updating some stuff, trying to get woodpecker, and grafana alerts off
the ground
This commit is contained in:
parent
12875ff891
commit
e7bfe88dcf
|
@ -24,7 +24,8 @@
|
||||||
services.NetworkManager-wait-online.wantedBy = pkgs.lib.mkForce [ ]; # Normally ["network-online.target"]
|
services.NetworkManager-wait-online.wantedBy = pkgs.lib.mkForce [ ]; # Normally ["network-online.target"]
|
||||||
};
|
};
|
||||||
|
|
||||||
programs.gnupg.agent.pinentryFlavor = "gtk2";
|
programs.gnupg.agent.enable = true;
|
||||||
|
programs.gnupg.agent.pinentryFlavor = "gnome3";
|
||||||
|
|
||||||
fileSystems."/mnt/ftp" = {
|
fileSystems."/mnt/ftp" = {
|
||||||
device = "192.168.1.240:/home/ftp";
|
device = "192.168.1.240:/home/ftp";
|
||||||
|
|
|
@ -58,6 +58,8 @@ in
|
||||||
unstable.sublime-music
|
unstable.sublime-music
|
||||||
unstable.nheko
|
unstable.nheko
|
||||||
unstable.tootle
|
unstable.tootle
|
||||||
|
newsflash
|
||||||
|
liferea
|
||||||
|
|
||||||
scrot
|
scrot
|
||||||
ripcord
|
ripcord
|
||||||
|
@ -69,7 +71,6 @@ in
|
||||||
calibre
|
calibre
|
||||||
fractal
|
fractal
|
||||||
mpv
|
mpv
|
||||||
newsflash
|
|
||||||
zeal
|
zeal
|
||||||
xclip
|
xclip
|
||||||
xdotool
|
xdotool
|
||||||
|
|
300
hosts/profiles/monitoring/alert-rules.yaml
Normal file
300
hosts/profiles/monitoring/alert-rules.yaml
Normal file
|
@ -0,0 +1,300 @@
|
||||||
|
groups:
|
||||||
|
- name: hosts
|
||||||
|
rules:
|
||||||
|
- alert: HostOutOfMemory
|
||||||
|
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host out of memory (instance {{ $labels.instance }})
|
||||||
|
description: "Node memory is filling up (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostMemoryUnderMemoryPressure
|
||||||
|
expr: rate(node_vmstat_pgmajfault[1m]) > 1000
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host memory under memory pressure (instance {{ $labels.instance }})
|
||||||
|
description: "The node is under heavy memory pressure. High rate of major page faults\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostUnusualNetworkThroughputIn
|
||||||
|
expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
|
||||||
|
for: 5m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host unusual network throughput in (instance {{ $labels.instance }})
|
||||||
|
description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostUnusualNetworkThroughputOut
|
||||||
|
expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
|
||||||
|
for: 5m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host unusual network throughput out (instance {{ $labels.instance }})
|
||||||
|
description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
# - alert: HostUnusualDiskReadRate
|
||||||
|
# expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 100
|
||||||
|
# for: 5m
|
||||||
|
# labels:
|
||||||
|
# severity: warning
|
||||||
|
# annotations:
|
||||||
|
# summary: Host unusual disk read rate (instance {{ $labels.instance }})
|
||||||
|
# description: "Disk is probably reading too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
#
|
||||||
|
# - alert: HostUnusualDiskWriteRate
|
||||||
|
# expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
|
||||||
|
# for: 2m
|
||||||
|
# labels:
|
||||||
|
# severity: warning
|
||||||
|
# annotations:
|
||||||
|
# summary: Host unusual disk write rate (instance {{ $labels.instance }})
|
||||||
|
# description: "Disk is probably writing too much data (> 50 MB/s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
# Please add ignored mountpoints in node_exporter parameters like
|
||||||
|
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
|
||||||
|
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
|
||||||
|
- alert: HostOutOfDiskSpace
|
||||||
|
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host out of disk space (instance {{ $labels.instance }})
|
||||||
|
description: "Disk is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
# Please add ignored mountpoints in node_exporter parameters like
|
||||||
|
# "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)".
|
||||||
|
# Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users.
