1
0
mirror of https://github.com/kmein/niveum synced 2026-03-21 20:31:07 +01:00

1 Commits

Author SHA1 Message Date
github-actions[bot]
b8ff81344d flake.lock: Update
Flake lock file updates:

• Updated input 'home-manager':
    'github:nix-community/home-manager/501cfec8277f931a9c9af9f23d3105c537faeafe?narHash=sha256-tWosziZTT039x6PgEZUhzGlV8oLvdDmIgKTE8ESMaEA%3D' (2025-07-02)
  → 'github:nix-community/home-manager/fc3add429f21450359369af74c2375cb34a2d204?narHash=sha256-oV695RvbAE4%2BR9pcsT9shmp6zE/%2BIZe6evHWX63f2Qg%3D' (2025-07-27)
• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/7a732ed41ca0dd64b4b71b563ab9805a80a7d693?narHash=sha256-u7ubvtxdTnFPpV27AHpgoKn7qHuE7sgWgza/1oj5nzA%3D' (2025-07-03)
  → 'github:NixOS/nixpkgs/59e69648d345d6e8fef86158c555730fa12af9de?narHash=sha256-IiiXB3BDTi6UqzAZcf2S797hWEPCRZOwyNThJIYhUfk%3D' (2025-08-01)
• Updated input 'nixpkgs-unstable':
    'github:NixOS/nixpkgs/07c3e0e2be593551abdccacabe29cc57206b396f?narHash=sha256-30JXBxkJD3pxBBGQwl/DDwxxJDGQ1nvkvWwEtTsmhA8%3D' (2025-07-05)
  → 'github:NixOS/nixpkgs/e960e6e1dc689e2b5fe9e3ee824fc12860d9f27c?narHash=sha256-hON5G3ENyUGUpqImXT%2BAg7TWbBsfthwqxMcAw8EiKw8%3D' (2025-08-03)
• Updated input 'nur':
    'github:nix-community/NUR/a26411970baba3604e425f23e5293da492069e4a?narHash=sha256-iDjz1tBd/ibtmZZse4k1NBxfPR8g9K5W4sRgCyOnrj0%3D' (2025-07-05)
  → 'github:nix-community/NUR/dbd17f07b63f5fc630ff9d3b5b832636259ac8e8?narHash=sha256-UhAauJWx4bcopgP29mm7KFVVw38ZRUYp22I6sMKrUMY%3D' (2025-08-02)
• Updated input 'nur/nixpkgs':
    'github:nixos/nixpkgs/3016b4b15d13f3089db8a41ef937b13a9e33a8df?narHash=sha256-P/SQmKDu06x8yv7i0s8bvnnuJYkxVGBWLWHaU%2Btt4YY%3D' (2025-06-30)
  → 'github:nixos/nixpkgs/94def634a20494ee057c76998843c015909d6311?narHash=sha256-K2ViRJfdVGE8tpJejs8Qpvvejks1%2BA4GQej/lBk5y7I%3D' (2025-07-31)
• Removed input 'nur/treefmt-nix'
• Removed input 'nur/treefmt-nix/nixpkgs'
• Updated input 'rust-overlay':
    'github:oxalica/rust-overlay/9e5e62a33a929a67a5427fb7324a6f583dced0b2?narHash=sha256-dYO5X5jK8bpQOeRAo8R5aUt6M/%2BJi1cZgstZI7SQ2IA%3D' (2025-07-05)
  → 'github:oxalica/rust-overlay/08ff39bf869cadca3102b39824f4c7025186b7dc?narHash=sha256-d6nZ%2B1e4VDqW6VAwfx9EAUDJdPxSwqwGiuli32FEgoE%3D' (2025-08-02)
• Updated input 'scripts':
    'github:kmein/scripts/f44c7a4a6caa1ef5d6b7bf7e93acea0d96f30c21?narHash=sha256-mDDxMwKFURX1K1Z8X/kmt%2BjYjswofDf0br%2BMkw2tmSE%3D' (2025-06-02)
  → 'github:kmein/scripts/cc37fa4aec70f53731b9131bb8830b4445b75b3d?narHash=sha256-TnfXFloY4Ntq%2B0hp%2Bq9GGmuhtB1oueFiB%2BpcBUNYzFs%3D' (2025-07-20)
• Updated input 'stockholm':
    'github:krebs/stockholm/d4abc837cc7b87b4f23fe48cc306df26e3de7aab?narHash=sha256-i2s6jU%2B8GLKVjhWDyvFYxmXI7A44c9p6apPPyKt0ETk%3D' (2025-05-13)
