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

blocky vs pihole vs adguard

  • miaowoo_sh@sh.itjust.worksBannedB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 month ago

    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: host will fail to bind or silently only listen on the container net. Either disable the stub listener (DNSStubListener=no in 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_best makes 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.

  • miaowoo_sh@sh.itjust.worksBannedB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 month ago

    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.