| 1 | { pkgs, ... }: |
| 2 | |
| 3 | { |
| 4 | services.prometheus = { |
| 5 | scrapeConfigs = [ |
| 6 | { |
| 7 | job_name = "zrepl"; |
| 8 | static_configs = [ |
| 9 | { |
| 10 | labels.role = "database"; |
| 11 | targets = [ |
| 12 | "mimas.nixos.org:9811" |
| 13 | ]; |
| 14 | } |
| 15 | ]; |
| 16 | } |
| 17 | ]; |
| 18 | |
| 19 | ruleFiles = [ |
| 20 | (pkgs.writeText "zrepl.rules" ( |
| 21 | builtins.toJSON { |
| 22 | groups = [ |
| 23 | { |
| 24 | name = "zrepl"; |
| 25 | rules = [ |
| 26 | { |
| 27 | alert = "ZreplLongTimeNoSuccess"; |
| 28 | expr = '' |
| 29 | time() - zrepl_replication_last_successful > ${toString (6 * 60 * 60)} |
| 30 | ''; |
| 31 | for = "6h"; |
| 32 | labels.severity = "warning"; |
| 33 | annotations.summary = "zrepl job {{ $labels.zrepl_job }} has not succeeded recently."; |
| 34 | } |
| 35 | ]; |
| 36 | } |
| 37 | ]; |
| 38 | } |
| 39 | )) |
| 40 | ]; |
| 41 | }; |
| 42 | } |