Compare commits

..
Author SHA1 Message Date
forust 5b3ef39102 template for lampa service 2026-01-21 11:36:36 +01:00
474 changed files with 19024 additions and 17997 deletions

No files matched your search

-191
View File
@@ -1,191 +0,0 @@
# Инструкция: Анализ хранилища Kubernetes и настройка NFS
## Цель
Проанализировать текущую конфигурацию хранилища Kubernetes и подготовить план внедрения NFS StorageClass для сохранения данных при удалении namespace.
## 1. Собрать информацию о кластере
### 1.1. Версия Kubernetes и тип дистрибутива
```bash
kubectl version --short
# или
kubectl version
```
Определить, используется ли k3s, k8s, microk8s и т.д.:
```bash
# Проверить наличие k3s
which k3s
# Проверить процесс
ps aux | grep -E 'kube|k3s'
```
### 1.2. StorageClass
```bash
kubectl get storageclass -o wide
```
Запомнить:
- `PROVISIONER` — какой драйвер используется
- `RECLAIMPOLICY` — Delete или Retain
- Какой StorageClass помечен как `(default)`
### 1.3. Существующие PV и PVC
```bash
kubectl get pv -o wide
kubectl get pvc --all-namespaces
```
Посмотреть, какие PVC привязаны к каким PV, и какой reclaimPolicy у PV.
### 1.4. Нода и диски
```bash
# Список нод
kubectl get nodes -o wide
# На каждой ноде (через ssh или локально):
lsblk
df -h
cat /etc/fstab
```
Определить:
- Есть ли отдельный раздел/диск для данных
- Куда смонтированы разделы
- Сколько свободного места
- Есть ли монтирование NTFS-разделов (как `/media/forust/Programs`)
### 1.5. Где local-path хранит данные (для k3s)
```bash
ls -la /var/lib/rancher/k3s/storage/ 2>/dev/null
# или для microk8s
ls -la /var/snap/microk8s/common/ 2>/dev/null
```
## 2. Анализ: сохраняются ли данные при удалении namespace?
| Сценарий | Результат |
|---|---|
| `kubectl delete ns <ns>` | Все PVC в namespace удаляются |
| PVC → PV c `reclaimPolicy: Delete` | PV и данные удалены |
| PVC → PV c `reclaimPolicy: Retain` | PV остаётся (статус Released), данные целы |
**Вывод:** Если reclaimPolicy в StorageClass = `Delete`, то данные **пропадут**. Если `Retain` — сохранятся.
## 3. План внедрения NFS
### 3.1. Проверить, установлен ли NFS
```bash
which nfsstat exportfs mount.nfs
systemctl status nfs-server 2>/dev/null || systemctl status nfs-kernel-server 2>/dev/null
```
### 3.2. Выбрать директорию для NFS-экспорта
Варианты (выбрать подходящий):
- `/var/lib/k8s-nfs/` — на корневом разделе
- `<путь к отдельному разделу>/k8s-nfs/` — если есть отдельный диск/раздел
- Не рекомендуется использовать NTFS-раздел (проблемы с правами и производительностью)
Требования:
- Файловая система: ext4 или xfs (не ntfs!)
- Достаточно свободного места
- Права: `755`, владелец root
### 3.3. Установить NFS-сервер
```bash
# Debian/Ubuntu
apt update && apt install -y nfs-kernel-server
# RHEL/Fedora
dnf install -y nfs-utils
```
### 3.4. Настроить экспорт
Создать директорию:
```bash
mkdir -p /var/lib/k8s-nfs
chmod 755 /var/lib/k8s-nfs
```
Добавить в `/etc/exports`:
```
/var/lib/k8s-nfs *(rw,sync,no_subtree_check,no_root_squash)
```
Применить:
```bash
exportfs -rav
```
Проверить:
```bash
showmount -e localhost
```
### 3.5. Выбрать способ интеграции с Kubernetes
#### Вариант A: nfs-subdir-external-provisioner (проще)
```bash
helm repo add nfs-subdir-external-provisioner https://kubernetes-sigs.github.io/nfs-subdir-external-provisioner/
helm install nfs-provisioner nfs-subdir-external-provisioner/nfs-subdir-external-provisioner \
--namespace kube-system \
--set nfs.server=127.0.0.1 \
--set nfs.path=/var/lib/k8s-nfs \
--set storageClass.name=nfs \
--set storageClass.defaultClass=false \
--set storageClass.reclaimPolicy=Retain
```
#### Вариант B: NFS CSI Driver
```bash
helm repo add csi-driver-nfs https://raw.githubusercontent.com/kubernetes-csi/csi-driver-nfs/master/charts
helm install csi-driver-nfs csi-driver-nfs/csi-driver-nfs --namespace kube-system
```
После установки CSI драйвера создать StorageClass:
```yaml
apiVersion: storage.k8s.io/v1
kind: StorageClass
metadata:
name: nfs
provisioner: nfs.csi.k8s.io
parameters:
server: 127.0.0.1
share: /var/lib/k8s-nfs
reclaimPolicy: Retain
volumeBindingMode: Immediate
```
### 3.6. Проверить результат
```bash
kubectl get storageclass
kubectl get pods -n kube-system | grep -E 'nfs|provisioner'
```
## 4. Итоговая конфигурация
После внедрения в кластере будет два StorageClass:
| Имя | Provisioner | ReclaimPolicy | Назначение |
|---|---|---|---|
| `local-path` (default) | rancher.io/local-path | Delete | Временные данные, stateless |
| `nfs` | nfs-subdir-external-provisioner или nfs.csi.k8s.io | Retain | Данные, которые нужно сохранять |
**Главное преимущество:** PVC c `storageClassName: nfs` при удалении namespace сохраняют данные на диске, так как NFS-провизор использует `reclaimPolicy: Retain` или файлы физически остаются в NFS-экспорте.
## 5. Ответы на частые вопросы
**В:** Не упадёт ли local-path при установке NFS?
**О:** Нет, они независимы. local-path продолжает работать как обычно.
**В:** Данные NFS и local-path будут на одном диске?
**О:** Да, можно настроить оба на одном разделе, в разных каталогах.
**В:** Что если у меня несколько нод?
**О:** NFS сервер нужно поднять на одной ноде, а с других нод должна быть доступна шари. Для multi-node лучше использовать отдельный сервер или distributed storage (Longhorn, Rook/Ceph).
**В:** Можно ли использовать существующий NTFS-раздел для NFS?
**О:** Не рекомендуется — NTFS не поддерживает права Linux (no_root_squash не сработает корректно), возможны проблемы с блокировками и производительностью.
-24
View File
@@ -1,24 +0,0 @@
root = true
[*]
indent_style = space
indent_size = 2
end_of_line = lf
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
[*.{yml,yaml}]
indent_size = 2
[*.{json,jsonc}]
indent_size = 2
[*.md]
trim_trailing_whitespace = false
[*.py]
indent_size = 4
[{Makefile,makefile}]
indent_style = tab
-10
View File
@@ -1,10 +0,0 @@
# actionlint configuration. Passed explicitly from the ci workflow:
# actionlint -config-file .gitea/actionlint.yaml .gitea/workflows/*.yaml
#
# The self-hosted act_runner registers custom labels that actionlint cannot know
# about, so declare them here instead of silencing the whole runner-label check.
self-hosted-runner:
labels:
- arch
- homelab
- prod
-80
View File
@@ -1,80 +0,0 @@
#!/usr/bin/env bash
# Local regressions only: kubectl is mocked and Docker is used for config parsing.
set -euo pipefail
repo="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
scratch="$(mktemp -d)"
trap 'rm -rf "$scratch"' EXIT
mkdir -p "$scratch/repo/app" "$scratch/repo/postgres" "$scratch/repo/netbird" "$scratch/repo/renovate"
git -C "$scratch/repo" init -q
for file in app/compose.yaml postgres/shared-compose.yaml netbird/client.compose.yaml renovate/renovate-compose.yaml; do
touch "$scratch/repo/$file"
done
git -C "$scratch/repo" add .
# shellcheck source=../workflows/compose-lint.sh
source "$repo/.gitea/workflows/compose-lint.sh"
actual="$(cd "$scratch/repo" && compose_files)"
expected=$'app/compose.yaml\nnetbird/client.compose.yaml\npostgres/shared-compose.yaml\nrenovate/renovate-compose.yaml'
[ "$actual" = "$expected" ] || { echo 'Compose discovery missed a file' >&2; exit 1; }
cat >"$scratch/compose.yaml" <<'YAML'
services:
example:
image: busybox:1.37.0
environment:
REQUIRED: ${HOMELAB_TEST_REQUIRED:?required for this regression}
YAML
unset HOMELAB_TEST_REQUIRED
if validate_compose_file "$scratch/compose.yaml" >"$scratch/config.log" 2>&1; then
echo 'Full Compose validation accepted a missing variable' >&2
exit 1
fi
grep -q 'required for this regression' "$scratch/config.log"
HOMELAB_TEST_REQUIRED=present validate_compose_file "$scratch/compose.yaml"
cat >"$scratch/resources.json" <<'JSON'
{"kind":"List","items":[
{"kind":"Deployment","metadata":{"namespace":"app"},"spec":{"template":{"spec":{
"containers":[{"envFrom":[{"secretRef":{"name":"credentials"}},{"secretRef":{"name":"optional","optional":true}}],"env":[{"valueFrom":{"secretKeyRef":{"name":"credentials","key":"password"}}}]}],
"initContainers":[{"envFrom":[{"secretRef":{"name":"init"}}]}],
"imagePullSecrets":[{"name":"registry"}],
"volumes":[{"secret":{"secretName":"mounted"}},{"projected":{"sources":[{"secret":{"name":"projected"}},{"secret":{"name":"optional-projected","optional":true}}]}}]
}}}},
{"kind":"CronJob","metadata":{},"spec":{"jobTemplate":{"spec":{"template":{"spec":{"containers":[{"envFrom":[{"secretRef":{"name":"cron"}}]}]}}}}}},
{"kind":"IngressRoute","metadata":{"namespace":"app"},"spec":{"tls":{"secretName":"controller-issued-tls"}}}
]}
JSON
actual="$(jq -r -f "$repo/.gitea/workflows/secret-references.jq" "$scratch/resources.json" | sort)"
expected=$'app credentials\napp init\napp mounted\napp projected\napp registry\ndefault cron'
[ "$actual" = "$expected" ] || { echo "Unexpected Secret references: $actual" >&2; exit 1; }
REPO="$repo"
# shellcheck source=../workflows/deploy-lib.sh
source "$repo/.gitea/workflows/deploy-lib.sh"
K8S_MANIFESTS=("$scratch/resources.json")
KUSTOMIZE_APPS=()
# No live cluster access. Reject credentials in app even if they exist elsewhere.
kubectl() {
case "$1" in
create) cat "$scratch/resources.json" ;;
get)
if [ "$3" = credentials ] && [ "$5" = app ]; then
return 1
fi
return 0
;;
*) echo "Unexpected kubectl invocation: $*" >&2; return 1 ;;
esac
}
if check_referenced_secrets >"$scratch/secrets.log"; then
echo 'Namespace-scoped Secret check accepted a missing Secret' >&2
exit 1
fi
grep -q 'MISSING OR UNREADABLE: app/credentials' "$scratch/secrets.log"
# API/rendering errors must not produce an empty reference list and pass.
kubectl() { return 1; }
if check_referenced_secrets >"$scratch/secrets.log"; then
echo 'Secret check accepted a failed manifest render' >&2
exit 1
fi
printf '%s\n' 'Deploy validation regressions passed.'
-550
View File
@@ -1,550 +0,0 @@
name: ci
on:
push:
branches:
- "**"
pull_request:
workflow_dispatch:
# Every job here is checkout plus local tools. The token needs to read the tree
# and nothing else, and saying so keeps a future step that reaches for the API
# from quietly holding a token that can write to the repository.
permissions:
contents: read
concurrency:
group: ci-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
env:
REGISTRY: gcr.forust.xyz
jobs:
lint-compose:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
# Structure check for every committed Compose file, active or not.
# Interpolation, env-file and bind-mount resolution are all switched off,
# because inactive stacks have no .env here and would only fail on their
# ${VAR:?} guards. Active stacks get the full check with interpolation in
# the deploy workflow, where the real .env files live.
- name: Validate Compose files
shell: bash
run: |
set -euo pipefail
source .gitea/workflows/compose-lint.sh
mapfile -t safe_flags < <(compose_safe_flags)
echo "docker compose config ${safe_flags[*]-}"
mapfile -t files < <(compose_files)
if [ "${#files[@]}" -eq 0 ]; then
echo "No Compose files found."
exit 0
fi
failed=0
for f in "${files[@]}"; do
if ! out="$(validate_compose_file "$f" ${safe_flags[@]+"${safe_flags[@]}"} 2>&1)"; then
failed=1
echo "::error file=${f}::$(printf '%s' "$out" | head -1)"
fi
done
if [ "$failed" -ne 0 ]; then
echo "Compose validation failed."
exit 1
fi
echo "checked ${#files[@]} Compose file(s)"
lint-actionlint:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint Gitea Actions workflows with actionlint
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh actionlint)"
export PATH="$tools_dir:$PATH"
actionlint -config-file .gitea/actionlint.yaml -color .gitea/workflows/*.yaml
lint-shellcheck:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint shell scripts with ShellCheck
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh shellcheck jq)"
export PATH="$tools_dir:$PATH"
mapfile -t scripts < <(
git ls-files '*.sh' ':(glob)**/*.bash'
)
if [ "${#scripts[@]}" -eq 0 ]; then
echo "No shell scripts found."
exit 0
fi
shellcheck --external-sources --source-path=SCRIPTDIR --severity=style "${scripts[@]}"
bash .gitea/tests/deploy-validation.sh
lint-prettier:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Check formatting with Prettier
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh prettier)"
export PATH="$tools_dir:$PATH"
mapfile -t prettier_files < <(
git ls-files \
| grep -E '\.(md|json|ya?ml|html|css)$' \
| grep -Ev '^(\.docs/|\.zed/|errorpages/html/|homepages/(forust_files|xdfnx_files)/)'
)
if [ "${#prettier_files[@]}" -eq 0 ]; then
echo "No Prettier-managed files found."
exit 0
fi
prettier --check --ignore-unknown "${prettier_files[@]}"
lint-ruff:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint and format-check Python with Ruff
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh ruff)"
export PATH="$tools_dir:$PATH"
ruff check .
ruff format --check .
lint-yaml:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint YAML syntax
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh yamllint)"
export PATH="$tools_dir:$PATH"
mapfile -t yaml_files < <(
git ls-files '*.yaml' '*.yml' \
':!node_modules/**' \
':!**/.venv/**'
)
if [ "${#yaml_files[@]}" -eq 0 ]; then
echo "No YAML files found."
exit 0
fi
yamllint -c .yamllint "${yaml_files[@]}"
lint-dockerfiles:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint Dockerfiles
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh hadolint)"
export PATH="$tools_dir:$PATH"
mapfile -t dockerfiles < <(
git ls-files ':(glob)**/Dockerfile' ':(glob)**/Dockerfile.*'
)
if [ "${#dockerfiles[@]}" -eq 0 ]; then
echo "No Dockerfiles found."
exit 0
fi
hadolint -c .hadolint.yaml "${dockerfiles[@]}"
validate:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 20
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Validate Kubernetes manifests against JSON schemas
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh kubeconform)"
export PATH="$tools_dir:$PATH"
mapfile -t manifests < <(
git ls-files ':(glob)**/k8s/**/*.yaml' ':(glob)**/k8s/**/*.yml' \
| grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$'
)
if [ "${#manifests[@]}" -eq 0 ]; then
echo "No Kubernetes manifests found."
exit 0
fi
kubeconform \
-strict \
-ignore-missing-schemas \
-summary \
"${manifests[@]}"
# kubeconform has no schemas for CRDs, so every IngressRoute, Certificate,
# PrometheusRule, Middleware, ServersTransport and ServiceMonitor is silently
# skipped above. The live API server knows the real CRD schemas (and runs the
# cert-manager / Traefik admission webhooks), so validate there too.
#
# Only services marked with a k8s/active marker are checked: server-side
# dry-run needs the target namespace to exist, and inactive services are not
# deployed. Services being enabled for the first time are still covered by
# the JSON-schema pass above.
#
# Main pushes only. `--dry-run=server` persists nothing, but it does execute
# the admission webhooks of the production API server, so anyone able to open
# a pull request would be able to run arbitrary manifest content through
# cert-manager and Traefik. A pull request has nothing to gain from it either:
# only main is ever deployed, and this job runs to completion before the
# deploy workflow is allowed to start, so a bad CRD is still caught before
# anything reaches the cluster -- just on the push rather than on the PR.
- name: Note the server-side check is not running here
if: github.event_name == 'pull_request' || github.ref != 'refs/heads/main'
shell: bash
run: |
echo "::notice::Skipping the server-side dry-run. It executes the cert-manager and" \
"Traefik admission webhooks against the production API server, so it is limited" \
"to pushes to main. CRDs are still schema-checked by kubeconform above, and the" \
"server-side pass still runs on main before the deploy."
