agent-pard0x/use-cases/incus-troubleshooting-summary.md

Incus Troubleshooting Session Summary

User Requests

1. Check all Incus containers in all projects on remote server
2. Check the logs of all containers from gta and default projects, and identify which ones must be taken care of
3. Check Incus configuration to find where container filesystems are mounted, then look directly at logs from the root host filesystem

My Responses

1. Container Discovery

   • Listed all projects and containers:
     • default: dns, gitea, jitsi, mail, matrix, radicale, seedreco, vaultwarden, web
     • gta: wireguard
     • test-project, vins: no containers

2. Attempted Container Log Retrieval (via Incus tooling)

   • Encountered limitations: direct log retrieval per project via incus query not supported as expected.
   • Explained alternative approaches (using incus exec or fetching from files inside containers).
   • Asked for your preferred log-checking method: journal inside the container, or files from the host.

3. Logs Inspected Directly from Host Filesystem

   • Used information about Incus container mountpoints to inspect /var/log/syslog and /var/log/messages for each container:
     • Most containers lack system logs at these paths.
     • jitsi: Found many repeated TURN server TLS/TCP socket errors (recommend investigation)
     • mail: ClamAV warning for outdated signatures (recommend update)
   • Recommended focusing on jitsi (TURN server errors) and mail (ClamAV out-of-date) for attention.

---

If you need further details on specific containers, deeper log analysis, or recommendations on fixes, just ask!