  → 'github:krebs/stockholm/4ec2ff1c3f0854e113714542e9a2b48a80d70b62?narHash=sha256-KnY7idadDb5Vx24q2KjAaiIJVyCVHJsV7om1qQLednA%3D' (2025-07-26)
• Updated input 'stockholm/buildbot-nix':
    'github:Mic92/buildbot-nix/7ad9b4886eccb5eecc0686a16266ddabf6cbefe9?narHash=sha256-mRnIdJLP%2B0NSim9ao30ue0Z3ttSuxzXwQG7UN1KuKfU%3D' (2025-05-07)
  → 'github:Mic92/buildbot-nix/47ad4c7afb169df6f9d48d0df3d7e2f71d9ddd8f?narHash=sha256-vCYcc/b8WizF6vnjuRVxSiU8hy9L3vOTWDVKpWM7xRE%3D' (2025-07-03)
• Updated input 'stockholm/buildbot-nix/flake-parts':
    'github:hercules-ci/flake-parts/c621e8422220273271f52058f618c94e405bb0f5?narHash=sha256-hIshGgKZCgWh6AYJpJmRgFdR3WUbkY04o82X05xqQiY%3D' (2025-04-01)
  → 'github:hercules-ci/flake-parts/77826244401ea9de6e3bac47c2db46005e1f30b5?narHash=sha256-Tyw1RjYEsp5scoigs1384gIg6e0GoBVjms4aXFfRssQ%3D' (2025-07-01)
• Updated input 'stockholm/buildbot-nix/hercules-ci-effects':
    'github:hercules-ci/hercules-ci-effects/5b6cec51c9ec095a0d3fd4c8eeb53eb5c59ae33e?narHash=sha256-1Z4WPGVky4w3lrhrgs89OKsLzPdtkbi1bPLNFWsoLfY%3D' (2025-04-15)
  → 'github:hercules-ci/hercules-ci-effects/231726642197817d20310b9d39dd4afb9e899489?narHash=sha256-EaAJhwfJGBncgIV/0NlJviid2DP93cTMc9h0q6P6xXk%3D' (2025-05-23)
• Updated input 'stockholm/buildbot-nix/treefmt-nix':
    'github:numtide/treefmt-nix/29ec5026372e0dec56f890e50dbe4f45930320fd?narHash=sha256-4h3s1L/kKqt3gMDcVfN8/4v2jqHrgLIe4qok4ApH5x4%3D' (2025-05-02)
  → 'github:numtide/treefmt-nix/ac8e6f32e11e9c7f153823abc3ab007f2a65d3e1?narHash=sha256-0IEdQB1nS%2BuViQw4k3VGUXntjkDp7aAlqcxdewb/hAc%3D' (2025-06-26)
• Updated input 'stockholm/nixpkgs':
    'github:NixOS/nixpkgs/d89fc19e405cb2d55ce7cc114356846a0ee5e956?narHash=sha256-3e%2BAVBczosP5dCLQmMoMEogM57gmZ2qrVSrmq9aResQ%3D' (2025-05-10)
  → 'github:NixOS/nixpkgs/1fd8bada0b6117e6c7eb54aad5813023eed37ccb?narHash=sha256-J1kI6oAj25IG4EdVlg2hQz8NZTBNYvIS0l4wpr9KcUo%3D' (2025-07-06)
• Updated input 'stylix':
    'github:danth/stylix/5dd301b72207d4fd8d8b929abd88ba1c486d1744?narHash=sha256-jqRbWjB8aH2qzq6nMQpwkzVBR4o9lNxAHFmRgGwnJ94%3D' (2025-07-04)
  → 'github:danth/stylix/5b81b0c4fbab3517b39d63f493760d33287150ad?narHash=sha256-MdMdQymbivEWWkC5HqeLYtP8FYu0SqiSpiRlyw9Fm3Y%3D' (2025-07-31)
• Removed input 'stylix/flake-compat'
• Removed input 'stylix/git-hooks'
• Removed input 'stylix/git-hooks/flake-compat'
• Removed input 'stylix/git-hooks/gitignore'
• Removed input 'stylix/git-hooks/gitignore/nixpkgs'
• Removed input 'stylix/git-hooks/nixpkgs'
• Removed input 'stylix/home-manager'
2025-08-03 01:18:31 +00:00
4 changed files with 175 additions and 232 deletions

View File

@@ -1,7 +1,5 @@
# niveum
> I must Create a System, or be enslav'd by another Man's. —William Blake
> [nĭvĕus](https://logeion.uchicago.edu/niveus), a, um, adj. [nix], _of_ or _from snow, snowy, snow-_ (poet.)