|
||||||
|
- alert: HostDiskWillFillIn24Hours
|
||||||
|
expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host disk will fill in 24 hours (instance {{ $labels.instance }})
|
||||||
|
description: "Filesystem is predicted to run out of space within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostOutOfInodes
|
||||||
|
expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host out of inodes (instance {{ $labels.instance }})
|
||||||
|
description: "Disk is almost running out of available inodes (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostInodesWillFillIn24Hours
|
||||||
|
expr: node_filesystem_files_free{mountpoint ="/rootfs"} / node_filesystem_files{mountpoint="/rootfs"} * 100 < 10 and predict_linear(node_filesystem_files_free{mountpoint="/rootfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/rootfs"} == 0
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host inodes will fill in 24 hours (instance {{ $labels.instance }})
|
||||||
|
description: "Filesystem is predicted to run out of inodes within the next 24 hours at current write rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
# - alert: HostUnusualDiskReadLatency
|
||||||
|
# expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0
|
||||||
|
# for: 2m
|
||||||
|
# labels:
|
||||||
|
# severity: warning
|
||||||
|
# annotations:
|
||||||
|
# summary: Host unusual disk read latency (instance {{ $labels.instance }})
|
||||||
|
# description: "Disk latency is growing (read operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
#
|
||||||
|
# - alert: HostUnusualDiskWriteLatency
|
||||||
|
# expr: rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 2 and rate(node_disk_writes_completed_total[1m]) > 0
|
||||||
|
# for: 2m
|
||||||
|
# labels:
|
||||||
|
# severity: warning
|
||||||
|
# annotations:
|
||||||
|
# summary: Host unusual disk write latency (instance {{ $labels.instance }})
|
||||||
|
# description: "Disk latency is growing (write operations > 100ms)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostHighCpuLoad
|
||||||
|
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 90
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host high CPU load (instance {{ $labels.instance }})
|
||||||
|
description: "CPU load is > 90%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostCpuStealNoisyNeighbor
|
||||||
|
expr: avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host CPU steal noisy neighbor (instance {{ $labels.instance }})
|
||||||
|
description: "CPU steal is > 10%. A noisy neighbor is killing VM performances or a spot instance may be out of credit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
# 10000 context switches is an arbitrary number.
|
||||||
|
# Alert threshold depends on nature of application.
|
||||||
|
# Please read: https://github.com/samber/awesome-prometheus-alerts/issues/58
|
||||||
|
- alert: HostContextSwitching
|
||||||
|
expr: (rate(node_context_switches_total[5m])) / (count without(cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 10000
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host context switching (instance {{ $labels.instance }})
|
||||||
|
description: "Context switching is growing on node (> 1000 / s)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostSwapIsFillingUp
|
||||||
|
expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host swap is filling up (instance {{ $labels.instance }})
