Monitoring & Observability

Tetrapus exposes Prometheus metrics on :9888/metrics, tracks frame-level GPU performance, ingestion throughput, and memory usage. Console and Wiretap panes provide real-time operational visibility.

Prometheus Metrics

Full inventory: histograms, gauges, counters for rendering, ingestion, and memory.

Alerts & Escalation

Threshold alerting with lifecycle tracking, escalation chains, and composite alarms.

Health & Diagnostics

Thread health, WAL status, Console log viewer, and Wiretap event stream.

Observability Stack

Prometheus, Grafana, Watchtower, Cloudflare Tunnel deployment.

Key Metrics

Category	Examples
Rendering	frame_time_ms, fps, draw_calls, triangles, gpu_submit_ms
Ingestion	ingest_received_total, ingest_failed_total, partition_queue_depth
System	memory_bytes (RSS via /proc/self/statm)
GPU	culling_time_ms, update_time_ms, upload_time_ms, upload_bytes

Questions?

Reach out for help with integration, deployment, or custom domain codecs.

Get Started Request a Demo