- name: Validate active manifests against the live API server
if: github.event_name != 'pull_request' && github.ref == 'refs/heads/main'
shell: bash
run: |
set -euo pipefail
if ! kubectl get --raw='/readyz' --request-timeout=10s >/dev/null 2>&1; then
echo "::warning::Cluster unreachable — skipped server-side validation of CRDs (IngressRoute, Certificate, PrometheusRule). Review manifest changes manually."
exit 0
fi
mapfile -t k8s_dirs < <(
git ls-files '*.yaml' '*.yml' \
| grep -E '(^|/)k8s/' \
| sed -E 's#((^|.*/)k8s)/.*#\1#' \
| sort -u
)
manifests=()
kustomize_apps=()
for dir in "${k8s_dirs[@]}"; do
if [ ! -f "${dir}/active" ]; then
echo "skip (no k8s/active): ${dir}"
continue
fi
if [ -f "${dir}/overlays/prod/kustomization.yaml" ]; then
kustomize_apps+=("${dir}/overlays/prod")
elif [ -f "${dir}/base/kustomization.yaml" ]; then
kustomize_apps+=("${dir}/base")
else
while IFS= read -r f; do
[ -n "$f" ] && manifests+=("$f")
done < <(
git ls-files "${dir}/*.yaml" "${dir}/*.yml" \
| grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$'
)
fi
done
echo "server-side dry-run: ${#manifests[@]} manifests, ${#kustomize_apps[@]} kustomize apps"
failed=0
for m in ${manifests[@]+"${manifests[@]}"}; do
if ! out="$(kubectl apply --dry-run=server -f "$m" 2>&1)"; then
failed=1
echo "::error file=${m}::$(printf '%s' "$out" | head -1)"
fi
done
for k in ${kustomize_apps[@]+"${kustomize_apps[@]}"}; do
if ! out="$(kubectl apply -k "$k" --dry-run=server 2>&1)"; then
failed=1
echo "::error file=${k}::$(printf '%s' "$out" | head -1)"
fi
done
if [ "$failed" -ne 0 ]; then
echo "Server-side validation failed. The API server (or an admission webhook) rejected these manifests."
exit 1
fi
echo "server-side dry-run: all active manifests accepted by the API server"
build:
needs:
# The panel's scan-deps/test-backend/test-frontend jobs gated here until
# userbot moved to its own repo; upstream's code is upstream's gate now.
# The rule is unchanged: publishing and passing the checks are the same
# gate, so a commit that fails any of these still cannot move :prod.
[lint-actionlint, lint-shellcheck, lint-compose, lint-prettier, lint-ruff, lint-yaml, lint-dockerfiles, validate]
if: github.event_name != 'pull_request' && (github.ref_name == 'main' || github.ref_name == 'dev') && !startsWith(github.ref_name, 'renovate/')
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 60
outputs:
services: ${{ steps.services.outputs.services }}
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
with:
fetch-depth: 0
- name: Detect changed docker-built services
id: services
shell: bash
run: |
set -euo pipefail
base="${{ github.event.before }}"
if [ -z "$base" ] || [ "$base" = "0000000000000000000000000000000000000000" ]; then
base="$(git rev-list --max-parents=0 HEAD)"
fi
# A failed diff used to leave changed_files empty, which reads exactly
# like "nothing to build": the job went green having built nothing and
# the tag never moved. The status is checked, not assumed.
if ! changed="$(git diff --name-only "$base" "${GITHUB_SHA}")"; then
echo "::error::cannot diff ${base}..${GITHUB_SHA}"
exit 1
fi
mapfile -t changed_files <<<"$changed"
services=()
add_service() {
local name="$1"
local seen=0
for existing in "${services[@]}"; do
if [ "$existing" = "$name" ]; then
seen=1
break
fi
done
if [ "$seen" -eq 0 ]; then
services+=("$name")
fi
}
for file in "${changed_files[@]}"; do
case "$file" in
errorpages/*)
add_service errorpages
;;
homepages/*)
add_service homepages
;;
edu_master/phpsessid-bot/*|edu_master/webinar-checker/*|edu_master/compose.yaml)
add_service edu_master
;;
esac
done
if [ "${#services[@]}" -eq 0 ]; then
echo "No docker-built services changed."
echo "services=" >> "$GITHUB_OUTPUT"
exit 0
fi
printf '%s\n' "${services[@]}" | tee /tmp/services.txt
echo "services=$(paste -sd, /tmp/services.txt)" >> "$GITHUB_OUTPUT"
- name: Log in to registry
# The pin step below also writes (manifest PUTs), and it runs on every
# main push — including manifest-only ones where services is empty. A
# stale persistent login on the old runner used to mask this; a clean
# runner pushes anonymously and gets 401.
if: steps.services.outputs.services != '' || github.ref_name == 'main'
shell: bash
# Through env, not by substitution into the script. A secret written
# into a run: block is pasted into the shell source before bash parses
# it, so a password containing a quote, a backtick or $(...) becomes
# code that runs. Masking the value in the log does not prevent that.
env:
REGISTRY_USERNAME: ${{ secrets.REGISTRY_USERNAME }}
REGISTRY_PASSWORD: ${{ secrets.REGISTRY_PASSWORD }}
run: |
set -euo pipefail
printf '%s' "$REGISTRY_PASSWORD" | docker login "${REGISTRY}" \
-u "$REGISTRY_USERNAME" \
--password-stdin
- name: Build and push changed images
if: steps.services.outputs.services != ''
shell: bash
run: |
# This step was the one run: block in the workflow without it, and it
# is the one that cannot afford it: a docker push that failed partway
# through the loop used to be followed by more pushes, the loop's exit
# status came from the last one, and the job went green with half the
# images missing from the registry.
set -euo pipefail
IFS=, read -r -a services <<< "${{ steps.services.outputs.services }}"
# Tags for this push. The commit-pinned name is the point of this
# step: the deploy resolves it in preference to :prod, so a deploy
# that sat in the queue behind a later push still gets the build of
# the commit CI validated, instead of whatever :prod points at by the
# time it runs. See render_pinned in deploy-lib.sh.
commit_tag=""
if [ "${GITHUB_REF_NAME}" = "main" ]; then
commit_tag="sha-${GITHUB_SHA:0:12}"
fi
set_tags() {
tags=()
case "${GITHUB_REF_NAME}" in
main) tags+=("main" "prod") ;;
dev) tags+=("dev") ;;
esac
if [ -n "$commit_tag" ]; then
tags+=("$commit_tag")
fi
}
for service in "${services[@]}"; do
case "$service" in
errorpages)
image="${REGISTRY}/forust/error-pages"
set_tags
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" errorpages
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
;;
homepages)
for variant in forust xdfnx; do
case "$variant" in
forust)
image="${REGISTRY}/forust/forust-homepage"
;;
xdfnx)
image="${REGISTRY}/forust/xdfnx-homepage"
;;
esac
set_tags
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" -f "homepages/Dockerfile.${variant}" homepages
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
done
;;
edu_master)
for variant in session-keeper webinar-checker; do
case "$variant" in
session-keeper)
context="edu_master/phpsessid-bot"
image="${REGISTRY}/forust/session-keeper"
;;
webinar-checker)
context="edu_master/webinar-checker"
image="${REGISTRY}/forust/webinar-checker"
;;
esac
set_tags
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" "$context"
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
done
;;
esac
done
# Every image the tree names has to carry the commit-pinned name, not only
# the ones this push rebuilt. A push that touches nothing but manifests
# builds nothing, and its deploy would then find no commit-pinned tag to
# resolve and quietly fall back to the moving :prod - which is the whole
# failure the commit-pinned name exists to remove.
#
# Re-tagging copies the manifest list and transfers no layers, so pinning
# six images that already exist costs six registry writes.
#
# The list is derived from the tree rather than written out here, so an
# image added to a manifest is covered without a second place to update.
- name: Pin the commit name on the images this push did not rebuild
if: github.ref_name == 'main'
shell: bash
run: |
set -euo pipefail
commit_tag="sha-${GITHUB_SHA:0:12}"
mapfile -t repos < <(
git grep -hoE 'gcr\.forust\.xyz/forust/[A-Za-z0-9._-]+' -- '*.yaml' '*.yml' \
| sort -u
)
if [ "${#repos[@]}" -eq 0 ]; then
echo "No own images referenced by the tree."
exit 0
fi
echo "pinning ${#repos[@]} image(s) to $commit_tag"
for repo in "${repos[@]}"; do
if docker buildx imagetools inspect "$repo:$commit_tag" >/dev/null 2>&1; then
echo " already built by this push: ${repo##*/}"
continue
fi
if ! docker buildx imagetools inspect "$repo:prod" >/dev/null 2>&1; then
echo " WARNING: ${repo##*/} has no :prod to pin and no build produced it"
continue
fi
docker buildx imagetools create --tag "$repo:$commit_tag" "$repo:prod"
echo " pinned ${repo##*/}"
done
-45
View File
@@ -1,45 +0,0 @@
#!/usr/bin/env bash
# Shared helpers for validating Compose files. Sourced both by steps in
# .gitea/workflows/ci.yaml and by deploy-lib.sh on the workstation.
#
# Two levels of checking, matching how the repo is structured:
#
# general every committed Compose file, active or not. Pure structure check:
# no ${VAR} interpolation, no .env lookup, no bind-mount path
# resolution. Disabled stacks deliberately have no .env in the repo
# and no values on the CI runner, so a full `config` run would fail on
# their `${VAR:?}` guards for reasons that have nothing to do with the
# change under review.
#
# full active stacks only, with interpolation and env-file resolution, so
# required variables and referenced files are actually resolved. Needs
# the gitignored .env files, so this only runs in the deploy workflow
# on the workstation.
#
# This file is meant to be sourced, not executed.
# All committed Compose files, including the ones deploy never starts.
compose_files() {
git ls-files \
'*compose.yaml' '*compose.yml'
}
# Prints the flags that turn `docker compose config` into the general check.
# Probed rather than hardcoded so an older Compose without --no-env-resolution
# still gets the flags it does support.
compose_safe_flags() {
local help flag
help="$(docker compose config --help 2>/dev/null || true)"
for flag in --no-interpolate --no-env-resolution --no-path-resolution; do
if printf '%s' "$help" | grep -q -- "$flag"; then
printf '%s\n' "$flag"
fi
done
}
# validate_compose_file <file> [extra docker compose config flags...]
validate_compose_file() {
local file="$1"
shift
docker compose -f "$file" config --quiet "$@"
}
File diff suppressed because it is too large. Load diff
-197
View File
@@ -1,197 +0,0 @@
name: deploy
on:
# Deploy only what CI already validated. workflow_run is used instead of
# workflow_dispatch so a red lint/validate run can never reach the cluster.
workflow_run:
workflows: [ci]
types: [completed]
workflow_dispatch:
# The deploy jobs read the tree, then reach the cluster over SSH with the
# deploy key. The Actions token itself is not part of that path, so it gets
# read-only contents and no more.
permissions:
contents: read
concurrency:
group: deploy-main
# Queue instead of cancelling. Cancelling a run kills the apply job mid-loop and
# takes the verify job down with it, so a superseded deploy would leave the
# cluster half-applied and unchecked — the exact failure the verify job exists
# to catch. kubectl apply and docker compose up are both idempotent, so letting
# the older run finish and then deploying the newer commit costs little.
cancel-in-progress: false
env:
DEPLOY_HOST: ${{ secrets.DEPLOY_HOST }}
DEPLOY_PORT: ${{ secrets.DEPLOY_PORT }}
DEPLOY_USER: ${{ secrets.DEPLOY_USER }}
DEPLOY_PATH: ${{ secrets.DEPLOY_PATH }}
DEPLOY_KEY: ${{ secrets.DEPLOY_SSH_KEY }}
APPLY_PRUNE: ${{ vars.APPLY_PRUNE }}
# workflow_run's own GITHUB_SHA points at the branch head, not at the commit the
# finished ci run checked. Pin the exact validated commit instead, so a push
# landing mid-deploy cannot make the workstation deploy something else. Also
# what the verify job checks the snapshot against. Empty for workflow_dispatch,
# which falls back to the current origin/main.
DEPLOY_SHA: ${{ github.event.workflow_run.head_sha }}
jobs:
preflight:
# Autodeploy defaults to OFF: pushes deploy only when the AUTODEPLOY repo
# variable is set to 'true' (Settings -> Actions -> Variables). A manual
# Run workflow always bypasses the switch: dispatching it is the explicit
# intent to deploy.
if: >-
(vars.AUTODEPLOY == 'true' || github.event_name == 'workflow_dispatch') &&
(github.event_name != 'workflow_run' ||
(github.event.workflow_run.conclusion == 'success' &&
github.event.workflow_run.head_branch == 'main'))
runs-on: [self-hosted, linux, arch, homelab, prod]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Fetch and reset workstation
shell: bash
run: |
set -euo pipefail
./.gitea/workflows/ssh-run.sh preflight
validate:
needs: [preflight]
runs-on: [self-hosted, linux, arch, homelab, prod]
timeout-minutes: 20
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Dry-run manifests and check Secrets
shell: bash
run: |
set -euo pipefail
./.gitea/workflows/ssh-run.sh validate
apply-k8s:
needs: [validate]
runs-on: [self-hosted, linux, arch, homelab, prod]
