대시보드

Мониторинг HQ-SRV и BR-SRV — ЦП, ОП, Диск

MinIO AIStor — RDMA. GPU-Direct RDMA (api side) and internode RDMA (server-to-server). Both populate only on clusters with RDMA-capable NICs and the feature enabled.

Dashboard for zyxel-exporter — PoE power, CPU/memory, port traffic and link status from a Zyxel switch scraped via Prometheus.

ZTE G5TS 5G CPE signal quality, CPU temperature, thermal policy and network monitoring via zte-cpe-go exporter

MinIO AIStor — Misc. Smaller subsystems collected in one place: software/build version, distributed locks, lambda function targets, stdout logger. Empty rows are normal when the relevant feature isn't configured.

MinIO AIStor — API QoS. Bucket-level rate-limiting metrics: configured limits per (bucket, rule, prefix), rate-limit-exceeded events, throttled requests. Empty until at least one QoS rule is configured.

Hardware report: server/PSU identity from BMC FRU, component temperatures (GPU/CPU/RAM/storage/PCIe) with averages and recommended-max exceedance, cooling and component health/state. BMC (IPMI) metrics update every minute; Redfish-sourced metrics every 5-10 minutes.

Apt Relay repository synchronization health, freshness, duration, file counters, size and process runtime metrics.

MinIO AIStor — Tables scanner + maintenance + recovery. Catalog scanner cycles and actions, maintenance configs and processing, recovery operations and zombie detection. A healthy cluster shows steady scanner cycles, low maintenance error rates, and zero recovery activity.

A new RabbitMQ Management Overview

Monitor inbound HTTP traffic in Spring Boot applications

GlassHub Otel observability platform

Watch either a single Pi-hole system or combine the statics of several in a single pane.

MinIO AIStor — Tables (Iceberg catalog). Catalog API request volume, errors, latency, in-flight concurrency, plus warehouse/namespace/table/view counts and active transactions. Dashboard data populates on any cluster with the tables feature enabled.

Monitoring cloud servers within Selectel.

Lightweight APM dashboard for monitoring OpenTelemetry-based services. Instrument your applications using OpenTelemetry SDKs and send traces, metrics, and logs to Tempo for traces, a Prometheus-compatible database like Mimir for metrics, and Loki for logs. This dashboard provides a centralized view of your application's health and performance. For a fully managed observability stack, consider using Grafana Cloud. Learn more about this dashboard on https://github.com/cyrille-lecler

A Palworld dedicated server dashboard for metrics exported by https://github.com/smbonn2005/palworld-exporter.

Prometheus Postfix exporter metrics.

CallCorp Prod Overview

Single-pane WordPress site health — traffic, latency, errors, security signals, and what each site is running. Companion to the Logystera WordPress agent.

APC UPS monitoring via prometheus-community snmp-exporter (apcups module). Requires snmp_exporter v0.30+ metric names (_seconds suffixes, EnumAsStateSet statuses). Status row for outage response, trends for battery/load/voltage history. Tested against an AP9630 (NMC2) management card.

Official dashboard for Synthetic Exporter. Monitors API health, SSL expiry, and active Playwright UI journeys.

Nvidia GPU Metrics based on the prometheus metrics from github.com/utkuozdemir/nvidia_gpu_exporter

NVIDIA GPU overview from DCGM metrics: utilisation, framebuffer memory, temperature and power, one series per GPU. Works against a real dcgm-exporter unchanged; temperature and power ship as recording rules.