Imported from qdrant/skills (
skills/qdrant-monitoring/setup/SKILL.md). Install upstream withnpx skills add qdrant/skills --skill setup. Copyright stays with the author.
How to Set Up Qdrant Monitoring
Get Prometheus scraping working first, then health probes, then alerting. Do not skip monitoring setup before going to production.
Prometheus Metrics
Use when: setting up metric collection for the first time or adding a new deployment.
- Node metrics at
/metricsendpoint Monitoring docs - Cluster metrics at
/sys_metrics(Qdrant Cloud only) - To add a prefix to metric names, see Metrics configuration
- Example self-hosted setup with Prometheus + Grafana prometheus-monitoring repo
- Datadog integration: collect metrics via the OpenMetrics
/metricsendpoint Datadog integration
Hybrid Cloud Scraping
Use when: running Qdrant Hybrid Cloud and need cluster-level visibility.
Do not just scrape Qdrant nodes. In Hybrid Cloud, you manage the Kubernetes data plane. You must also scrape the cluster-exporter and operator pods for full cluster visibility and operator state.
- Hybrid Cloud Prometheus setup tutorial Hybrid Cloud Prometheus
- Official Grafana dashboards Grafana dashboard repo
Liveness and Readiness Probes
Use when: configuring Kubernetes health checks.
- Use
/healthz,/livez,/readyzfor basic status, liveness, and readiness Kubernetes health endpoints
Alerting
Use when: setting up alerts for production or Hybrid Cloud deployments.
- Qdrant Cloud provides pre-configured email alerts for 11 cluster issues. Use scraped metrics when you need custom alerts or routing to other targets. See Cloud cluster monitoring
- Use AlertmanagerConfig to route alerts to Slack, PagerDuty, or other targets based on labels
- At minimum, alert on: optimizer errors, node not ready, replication factor below target, disk usage >80%
Log Centralization and Audit Logging
Use when: enterprise compliance requires centralized logs or audit trails.
- Enable JSON log format for structured analysis: set
logger.formattojsonin config Configuration - Use FluentD/OpenSearch for log aggregation
- Audit logging (v1.17+) is off by default; turn it on with
audit.enabled: trueAudit logging. Audit logs write to local filesystem (/qdrant/storage/audit/) by default. On v1.20 or newer, setaudit.outputtostdout,stderr,file_and_stdout, orfile_and_stderr(env varQDRANT__AUDIT__OUTPUT) so a DaemonSet can collect them with no sidecar or Persistent Volume. Each line carries"kind": "audit"to tell it from regular logs, and the/audit/logsAPI returns nothing on a node that writes only to a stream. On v1.19 or older, mount a Persistent Volume and deploy a sidecar container to tail the files to stdout. Audit logging
What NOT to Do
- Scrape
/sys_metricson self-hosted (only available on Qdrant Cloud) - Scrape only Qdrant nodes in Hybrid Cloud (miss cluster-exporter and operator metrics)
- Skip monitoring setup before going to production (you will regret it)
- Alert on page cache memory usage (it's supposed to fill available RAM, normal OS behavior)