# Apply only, no verification, so this is just the work itself: snapshot,
# then sequential `helm upgrade --install --wait --rollback-on-failure --timeout 10m`, then the apply loop.
# Verification has its own job and its own budget.
#
# 45 is roughly four times the measured cost of the stage, which is
# deliberately not raised on a theory:
#
# helm, healthy 3 no-op upgrades ~3-5 min
# helm, one release bad rollback-on-failure spends its 10m, ~10-15 min
# then rolls that one back
# apply loop ~40 manifests, 4 of which ~1 min
# resolve an image digest
# restart_stale_images 7.6s to find 8 workloads, ~0.5 min
# 9.8s to resolve their digests
#
# The helm figure is one release, not three: `set -e` aborts
# upgrade_helm_releases on the first failure, so a broken release costs
# 10m and the other two are never attempted. Multiplying 10m by three
# overstates the worst case by 20 minutes.
#
# The 45 minutes this was last raised to 45 were still not enough, and the
# job logs for those runs no longer exist, so what actually consumed the
# budget is not known - the two measurable candidates above account for
# ~15 of it. The unbounded `docker manifest inspect` against the registry's
# known hang mode is now bounded inside registry_digest (25s timeout, 3
# attempts): a dead registry fails each owned image after ~85s instead of
# hanging the stage, and a blinking one is retried instead of failing the
# whole apply file. Still open: make the stage announce which manifest it
# is working on, so a killed run leaves a diagnosable last line.
timeout-minutes: 45
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Apply Kubernetes manifests
shell: bash
run: |
set -euo pipefail
./.gitea/workflows/ssh-run.sh apply-k8s
apply-compose:
needs: [validate]
runs-on: [self-hosted, linux, arch, homelab, prod]
timeout-minutes: 30
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Redeploy docker compose stacks
shell: bash
run: |
set -euo pipefail
./.gitea/workflows/ssh-run.sh apply-compose
# Watches the workloads this deploy changed and rolls back the ones that never
# became healthy. Runs even when the apply jobs failed, timed out or were
# cancelled — that is the whole point of splitting it out. `always()` is what
# lets it start after a failed dependency; the needs on apply-compose are a
# barrier, so verification begins only once both applies are done.
verify-k8s:
needs: [apply-k8s, apply-compose]
if: >-
always() &&
needs.apply-k8s.result != 'skipped' &&
needs.apply-compose.result != 'skipped'
runs-on: [self-hosted, linux, arch, homelab, prod]
# Not raised, because the arithmetic does not close.
#
# 32 workloads are under management and the wave width is 8, so the verify
# itself is 4 waves of ROLLOUT_TIMEOUT (300s) = 20 minutes worst case, when
# every rollout times out rather than converging. That is already 20 of 30.
#
# The other 10 would have to absorb rollback, and rollback_workloads is a
# serial `while read` loop at 300s per failed workload. 10 minutes buys two.
# Any larger number is buying a bigger multiple of an unbounded term rather
# than covering a known cost: 60 minutes buys eight, and 60 minutes is
# therefore not a bound, it is a guess with two digits.
#
# The number becomes derivable the moment rollback uses the same wave width
# as the verify: 32 failures then cost 4 waves = 20 minutes instead of 160,
# and 45 covers verify plus rollback at full width. That change is to the
# recovery path and is not folded into a timeout edit.
timeout-minutes: 30
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Verify workloads and roll back on failure
shell: bash
run: |
set -euo pipefail
./.gitea/workflows/ssh-run.sh verify-k8s
# Asks the public route of every active service whether it is actually
# serving, which the rollout check above structurally cannot: a pod can
# converge and still be crash-looping, or be listening on a port no Service
# points at, or answer 500.
#
# `always()` for the same reason verify-k8s has it, and it runs after that job
# specifically because a rollback is when a route most needs re-checking. The
# needs is a barrier, not a filter: whether verify-k8s passed, failed or was
# cancelled, the probes are what say whether the cluster is serving, and
# suppressing them on a rollback would hide the one run where the answer
# matters most.
smoke:
needs: [verify-k8s]
if: always() && needs.verify-k8s.result != 'skipped'
runs-on: [self-hosted, linux, arch, homelab, prod]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Probe the public route of every active service
shell: bash
run: |
set -euo pipefail
./.gitea/workflows/ssh-run.sh smoke
-264
View File
@@ -1,264 +0,0 @@
#!/usr/bin/env bash
# Installs the pinned CI tools into "$TOOLS_DIR/bin" and echoes that directory
# on stdout, so callers can do:
#
# export PATH="$(bash .gitea/workflows/install-ci-tools.sh kubeconform shellcheck):$PATH"
#
# Versions come from tool-versions.env next to this script and are kept fresh by
# Renovate. Re-running is cheap: an already-installed tool at the pinned version
# is left alone.
set -euo pipefail
here="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck source=tool-versions.env
. "$here/tool-versions.env"
TOOLS_DIR="${TOOLS_DIR:-${RUNNER_TEMP:-/tmp}/homelab-tools}"
BIN_DIR="$TOOLS_DIR/bin"
mkdir -p "$BIN_DIR"
# The just-installed tools must resolve inside this script too: callers only
# prepend BIN_DIR to PATH after the script exits, so a bare `uv` below would
# miss the binary install_uv just placed (exit 127 on a clean runner).
export PATH="$BIN_DIR:$PATH"
arch="$(uname -m)"
# Upstream projects disagree on arch spelling: kubeconform and actionlint use
# Go names (amd64/arm64), shellcheck uses uname names (x86_64/aarch64), node
# uses neither (x64/arm64), and hadolint mixes the two in a single release
# (x86_64 but arm64).
case "$arch" in
x86_64 | amd64)
goarch=amd64
sharch=x86_64
nodearch=x64
hadolintarch=x86_64
;;
aarch64 | arm64)
goarch=arm64
sharch=aarch64
nodearch=arm64
hadolintarch=arm64
;;
*)
echo "install-ci-tools: unsupported architecture: $arch" >&2
exit 1
;;
esac
fetch() {
# fetch <url> <dest>
if command -v curl >/dev/null 2>&1; then
curl -sSLf --retry 3 -o "$2" "$1"
elif command -v wget >/dev/null 2>&1; then
wget -q -O "$2" "$1"
else
echo "install-ci-tools: neither curl nor wget is available" >&2
exit 1
fi
}
# resolve <command>
# Absolute path to use for invoking a tool: the copy in BIN_DIR when present,
# otherwise the name for PATH lookup. Every version check and every in-script
# invocation goes through this, so a tool missing from both places reads as
# "not installed" instead of dying with 127 under `set -e`.
resolve() {
if [ -x "$BIN_DIR/$1" ]; then
printf '%s' "$BIN_DIR/$1"
else
printf '%s' "$1"
fi
}
# installed_version <command>
# Prints the version of an already-installed tool, or nothing. Each tool spells
# its version flag differently, hence the case.
installed_version() {
local bin out
bin="$(resolve "$1")"
if ! command -v "$bin" >/dev/null 2>&1; then
return 0
fi
case "$1" in
kubeconform) out="$("$bin" -v 2>/dev/null | head -1 || true)" ;;
*) out="$("$bin" --version 2>/dev/null | head -1 || true)" ;;
esac
printf '%s' "$out"
}
# at_version <command> <expected>
at_version() {
case "$(installed_version "$1")" in
*"$2"*) return 0 ;;
*) return 1 ;;
esac
}
install_kubeconform() {
if at_version kubeconform "v${KUBECONFORM_VERSION}"; then
return 0
fi
local tmp
tmp="$(mktemp -d)"
fetch "https://github.com/yannh/kubeconform/releases/download/v${KUBECONFORM_VERSION}/kubeconform-linux-${goarch}.tar.gz" \
"$tmp/kubeconform.tar.gz"
tar -xzf "$tmp/kubeconform.tar.gz" -C "$tmp" kubeconform
install -m 0755 "$tmp/kubeconform" "$BIN_DIR/kubeconform"
rm -rf "$tmp"
}
install_shellcheck() {
if at_version shellcheck "${SHELLCHECK_VERSION}"; then
return 0
fi
local tmp
tmp="$(mktemp -d)"
fetch "https://github.com/koalaman/shellcheck/releases/download/v${SHELLCHECK_VERSION}/shellcheck-v${SHELLCHECK_VERSION}.linux.${sharch}.tar.xz" \
"$tmp/shellcheck.tar.xz"
tar -xJf "$tmp/shellcheck.tar.xz" -C "$tmp" --strip-components=1 "shellcheck-v${SHELLCHECK_VERSION}/shellcheck"
install -m 0755 "$tmp/shellcheck" "$BIN_DIR/shellcheck"
rm -rf "$tmp"
}
install_jq() {
if at_version jq "${JQ_VERSION}"; then
return 0
fi
fetch "https://github.com/jqlang/jq/releases/download/jq-${JQ_VERSION}/jq-linux-${goarch}" \
"$BIN_DIR/jq"
chmod 0755 "$BIN_DIR/jq"
}
install_uv() {
if at_version uv "${UV_VERSION}"; then
return 0
fi
local tmp
tmp="$(mktemp -d)"
# uv release tags carry no leading v, unlike every other tool installed here.
fetch "https://github.com/astral-sh/uv/releases/download/${UV_VERSION}/uv-${sharch}-unknown-linux-gnu.tar.gz" \
"$tmp/uv.tar.gz"
tar -xzf "$tmp/uv.tar.gz" -C "$tmp" --strip-components=1 "uv-${sharch}-unknown-linux-gnu/uv"
install -m 0755 "$tmp/uv" "$BIN_DIR/uv"
rm -rf "$tmp"
}
install_hadolint() {
if at_version hadolint "${HADOLINT_VERSION}"; then
return 0
fi
# A bare binary, no archive: hadolint ships one file per platform.
fetch "https://github.com/hadolint/hadolint/releases/download/v${HADOLINT_VERSION}/hadolint-linux-${hadolintarch}" \
"$BIN_DIR/hadolint"
chmod 0755 "$BIN_DIR/hadolint"
}
# ruff and yamllint both come from PyPI as wheels, which uv unpacks for us.
install_uv_tool() {
# <package> <pinned version>
if at_version "$1" "$2"; then
return 0
fi
install_uv
UV_TOOL_BIN_DIR="$BIN_DIR" "$BIN_DIR/uv" tool install --force "$1==$2" >/dev/null
}
install_ruff() {
install_uv_tool ruff "${RUFF_VERSION}"
}
install_yamllint() {
install_uv_tool yamllint "${YAMLLINT_VERSION}"
}
install_pip_audit() {
install_uv_tool pip-audit "${PIP_AUDIT_VERSION}"
}
install_prettier() {
if at_version prettier "${PRETTIER_VERSION}"; then
return 0
fi
# Not a standalone binary: prettier's entry point requires ../package.json
# relative to its own real path, so the package directory has to survive
# next to it. Hence a versioned directory plus a relative symlink, rather
# than copying the one file out as the other installers do.
local dir="$BIN_DIR/prettier-${PRETTIER_VERSION}"
if [ ! -f "$dir/package/package.json" ]; then
rm -rf "$dir"
mkdir -p "$dir"
fetch "https://registry.npmjs.org/prettier/-/prettier-${PRETTIER_VERSION}.tgz" "$dir/prettier.tgz"
tar -xzf "$dir/prettier.tgz" -C "$dir"
rm -f "$dir/prettier.tgz"
# npm strips the exec bit from bin/ on the way into the tarball.
chmod 0755 "$dir/package/bin/prettier.cjs"
fi
# Relative, so the whole tree stays valid if TOOLS_DIR is relocated.
ln -sfn "prettier-${PRETTIER_VERSION}/package/bin/prettier.cjs" "$BIN_DIR/prettier"
}
install_node() {
# npm gets checked by running it, not by looking it up: what matters is that
# it answers, so a stub, a half-removed Arch package or a name that resolves
# to something broken all have to read as "not installed". The runner's npm
# is a symlink into /usr/lib/node_modules/npm, which is exactly the kind of
# thing that disappears between runs.
if at_version node "v${NODE_VERSION}" && [ -n "$(installed_version npm)" ]; then
return 0
fi
# Same shape as prettier above: the tarball's bin/npm and bin/npx are links
# into lib/node_modules, so the whole tree has to survive next to them.
local dir="$BIN_DIR/node-${NODE_VERSION}"
if [ ! -x "$dir/bin/node" ]; then
rm -rf "$dir"
mkdir -p "$dir"
fetch "https://nodejs.org/dist/v${NODE_VERSION}/node-v${NODE_VERSION}-linux-${nodearch}.tar.xz" \
"$dir/node.tar.xz"
tar -xJf "$dir/node.tar.xz" -C "$dir" --strip-components=1 "node-v${NODE_VERSION}-linux-${nodearch}"
rm -f "$dir/node.tar.xz"
fi
# Relative, so the whole tree stays valid if TOOLS_DIR is relocated.
for bin in node npm npx; do
ln -sfn "node-${NODE_VERSION}/bin/${bin}" "$BIN_DIR/${bin}"
done
}
install_actionlint() {
if at_version actionlint "${ACTIONLINT_VERSION}"; then
return 0
fi
local tmp
tmp="$(mktemp -d)"
fetch "https://github.com/rhysd/actionlint/releases/download/v${ACTIONLINT_VERSION}/actionlint_${ACTIONLINT_VERSION}_linux_${goarch}.tar.gz" \
"$tmp/actionlint.tar.gz"
tar -xzf "$tmp/actionlint.tar.gz" -C "$tmp" actionlint
install -m 0755 "$tmp/actionlint" "$BIN_DIR/actionlint"
rm -rf "$tmp"
}
wanted=("$@")
if [ "${#wanted[@]}" -eq 0 ]; then
wanted=(kubeconform shellcheck actionlint prettier ruff yamllint hadolint)
fi
for tool in "${wanted[@]}"; do
case "$tool" in
kubeconform) install_kubeconform ;;
shellcheck) install_shellcheck ;;
jq) install_jq ;;
actionlint) install_actionlint ;;
prettier) install_prettier ;;
ruff) install_ruff ;;
yamllint) install_yamllint ;;
pip-audit) install_pip_audit ;;
hadolint) install_hadolint ;;
node) install_node ;;
uv) install_uv ;;
*)
echo "install-ci-tools: unknown tool: $tool" >&2
exit 1
;;
esac
done
printf '%s\n' "$BIN_DIR"
-76
View File
@@ -1,76 +0,0 @@
name: renovate-ci
on:
pull_request:
push:
branches:
- main
workflow_dispatch:
permissions:
contents: read
jobs:
validate-renovate:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 20
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
# renovate/k8s/cronjob.yaml is the single source of truth for the image tag,
# so the same version that runs in the cluster is the one validated here.
- name: Resolve the deployed Renovate image
id: image
shell: bash
run: |
set -euo pipefail
image="$(sed -n 's|.*image:[[:space:]]*\(renovate/renovate:[^[:space:]]*\).*|\1|p' \
renovate/k8s/cronjob.yaml | head -1)"
if [ -z "$image" ]; then
echo "::error::no renovate/renovate image found in renovate/k8s/cronjob.yaml"
exit 1
fi
echo "using $image"
echo "image=$image" >> "$GITHUB_OUTPUT"
- name: Validate Renovate repository config
shell: bash
run: |
set -euo pipefail
docker run --rm \
-v "$PWD/renovate:/opt/renovate:ro" \
-e RENOVATE_CONFIG_FILE=/opt/renovate/renovate.json \
"${{ steps.image.outputs.image }}" \
renovate-config-validator /opt/renovate/renovate.json
# The CronJob cannot read the repository, so renovate/k8s/configmap.yaml
# carries an inlined copy of the config. Fail if it no longer matches.
- name: Check the generated Renovate ConfigMap
shell: bash
run: |
set -euo pipefail
./.gitea/workflows/sync-renovate-configmap.sh --check
- name: Validate Renovate Kubernetes manifests
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh kubeconform)"
export PATH="$tools_dir:$PATH"
kubeconform \
-strict \
-ignore-missing-schemas \
-summary \
renovate/k8s/namespace.yaml \
renovate/k8s/configmap.yaml \
renovate/k8s/cronjob.yaml
- name: Validate Renovate Compose file
shell: bash
run: |
set -euo pipefail
source .gitea/workflows/compose-lint.sh
mapfile -t safe_flags < <(compose_safe_flags)
validate_compose_file renovate/renovate-compose.yaml \
${safe_flags[@]+"${safe_flags[@]}"}
-92
View File
@@ -1,92 +0,0 @@
name: renovate-run
on:
workflow_dispatch:
inputs:
repositories:
description: "Repositories to scan (comma-separated)"
required: false
default: "forust/homelab"
log_level:
description: "Renovate log level"
required: false
default: "info"
type: choice
options:
- info
- debug
dry_run:
description: "Plan only, do not open or update PRs"
required: false
default: false
type: boolean
# Renovate writes through its own bot PAT, passed in as RENOVATE_TOKEN, so the
# Actions token is only ever used to read the checkout.
permissions:
contents: read
concurrency:
group: renovate-run
cancel-in-progress: false
jobs:
run-renovate:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 60
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
# renovate/k8s/cronjob.yaml is the single source of truth for the image tag.
# Reading it here means this workflow validates and runs the exact version
# that is deployed, instead of a copy that silently goes stale.
- name: Resolve the deployed Renovate image
id: image
shell: bash
run: |
set -euo pipefail
image="$(sed -n 's|.*image:[[:space:]]*\(renovate/renovate:[^[:space:]]*\).*|\1|p' \
renovate/k8s/cronjob.yaml | head -1)"
if [ -z "$image" ]; then
echo "::error::no renovate/renovate image found in renovate/k8s/cronjob.yaml"
exit 1
fi
echo "using $image"
echo "image=$image" >> "$GITHUB_OUTPUT"
- name: Validate Renovate config
shell: bash
run: |
set -euo pipefail
docker run --rm \
-v "$PWD/renovate/renovate.json:/opt/renovate/renovate.json:ro" \
-e RENOVATE_CONFIG_FILE=/opt/renovate/renovate.json \
"${{ steps.image.outputs.image }}" \
renovate-config-validator
- name: Run Renovate
shell: bash
env:
RENOVATE_TOKEN: ${{ secrets.RENOVATE_TOKEN }}
RENOVATE_GITHUB_COM_TOKEN: ${{ secrets.RENOVATE_GITHUB_COM_TOKEN }}
RENOVATE_REPOSITORIES: ${{ inputs.repositories }}
RENOVATE_DRY_RUN: ${{ inputs.dry_run && 'full' || '' }}
LOG_LEVEL: ${{ inputs.log_level }}
run: |
set -euo pipefail
: "${RENOVATE_TOKEN:?missing RENOVATE_TOKEN secret — add a renovate-bot PAT in repo/org Actions secrets}"
docker run --rm \
-v "$PWD/renovate/renovate.json:/opt/renovate/renovate.json:ro" \
-e RENOVATE_PLATFORM=gitea \
-e RENOVATE_ENDPOINT=https://git.forust.xyz/api/v1 \
-e RENOVATE_TOKEN="$RENOVATE_TOKEN" \
-e RENOVATE_GITHUB_COM_TOKEN="${RENOVATE_GITHUB_COM_TOKEN:-}" \
-e RENOVATE_REPOSITORIES="${RENOVATE_REPOSITORIES:-forust/homelab}" \
-e RENOVATE_DRY_RUN="${RENOVATE_DRY_RUN:-}" \
-e RENOVATE_CONFIG_FILE=/opt/renovate/renovate.json \
-e RENOVATE_BASE_DIR=/tmp/renovate \
-e LOG_LEVEL="${LOG_LEVEL:-info}" \
"${{ steps.image.outputs.image }}"
-13
View File
@@ -1,13 +0,0 @@
# kubectl emits a List for files containing multiple resources.
(if .kind == "List" then .items[] else . end)
| (.metadata.namespace // "default") as $ns
| [
(.. | objects
| (.secretRef? // empty), (.secretKeyRef? // empty), (.secret? // empty)
| select(.optional != true)
| .name // .secretName // empty),
(.. | objects | .imagePullSecrets[]?.name)
]
| unique[]
| select(. != null and . != "")
| "\($ns) \(.)"
-71
View File
@@ -1,71 +0,0 @@
#!/usr/bin/env bash
# usage: ssh-run.sh <stage>
# Runs one deploy-lib.sh stage on the workstation over SSH.
set -euo pipefail
: "${DEPLOY_HOST:?missing DEPLOY_HOST}"
: "${DEPLOY_USER:?missing DEPLOY_USER}"
: "${DEPLOY_KEY:?missing DEPLOY_SSH_KEY}"
deploy_port="${DEPLOY_PORT:-22}"
deploy_path="${DEPLOY_PATH:-/srv/homelab}"
deploy_path="$(printf '%s' "$deploy_path" | tr -d '\"' | tr -d '\r' | xargs)"
# The private key is written to a per-run directory that is removed on exit, so a
# failed or cancelled job cannot leave deploy credentials in the runner's temp
# directory. Do not use a fixed path: apply-k8s and apply-compose run in parallel.
key_dir="$(mktemp -d "${RUNNER_TEMP:-/tmp}/homelab-deploy-key.XXXXXXXX")"
trap 'rm -rf "$key_dir"' EXIT INT TERM
ssh_key="$key_dir/deploy_key"
printf '%s\n' "$DEPLOY_KEY" > "$ssh_key"
chmod 600 "$ssh_key"
# A connection that died silently used to hang until the job timeout, and the
# stage was never re-run: one flaky TCP session cost a whole 45-minute apply.
# ServerAlive* bounds how long a dead peer goes unnoticed, ConnectTimeout bounds
# setup. Only exit 255 - ssh's own transport failures - is retried. A stage that
# fails on its own merits exits with the remote's status, so a real failure
# still surfaces its own log instead of burning three attempts. The stages are
# declarative applies, so re-running one that had already committed is harmless.
ssh_opts=(
-i "$ssh_key" -p "$deploy_port"
-o BatchMode=yes -o StrictHostKeyChecking=accept-new
-o ConnectTimeout=15
-o ServerAliveInterval=15 -o ServerAliveCountMax=4
)
rc=0
# apply-k8s and apply-compose are separate workflow jobs so the graph stays
# intact for the verify job, but on a single node they must not run at once:
# host docker churn on top of cluster churn is what melts the node (load 40+,
# netbird/ssh die, helm is left pending-*). Serialize them on the workstation
# with a shared lock; whoever arrives second waits.
remote_cmd=(bash -se)
case "$1" in
apply-k8s | apply-compose)
remote_cmd=(flock -w 5400 /tmp/homelab-apply.lock bash -se)
;;
esac
for attempt in 1 2 3; do
if [ "$attempt" -gt 1 ]; then
echo ":: warning::ssh transport failed, retrying (${attempt}/3)"
sleep $((attempt * 5))
fi
rc=0
# shellcheck disable=SC2029 # remote_cmd/ssh_opts expand on the client on purpose: they select the local ssh invocation, only the heredoc runs remotely.
ssh "${ssh_opts[@]}" "${DEPLOY_USER}@${DEPLOY_HOST}" \
env "REPO=$deploy_path" "APPLY_PRUNE=${APPLY_PRUNE:-false}" \
"DEPLOY_SHA=${DEPLOY_SHA:-}" "DEPLOY_SNAPSHOT_DIR=${DEPLOY_SNAPSHOT_DIR:-}" \
"STAGE=$1" "${remote_cmd[@]}" <<'EOF' || rc=$?
source "$REPO/.gitea/workflows/deploy-lib.sh"
run_stage "$STAGE"
EOF
[ "$rc" -eq 0 ] && break
[ "$rc" -ne 255 ] && break
done
if [ "$rc" -ne 0 ]; then
echo ":: error::stage $1 failed over ssh (exit $rc)"
fi
exit "$rc"
@@ -1,55 +0,0 @@
#!/usr/bin/env bash
# Regenerates renovate/k8s/configmap.yaml from renovate/renovate.json.
#
# renovate/renovate.json is the single source of truth: the CronJob, the Compose
# file and the renovate-run workflow all mount that exact file. A ConfigMap cannot
# read a file from the repository, so the same bytes are inlined here as a literal
# block. This script keeps the copy honest:
#
# .gitea/workflows/sync-renovate-configmap.sh # rewrite in place
# .gitea/workflows/sync-renovate-configmap.sh --check # fail if out of date
#
# renovate-ci runs the --check form on every PR and push, so a config change that
# forgets to regenerate the ConfigMap cannot be merged.
set -euo pipefail
here="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
repo="$(git -C "$here" rev-parse --show-toplevel)"
src="$repo/renovate/renovate.json"
dst="$repo/renovate/k8s/configmap.yaml"
[ -f "$src" ] || {
echo "missing $src" >&2
exit 1
}
render() {
cat <<'HEADER'
# GENERATED FILE - do not edit by hand.
# Source: renovate/renovate.json
# Regenerate: .gitea/workflows/sync-renovate-configmap.sh
# Verify: .gitea/workflows/sync-renovate-configmap.sh --check
apiVersion: v1
kind: ConfigMap
metadata:
name: renovate-config
namespace: renovate
data:
renovate.json: |
HEADER
sed 's/^/ /' "$src"
}
if [ "${1:-}" = "--check" ]; then
if ! diff -u "$dst" <(render) >/dev/null 2>&1; then
echo "ERROR: $dst is out of sync with renovate/renovate.json"
echo "Run: .gitea/workflows/sync-renovate-configmap.sh"
diff -u "$dst" <(render) || true
exit 1
fi
echo "renovate/k8s/configmap.yaml is in sync with renovate/renovate.json"
exit 0
fi
render >"$dst"
echo "wrote $dst"
-36
View File
@@ -1,36 +0,0 @@
# Pinned versions of the CI tools installed by install-ci-tools.sh.
# Renovate keeps these up to date (see customManagers in renovate/renovate.json).
#
# Every version here except NODE_VERSION matches what was already installed on
# the runner, so pinning them changes what CI does not at all. It changes what
# CI does when the runner is rebuilt with something else: today
# install-ci-tools.sh finds the pinned version already on PATH and installs
# nothing, and a runner that drifts gets the pinned one installed over it.
#
# The renovate image version is NOT pinned here: renovate/k8s/cronjob.yaml is the
# single source of truth and the workflows read the tag from it, so there is
# nothing to drift.
ACTIONLINT_VERSION="1.7.7"
SHELLCHECK_VERSION="0.11.0"
KUBECONFORM_VERSION="0.8.0"
PRETTIER_VERSION="3.8.1"
RUFF_VERSION="0.16.8"
YAMLLINT_VERSION="1.38.0"
HADOLINT_VERSION="2.14.0"
# pip-audit reads the advisory database over the network, so a floating version
# would make the same commit report different things on different days. Pin it
# like the rest: the advisories themselves are the moving part, not the tool.
PIP_AUDIT_VERSION="2.10.1"
# uv builds the throwaway venv the pytest job runs in, and unpacks the PyPI
# wheels for ruff, yamllint and pip-audit.
UV_VERSION="0.12.17"
# node runs `npm ci` for the frontend tests and the npm audit, and it is the one
# pin here that does NOT come from the runner: the runner's system node is a
# rolling Arch package (it was node 26 with no npm at all when this was pinned),
# and the panel image is node:22-alpine. Pinned to the image's major on purpose,
# so the tree that gets tested is the tree that gets built. Renovate keeps this
# in step with the Dockerfile's node: tag via the "node runtime" group.
NODE_VERSION="22.23.3"
# Secret-reference regression tests parse rendered Kubernetes objects.
JQ_VERSION="1.8.1"
+7 -31
View File
@@ -5,12 +5,12 @@ sync.ffs_lock
# Copyparty # Copyparty
*.hist/ *.hist/
# Volumes, configs and data directories # Volumes and data directories
gitea/gitea-db/ gitea/gitea-db/
gitea/gitea-data/* gitea/gitea-data/*
n8n/n8n-data/* n8n/n8n-data/*
n8n/n8n-node-data/* n8n/n8n-node-data/*
adguardhome/conf/* adguardhome/data/*
dockmon/data/* dockmon/data/*
portainer/portainer_data/* portainer/portainer_data/*
metube/MeTube_downloads metube/MeTube_downloads
@@ -21,10 +21,6 @@ checkmk/checkmk/*
downtify/Downtify_downloads downtify/Downtify_downloads
headscale/config/* headscale/config/*
headscale/data/* headscale/data/*
# NetBird local hostnames and generated secrets
netbird/.env
netbird/secrets/
searxng/core-config/*
# Steaming services files # Steaming services files
streaming/jellyfin/* streaming/jellyfin/*
@@ -35,28 +31,23 @@ streaming/data/*
streaming/qbittorrent/* streaming/qbittorrent/*
streaming/prowlarr/* streaming/prowlarr/*
# Homepage # Homepage
homepages/forust_files/assets/images/team/*
homepages/forust_files/.well-known/* homepages/forust_files/.well-known/*
# Traefik files # Traefik files
traefik/letsencrypt/acme.json traefik/letsencrypt/acme.json
traefik/dynamic/fileservers.yml traefik/dynamic/fileservers.yml
traefik/dynamic/*.local.y*ml.*
traefik/dynamic/*.external.y*ml
traefik/k8s/fileservers.y*ml
traefik/k8s/aliasHeadersStrategy.md
traefik/logs/* traefik/logs/*
# SSL Certificates # SSL Certificates
adguardhome/certs/* adguardhome/certs/*
traefik/certs/* traefik/certs/*
certs/
# Monitoring # Monitoring
monitoring/prometheus.yml monitoring/prometheus.yml
# Python # Python
.python-version .python-version
venv/ venv/
pyc pyc
@@ -86,8 +77,6 @@ replacements.txt
# Git # Git
.gitattributes .gitattributes
# Gitea/github Runners
.runner
# Misc # Misc
.DS_Store .DS_Store
@@ -96,23 +85,10 @@ replacements.txt
# Temp files # Temp files
edu_master/temp/ edu_master/temp/
temp/* temp/*
# Local-only tooling scratch space (pinned CI tools, verification scripts)
tmp/
# Environment # Environment
.env .env
.env.anna .env.anna
.env.forust .env.forust
.env.* .env.*
!*example !*example
# kubernetes
*/k8s/*secret*
!*/k8s/*secret*.example
**/k8s/*secret*
!**/k8s/*secret*.example
# Local-only tweaks, not for upstream
prometheus-stack/k8s/grafana-values.yaml
traefik/k8s/local-tls.yaml
converters/k8s/config.yaml
convertx/k8s/config.yaml
-10
View File
@@ -1,10 +0,0 @@
ignored:
- DL3008
- DL3042
- DL3018
- DL3059
trustedRegistries:
- docker.io
- ghcr.io
- quay.io
- gcr.forust.xyz
-8
View File
@@ -1,8 +0,0 @@
{
"default": true,
"MD013": false,
"MD024": false,
"MD033": false,
"MD041": false,
"MD046": false
}
-7
View File
@@ -1,7 +0,0 @@
bracketSameLine: true
htmlWhitespaceSensitivity: css
printWidth: 120
tabWidth: 2
trailingComma: all
proseWrap: preserve
endOfLine: lf
-22
View File
@@ -1,22 +0,0 @@
extends: default
rules:
comments:
min-spaces-from-content: 1
comments-indentation: false
document-start: disable
line-length: disable
braces:
min-spaces-inside: 0
max-spaces-inside: 1
brackets:
min-spaces-inside: 0
max-spaces-inside: 1
indentation:
spaces: 2
indent-sequences: consistent
truthy:
allowed-values:
- "true"
- "false"
- "on"
-40
View File
@@ -1,40 +0,0 @@
{
"tab_size": 2,
"soft_wrap": "prefer_line",
"preferred_line_length": 120,
"format_on_save": "on",
"languages": {
"YAML": {
"tab_size": 2,
"hard_tabs": false,
"format_on_save": "on",
"formatter": {
"language_server": { "name": "yaml-language-server" },
},
},
"Python": {
"tab_size": 4,
"format_on_save": "on",
"language_servers": ["pyright", "ruff"],
"formatter": {
"language_server": { "name": "ruff" },
},
},
},
"lsp": {
"yaml-language-server": {
"settings": {
"yaml": {
"schemas": {
"kubernetes": ["**/k8s/*.yaml", "**/k8s/*.yml"],
},
"validate": true,
"completion": true,
"format": {
"enable": true,
},
},
},
},
},
}
+14 -12
View File
@@ -1,6 +1,6 @@
services: services:
adguard: adguard:
image: adguard/adguardhome:v0.107.79 image: adguard/adguardhome:latest
container_name: adguardhome container_name: adguardhome
restart: unless-stopped restart: unless-stopped
ports: ports:
@@ -11,38 +11,40 @@ services:
# - "68:68/tcp" # DHCP # - "68:68/tcp" # DHCP
# - "3000:3000/tcp" # - "3000:3000/tcp"
volumes: volumes:
- data:/opt/adguardhome/work - ./data/work:/opt/adguardhome/work
- ./conf:/opt/adguardhome/conf - ./data/conf:/opt/adguardhome/conf
- ./certs:/certs:ro - ./certs:/certs:ro
labels: labels:
- "traefik.enable=true" - "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.adguard.loadbalancer.server.port=3000" - "traefik.http.services.adguard.loadbalancer.server.port=3000"
# Prod Router # Prod Router
- "traefik.http.routers.adguard.rule=Host(`dns.forust.xyz`) || Host(`adguard.forust.xyz`)" - "traefik.http.routers.adguard.rule=Host(`dns.forust.xyz`) || Host(`adguard.forust.xyz`)"
- "traefik.http.routers.adguard.entrypoints=websecure" - "traefik.http.routers.adguard.entrypoints=websecure"
- "traefik.http.routers.adguard.tls.certresolver=letsencrypt" - "traefik.http.routers.adguard.middlewares=security-headers@file"
- "traefik.http.routers.adguard.tls=true"
# Local Router # Local Router
- "traefik.http.routers.adguard-local.rule=Host(`adguard.workstation.internal`) || Host(`dns.workstation.internal`)" - "traefik.http.routers.adguard-local.rule=Host(`adguard.workstation.internal`) || Host(`dns.workstation.internal`)"
- "traefik.http.routers.adguard-local.entrypoints=websecure" - "traefik.http.routers.adguard-local.entrypoints=websecure"
- "traefik.http.routers.adguard-local.middlewares=security-headers@file"
- "traefik.http.routers.adguard-local.tls=true" - "traefik.http.routers.adguard-local.tls=true"
# Dev Router # Dev Router
- "traefik.http.routers.adguard-dev.rule=Host(`adguard.gigaforust.internal`) || Host(`dns.gigaforust.internal`)" - "traefik.http.routers.adguard-dev.rule=Host(`adguard.gigaforust.internal`) Host(`dns.gigaforust.internal`)"
- "traefik.http.routers.adguard-dev.entrypoints=websecure" - "traefik.http.routers.adguard-dev.entrypoints=websecure"
- "traefik.http.routers.adguard-dev.middlewares=security-headers@file"
- "traefik.http.routers.adguard-dev.tls=true" - "traefik.http.routers.adguard-dev.tls=true"
# DoH Router # DoH Router
- "traefik.http.routers.dns-over-https.rule=(Host(`dns.forust.xyz` || Host(`adguard.forust.xyz`)) && PathPrefix(`/dns-query`))" - "traefik.http.routers.dns.rule=(Host(`dns.forust.xyz`) && PathPrefix(`/dns-query`))"
- "traefik.http.routers.dns-over-https.entrypoints=websecure" - "traefik.http.routers.dns.entrypoints=websecure"
- "traefik.http.routers.dns-over-https.tls.certresolver=letsencrypt" - "traefik.http.routers.dns.tls.certresolver=letsencrypt"
# Glance Metadata # Glance Metadata
- glance.name=adguard - glance.name=adguard
- glance.url=https://adguard.forust.xyz/ - glance.url=https://adguard.forust.xyz/
- glance.description=AdGuard Home is a network-wide software for blocking ads. - glance.description=AdGuard Home is a network-wide software for blocking ads.