>
> 1. Lit.: aggeribus niveis informis, Verg. G. 3, 354: aqua, _cooled with snow_, Mart. 12, 17, 6; cf. id. 14, 104 and 117: mons, _covered with snow_, Cat. 64, 240.—

View File

@@ -17,7 +17,11 @@ in {
chmod o+rx ${stateDir}
cd ${stateDir}
(${pkgs.curl}/bin/curl -s -o wallpaper.tmp -z wallpaper.tmp ${lib.escapeShellArg url} && cp wallpaper.tmp wallpaper) || :
${pkgs.feh}/bin/feh --no-fehbg --bg-scale wallpaper
if [ -z $SWAYSOCK ]; then
${pkgs.feh}/bin/feh --no-fehbg --bg-scale wallpaper
else
${pkgs.sway}/bin/swaymsg -s $SWAYSOCK 'output * bg ${stateDir}/wallpaper fill'
fi
'';
startAt = "*:00,10,20,30,40,50";
serviceConfig = {

48
flake.lock generated
View File

@@ -12,11 +12,11 @@
"systems": "systems"
},
"locked": {
"lastModified": 1754433428,
"narHash": "sha256-NA/FT2hVhKDftbHSwVnoRTFhes62+7dxZbxj5Gxvghs=",
"lastModified": 1750173260,
"narHash": "sha256-9P1FziAwl5+3edkfFcr5HeGtQUtrSdk/MksX39GieoA=",
"owner": "ryantm",
"repo": "agenix",
"rev": "9edb1787864c4f59ae5074ad498b6272b3ec308d",
"rev": "531beac616433bac6f9e2a19feb8e99a22a66baf",
"type": "github"
},
"original": {
@@ -1045,11 +1045,11 @@
},
"nixpkgs-unstable_2": {
"locked": {
"lastModified": 1754787963,
"narHash": "sha256-BExvuIabyDAgm8oLgGi/rbTbCouydsLMLaL2Fzpdvcc=",
"lastModified": 1754182383,
"narHash": "sha256-hON5G3ENyUGUpqImXT+Ag7TWbBsfthwqxMcAw8EiKw8=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "796902fa97f5d4174251562eee6fa4d138c4a5e8",
"rev": "e960e6e1dc689e2b5fe9e3ee824fc12860d9f27c",
"type": "github"
},
"original": {
@@ -1167,11 +1167,11 @@
},
"nixpkgs_7": {
"locked": {
"lastModified": 1754689972,
"narHash": "sha256-eogqv6FqZXHgqrbZzHnq43GalnRbLTkbBbFtEfm1RSc=",
"lastModified": 1754028485,
"narHash": "sha256-IiiXB3BDTi6UqzAZcf2S797hWEPCRZOwyNThJIYhUfk=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "fc756aa6f5d3e2e5666efcf865d190701fef150a",
"rev": "59e69648d345d6e8fef86158c555730fa12af9de",
"type": "github"
},
"original": {
@@ -1183,11 +1183,11 @@
},
"nixpkgs_8": {
"locked": {
"lastModified": 1754498491,
