commit 44555e4c25b43ce200001b57ebc574bf3d2a4556 from: mtmn date: Wed Jul 15 19:48:38 2026 UTC more optimistic alert rules commit - b28f889be9310436e8ba1d5ec453535d21a870d9 commit + 44555e4c25b43ce200001b57ebc574bf3d2a4556 blob - ff8b1c9fb0d73aa4a18a60f1df7a53cb7b0631b3 blob + c517df032c2f47d66c1a6f4c2e5701d4715dbf5c --- flake.lock +++ flake.lock @@ -164,11 +164,11 @@ ] }, "locked": { - "lastModified": 1784123766, - "narHash": "sha256-PZcuvieLhy1OaX5LQr4kZgO59x/7rS47vWSqOXiBhts=", + "lastModified": 1784129366, + "narHash": "sha256-N5JiyICSeQF14x+OQebNyPpYowOT9Rs1iKyeCylSzOA=", "owner": "nix-community", "repo": "home-manager", - "rev": "6dc9e081ba2afc8c3b81ccddcb895f786155b292", + "rev": "165228b0efefc3e635e5174020c40ea64271dc25", "type": "github" }, "original": { blob - d62d095d47205a33cf0ea64f6131792b55308fb6 blob + a29eb3bc94eae330455bd567ead0f40fad2b6630 Binary files hosts/nixaran/configuration.nix and hosts/nixaran/configuration.nix differ blob - 80db3c572caa3541c32d8d17e60ce0919c946322 blob + 2b32065995bbab0511eba441337881c6c9368913 --- modules/mixins/dotfiles/config/newsraft/feeds +++ modules/mixins/dotfiles/config/newsraft/feeds @@ -101,6 +101,10 @@ https://feed.podbean.com/acmbytecast/feed.xml https://feeds.acast.com/public/shows/disseminate +@ other < reload-period 120 +https://plan.cat/rss + + @ music < reload-period 120 https://firstfloor.substack.com/feed https://acloserlisten.substack.com/feed blob - ba89816a9b021f423faab2c74b9aa9402b74d7b2 blob + 51344cef3ba48af808e8d76a5c48da6a35e55727 --- modules/mixins/monitoring/alert-rules.yaml +++ modules/mixins/monitoring/alert-rules.yaml @@ -16,21 +16,21 @@ groups: rules: - alert: HighCPULoad expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 90 - for: 10m + for: 30m labels: severity: warning annotations: summary: "High CPU load: {{ $value | printf \"%.0f\" }}%" - description: "CPU usage has been above 90% for more than 10 minutes." + description: "CPU usage has been above 90% for more than 30 minutes." - alert: HighMemoryUsage expr: (1 - (node_memory_MemAvailable_bytes or node_memory_free_bytes) / node_memory_MemTotal_bytes) * 100 > 90 - for: 5m + for: 15m labels: severity: warning annotations: summary: "High memory usage: {{ $value | printf \"%.0f\" }}%" - description: "Available memory has been below 10% for more than 5 minutes." + description: "Available memory has been below 10% for more than 15 minutes." - alert: HighDiskUsage expr: | @@ -38,15 +38,15 @@ groups: 1 - node_filesystem_avail_bytes{fstype!~"tmpfs|fuse.lxcfs|squashfs|ramfs|overlay"} / clamp_min(node_filesystem_size_bytes, 1) - ) * 100 > 85 - for: 5m + ) * 100 > 95 + for: 30m labels: severity: warning annotations: summary: "High disk usage on {{ $labels.mountpoint }}: {{ $value | printf \"%.0f\" }}%" description: > Disk usage on {{ $labels.mountpoint }} ({{ $labels.device }}) has been - above 85% for more than 5 minutes. + above 95% for more than 30 minutes. - alert: DiskWillFillSoon expr: > @@ -65,16 +65,16 @@ groups: - alert: HighSystemLoad expr: node_load15 / count without(cpu, mode) (node_cpu_seconds_total{mode="idle"}) > 2 - for: 15m + for: 30m labels: severity: warning annotations: summary: "High 15-minute load average: {{ $value | printf \"%.2f\" }}" - description: "The 15-minute load average per CPU core has been above 2 for 15 minutes." + description: "The 15-minute load average per CPU core has been above 2 for 30 minutes." - alert: FilesystemReadOnly expr: node_filesystem_readonly{fstype!~"tmpfs|fuse.lxcfs|squashfs|ramfs|overlay"} == 1 - for: 1m + for: 3m labels: severity: critical annotations: @@ -142,14 +142,14 @@ groups: read-only. - alert: ZFSPoolHighCapacity - expr: zfs_pool_allocated_bytes / zfs_pool_size_bytes * 100 > 85 + expr: zfs_pool_allocated_bytes / zfs_pool_size_bytes * 100 > 95 for: 5m labels: severity: warning annotations: summary: "ZFS pool {{ $labels.pool }} is {{ $value | printf \"%.0f\" }}% full" description: > - ZFS pool {{ $labels.pool }} on {{ $labels.instance }} has been above 85% + ZFS pool {{ $labels.pool }} on {{ $labels.instance }} has been above 95% capacity for more than 5 minutes. - alert: ZFSDatasetQuotaHigh @@ -157,7 +157,7 @@ groups: zfs_dataset_used_bytes{type="filesystem"} / (zfs_dataset_used_bytes{type="filesystem"} + zfs_dataset_available_bytes{type="filesystem"}) - * 100 > 85 + * 100 > 95 for: 5m labels: severity: warning @@ -165,7 +165,7 @@ groups: summary: "ZFS dataset {{ $labels.name }} is {{ $value | printf \"%.0f\" }}% full" description: > ZFS dataset {{ $labels.name }} (pool {{ $labels.pool }}) on - {{ $labels.instance }} has been above 85% used space for more than 5 minutes. + {{ $labels.instance }} has been above 95% used space for more than 5 minutes. - name: h2o rules: @@ -220,17 +220,17 @@ groups: rules: - alert: BlackboxProbeFailed expr: probe_success == 0 - for: 1m + for: 5m labels: severity: critical annotations: summary: "Probe failed: {{ $labels.instance }}" description: > The blackbox probe for {{ $labels.instance }} (module: {{ $labels.module }}) - has been failing for more than 1 minute. + has been failing for more than 5 minutes. - alert: BlackboxProbeSlow - expr: probe_duration_seconds > 2 + expr: probe_duration_seconds > 5 for: 5m labels: severity: warning @@ -238,7 +238,7 @@ groups: summary: "Probe is slow: {{ $labels.instance }}" description: > The blackbox probe for {{ $labels.instance }} (module: {{ $labels.module }}) - has taken more than 2 seconds for more than 5 minutes. + has taken more than 5 seconds for more than 5 minutes. - alert: SSLCertificateExpiringSoon expr: (probe_ssl_cert_expiry - time()) / 86400 < 21