networks: networks:
- proxy - proxy
volumes:
data:
networks: networks:
proxy: proxy:
external: true external: true
-127
View File
@@ -1,127 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: adguard-lb-service
namespace: adguard
annotations:
metallb.io/loadBalancerIPs: "192.168.80.3"
spec:
type: LoadBalancer
externalTrafficPolicy: Local
selector:
app: adguard
ports:
- name: dns-udp
port: 53
targetPort: 53
protocol: UDP
- name: dns-tcp
port: 53
targetPort: 53
protocol: TCP
- name: dot
port: 853
targetPort: 853
protocol: TCP
---
apiVersion: v1
kind: Service
metadata:
name: adguard-service
namespace: adguard
spec:
selector:
app: adguard
ports:
- port: 3000
name: webui
targetPort: 3000
- port: 53
name: dns
targetPort: 53
protocol: UDP
- port: 53
name: dns-tcp
targetPort: 53
protocol: TCP
- port: 853
name: dot
targetPort: 853
---
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: adguard-deployment
namespace: adguard
spec:
replicas: 1
selector:
matchLabels:
app: adguard
strategy:
type: Recreate
template:
metadata:
labels:
app: adguard
spec:
containers:
- name: adguard
image: adguard/adguardhome:v0.107.79
resources:
limits:
memory: "1.5Gi"
cpu: "300m"
requests:
memory: "512Mi"
cpu: "50m"
ports:
- containerPort: 3000
name: webui
- containerPort: 53
name: dns
- containerPort: 853
name: dot
readinessProbe:
tcpSocket:
port: dns
initialDelaySeconds: 5
periodSeconds: 5
successThreshold: 1
failureThreshold: 3
volumeMounts:
- name: adguard-data
mountPath: /opt/adguardhome/work
subPath: work
- name: adguard-data
mountPath: /opt/adguardhome/conf
subPath: conf
- name: adguard-certs
mountPath: /certs
readOnly: true
volumes:
- name: adguard-data
persistentVolumeClaim:
claimName: adguard-pvc
- name: adguard-certs
secret:
secretName: adguard-certs
items:
- key: tls.crt
path: fullchain.pem
- key: tls.key
path: privkey.pem
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: adguard-pvc
namespace: adguard
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 2Gi
-12
View File
@@ -1,12 +0,0 @@
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: adguard-certs
namespace: adguard
spec:
secretName: adguard-certs
dnsNames:
- dns.forust.xyz
issuerRef:
name: letsencrypt-prod
kind: ClusterIssuer
-43
View File
@@ -1,43 +0,0 @@
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: adguard-prod
namespace: adguard
spec:
entryPoints:
- websecure
routes:
- match: Host(`dns.forust.xyz`)
kind: Rule
services:
- name: adguard-service
port: 3000
- match: (Host(`dns.forust.xyz`)) && PathPrefix(`/dns-query`)
kind: Rule
services:
- name: adguard-service
port: 3000
tls:
secretName: adguard-certs
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: adguard-local
namespace: adguard
spec:
entryPoints:
- websecure
routes:
- match: Host(`adguard.workstation.internal`) || Host(`dns.workstation.internal`) || Host(`adguard.gigaforust.internal`) || Host(`dns.gigaforust.internal`)
kind: Rule
services:
- name: adguard-service
port: 3000
- match: (Host(`adguard.workstation.internal`) || Host(`dns.workstation.internal`) || Host(`adguard.gigaforust.internal`) || Host(`dns.gigaforust.internal`)) && PathPrefix(`/dns-query`)
kind: Rule
services:
- name: adguard-service
port: 3000
tls:
secretName: internal-wildcard-tls
-15
View File
@@ -1,15 +0,0 @@
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: internal-wildcard-tls
namespace: adguard
spec:
secretName: internal-wildcard-tls
dnsNames:
- "*.workstation.internal"
- "*.gigaforust.internal"
- workstation.internal
- gigaforust.internal
issuerRef:
name: internal-ca
kind: ClusterIssuer
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: adguard
-10
View File
@@ -1,10 +0,0 @@
kubectl apply -f k8s/namespace.yaml && \
kubectl create secret tls adguard-certs -n adguard \
--cert=certs/fullchain.pem \
--key=certs/privkey.pem --dry-run=client -o yaml > \
k8s/secrets.yaml
# OR WITH NO FILE CREATION:
kubectl create secret tls adguard-certs -n adguard \
--cert=certs/fullchain.pem --key=certs/privkey.pem \
--save-config
+9 -3
View File
@@ -1,6 +1,6 @@
services: services:
postgresql: postgresql:
image: docker.io/library/postgres:15.19-alpine image: docker.io/library/postgres:15-alpine
restart: unless-stopped restart: unless-stopped
env_file: env_file:
- .env - .env
@@ -42,20 +42,26 @@ services:
- ./custom-templates:/templates - ./custom-templates:/templates
labels: labels:
- "traefik.enable=true" - "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.authentik-server.loadbalancer.server.port=9000" - "traefik.http.services.authentik-server.loadbalancer.server.port=9000"
# Prod Router # Prod Router
- "traefik.http.routers.authentik-server.rule=Host(`auth.forust.xyz`)" - "traefik.http.routers.authentik-server.rule=Host(`auth.forust.xyz`)"
- "traefik.http.routers.authentik-server.entrypoints=websecure" - "traefik.http.routers.authentik-server.entrypoints=websecure"
- "traefik.http.routers.authentik-server.tls.certresolver=letsencrypt" - "traefik.http.routers.authentik-server.middlewares=security-headers@file"
- "traefik.http.routers.authentik-server.service=authentik-server"
- "traefik.http.routers.authentik-server.tls=true"
# Local Router # Local Router
- "traefik.http.routers.authentik-server-local.rule=Host(`auth.workstation.internal`)" - "traefik.http.routers.authentik-server-local.rule=Host(`auth.workstation.internal`) || Host(`auth-dashboard.internal`)"
- "traefik.http.routers.authentik-server-local.entrypoints=websecure" - "traefik.http.routers.authentik-server-local.entrypoints=websecure"
- "traefik.http.routers.authentik-server-local.middlewares=security-headers@file"
- "traefik.http.routers.authentik-server-local.service=authentik-server"
- "traefik.http.routers.authentik-server-local.tls=true" - "traefik.http.routers.authentik-server-local.tls=true"
# Dev Router # Dev Router
- "traefik.http.routers.authentik-server-dev.rule=Host(`auth.gigaforust.internal`)" - "traefik.http.routers.authentik-server-dev.rule=Host(`auth.gigaforust.internal`)"
- "traefik.http.routers.authentik-server-dev.entrypoints=websecure" - "traefik.http.routers.authentik-server-dev.entrypoints=websecure"
- "traefik.http.routers.authentik-server-dev.middlewares=security-headers@file" - "traefik.http.routers.authentik-server-dev.middlewares=security-headers@file"
- "traefik.http.routers.authentik-server-dev.service=authentik-server"
- "traefik.http.routers.authentik-server-dev.tls=true" - "traefik.http.routers.authentik-server-dev.tls=true"
networks: networks:
- proxy - proxy
-101
View File
@@ -1,101 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: authentik-server-service
namespace: authentik
spec:
type: ClusterIP
selector:
app: authentik-server
ports:
- port: 9000
targetPort: 9000
---
apiVersion: v1
kind: Service
metadata:
name: authentik-worker-service
namespace: authentik
spec:
type: ClusterIP
selector:
app: authentik-worker
ports:
- port: 9000
targetPort: 9000
---
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: authentik-server-deployment
namespace: authentik
spec:
replicas: 1
selector:
matchLabels:
app: authentik-server
strategy:
type: Recreate
template:
metadata:
labels:
app: authentik-server
spec:
containers:
- name: authentik-server
image: ghcr.io/goauthentik/server:2026.8.3
args: ["server"]
envFrom:
- configMapRef:
name: authentik-config
- secretRef:
name: authentik-secrets
ports:
- containerPort: 9000
resources:
requests:
memory: "768Mi"
cpu: "100m"
limits:
memory: "1.5Gi"
cpu: "1000m"
---
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: authentik-worker-deployment
namespace: authentik
spec:
replicas: 1
selector:
matchLabels:
app: authentik-worker
strategy:
type: Recreate
template:
metadata:
labels:
app: authentik-worker
spec:
containers:
- name: authentik-worker
image: ghcr.io/goauthentik/server:2026.8.3
args: ["worker"]
securityContext:
runAsUser: 0
envFrom:
- configMapRef:
name: authentik-config
- secretRef:
name: authentik-secrets
resources:
requests:
memory: "320Mi"
cpu: "100m"
limits:
memory: "768Mi"
cpu: "700m"
-28
View File
@@ -1,28 +0,0 @@
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: authentik-prod-tls
namespace: authentik
spec:
secretName: authentik-prod-tls
dnsNames:
- auth.forust.xyz
issuerRef:
name: letsencrypt-prod
kind: ClusterIssuer
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: internal-wildcard-tls
namespace: authentik
spec:
secretName: internal-wildcard-tls
dnsNames:
- "*.workstation.internal"
- "*.gigaforust.internal"
- workstation.internal
- gigaforust.internal
issuerRef:
name: internal-ca
kind: ClusterIssuer
-11
View File
@@ -1,11 +0,0 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: authentik-config
namespace: authentik
data:
AUTHENTIK_IMAGE: ghcr.io/goauthentik/server
AUTHENTIK_TAG: "2025.10.2"
AUTHENTIK_POSTGRESQL__HOST: postgres.database.svc.cluster.local
AUTHENTIK_POSTGRESQL__NAME: authentik
AUTHENTIK_ERROR_REPORTING__ENABLED: "true"
-33
View File
@@ -1,33 +0,0 @@
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: authentik-prod
namespace: authentik
spec:
entryPoints:
- websecure
routes:
- match: Host(`auth.forust.xyz`)
kind: Rule
services:
- name: authentik-server-service
port: 9000
tls:
secretName: authentik-prod-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: authentik-local
namespace: authentik
spec:
entryPoints:
- websecure
routes:
- match: Host(`auth.workstation.internal`) || Host(`auth.gigaforust.internal`)
kind: Rule
services:
- name: authentik-server-service
port: 9000
tls:
secretName: internal-wildcard-tls
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: authentik
-11
View File
@@ -1,11 +0,0 @@
apiVersion: v1
kind: Secret
metadata:
name: authentik-secrets
namespace: authentik
type: Opaque
stringData:
AUTHENTIK_SECRET_KEY: ""
AUTHENTIK_POSTGRESQL__PASSWORD: ""
AUTHENTIK_POSTGRESQL__USER: authentik
AUTHENTIK_BOOTSTRAP_PASSWORD: authentik
@@ -1,9 +0,0 @@
crds:
enabled: true
prometheus:
servicemonitor:
enabled: true
interval: 60s
scrapeTimeout: 30s
labels:
release: prometheus-stack
-29
View File
@@ -1,29 +0,0 @@
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: letsencrypt-staging
spec:
acme:
email: bobrovod@national.shitposting.agency
server: https://acme-staging-v02.api.letsencrypt.org/directory
privateKeySecretRef:
name: letsencrypt-staging-account-key
solvers:
- http01:
ingress:
class: traefik
---
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: letsencrypt-prod
spec:
acme:
email: bobrovod@national.shitposting.agency
server: https://acme-v02.api.letsencrypt.org/directory
privateKeySecretRef:
name: letsencrypt-prod-account-key
solvers:
- http01:
ingress:
class: traefik
@@ -1,30 +0,0 @@
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
-33
View File
@@ -1,33 +0,0 @@
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: selfsigned
spec:
selfSigned: {}
---
# Homelab internal root CA (10y). Install the .crt on clients (see below).
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: internal-ca-root
namespace: cert-manager
spec:
isCA: true
commonName: homelab internal root CA
duration: 87600h
renewBefore: 7200h
secretName: internal-ca-root
privateKey:
algorithm: RSA
size: 4096
issuerRef:
name: selfsigned
kind: ClusterIssuer
---
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: internal-ca
spec:
ca:
secretName: internal-ca-root
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: cert-manager
-15
View File
@@ -1,15 +0,0 @@
CLOUDFLARE_API_TOKEN=YOUR_CLOUDFLARE_API_TOKEN
DOMAINS=example.com,dns.example.com,mc.example.com,auth.example.com,ssh.example.com
IP4_DOMAINS=
IP6_DOMAINS=
IP4_PROVIDER=cloudflare.trace
IP6_PROVIDER=none # change if you want to update AAAA
UPDATE_CRON=@every 5m
UPDATE_ON_START=true
DELETE_ON_STOP=false
DELETE_ON_FAILURE=true
TTL=1
PROXIED=!is(dns.example.com) && !is(mc.example.com) && !is(ssh.example.com)
EMOJI=true
UPTIMEKUMA=https://uptime-kuma.example.com/api/push/AsaSDFGFkfklaFALSKffkfFKfkfkfkFK?status=up&msg=OK&ping=
REJECT_CLOUDFLARE_IPS=true
+6 -23
View File
@@ -1,30 +1,13 @@
services: services:
cloudflare-ddns: cloudflare-ddns:
image: timothyjmiller/cloudflare-ddns:2.2.0 image: timothyjmiller/cloudflare-ddns:latest
container_name: cloudflare-ddns container_name: cloudflare-ddns
restart: unless-stopped restart: unless-stopped
security_opt: security_opt:
- no-new-privileges:true - no-new-privileges:true
network_mode: "host" network_mode: 'host'
# https://github.com/timothymiller/cloudflare-ddns#-quick-start
environment: environment:
- CLOUDFLARE_API_TOKEN=${CLOUDFLARE_API_TOKEN:?Cloudflare API token is required} - PUID=1000
- DOMAINS=${DOMAINS:-} - PGID=1000
- IP4_DOMAINS=${IP4_DOMAINS:-} volumes:
- IP6_DOMAINS=${IP6_DOMAINS:-} - ./config.json:/config.json
- IP4_PROVIDER=${IP4_PROVIDER:-cloudflare.trace}
- IP6_PROVIDER=${IP6_PROVIDER:-none}
- UPDATE_CRON=${UPDATE_CRON:-@every 5m}
- UPDATE_ON_START=${UPDATE_ON_START:-true}
- DELETE_ON_STOP=${DELETE_ON_STOP:-false}
- DELETE_ON_FAILURE=${DELETE_ON_FAILURE:-true}
- TTL=${TTL:-1} # 1=auto
# to proxy only "dns.example.com" and "wfs.example.com" use "!is(dns.domain.com) && !is (wfs.domain.com)"
- PROXIED=${PROXIED:-true}
- EMOJI=${EMOJI:-true}
- UPTIMEKUMA=${UPTIMEKUMA:-}
- HEALTHCHECKS=${HEALTHCHECKS:-}
- REJECT_CLOUDFLARE_IPS=${REJECT_CLOUDFLARE_IPS:-true}
# volumes:
# Prefer using environment variables for configuration, config.json legacy support
# - ./config.json:/config.json
+1 -1
View File
@@ -7,7 +7,7 @@
"api_key": { "api_key": {
"api_key": "api_key_here", "api_key": "api_key_here",
"account_email": "your_email_here" "account_email": "your_email_here"
}, }
"zone_id": "your_zone-id", "zone_id": "your_zone-id",
"subdomains": [ "subdomains": [
{ "name": "", "proxied": true }, { "name": "", "proxied": true },
-1
View File
@@ -1 +0,0 @@
secret.yaml
View File
Whitespace-only changes.
-36
View File
@@ -1,36 +0,0 @@
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: cfddns
labels:
app: cfddns
spec:
replicas: 1
selector:
matchLabels:
app: cfddns
strategy:
type: Recreate
template:
metadata:
labels:
app: cfddns
spec:
hostNetwork: true
dnsPolicy: ClusterFirstWithHostNet
containers:
- name: cloudflare-ddns
image: timothyjmiller/cloudflare-ddns:2.2.0
imagePullPolicy: Always
resources:
requests:
memory: "32Mi"
cpu: "30m"
limits:
memory: "128Mi"
cpu: "50m"
envFrom:
- secretRef:
name: cfddns-secrets
-18
View File
@@ -1,18 +0,0 @@
apiVersion: v1
kind: Secret
metadata:
name: cfddns-secrets
type: Opaque
stringData:
CLOUDFLARE_API_TOKEN: your_token
DOMAINS: "example.com,www.example.com"
IP4_PROVIDER: cloudflare.trace
IP6_PROVIDER: none
UPDATE_CRON: "@every 5m"
UPDATE_ON_START: "true"
DELETE_ON_STOP: "false"
DELETE_ON_FAILURE: "true"
TTL: "1"
PROXIED: "true"
EMOJI: "true"
REJECT_CLOUDFLARE_IPS: "true"
+6 -3
View File
@@ -1,6 +1,6 @@
services: services:
checkmk: checkmk:
image: "checkmk/check-mk-raw:2.4.0-2026.09.14" image: "checkmk/check-mk-raw:2.4.0-latest"
container_name: "checkmk" container_name: "checkmk"
restart: unless-stopped restart: unless-stopped
# ports: # ports:
@@ -13,21 +13,24 @@ services:
environment: environment:
- CMK_PASSWORD=${CMK_PASSWORD:-password} - CMK_PASSWORD=${CMK_PASSWORD:-password}
- CMK_SITE_ID=cmk - CMK_SITE_ID=cmk
- TZ=${TZ:-Etc/UTC}
labels: labels:
- "traefik.enable=true" - "traefik.enable=true"
- "traefik.docker.network=proxy"
- "traefik.http.services.checkmk.loadbalancer.server.port=5000" - "traefik.http.services.checkmk.loadbalancer.server.port=5000"
# Prod Router # Prod Router
- "traefik.http.routers.checkmk.rule=Host(`cmk.forust.xyz`)" - "traefik.http.routers.checkmk.rule=Host(`cmk.forust.xyz`)"
- "traefik.http.routers.checkmk.entrypoints=websecure" - "traefik.http.routers.checkmk.entrypoints=websecure"
- "traefik.http.routers.checkmk.tls.certresolver=letsencrypt" - "traefik.http.routers.checkmk.middlewares=security-headers@file"
- "traefik.http.routers.checkmk.tls=true"
# Local Router # Local Router
- "traefik.http.routers.checkmk-local.rule=Host(`cmk.workstation.internal`)" - "traefik.http.routers.checkmk-local.rule=Host(`cmk.workstation.internal`)"
- "traefik.http.routers.checkmk-local.entrypoints=websecure" - "traefik.http.routers.checkmk-local.entrypoints=websecure"
- "traefik.http.routers.checkmk-local.middlewares=security-headers@file"
- "traefik.http.routers.checkmk-local.tls=true" - "traefik.http.routers.checkmk-local.tls=true"
# Dev Router # Dev Router
- "traefik.http.routers.checkmk-dev.rule=Host(`cmk.gigaforust.internal`)" - "traefik.http.routers.checkmk-dev.rule=Host(`cmk.gigaforust.internal`)"
- "traefik.http.routers.checkmk-dev.middlewares=security-headers@file"
- "traefik.http.routers.checkmk-dev.entrypoints=websecure" - "traefik.http.routers.checkmk-dev.entrypoints=websecure"
- "traefik.http.routers.checkmk-dev.tls=true" - "traefik.http.routers.checkmk-dev.tls=true"
networks: networks:
-28
View File
@@ -1,28 +0,0 @@
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: checkmk-prod-tls
namespace: checkmk
spec:
secretName: checkmk-prod-tls
dnsNames:
- cmk.forust.xyz
issuerRef:
name: letsencrypt-prod
kind: ClusterIssuer
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: internal-wildcard-tls
namespace: checkmk
spec:
secretName: internal-wildcard-tls
dnsNames:
- "*.workstation.internal"
- "*.gigaforust.internal"
- workstation.internal
- gigaforust.internal
issuerRef:
name: internal-ca
kind: ClusterIssuer
-79
View File
@@ -1,79 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: checkmk-service
namespace: checkmk
spec:
selector:
app: checkmk
ports:
- name: web
port: 5000
targetPort: 5000
- name: agent-receiver
port: 8000
targetPort: 8000
---
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: checkmk-deployment
namespace: checkmk
spec:
replicas: 1
selector:
matchLabels:
app: checkmk
strategy:
type: Recreate
template:
metadata:
labels:
app: checkmk
spec:
containers:
- name: checkmk
image: checkmk/check-mk-raw:2.4.0-2026.09.14
envFrom:
- secretRef:
name: checkmk-secrets
- configMapRef:
name: checkmk-config
ports:
- name: web
containerPort: 5000
- name: agent-receiver
containerPort: 8000
volumeMounts:
- name: sites
mountPath: /omd/sites
- name: tmp
mountPath: /opt/omd/sites/cmk/tmp
resources:
requests:
memory: "2Gi"
cpu: "600m"
limits:
memory: "5Gi"
cpu: "4"
volumes:
- name: sites
persistentVolumeClaim:
claimName: checkmk-sites-pvc
- name: tmp
emptyDir:
medium: Memory
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: checkmk-sites-pvc
namespace: checkmk
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 5Gi
-8
View File
@@ -1,8 +0,0 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: checkmk-config
namespace: checkmk
data:
TZ: Europe/Bratislava
CMK_SITE_ID: cmk
-49
View File
@@ -1,49 +0,0 @@
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: checkmk-prod
namespace: checkmk
spec:
entryPoints:
- websecure
routes:
- match: Host(`cmk.forust.xyz`)
kind: Rule
services:
- name: checkmk-service
port: 5000
tls:
secretName: checkmk-prod-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRouteTCP
metadata:
name: checkmk-agent-receiver
namespace: checkmk
spec:
entryPoints:
- checkmk-agent
routes:
- match: HostSNI(`*`)
services:
- name: checkmk-service
port: 8000
tls:
passthrough: true
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: checkmk-local
namespace: checkmk
spec:
entryPoints:
- websecure
routes:
- match: Host(`cmk.workstation.internal`) || Host(`cmk.gigaforust.internal`)
kind: Rule
services:
- name: checkmk-service
port: 5000
tls:
secretName: internal-wildcard-tls
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: checkmk
-8
View File
@@ -1,8 +0,0 @@
apiVersion: v1
kind: Secret
metadata:
name: checkmk-secrets
namespace: checkmk
type: Opaque
stringData:
CMK_PASSWORD: "password"
-1
View File
@@ -1 +0,0 @@
secret.yaml
-41
View File
@@ -1,41 +0,0 @@
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: cloudflared
labels:
app: cloudflared
spec:
replicas: 1
selector:
matchLabels:
app: cloudflared
strategy:
type: Recreate
template:
metadata:
labels:
app: cloudflared
spec:
containers:
- name: cloudflared
image: cloudflare/cloudflared:2026.9.3
imagePullPolicy: IfNotPresent
args:
- tunnel
- --no-autoupdate
- run
env:
- name: TUNNEL_TOKEN
valueFrom:
secretKeyRef:
name: cloudflared-secrets
key: TUNNEL_TOKEN
resources:
requests:
memory: "128Mi"
cpu: "30m"
limits:
memory: "256Mi"
cpu: "200m"
-7
View File
@@ -1,7 +0,0 @@
apiVersion: v1
kind: Secret
metadata:
name: cloudflared-secrets
type: Opaque
stringData:
TUNNEL_TOKEN: your_tunnel_token_here
-9
View File
@@ -1,9 +0,0 @@
ACCOUNT_REGISTRATION=false
HTTP_ALLOWED=false
ALLOW_UNAUTHENTICAED=false
AUTO_DELETE_EVERY_N_HOURS=24
WEBROOT=/convert
HIDE_HISTORY=false
LANGUAGE=en
UNAUTHED_USER_SHARING=false
MAX_CONVERT_PROCESS=0
-70
View File
@@ -1,70 +0,0 @@
services:
convertx:
container_name: convertx
image: ghcr.io/c4illin/convertx:v0.19.0
restart: unless-stopped
ports:
- "9992:3000"
# https://github.com/C4illin/ConvertX#environment-variables
environment:
- JWT_SECRET=$(JWT_SECRET)
- ACCOUNT_REGISTRATION=$(ACCOUNT_REGISTRATION:-false)
- HTTP_ALLOWED=$(HTTP_ALLOWED:-false)
- ALLOW_UNAUTHENTICATED=$(ALLOW_UNAUTHENTICATED:-false)
- AUTO_DELETE_EVERY_N_HOURS=$(AUTO_DELETE_EVERY_N_HOURS:-24)
- WEBROOT=$(WEBROOT)
- HIDE_HISTORY=$(HIDE_HISTORY:-false)
- LANGUAGE=$(LANGUAGE:-en)
- UNAUTHENTICATED_USER_SHARING=$(UNAUTHENTICATED_USER_SHARING:-false)
- MAX_CONVERT_PROCESS=$(MAX_CONVERT_PROCESS:-0)
labels:
- "traefik.enable=true"
- "traefik.http.services.convertx.loadbalancer.server.port=3000"
# Prod Router
- "traefik.http.routers.convertx.rule=(Host(`forust.xyz`) || Host(`www.forust.xyz`)) && PathPrefix(`/convert`)"
- "traefik.http.routers.convertx.entrypoints=websecure"
- "traefik.http.routers.convertx.priority=50"
- "traefik.http.routers.convertx.tls.certresolver=letsencrypt"
# Local Router
- "traefik.http.routers.convertx-local.rule=Host(`workstation.internal`) && PathPrefix(`/convert`)"
- "traefik.http.routers.convertx-local.entrypoints=websecure"
- "traefik.http.routers.convertx-local.priority=50"
- "traefik.http.routers.convertx-local.tls=true"
# Dev Router
- "traefik.http.routers.convertx-dev.rule=Host(`gigaforust.internal`) && PathPrefix(`/convert`)"
- "traefik.http.routers.convertx-dev.entrypoints=websecure"
- "traefik.http.routers.convertx-dev.priority=50"
- "traefik.http.routers.convertx-dev.tls=true"
networks:
- proxy
volumes:
- data:/app/data
bentopdf:
container_name: bentopdf
image: bentopdf/bentopdf@sha256:4eb4ec8f5030faf87c29a73d3d5a2781f28a597cf440c3ab111eb96aee550871
restart: unless-stopped
labels:
- "traefik.enable=true"
- "traefik.http.services.bentopdf.loadbalancer.server.port=8080"
# Prod router
- "traefik.http.routers.bentopdf.rule=Host(`pdf.forust.xyz`)"
- "traefik.http.routers.bentopdf.entrypoints=websecure"
- "traefik.http.routers.bentopdf.tls.certresolver=letsencrypt"
- "traefik.http.routers.bentopdf.tls=true"
# Local router
- "traefik.http.routers.bentopdf-local.rule=Host(`pdf.workstation.internal`)"
- "traefik.http.routers.bentopdf-local.entrypoints=websecure"
- "traefik.http.routers.bentopdf-local.tls=true"
# Dev router
- "traefik.http.routers.bentopdf-dev.rule=Host(`pdf.gigaforust.internal`)"
- "traefik.http.routers.bentopdf-dev.entrypoints=websecure"
- "traefik.http.routers.bentopdf-dev.tls=true"
networks:
- proxy
networks:
proxy:
external: true
volumes:
data:
View File
Whitespace-only changes.