"narHash": "sha256-erbiH2agUTD0Z30xcVSFcDHzkRvkRXOQ3lb887bcVrs=",
"lastModified": 1753939845,
"narHash": "sha256-K2ViRJfdVGE8tpJejs8Qpvvejks1+A4GQej/lBk5y7I=",
"owner": "nixos",
"repo": "nixpkgs",
"rev": "c2ae88e026f9525daf89587f3cbee584b92b6134",
"rev": "94def634a20494ee057c76998843c015909d6311",
"type": "github"
},
"original": {
@@ -1330,11 +1330,11 @@
"nixpkgs": "nixpkgs_8"
},
"locked": {
"lastModified": 1754771961,
"narHash": "sha256-aLtVkt7vTReGT/M51TvKpUNOhvs+XFAdimadlUiOPfg=",
"lastModified": 1754178761,
"narHash": "sha256-UhAauJWx4bcopgP29mm7KFVVw38ZRUYp22I6sMKrUMY=",
"owner": "nix-community",
"repo": "NUR",
"rev": "27dfc5e3bedd281be925bc290351890571a720d2",
"rev": "dbd17f07b63f5fc630ff9d3b5b832636259ac8e8",
"type": "github"
},
"original": {
@@ -1529,11 +1529,11 @@
]
},
"locked": {
"lastModified": 1754707163,
"narHash": "sha256-wgVgOsyJUDn2ZRpzu2gELKALoJXlBSoZJSln+Tlg5Pw=",
"lastModified": 1754102567,
"narHash": "sha256-d6nZ+1e4VDqW6VAwfx9EAUDJdPxSwqwGiuli32FEgoE=",
"owner": "oxalica",
"repo": "rust-overlay",
"rev": "ac39ab4c8ed7cefe48d5ae5750f864422df58f01",
"rev": "08ff39bf869cadca3102b39824f4c7025186b7dc",
"type": "github"
},
"original": {
@@ -1607,11 +1607,11 @@
"nixpkgs": "nixpkgs_9"
},
"locked": {
"lastModified": 1754761025,
"narHash": "sha256-Mo2BkJXIz6HKM8cX2S7bRdX6Q3E1UOcyVL4v10QEUzk=",
"lastModified": 1753556729,
"narHash": "sha256-KnY7idadDb5Vx24q2KjAaiIJVyCVHJsV7om1qQLednA=",
"owner": "krebs",
"repo": "stockholm",
"rev": "fc32e4609140fffa1312a4ca1aeea550b7467448",
"rev": "4ec2ff1c3f0854e113714542e9a2b48a80d70b62",
"type": "github"
},
"original": {
@@ -1671,11 +1671,11 @@
"tinted-zed": "tinted-zed"
},
"locked": {
"lastModified": 1754599117,
"narHash": "sha256-AzAYdZlat002vCjCKWdFpGi2xUaiOU4DtIPnv1nomD8=",
"lastModified": 1753979771,
"narHash": "sha256-MdMdQymbivEWWkC5HqeLYtP8FYu0SqiSpiRlyw9Fm3Y=",
"owner": "danth",
"repo": "stylix",
"rev": "312dec38b2231b21f36903d1bdce96daa11548ff",
"rev": "5b81b0c4fbab3517b39d63f493760d33287150ad",
"type": "github"
},
"original": {

View File

@@ -3,13 +3,11 @@
config,
pkgs,
...