|
||||||
|
description: "Swap is filling up (>80%)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostSystemdServiceCrashed
|
||||||
|
expr: node_systemd_unit_state{state="failed"} == 1
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host systemd service crashed (instance {{ $labels.instance }})
|
||||||
|
description: "systemd service crashed: {{ $labels.name }} on {{ $labels.job }}"
|
||||||
|
|
||||||
|
- alert: HostPhysicalComponentTooHot
|
||||||
|
expr: node_hwmon_temp_celsius > 75
|
||||||
|
for: 5m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host physical component too hot (instance {{ $labels.instance }})
|
||||||
|
description: "Physical hardware component too hot\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostNodeOvertemperatureAlarm
|
||||||
|
expr: node_hwmon_temp_crit_alarm_celsius == 1
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: critical
|
||||||
|
annotations:
|
||||||
|
summary: Host node overtemperature alarm (instance {{ $labels.instance }})
|
||||||
|
description: "Physical node temperature alarm triggered\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostRaidArrayGotInactive
|
||||||
|
expr: node_md_state{state="inactive"} > 0
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: critical
|
||||||
|
annotations:
|
||||||
|
summary: Host RAID array got inactive (instance {{ $labels.instance }})
|
||||||
|
description: "RAID array {{ $labels.device }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostRaidDiskFailure
|
||||||
|
expr: node_md_disks{state="failed"} > 0
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host RAID disk failure (instance {{ $labels.instance }})
|
||||||
|
description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostKernelVersionDeviations
|
||||||
|
expr: count(sum(label_replace(node_uname_info, "kernel", "$1", "release", "([0-9]+.[0-9]+.[0-9]+).*")) by (kernel)) > 2
|
||||||
|
for: 6h
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host kernel version deviations (instance {{ $labels.instance }})
|
||||||
|
description: "Different kernel versions are running\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostOomKillDetected
|
||||||
|
expr: increase(node_vmstat_oom_kill[1m]) > 0
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host OOM kill detected (instance {{ $labels.instance }})
|
||||||
|
description: "OOM kill detected\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostEdacCorrectableErrorsDetected
|
||||||
|
expr: increase(node_edac_correctable_errors_total[1m]) > 0
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: info
|
||||||
|
annotations:
|
||||||
|
summary: Host EDAC Correctable Errors detected (instance {{ $labels.instance }})
|
||||||
|
description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} correctable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostEdacUncorrectableErrorsDetected
|
||||||
|
expr: node_edac_uncorrectable_errors_total > 0
|
||||||
|
for: 0m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host EDAC Uncorrectable Errors detected (instance {{ $labels.instance }})
|
||||||
|
description: "Host {{ $labels.instance }} has had {{ printf \"%.0f\" $value }} uncorrectable memory errors reported by EDAC in the last 5 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostNetworkReceiveErrors
|
||||||
|
expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host Network Receive Errors (instance {{ $labels.instance }})
|
||||||
|
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last five minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostNetworkTransmitErrors
|
||||||
|
expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host Network Transmit Errors (instance {{ $labels.instance }})
|
||||||
|
description: "Host {{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last five minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostNetworkInterfaceSaturated
|
||||||
|
expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8
|
||||||
|
for: 1m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host Network Interface Saturated (instance {{ $labels.instance }})
|
||||||
|
description: "The network interface \"{{ $labels.interface }}\" on \"{{ $labels.instance }}\" is getting overloaded.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostConntrackLimit
|
||||||
|
expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
|
||||||
|
for: 5m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host conntrack limit (instance {{ $labels.instance }})
|
||||||
|
description: "The number of conntrack is approching limit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostClockSkew
|
||||||
|
expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host clock skew (instance {{ $labels.instance }})
|
||||||
|
description: "Clock skew detected. Clock is out of sync.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
- alert: HostClockNotSynchronising
|
||||||
|
expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: Host clock not synchronising (instance {{ $labels.instance }})
|
||||||
|
description: "Clock not synchronising.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||||
|
|
||||||
|
# 26 hours since last backup
|
||||||
|
- alert: NoRecentBackup
|
||||||
|
expr: (time()*1000 - borgbackup_last_backup) > (1000 * 60 * 60 * 26)
|
||||||
|
for: 2m
|
||||||
|
labels:
|
||||||
|
severity: warning
|
||||||
|
annotations:
|
||||||
|
summary: No backup in the last 26 hours (instance {{ $labels.exported_job }})
|
||||||
|
description: "to repository {{ $labels.repo }}"
|
|
@ -1,4 +1,4 @@
|
||||||
{ config, pkgs, ... }: {
|
{ self, config, pkgs, ... }: {
|
||||||
# grafana configuration
|
# grafana configuration
|
||||||
services.grafana = {
|
services.grafana = {
|
||||||
enable = true;
|
enable = true;
|
||||||
|
@ -7,6 +7,8 @@
|
||||||
http_port = 2342;
|
http_port = 2342;
|
||||||
http_addr = "127.0.0.1";
|
http_addr = "127.0.0.1";
|
||||||
};
|
};
|
||||||
|
# TODO enable
|
||||||
|
# provision.alerting.rules.path = "${self}/hosts/profiles/monitoring/alert-rules.yaml";
|
||||||
};
|
};
|
||||||
|
|
||||||
# nginx reverse proxy
|
# nginx reverse proxy
|
||||||
|
|
65
hosts/profiles/woodpecker-agent/default.nix
Normal file
65
hosts/profiles/woodpecker-agent/default.nix
Normal file
|
@ -0,0 +1,65 @@
|
||||||
|
{
|
||||||
|
|
||||||
|
users.users.woodpecker-runner = {
|
||||||
|
isSystemUser = true;
|
||||||
|
group = "woodpecker-runner";
|
||||||
|
};
|
||||||
|
users.groups.woodpecker-runner = { };
|
||||||
|
# Allow the exec runner to write to build with nix
|
||||||
|
nix.allowedUsers = [ "woodpecker-runner" ];
|
||||||
|
|
||||||
|
systemd.services.woodpecker-runner-exec = {
|
||||||
|
enable = true;
|
||||||
|
