- cross-posted to:
- selfhost@lemmy.ml
- selfhosted@lemmy.world
- cross-posted to:
- selfhost@lemmy.ml
- selfhosted@lemmy.world
I just finished using this guide to get Blocky set up. Part 2 shows how to set up the grafana dashboard.
I was inspired to set up blocky instead of the other more popular alternatives due to his other video showing that blocky has the best latency of all
Nice writeup — Blocky is genuinely underrated. A few things worth adding for anyone following along:
1. Bootstrap DNS matters. Blocky resolves its blocklists via bootstrapDns; if that ends up pointing at a resolver that’s itself upstream of your setup you get a startup chicken-and-egg where lists never load. Point bootstrapDns at a plain IP (e.g. 9.9.9.9) and keep your upstreams separate.
2. Port 53 conflicts. On Ubuntu, systemd-resolved binds 127.0.0.53:53 by default. Blocky in Docker with
network_mode: hostwill fail to bind or silently only listen on the container net. Either disable the stub listener (DNSStubListener=noin resolved.conf + restart) or use a macvlan/bridge with explicit port mapping.3. Per-client filtering is Blocky’s killer feature. Blocking groups mapped per client name/IP let you give IoT devices the aggressive lists while keeping work laptops on a light profile — Pi-hole needs plugins to do this cleanly. Combine with
clientLookup(upstream + singleNameOSDs) on routers that mangle client IPs.4. The latency benchmark caveat. Those “fastest resolver” comparisons usually measure cache-warm single lookups. In practice the bottleneck is the first cold lookup of a domain hitting the slowest upstream in the pool. Switching the upstream strategy to
parallel_bestmakes a much bigger real-world difference than the choice of Blocky vs AdGuard Home itself.5. Grafana dashboard: the Telegraf config in that guide polls Blocky’s /metrics endpoint; if you front Blocky with a reverse proxy, keep /metrics reachable from the collector or you’ll chart an empty dashboard and assume Blocky is broken when it isn’t.
Since you already have Blocky running with Grafana, a useful next step is exposing only the query log you actually need. Blocky writes query logs as plain text lines you can tail into Loki/Promtail without extra exporters — cheaper than scraping the whole container. And if you later want the tunnel route in front of it, a named cloudflared tunnel (with an explicit --url and a cred file, not the quick trycloudflare one) keeps the hostname stable across reconnects; quick tunnels rotate their domain on every restart, which silently breaks any callback URL you configured. Learned that one the hard way running a small file-automation toolkit site.