}:
let
}: let
lokiConfig = import ./loki.nix;
blackboxConfig = import ./blackbox.nix;
inherit (import ../../../lib) restic;
in
{
in {
services.grafana = {
enable = true;
settings = {
@@ -82,150 +80,143 @@ in
}
];
services.prometheus.rules =
let
diskFreeThreshold = 10;
in
[
(builtins.toJSON {
groups = [
{
name = "niveum";
rules = [
{
alert = "HostSystemdServiceCrashed";
expr = ''(node_systemd_unit_state{state="failed"} == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'';
annotations = {
description = "{{$labels.name}} failed on {{$labels.instance}}";
};
}
{
alert = "RootPartitionFull";
for = "10m";
expr = ''(node_filesystem_free_bytes{mountpoint="/"} * 100) / node_filesystem_size_bytes{mountpoint="/"} < ${toString diskFreeThreshold}'';
annotations = {
description = ''{{ $labels.instance }} running out of space: {{ $value | printf "%.2f" }}% < ${toString diskFreeThreshold}%'';
};
}
{
alert = "RootPartitionFullWeek";
for = "1h";
expr =
''node_filesystem_free_bytes{mountpoint="/"} ''
+ ''and predict_linear(node_filesystem_free_bytes{mountpoint="/"}[2d], 7*24*3600) <= 0'';
annotations = {
description = "{{$labels.instance}} running out of space in 7 days";
};
}
{
alert = "HighLoad";
expr = ''node_load15 / on(job) count(node_cpu_seconds_total{mode="system"}) by (job) >= 1.0'';
for = "10m";
annotations = {
description = "{{$labels.instance}} running on high load: {{$value}}";
};
}
{
alert = "HostUnusualNetworkThroughputIn";
expr = ''(rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100'';
for = "5m";
annotations.description = "Host unusual network throughput in (instance {{ $labels.instance }})";
}
{
alert = "HostUnusualNetworkThroughputOut";
expr = ''(rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100'';
for = "5m";
annotations.description = "Host unusual network throughput out (instance {{ $labels.instance }})";
}
{
alert = "HostUnusualDiskReadRate";
expr = ''(rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50'';
for = "5m";
annotations.description = "Host unusual disk read rate (instance {{ $labels.instance }})";
}
{
alert = "HostUnusualDiskWriteRate";
expr = ''(rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50'';
for = "2m";
annotations.description = "Host unusual disk write rate (instance {{ $labels.instance }})";
}
{
alert = "HostOutOfInodes";
expr = ''node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'';
for = "2m";
annotations.description = "Host out of inodes (instance {{ $labels.instance }})";
}
{
alert = "HostInodesWillFillIn24Hours";
expr = ''node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{fstype!="msdosfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{fstype!="msdosfs"} == 0'';
for = "2m";
annotations.description = "Host inodes will fill in 24 hours (instance {{ $labels.instance }})";
}
{
alert = "HighRAM";
expr = "node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes < node_memory_MemTotal_bytes * 0.1";
for = "1h";
annotations.description = "{{$labels.instance}} using lots of RAM";
}
{
alert = "UptimeMonster";
expr = "time() - node_boot_time_seconds > 2592000";
annotations.description = "uptime monster {{$labels.instance}} up for more than 30 days";
}
{
alert = "HostDown";
expr = ''up == 0'';
for = "5m";
annotations = {
description = "{{ $labels.instance }} seeming down since 5 minutes";
};
}
{
alert = "Reboot";
expr = "time() - node_boot_time_seconds < 300";
annotations.description = "{{$labels.instance}} rebooted";
}
{
alert = "Mastodon";
expr = ''probe_success{instance="https://social.krebsco.de"}'';
for = "5m";
annotations.description = "Mastodon instance {{$labels.instance}} is down";
}
{
alert = "ProbeFailed";
expr = "probe_success == 0";
for = "5m";
annotations.description = "HTTP probe failed for {{$labels.instance}}";
}
{
alert = "SlowProbe";
expr = "avg_over_time(probe_http_duration_seconds[1m]) > 1";
for = "5m";
annotations.description = "HTTP probe slow for {{$labels.instance}}";