wantedBy = [ "multi-user.target" ];
|
||||||
|
### MANUALLY RESTART SERVICE IF CHANGED
|
||||||
|
restartIfChanged = true;
|
||||||
|
confinement.enable = true;
|
||||||
|
confinement.packages = [
|
||||||
|
pkgs.git
|
||||||
|
pkgs.gnutar
|
||||||
|
pkgs.bash
|
||||||
|
pkgs.nixFlakes
|
||||||
|
pkgs.gzip
|
||||||
|
];
|
||||||
|
path = [
|
||||||
|
pkgs.git
|
||||||
|
pkgs.gnutar
|
||||||
|
pkgs.bash
|
||||||
|
pkgs.nixFlakes
|
||||||
|
pkgs.gzip
|
||||||
|
];
|
||||||
|
serviceConfig = {
|
||||||
|
Environment = [
|
||||||
|
"WOODPECKER_RUNNER_CAPACITY=2"
|
||||||
|
"WOODPECKER_RUNNER_NAME=woodpecker-agent"
|
||||||
|
"NIX_REMOTE=daemon"
|
||||||
|
"PAGER=cat"
|
||||||
|
];
|
||||||
|
BindPaths = [
|
||||||
|
"/nix/var/nix/daemon-socket/socket"
|
||||||
|
"/run/nscd/socket"
|
||||||
|
# "/var/lib/woodpecker"
|
||||||
|
];
|
||||||
|
BindReadOnlyPaths = [
|
||||||
|
"/etc/passwd:/etc/passwd"
|
||||||
|
"/etc/group:/etc/group"
|
||||||
|
"/nix/var/nix/profiles/system/etc/nix:/etc/nix"
|
||||||
|
"${config.environment.etc."ssl/certs/ca-certificates.crt".source}:/etc/ssl/certs/ca-certificates.crt"
|
||||||
|
"${config.environment.etc."ssh/ssh_known_hosts".source}:/etc/ssh/ssh_known_hosts"
|
||||||
|
"${builtins.toFile "ssh_config" ''
|
||||||
|
Host git.sealight.xyz
|
||||||
|
ForwardAgent yes
|
||||||
|
''}:/etc/ssh/ssh_config"
|
||||||
|
"/etc/machine-id"
|
||||||
|
"/etc/resolv.conf"
|
||||||
|
"/nix/"
|
||||||
|
];
|
||||||
|
EnvironmentFile = [
|
||||||
|
# /run/agenix/woodpecker-agent-secret
|
||||||
|
];
|
||||||
|
ExecStart = "${pkgs.woodpecker-agent}/bin/woodpecker-agent";
|
||||||
|
User = "woodpecker-runner";
|
||||||
|
Group = "woodpecker-runner";
|
||||||
|
};
|
||||||
|
};
|
||||||
|
}
|
52
hosts/profiles/woodpecker-server/default.nix
Normal file
52
hosts/profiles/woodpecker-server/default.nix
Normal file
|
@ -0,0 +1,52 @@
|
||||||
|
{
|
||||||
|
users.users.woodpecker = {
|
||||||
|
group = woodpecker;
|
||||||
|
description = "woodpecker user";
|
||||||
|
home = "/var/lib/woodpecker";
|
||||||
|
createHome = true;
|
||||||
|
};
|
||||||
|
|
||||||
|
users.groups.woodpecker = { };
|
||||||
|
|
||||||
|
services.nginx.virtualHosts."ci.sealight.xyz" = {
|
||||||
|
enableACME = true;
|
||||||
|
forceSSL = true;
|
||||||
|
locations."/".proxyPass = "http://localhost:3030/";
|
||||||
|
};
|
||||||
|
|
||||||
|
services.postgresql = {
|
||||||
|
ensureDatabases = [ "woodpecker" ];
|
||||||
|
ensureUsers = [{
|
||||||
|
name = "woodpecker";
|
||||||
|
ensurePermissions = {
|
||||||
|
"DATABASE woodpecker" = "ALL PRIVILEGES";
|
||||||
|
};
|
||||||
|
}];
|
||||||
|
};
|
||||||
|
|
||||||
|
systemd.services.woodpecker-server = {
|
||||||
|
wantedBy = [ "multi-user.target" ];
|
||||||
|
serviceConfig = {
|
||||||
|
EnvironmentFile = [
|
||||||
|
# GITEA_CLIENT_SECRET etc
|
||||||
|
# /run/agenix/woodpecker
|
||||||
|
];
|
||||||
|
Environment = [
|
||||||
|
"WOODPECKER_OPEN=true"
|
||||||
|
"WOODPECKER_AGENT_SECRET=${WOODPECKER_AGENT_SECRET}"
|
||||||
|
|
||||||
|
"WOODPECKER_GITEA=true"
|
||||||
|
"WOODPECKER_GITEA_URL=https://git.sealight.xyz"
|
||||||
|
|
||||||
|
"WOODPECKER_DATABASE_DATASOURCE=postgres:///woodpecker?host=/run/postgresql"
|
||||||
|
"WOODPECKER_DATABASE_DRIVER=postgres"
|
||||||
|
"WOODPECKER_SERVER_PORT=:3030"
|
||||||
|
"WOODPECKER_USER_CREATE=username:aynish,admin:true" # set your admin username
|
||||||
|
];
