventory, calculating Serverless compute (DCU-Hours) and shuffle storage consumption, detecting idle or zombie clusters, inspecting scheduled pipeline cadence health, investigating failed cluster operations or stockouts, checking quotas and alerting coverage, or querying Cloud Monitoring and Cloud Logging telemetry. Don't use for deep root-cause analysis or performance optimization of a specific job or batch (use gcp-spark-troubleshooting), authoring new PySpark code (use gcp-spark), or upgrading Spark versions (use gcp-managed-spark-upgrades).
- Version
- v1
- License
- Apache-2.0
Pinned to revision 6f4818a4c525, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/gcp-spark-observability/SKILL.md
- skills/gcp-spark-observability/references/gcloud_observability_reference.md
Every link opens the file at its source, pinned to the revision this page describes.