}
{
alert = "HttpStatusCode";
expr = "probe_http_status_code != 0 AND (probe_http_status_code <= 199 OR probe_http_status_code >= 400)";
for = "5m";
annotations.description = "status code {{$value}} for {{$labels.instance}}";
}
{
alert = "SslExpirySoon";
expr = "probe_ssl_earliest_cert_expiry - time() < 86400 * 30";
for = "5m";
annotations.description = "SSL certificate for {{$labels.instance}} expires in 30 days";
}
{
alert = "SslExpiry";
expr = "probe_ssl_earliest_cert_expiry - time() <= 0";
for = "5m";
annotations.description = "SSL certificate for {{$labels.instance}} has expired";
}
];
}
];
})
];
services.prometheus.rules = let
diskFreeThreshold = 10;
in [
(builtins.toJSON {
groups = [
{
name = "niveum";
rules = [
{
alert = "HostSystemdServiceCrashed";
expr = ''(node_systemd_unit_state{state="failed"} == 1) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}'';
annotations = {
description = "{{$labels.name}} failed on {{$labels.instance}}";
};
}
{
alert = "RootPartitionFull";
for = "10m";
expr = ''(node_filesystem_free_bytes{mountpoint="/"} * 100) / node_filesystem_size_bytes{mountpoint="/"} < ${toString diskFreeThreshold}'';
annotations = {
description = ''{{ $labels.instance }} running out of space: {{ $value | printf "%.2f" }}% < ${toString diskFreeThreshold}%'';
};
}
{
alert = "RootPartitionFullWeek";
for = "1h";
expr =
''node_filesystem_free_bytes{mountpoint="/"} ''
+ ''and predict_linear(node_filesystem_free_bytes{mountpoint="/"}[2d], 7*24*3600) <= 0'';
annotations = {
description = "{{$labels.instance}} running out of space in 7 days";
};
}
{
alert = "HighLoad";
expr = ''node_load15 / on(job) count(node_cpu_seconds_total{mode="system"}) by (job) >= 1.0'';
for = "10m";
annotations = {
description = "{{$labels.instance}} running on high load: {{$value}}";
};
}
{
alert = "HostUnusualNetworkThroughputIn";
expr = ''(rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100'';
for = "5m";
annotations.description = "Host unusual network throughput in (instance {{ $labels.instance }})";
}
{
alert = "HostUnusualNetworkThroughputOut";
expr = ''(rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100'';
for = "5m";
annotations.description = "Host unusual network throughput out (instance {{ $labels.instance }})";
}
{
alert = "HostUnusualDiskReadRate";
expr = ''(rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50'';
for = "5m";
annotations.description = "Host unusual disk read rate (instance {{ $labels.instance }})";
}
{
alert = "HostUnusualDiskWriteRate";
expr = ''(rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50'';
for = "2m";
annotations.description = "Host unusual disk write rate (instance {{ $labels.instance }})";
}
{
alert = "HostOutOfInodes";
expr = ''node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0'';
for = "2m";
annotations.description = "Host out of inodes (instance {{ $labels.instance }})";
}
{
alert = "HostInodesWillFillIn24Hours";
expr = ''node_filesystem_files_free{fstype!="msdosfs"} / node_filesystem_files{fstype!="msdosfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{fstype!="msdosfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{fstype!="msdosfs"} == 0'';
for = "2m";
annotations.description = "Host inodes will fill in 24 hours (instance {{ $labels.instance }})";
}
{
alert = "HighRAM";
expr = "node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes < node_memory_MemTotal_bytes * 0.1";
for = "1h";
annotations.description = "{{$labels.instance}} using lots of RAM";
}
{
alert = "UptimeMonster";
expr = "time() - node_boot_time_seconds > 2592000";
annotations.description = "uptime monster {{$labels.instance}} up for more than 30 days";
}
{
alert = "HostDown";
expr = ''up == 0'';
for = "5m";
annotations = {
description = "{{ $labels.instance }} seeming down since 5 minutes";
};
}
{
alert = "Reboot";
expr = "time() - node_boot_time_seconds < 300";
annotations.description = "{{$labels.instance}} rebooted";