|
||||||
|
ExecStart = "${pkgs.woodpecker-server}/bin/woodpecker-server";
|
||||||
|
User = woodpecker;
|
||||||
|
Group = woodpecker;
|
||||||
|
};
|
||||||
|
};
|
||||||
|
|
||||||
|
}
|
195
modules/nixos/woodpecker.nix
Normal file
195
modules/nixos/woodpecker.nix
Normal file
|
@ -0,0 +1,195 @@
|
||||||
|
{ config, pkgs, lib, ... }:
|
||||||
|
# I gave up writing this lol
|
||||||
|
|
||||||
|
with lib;
|
||||||
|
|
||||||
|
let
|
||||||
|
cfg = config.services.woodpecker;
|
||||||
|
droneserver = config.users.users.droneserver.name;
|
||||||
|
|
||||||
|
in
|
||||||
|
{
|
||||||
|
options = {
|
||||||
|
enable = mkEnableOption "Woodpecker CI/CD";
|
||||||
|
|
||||||
|
user = mkOption {
|
||||||
|
type = types.str;
|
||||||
|
default = "woodpeckerserver";
|
||||||
|
description = "User account under which gonic runs.";
|
||||||
|
};
|
||||||
|
|
||||||
|
group = mkOption {
|
||||||
|
type = types.str;
|
||||||
|
default = "woodpeckerserver";
|
||||||
|
description = "Group account under which gonic runs.";
|
||||||
|
};
|
||||||
|
|
||||||
|
hostname = mkOption {
|
||||||
|
type = types.str;
|
||||||
|
example = "woodpecker.example.com";
|
||||||
|
description = "VirtualHost created for nginx";
|
||||||
|
};
|
||||||
|
};
|
||||||
|
|
||||||
|
config = mkIf cfg.enable {
|
||||||
|
users.users = optionalAttrs (cfg.user == name) {
|
||||||
|
${name} = {
|
||||||
|
group = cfg.group;
|
||||||
|
description = "woodpecker user";
|
||||||
|
home = cfg.dataDir;
|
||||||
|
createHome = true;
|
||||||
|
};
|
||||||
|
};
|
||||||
|
|
||||||
|
users.groups = optionalAttrs (cfg.group == name) {
|
||||||
|
${name}.gid = config.ids.gids.headphones;
|
||||||
|
};
|
||||||
|
|
||||||
|
services.nginx.virtualHosts."drone.my-server.tld" = {
|
||||||
|
enableACME = true;
|
||||||
|
forceSSL = true;
|
||||||
|
locations."/".proxyPass = "http://localhost:3030/";
|
||||||
|
};
|
||||||
|
|
||||||
|
services.postgresql = {
|
||||||
|
ensureDatabases = [ droneserver ];
|
||||||
|
ensureUsers = [{
|
||||||
|
name = droneserver;
|
||||||
|
ensurePermissions = {
|
||||||
|
"DATABASE ${droneserver}" = "ALL PRIVILEGES";
|
||||||
|
};
|
||||||
|
}];
|
||||||
|
};
|
||||||
|
|
||||||
|
# Secrets configured:
|
||||||
|
# - DRONE_GITEA_CLIENT_ID
|
||||||
|
# - DRONE_GITEA_CLIENT_SECRET
|
||||||
|
# - DRONE_RPC_SECRET
|
||||||
|
# To get these secrets, please check Drone's documentation for Gitea integration:
|
||||||
|
# https://docs.drone.io/server/provider/gitea/
|
||||||
|
|
||||||
|
sops.secrets.drone = {
|
||||||
|
sopsFile = ../.secrets/drone.yaml;
|
||||||
|
};
|
||||||
|
|
||||||
|
systemd.services.drone-server = {
|
||||||
|
wantedBy = [ "multi-user.target" ];
|
||||||
|
serviceConfig = {
|
||||||
|
EnvironmentFile = [
|
||||||
|
config.sops.secrets.drone.path
|
||||||
|
];
|
||||||
|
Environment = [
|
||||||
|
"DRONE_DATABASE_DATASOURCE=postgres:///droneserver?host=/run/postgresql"
|
||||||
|
"DRONE_DATABASE_DRIVER=postgres"
|
||||||
|
"DRONE_SERVER_PORT=:3030"
|
||||||
|
"DRONE_USER_CREATE=username:viperML,admin:true" # set your admin username
|
||||||
|
|
||||||
|
"DRONE_GITEA_SERVER=https://git.my-domain.tld"
|
||||||
|
"DRONE_SERVER_HOST=drone.my-domain.tld"
|
||||||
|
"DRONE_SERVER_PROTO=https"
|
||||||
|
];
|
||||||
|
ExecStart = "${pkgs.drone}/bin/drone-server";
|
||||||
|
User = droneserver;
|
||||||
|
Group = droneserver;
|
||||||
|
};
|