}
{
alert = "ProbeFailed";
expr = "probe_success == 0";
for = "5m";
annotations.description = "HTTP probe failed for {{$labels.instance}}";
}
{
alert = "SlowProbe";
expr = "avg_over_time(probe_http_duration_seconds[1m]) > 1";
for = "5m";
annotations.description = "HTTP probe slow for {{$labels.instance}}";
}
{
alert = "HttpStatusCode";
expr = "probe_http_status_code != 0 AND (probe_http_status_code <= 199 OR probe_http_status_code >= 400)";
for = "5m";
annotations.description = "status code {{$value}} for {{$labels.instance}}";
}
{
alert = "SslExpirySoon";
expr = "probe_ssl_earliest_cert_expiry - time() < 86400 * 30";
for = "5m";
annotations.description = "SSL certificate for {{$labels.instance}} expires in 30 days";
}
{
alert = "SslExpiry";
expr = "probe_ssl_earliest_cert_expiry - time() <= 0";
for = "5m";
annotations.description = "SSL certificate for {{$labels.instance}} has expired";
}
];
}
];
})
];
# ref https://github.com/Mic92/dotfiles/blob/f44bac5dd6970ed3fbb4feb906917331ec3c2be5/machines/eva/modules/prometheus/default.nix
systemd.services.matrix-hook = {
@@ -255,33 +246,6 @@ in
};
};
systemd.services.matrix-hook-lassulus = {
description = "Matrix Hook";
after = [ "network.target" ];
wantedBy = [ "multi-user.target" ];
environment = {
HTTP_ADDRESS = "[::1]";
HTTP_PORT = "9089";
MX_HOMESERVER = "https://matrix.4d2.org";
MX_ID = "@lakai:4d2.org";
MX_ROOMID = "!MJAGqBAOKZGMywzwkI:lassul.us";
MX_MSG_TEMPLATE = "${pkgs.matrix-hook}/message.html.tmpl";
};
serviceConfig = {
EnvironmentFile = [
# format: MX_TOKEN=<token>
config.age.secrets.matrix-token-lakai-env.path
];
Type = "simple";
ExecStart = "${pkgs.matrix-hook}/bin/matrix-hook";
Restart = "always";
RestartSec = "10";
DynamicUser = true;
User = "matrix-hook";
Group = "matrix-hook";
};
};
age.secrets = {
matrix-token-lakai-env.file = ../../../secrets/matrix-token-lakai-env.age;
};
@@ -296,23 +260,8 @@ in
group_wait = "30s";
repeat_interval = "24h";
receiver = "matrix";
routes = [
{
receiver = "lassulus";
matchers = [ "alertname = \"Mastodon\"" ];
}
];
};
receivers = [
{
name = "lassulus";
webhook_configs = [
{
url = "http://localhost:9089/alert";
max_alerts = 5;
}
];
}
{
name = "matrix";
webhook_configs = [
@@ -357,21 +306,13 @@ in
{
scheme = "http";
path_prefix = "/";
static_configs = [
{ targets = [ "localhost:${toString config.services.prometheus.alertmanager.port}" ]; }
];
static_configs = [{targets = ["localhost:${toString config.services.prometheus.alertmanager.port}"];}];
}
];
# otherwise bearer_token_file will fail
services.prometheus.checkConfig = "syntax-only";
services.prometheus.extraFlags = [
"--storage.tsdb.retention.time=7d"
"--storage.tsdb.retention.size=2GB"
"--storage.tsdb.wal-compression"
];
services.prometheus.scrapeConfigs = [
{
job_name = "makanek";
@@ -387,14 +328,14 @@ in
scrape_interval = "5m";
job_name = "blackbox";
metrics_path = "/probe";
params.module = [ "http_2xx" ];
params.module = ["http_2xx"];
relabel_configs = [
{
source_labels = [ "__address__" ];
source_labels = ["__address__"];
target_label = "__param_target";
}
{
source_labels = [ "__param_target" ];
source_labels = ["__param_target"];
target_label = "instance";
}
{
@@ -452,7 +393,7 @@ in
scrape_interval = "60s";
metrics_path = "/api/prometheus";
scheme = "http";
static_configs = [ { targets = [ "zaatar.r:8123" ]; } ];
static_configs = [{targets = ["zaatar.r:8123"];}];
bearer_token_file = config.age.secrets.home-assistant-token.path;
}
{
@@ -469,7 +410,7 @@ in
services.prometheus.exporters.blackbox = {
enable = true;
configFile = (pkgs.formats.yaml { }).generate "blackbox.yaml" blackboxConfig;
configFile = (pkgs.formats.yaml {}).generate "blackbox.yaml" blackboxConfig;
};
networking.firewall.allowedTCPPorts = [
@@ -478,6 +419,6 @@ in
services.loki = {
enable = true;
configFile = (pkgs.formats.yaml { }).generate "loki.yaml" lokiConfig;
configFile = (pkgs.formats.yaml {}).generate "loki.yaml" lokiConfig;
};
}