||||||
|
};
|
||||||
|
|
||||||
|
### Docker runner
|
||||||
|
|
||||||
|
users.users.drone-runner-docker = {
|
||||||
|
isSystemUser = true;
|
||||||
|
group = "drone-runner-docker";
|
||||||
|
};
|
||||||
|
users.groups.drone-runner-docker = { };
|
||||||
|
# Allow the runner to use docker
|
||||||
|
users.groups.docker.members = [ "drone-runner-docker" ];
|
||||||
|
|
||||||
|
systemd.services.drone-runner-docker = {
|
||||||
|
enable = true;
|
||||||
|
wantedBy = [ "multi-user.target" ];
|
||||||
|
### MANUALLY RESTART SERVICE IF CHANGED
|
||||||
|
restartIfChanged = false;
|
||||||
|
serviceConfig = {
|
||||||
|
Environment = [
|
||||||
|
"DRONE_RPC_PROTO=http"
|
||||||
|
"DRONE_RPC_HOST=localhost:3030"
|
||||||
|
"DRONE_RUNNER_CAPACITY=2"
|
||||||
|
"DRONE_RUNNER_NAME=drone-runner-docker"
|
||||||
|
];
|
||||||
|
EnvironmentFile = [
|
||||||
|
config.sops.secrets.drone.path
|
||||||
|
];
|
||||||
|
ExecStart = "${pkgs.drone-runner-docker}/bin/drone-runner-docker";
|
||||||
|
User = "drone-runner-docker";
|
||||||
|
Group = "drone-runner-docker";
|
||||||
|
};
|
||||||
|
};
|
||||||
|
|
||||||
|
### Exec runner
|
||||||
|
|
||||||
|
users.users.drone-runner-exec = {
|
||||||
|
isSystemUser = true;
|
||||||
|
group = "drone-runner-exec";
|
||||||
|
};
|
||||||
|
users.groups.drone-runner-exec = { };
|
||||||
|
# Allow the exec runner to write to build with nix
|
||||||
|
nix.allowedUsers = [ "drone-runner-exec" ];
|
||||||
|
|
||||||
|
systemd.services.drone-runner-exec = {
|
||||||
|
enable = true;
|
||||||
|
wantedBy = [ "multi-user.target" ];
|
||||||
|
### MANUALLY RESTART SERVICE IF CHANGED
|
||||||
|
restartIfChanged = true;
|
||||||
|
confinement.enable = true;
|
||||||
|
confinement.packages = [
|
||||||
|
pkgs.git
|
||||||
|
pkgs.gnutar
|
||||||
|
pkgs.bash
|
||||||
|
pkgs.nixFlakes
|
||||||
|
pkgs.gzip
|
||||||
|
];
|
||||||
|
path = [
|
||||||
|
pkgs.git
|
||||||
|
pkgs.gnutar
|
||||||
|
pkgs.bash
|
||||||
|
pkgs.nixFlakes
|
||||||
|
pkgs.gzip
|
||||||
|
];
|
||||||
|
serviceConfig = {
|
||||||
|
Environment = [
|
||||||
|
"DRONE_RPC_PROTO=http"
|
||||||
|
"DRONE_RPC_HOST=127.0.0.1:3030"
|
||||||
|
"DRONE_RUNNER_CAPACITY=2"
|
||||||
|
"DRONE_RUNNER_NAME=drone-runner-exec"
|
||||||
|
"NIX_REMOTE=daemon"
|
||||||
|
"PAGER=cat"
|
||||||
|
"DRONE_DEBUG=true"
|
||||||
|
];
|
||||||
|
BindPaths = [
|
||||||
|
"/nix/var/nix/daemon-socket/socket"
|
||||||
|
"/run/nscd/socket"
|
||||||
|
# "/var/lib/drone"
|
||||||
|
];
|
||||||
|
BindReadOnlyPaths = [
|
||||||
|
"/etc/passwd:/etc/passwd"
|
||||||
|
"/etc/group:/etc/group"
|
||||||
|
"/nix/var/nix/profiles/system/etc/nix:/etc/nix"
|
||||||
|
"${config.environment.etc."ssl/certs/ca-certificates.crt".source}:/etc/ssl/certs/ca-certificates.crt"
|
||||||
|
"${config.environment.etc."ssh/ssh_known_hosts".source}:/etc/ssh/ssh_known_hosts"
|
||||||
|
"${builtins.toFile "ssh_config" ''
|
||||||
|
Host git.ayats.org
|
||||||
|
ForwardAgent yes
|
||||||
|
''}:/etc/ssh/ssh_config"
|
||||||
|
"/etc/machine-id"
|
||||||
|
"/etc/resolv.conf"
|
||||||
|
"/nix/"
|
||||||
|
];
|
||||||
|
EnvironmentFile = [
|
||||||
|
config.sops.secrets.drone.path
|
||||||
|
];
|
||||||
|
ExecStart = "${pkgs.drone-runner-exec}/bin/drone-runner-exec";
|
||||||
|
User = "drone-runner-exec";
|
||||||
|
Group = "drone-runner-exec";
|
||||||
|
};
|
||||||
|
};
|
||||||
|
};
|
Loading…
Reference in a new issue