-43
View File
@@ -1,43 +0,0 @@
kind: Service
apiVersion: v1
metadata:
name: bentopdf-service
namespace: converters
spec:
selector:
app: bentopdf
ports:
- port: 8080
targetPort: 8080
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: bentopdf-deployment
namespace: converters
spec:
replicas: 2
selector:
matchLabels:
app: bentopdf
template:
metadata:
labels:
app: bentopdf
spec:
containers:
- image: bentopdf/bentopdf@sha256:4eb4ec8f5030faf87c29a73d3d5a2781f28a597cf440c3ab111eb96aee550871
imagePullPolicy: Always
name: bentopdf
ports:
- containerPort: 8080
# p95 4M, max 11M over 7 days. Was 50Mi/700Mi.
resources:
requests:
memory: "32Mi"
cpu: "50m"
ephemeral-storage: "100Mi"
limits:
memory: "128Mi"
cpu: "700m"
ephemeral-storage: "5Gi"
-42
View File
@@ -1,42 +0,0 @@
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: convertx-prod-tls
namespace: converters
spec:
secretName: convertx-prod-tls
dnsNames:
- forust.xyz
- www.forust.xyz
issuerRef:
name: letsencrypt-prod
kind: ClusterIssuer
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: bentopdf-prod-tls
namespace: converters
spec:
secretName: bentopdf-prod-tls
dnsNames:
- pdf.forust.xyz
issuerRef:
name: letsencrypt-prod
kind: ClusterIssuer
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: internal-wildcard-tls
namespace: converters
spec:
secretName: internal-wildcard-tls
dnsNames:
- "*.workstation.internal"
- "*.gigaforust.internal"
- workstation.internal
- gigaforust.internal
issuerRef:
name: internal-ca
kind: ClusterIssuer
-16
View File
@@ -1,16 +0,0 @@
# test manifest with docker and k8s config keys mismatch
apiVersion: v1
kind: ConfigMap
metadata:
name: convertx-config
namespace: converters
data:
ACCOUNT_REGISTRATION: "false"
HTTP_ALLOWED: "false"
ALLOW_UNAUTHENTICAED: "false"
AUTO_DELETE_EVERY_N_HOURS: "24"
WEBROOT: "/convert"
HIDE_HISTORY: "false"
LANGUAGE: "en"
UNAUTHED_USER_SHARING: "false"
MAX_CONVERT_PROCESS: "0"
-68
View File
@@ -1,68 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: convertx-service
namespace: converters
spec:
selector:
app: convertx
ports:
- port: 3000
targetPort: 3000
---
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: convertx-deployment
namespace: converters
spec:
replicas: 1
selector:
matchLabels:
app: convertx
strategy:
type: Recreate
template:
metadata:
labels:
app: convertx
spec:
containers:
- image: ghcr.io/c4illin/convertx:v0.19.0
name: convertx
envFrom:
- configMapRef:
name: convertx-config
- secretRef:
name: convertx-secrets
ports:
- containerPort: 3000
volumeMounts:
- mountPath: /data
name: data
# p95 85M, max 136M over 7 days, spikes while converting. Was 250Mi/1.5Gi.
resources:
requests:
memory: "128Mi"
cpu: "100m"
limits:
cpu: "1500m"
memory: "512Mi"
volumes:
- name: data
persistentVolumeClaim:
claimName: convertx-pvc
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: convertx-pvc
namespace: converters
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 2Gi
-70
View File
@@ -1,70 +0,0 @@
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: convertx-prod
namespace: converters
spec:
entryPoints:
- websecure
routes:
- match: (Host(`forust.xyz`) || Host(`www.forust.xyz`)) && PathPrefix(`/convert`)
kind: Rule
priority: 50
services:
- name: convertx-service
port: 3000
tls:
secretName: convertx-prod-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: convertx-local
namespace: converters
spec:
entryPoints:
- websecure
routes:
- match: (Host(`workstation.internal`) || Host(`gigaforust.internal`)) && PathPrefix(`/convert`)
kind: Rule
priority: 50
services:
- name: convertx-service
port: 3000
tls:
secretName: internal-wildcard-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: bentopdf-prod
namespace: converters
spec:
entryPoints:
- websecure
routes:
- match: Host(`pdf.forust.xyz`)
kind: Rule
services:
- name: bentopdf-service
port: 8080
tls:
secretName: bentopdf-prod-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: bentopdf-local
namespace: converters
spec:
entryPoints:
- websecure
routes:
- match: Host(`pdf.workstation.internal`) || Host(`pdf.gigaforust.internal`)
kind: Rule
services:
- name: bentopdf-service
port: 8080
tls:
secretName: internal-wildcard-tls
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: converters
-8
View File
@@ -1,8 +0,0 @@
apiVersion: v1
kind: Secret
metadata:
name: convertx-secrets
namespace: converters
type: Opaque
stringData:
jwt-secret: ""
-203
View File
@@ -1,203 +0,0 @@
container_runtime: containerd
agent:
acquisition: []
additionalAcquisition:
- labels:
type: traefik
limit: 1000
query: |
{namespace="traefik"}
source: loki
url: http://loki.prometheus.svc.cluster.local:3100/
wait_for_ready: 30s
env:
- name: COLLECTIONS
value: crowdsecurity/traefik crowdsecurity/base-http-scenarios
- name: DISABLE_COLLECTIONS
value: crowdsecurity/sshd
# Bans on 401/403 bursts hurt more than they protect: with L3 enforcement
# a false positive cuts the IP off everything (SSH included), and past
# incidents show legit automation (deploy runner, mesh peers, registry
# pulls) tripping this probe. Probing/XSS/SQLi/CVE scenarios stay.
- name: DISABLE_SCENARIOS
value: crowdsecurity/http-generic-bf
metrics:
enabled: true
serviceMonitor:
additionalLabels:
release: prometheus-stack
enabled: true
# Static machine identity: agent pods mount pre-created LAPI credentials
# (Secret crowdsec-agent-credentials, key local_api_credentials.yaml)
# at the exact path the agent entrypoint expects. Together with the
# patched register-init (enforced by janitor-cronjob.yaml) the agent
# never calls `cscli lapi register` in steady state, so pod names,
# restarts and reboots can no longer break it.
extraVolumes:
- name: static-creds
secret:
secretName: crowdsec-agent-credentials
items:
- key: local_api_credentials.yaml
path: local_api_credentials.yaml
extraVolumeMounts:
- name: static-creds
mountPath: /tmp_config/local_api_credentials.yaml
subPath: local_api_credentials.yaml
readOnly: true
resources:
limits:
cpu: 200m
memory: 500Mi
requests:
cpu: 50m
memory: 100Mi
config:
parsers:
s02-enrich:
mobile-whitelist.yaml: |
name: forust/mobile-whitelist
description: "Whitelist SWAN/4ka mobile network"
whitelist:
reason: "Mobile IP whitelist"
cidr:
- "84.245.64.0/18"
# CrowdSec's own guidance: CIDR allowlisting belongs at the parser stage.
# A parser whitelist discards the event before it reaches a bucket, so
# these addresses never produce an overflow and never become a decision.
# A postoverflow whitelist is checked only *after* the ban exists, and
# the bouncer answers 403 for as long as it does - which is a window we
# do not want the deploy sitting in.
local-network.yaml: |
name: forust/local-network
description: "Whitelist loopback, private and VPN networks"
whitelist:
reason: "Local network"
cidr:
- "127.0.0.0/8"
- "10.0.0.0/8"
- "172.16.0.0/12"
- "192.168.0.0/16"
# CGNAT range (RFC 6598). The workstation and the k0s node live
# here on WireGuard, and 100.64.0.0/10 is not covered by the
# RFC 1918 blocks above.
- "100.64.0.0/10"
- "169.254.0.0/16"
- "fc00::/7"
- "fe80::/10"
vps-whitelist.yaml: |
name: forust/vps-whitelist
description: "Whitelist static VPS"
whitelist:
reason: "VPS"
ip:
- "193.181.211.79"
postoverflows:
s01-whitelist:
# The one whitelist that has to stay here: resolving a hostname is a
# network call, and the docs put expensive lookups in postoverflows on
# purpose - it runs only when a bucket actually overflows.
# ddns.forust.xyz is the public home address, not a private one, so
# forust/local-network does not cover it.
home-dynamic-ip.yaml: |
name: forust/home-dynamic-ip
description: "Whitelist home dynamic IP"
whitelist:
reason: "Home dynamic IP"
expression:
- evt.Overflow.Alert.Source.IP in LookupHost("ddns.forust.xyz")
# LAPI-only main config override, merged over config.yaml. NOTE: the
# chart's own default for this key is REPLACED, not merged, so its
# auto_registration block is repeated verbatim below - drop it and the
# agent can no longer register itself.
config.yaml.local: |
api:
server:
auto_registration: # Activate if not using TLS for authentication
enabled: true
token: "${REGISTRATION_TOKEN}" # /!\ Do not modify this variable (auto-generated and handled by the chart)
allowed_ranges: # /!\ Make sure to adapt to the pod IP ranges used by your cluster
- "127.0.0.1/32"
- "192.168.0.0/16"
- "10.0.0.0/8"
- "172.16.0.0/12"
# This homelab has no egress to console.crowdsec.cloud: DNS does
# not resolve. The LAPI kept trying anyway ("Signal push: N
# signals to push", "capi metrics: sending" every 10s) and each
# attempt sat on a resolver timeout WHILE HOLDING A WRITE
# TRANSACTION, which is what kept stalling per-request decision
# lookups even with WAL enabled. Nothing to share and nothing to
# pull - turn the Central API off instead of letting it block the
# only database writer we have.
online_client:
sharing: false
pull:
community: false
blocklists: false
disable_usage_metrics_export: true
db_config:
# SQLite without WAL serialises every reader behind the writer's
# rollback journal, and the LAPI writes constantly: the agent pushes
# Traefik alerts read from Loki, the metrics collector counts
# decisions, the bouncer touches "last pull" on every request.
# Symptom: decision lookups taking 10-30s (and a second connection
# that could not even open the database) while the LAPI sat at 28m
# CPU - the process was blocked in fsync, not computing. Every
# bouncer-protected request then blew through the plugin timeout and
# fail-closed with 403, on every site at once.
# The PVC is local-path-retain (hostPath), not a network share, so
# WAL is safe here; the crowdsec docs recommend it for exactly this
# ("allowing more concurrency in SQLite that will improve
# performances in most scenarios").
use_wal: true
# Keeps the alert table bounded. At the 5000/7d default the file
# reached 54MB in 15 days off the Traefik access log alone, and the
# metrics collector counts decisions on a timer; a smaller working
# set means fewer full scans. Crowdsec only prunes - SQLite never
# shrinks the file, so the size stays until a manual VACUUM.
flush:
max_items: 1000
max_age: 24h
lapi:
env:
- name: COLLECTIONS
value: crowdsecurity/traefik crowdsecurity/base-http-scenarios
- name: DISABLE_COLLECTIONS
value: crowdsecurity/linux crowdsecurity/sshd
metrics:
enabled: true
serviceMonitor:
additionalLabels:
release: prometheus-stack
enabled: true
persistentVolume:
config:
enabled: true
size: 100Mi
storageClassName: local-path-retain
data:
enabled: true
size: 1Gi
storageClassName: local-path-retain
# LAPI answers a blocking /v1/decisions lookup for EVERY bouncer-protected
# request (whole Traefik front door), so it is the hot path of the proxy.
# At 400m/500Mi it went CPU-throttled and idle lookups measured 1.3-7.4s,
# which pushed requests into the bouncer's fail-closed 403.
# Single replica on purpose: LAPI is stateful (BoltDB on the `data` PVC,
# credentials on the `config` PVC) - two replicas sharing those RWO
# volumes would corrupt the decision store. Scale up CPU, not replicas.
resources:
limits:
cpu: 1500m
memory: 1Gi
requests:
cpu: 250m
memory: 500Mi
service:
type: ClusterIP
storeLAPICscliCredentialsInSecret: true
-32
View File
@@ -1,32 +0,0 @@
apiVersion: v1
data:
crowdsec-overview.json: "{\n \"__inputs\": [\n {\n \"name\": \"DS_PROMETHEUS\",\n \"label\": \"Prometheus\",\n \"description\": \"\",\n \"type\": \"datasource\",\n \"pluginId\": \"prometheus\",\n \"pluginName\": \"Prometheus\"\n }\n ],\n \"__requires\": [\n {\n \"type\": \"grafana\",\n \"id\": \"grafana\",\n \"name\": \"Grafana\",\n \"version\": \"8.1.2\"\n },\n {\n \"type\": \"panel\",\n \"id\": \"graph\",\n \"name\": \"Graph (old)\",\n \"version\": \"\"\n },\n {\n \"type\": \"datasource\",\n \"id\": \"prometheus\",\n \"name\": \"Prometheus\",\n \"version\": \"1.0.0\"\n },\n {\n \"type\": \"panel\",\n \"id\": \"stat\",\n \"name\": \"Stat\",\n \"version\": \"\"\n },\n {\n \"type\": \"panel\",\n \"id\": \"timeseries\",\n \"name\": \"Time series\",\n \"version\": \"\"\n }\n ],\n \"annotations\": {\n \"list\": [\n {\n \"builtIn\": 1,\n \"datasource\": \"-- Grafana --\",\n \"enable\": true,\n \"hide\": true,\n \"iconColor\": \"rgba(0, 211, 255, 1)\",\n \"name\": \"Annotations & Alerts\",\n \"target\": {\n \"limit\": 100,\n \"matchAny\": false,\n \"tags\": [],\n \"type\": \"dashboard\"\n },\n \"type\": \"dashboard\"\n }\n ]\n },\n \"editable\": true,\n \"gnetId\": null,\n \"graphTooltip\": 0,\n \"id\": null,\n \"links\": [],\n \"panels\": [\n {\n \"collapsed\": false,\n \"datasource\": null,\n \"gridPos\": {\n \"h\": 1,\n \"w\": 24,\n \"x\": 0,\n \"y\": 0\n },\n \"id\": 24,\n \"panels\": [],\n \"title\": \"Summary\",\n \"type\": \"row\"\n },\n {\n \"cacheTimeout\": null,\n \"datasource\": \"${DS_PROMETHEUS}\",\n \"fieldConfig\": {\n \"defaults\": {\n \"color\": {\n \"mode\": \"thresholds\"\n },\n \"mappings\": [\n {\n \"options\": {\n \"match\": \"null\",\n \"result\": {\n \"text\": \"N/A\"\n }\n },\n \"type\": \"special\"\n }\n ],\n \"thresholds\": {\n \"mode\": \"absolute\",\n \"steps\": [\n {\n \"color\": \"#E02F44\",\n \"value\": null\n },\n {\n \"color\": \"#E02F44\",\n \"value\": 10\n },\n {\n \"color\": \"#299c46\",\n \"value\": 10\n }\n ]\n },\n \"unit\": \"none\"\n },\n \"overrides\": []\n },\n \"gridPos\": {\n \"h\": 8,\n \"w\": 6,\n \"x\": 0,\n \"y\": 1\n },\n \"id\": 2,\n \"interval\": null,\n \"links\": [],\n \"maxDataPoints\": 100,\n \"options\": {\n \"colorMode\": \"background\",\n \"graphMode\": \"none\",\n \"justifyMode\": \"auto\",\n \"orientation\": \"horizontal\",\n \"reduceOptions\": {\n \"calcs\": [\n \"lastNotNull\"\n ],\n \"fields\": \"\",\n \"values\": false\n },\n \"text\": {},\n \"textMode\": \"auto\"\n },\n \"pluginVersion\": \"8.1.2\",\n \"targets\": [\n {\n \"exemplar\": true,\n \"expr\": \"count(cs_info)\",\n \"interval\": \"\",\n \"legendFormat\": \"\",\n \"refId\": \"A\"\n }\n ],\n \"timeFrom\": null,\n \"timeShift\": null,\n \"title\": \"Running Crowdsec\",\n \"transparent\": true,\n \"type\": \"stat\"\n },\n {\n \"aliasColors\": {},\n \"bars\": false,\n \"dashLength\": 10,\n \"dashes\": false,\n \"datasource\": \"${DS_PROMETHEUS}\",\n \"decimals\": 1,\n \"fieldConfig\": {\n \"defaults\": {\n \"links\": []\n },\n \"overrides\": []\n },\n \"fill\": 1,\n \"fillGradient\": 0,\n \"gridPos\": {\n \"h\": 8,\n \"w\": 18,\n \"x\": 6,\n \"y\": 1\n },\n \"hiddenSeries\": false,\n \"id\": 8,\n \"legend\": {\n \"alignAsTable\": true,\n \"avg\": false,\n \"current\": false,\n \"max\": false,\n \"min\": false,\n \"rightSide\": true,\n \"show\": true,\n \"sort\": \"total\",\n \"sortDesc\": true,\n \"total\": true,\n \"values\": true\n },\n \"lines\": true,\n \"linewidth\": 1,\n \"nullPointMode\": \"null\",\n \"options\": {\n \"alertThreshold\": true\n },\n \"percentage\": false,\n \"pluginVersion\": \"8.1.2\",\n \"pointradius\": 2,\n \"points\": false,\n \"renLine truncated
kind: ConfigMap
metadata:
labels:
app.kubernetes.io/managed-by: manual
grafana_dashboard: "1"
name: crowdsec-crowdsec-overview
namespace: prometheus
---
apiVersion: v1
data:
crowdsec-lapi-metrics.json: "{\n \"__inputs\": [\n {\n \"name\": \"DS_PROMETHEUS\",\n \"label\": \"Prometheus\",\n \"description\": \"\",\n \"type\": \"datasource\",\n \"pluginId\": \"prometheus\",\n \"pluginName\": \"Prometheus\"\n }\n ],\n \"__requires\": [\n {\n \"type\": \"panel\",\n \"id\": \"bargauge\",\n \"name\": \"Bar gauge\",\n \"version\": \"\"\n },\n {\n \"type\": \"grafana\",\n \"id\": \"grafana\",\n \"name\": \"Grafana\",\n \"version\": \"8.1.2\"\n },\n {\n \"type\": \"datasource\",\n \"id\": \"prometheus\",\n \"name\": \"Prometheus\",\n \"version\": \"1.0.0\"\n }\n ],\n \"annotations\": {\n \"list\": [\n {\n \"builtIn\": 1,\n \"datasource\": \"-- Grafana --\",\n \"enable\": true,\n \"hide\": true,\n \"iconColor\": \"rgba(0, 211, 255, 1)\",\n \"name\": \"Annotations & Alerts\",\n \"target\": {\n \"limit\": 100,\n \"matchAny\": false,\n \"tags\": [],\n \"type\": \"dashboard\"\n },\n \"type\": \"dashboard\"\n }\n ]\n },\n \"editable\": true,\n \"gnetId\": null,\n \"graphTooltip\": 0,\n \"id\": null,\n \"iteration\": 1655915193937,\n \"links\": [],\n \"panels\": [\n {\n \"collapsed\": false,\n \"datasource\": null,\n \"gridPos\": {\n \"h\": 1,\n \"w\": 24,\n \"x\": 0,\n \"y\": 0\n },\n \"id\": 10,\n \"panels\": [],\n \"title\": \"Agents\",\n \"type\": \"row\"\n },\n {\n \"datasource\": \"${DS_PROMETHEUS}\",\n \"fieldConfig\": {\n \"defaults\": {\n \"color\": {\n \"mode\": \"thresholds\"\n },\n \"mappings\": [],\n \"thresholds\": {\n \"mode\": \"absolute\",\n \"steps\": [\n {\n \"color\": \"green\",\n \"value\": null\n },\n {\n \"color\": \"red\",\n \"value\": 80\n }\n ]\n }\n },\n \"overrides\": []\n },\n \"gridPos\": {\n \"h\": 8,\n \"w\": 12,\n \"x\": 0,\n \"y\": 1\n },\n \"id\": 2,\n \"options\": {\n \"displayMode\": \"gradient\",\n \"orientation\": \"vertical\",\n \"reduceOptions\": {\n \"calcs\": [\n \"lastNotNull\"\n ],\n \"fields\": \"\",\n \"values\": false\n },\n \"showUnfilled\": false,\n \"text\": {}\n },\n \"pluginVersion\": \"8.1.2\",\n \"repeat\": \"query0\",\n \"repeatDirection\": \"h\",\n \"targets\": [\n {\n \"exemplar\": false,\n \"expr\": \"sum(rate(cs_lapi_request_duration_seconds_bucket{endpoint=\\\"/v1/watchers/login\\\", instance=\\\"$lapi\\\"}[$__rate_interval])) by (le)\",\n \"format\": \"heatmap\",\n \"interval\": \"\",\n \"legendFormat\": \"{{le}}\",\n \"refId\": \"A\"\n }\n ],\n \"title\": \"Agents Login\",\n \"type\": \"heatmap\"\n },\n {\n \"datasource\": \"${DS_PROMETHEUS}\",\n \"fieldConfig\": {\n \"defaults\": {\n \"color\": {\n \"mode\": \"thresholds\"\n },\n \"mappings\": [],\n \"thresholds\": {\n \"mode\": \"absolute\",\n \"steps\": [\n {\n \"color\": \"green\",\n \"value\": null\n }\n ]\n },\n \"unit\": \"none\"\n },\n \"overrides\": []\n },\n \"gridPos\": {\n \"h\": 8,\n \"w\": 12,\n \"x\": 12,\n \"y\": 1\n },\n \"id\": 6,\n \"options\": {\n \"displayMode\": \"gradient\",\n \"orientation\": \"auto\",\n \"reduceOptions\": {\n \"calcs\": [\n \"lastNotNull\"\n ],\n \"fields\": \"\",\n \"values\": false\n },\n \"showUnfilled\": false,\n \"text\": {}\n },\n \"pluginVersion\": \"8.1.2\",\n \"targets\": [\n {\n \"exemplar\": true,\n \"expr\": \"sum(rate(cs_lapi_request_duration_seconds_bucket{endpoint=\\\"/v1/watchers/login\\\"}[$__rate_interval])) by (le)\",\n \"format\": \"heatmap\",\n \"interval\": \"\",\n \"legendFormat\": \"{{le}}\",\n \"refId\": \"A\"\n }\n ],\n \"title\": \"Heartbeat\",\n \"type\": \"heatmap\"\n },\n {\n \"collapsed\": false,\n \"datasource\": null,\n \"gridPos\": {\n \"h\": 1,\n \"w\": 24,\n \"x\": 0,\n \"y\": 9\n },\n \"id\": 12,\n \"panels\": [],\n \"title\": \"Decisions\",\n \"type\": \"row\"\n },\n {\n \"datasource\": \"${DS_PROMETHEUS}\",\n Line truncated
kind: ConfigMap
metadata:
labels:
app.kubernetes.io/managed-by: manual
grafana_dashboard: "1"
name: crowdsec-crowdsec-lapi-metrics
namespace: prometheus
---
apiVersion: v1
data:
crowdsec-insight.json: "{\n \"__inputs\": [\n {\n \"name\": \"DS_PROMETHEUS\",\n \"label\": \"Prometheus\",\n \"description\": \"\",\n \"type\": \"datasource\",\n \"pluginId\": \"prometheus\",\n \"pluginName\": \"Prometheus\"\n }\n ],\n \"__requires\": [\n {\n \"type\": \"panel\",\n \"id\": \"bargauge\",\n \"name\": \"Bar gauge\",\n \"version\": \"\"\n },\n {\n \"type\": \"panel\",\n \"id\": \"gauge\",\n \"name\": \"Gauge\",\n \"version\": \"\"\n },\n {\n \"type\": \"grafana\",\n \"id\": \"grafana\",\n \"name\": \"Grafana\",\n \"version\": \"8.1.2\"\n },\n {\n \"type\": \"datasource\",\n \"id\": \"prometheus\",\n \"name\": \"Prometheus\",\n \"version\": \"1.0.0\"\n },\n {\n \"type\": \"panel\",\n \"id\": \"stat\",\n \"name\": \"Stat\",\n \"version\": \"\"\n }\n ],\n \"annotations\": {\n \"list\": [\n {\n \"builtIn\": 1,\n \"datasource\": \"-- Grafana --\",\n \"enable\": true,\n \"hide\": true,\n \"iconColor\": \"rgba(0, 211, 255, 1)\",\n \"name\": \"Annotations & Alerts\",\n \"target\": {\n \"limit\": 100,\n \"matchAny\": false,\n \"tags\": [],\n \"type\": \"dashboard\"\n },\n \"type\": \"dashboard\"\n }\n ]\n },\n \"editable\": true,\n \"gnetId\": null,\n \"graphTooltip\": 0,\n \"id\": null,\n \"iteration\": 1655915159751,\n \"links\": [],\n \"panels\": [\n {\n \"collapsed\": true,\n \"datasource\": null,\n \"gridPos\": {\n \"h\": 1,\n \"w\": 24,\n \"x\": 0,\n \"y\": 0\n },\n \"id\": 22,\n \"panels\": [\n {\n \"cacheTimeout\": null,\n \"datasource\": \"${DS_PROMETHEUS}\",\n \"fieldConfig\": {\n \"defaults\": {\n \"color\": {\n \"mode\": \"thresholds\"\n },\n \"mappings\": [\n {\n \"options\": {\n \"match\": \"null\",\n \"result\": {\n \"text\": \"N/A\"\n }\n },\n \"type\": \"special\"\n }\n ],\n \"thresholds\": {\n \"mode\": \"absolute\",\n \"steps\": [\n {\n \"color\": \"green\",\n \"value\": null\n },\n {\n \"color\": \"red\",\n \"value\": 80\n }\n ]\n },\n \"unit\": \"dateTimeAsIso\"\n },\n \"overrides\": []\n },\n \"gridPos\": {\n \"h\": 9,\n \"w\": 5,\n \"x\": 2,\n \"y\": 1\n },\n \"id\": 2,\n \"interval\": null,\n \"links\": [],\n \"maxDataPoints\": 100,\n \"options\": {\n \"colorMode\": \"none\",\n \"graphMode\": \"none\",\n \"justifyMode\": \"auto\",\n \"orientation\": \"horizontal\",\n \"reduceOptions\": {\n \"calcs\": [\n \"lastNotNull\"\n ],\n \"fields\": \"\",\n \"values\": false\n },\n \"text\": {},\n \"textMode\": \"auto\"\n },\n \"pluginVersion\": \"8.1.2\",\n \"targets\": [\n {\n \"exemplar\": true,\n \"expr\": \"(process_start_time_seconds{instance=\\\"$instance\\\"})*1000\",\n \"interval\": \"\",\n \"legendFormat\": \"{{instance}}\",\n \"refId\": \"A\"\n }\n ],\n \"timeFrom\": null,\n \"timeShift\": null,\n \"title\": \"Up since\",\n \"type\": \"stat\"\n },\n {\n \"datasource\": \"${DS_PROMETHEUS}\",\n \"fieldConfig\": {\n \"defaults\": {\n \"displayName\": \"\",\n \"mappings\": [],\n \"thresholds\": {\n \"mode\": \"absolute\",\n \"steps\": [\n {\n \"color\": \"green\",\n \"value\": null\n }\n ]\n },\n \"unit\": \"decbytes\"\n },\n \"overrides\": []\n },\n \"gridPos\": {\n \"h\": 9,\n \"w\": 5,\n \"x\": 7,\n \"y\": 1\n },\n \"id\": 4,\n \"options\": {\n \"orientation\": \"auto\",\n \"reduceOptions\": {\n \"calcs\": [\n \"mean\"\n ],\n \"fields\": \"\",\n \"values\": false\n },\Line truncated
kind: ConfigMap
metadata:
labels:
app.kubernetes.io/managed-by: manual
grafana_dashboard: "1"
name: crowdsec-crowdsec-insight
namespace: prometheus
-202
View File
@@ -1,202 +0,0 @@
# CrowdSec self-healing: static machine identity + enforcement loops.
#
# Problem it fixes: the chart's agent init container runs
# `cscli lapi register --machine "$POD_NAME" ...`
# unconditionally. Credentials live in an emptyDir, the machine row lives
# in LAPI's persistent DB. Any init re-run for an already-known pod name
# (kubelet restart, node reboot) dies with
# 403 Forbidden: user '<pod>' already exist
# and the DaemonSet pod sticks in Init forever. Every DS restart also
# leaves an orphan machine row that is never cleaned.
#
# Design (name-independent):
# * Agent identity is a STATIC machine `crowdsec-agent-workstation`
# whose password lives in Secret `crowdsec-agent-credentials`
# (created once, manually - like all other secrets in this repo).
# The secret is mounted into agent pods at
# /tmp_config/local_api_credentials.yaml (see extraVolumeMounts in
# crowdsec-values.yaml), which is exactly the path the agent's main
# container copies into place at startup.
# * The DS init command is patched (strategic merge, by container name)
# to SKIP registration when that file exists, keeping the legacy
# register path only as fallback. Detection marker in the patched
# command: `[ -s /tmp_config`.
# * This CronJob enforces the desired state hourly, so recovery is
# automatic even after `helm upgrade` reverts the DS patch or the
# LAPI database is wiped:
# 1. patch DS init if it still has the unconditional register
# (no-op otherwise - no restart churn);
# 2. prune machines with no heartbeat for 2h (orphan hygiene);
# 3. ensure the static machine exists, recreating it with the
# Secret password if missing (agent retry loops reconnect
# on their own - same name + same password);
# 4. prune bouncer entries idle for 30d.
#
# It used to also delete LePresidente/http-generic-403-bf decisions hourly.
# That was a workaround for the bouncer failing closed on a slow LAPI and
# 403-ing the deploy runner into a 4h ban. The bouncer now polls decisions
# into a cache and never blocks on an unreachable LAPI, so it cannot
# manufacture those 403s any more, and the scenario only fires against real
# scanners - deleting their decisions hourly was undoing a working ban.
#
# Manual apply (crowdsec/k8s is NOT managed by deploy.yaml):
# kubectl apply -f crowdsec/k8s/janitor-cronjob.yaml
# Force a run:
# kubectl create job -n crowdsec --from=cronjob/crowdsec-janitor janitor-now
#
# Helm upgrades: the janitor's strategic patch puts the DS field under
# the `kubectl-patch` field manager, so a plain `helm upgrade` FAILS
# with an SSA conflict on initContainers[].command. Procedure:
# 1. revert init to chart state (kills the conflict):
# helm template crowdsec crowdsec/crowdsec --version <ver> \
# -n crowdsec -f crowdsec/k8s/crowdsec-values.yaml > /tmp/r.yaml
# python3 -c "import yaml,json; ..." # build revert patch from
# the rendered DaemonSet init command, then
# kubectl patch ds crowdsec-agent -n crowdsec \
# --type strategic -p "\$(cat /tmp/revert_patch.json)"
# 2. helm upgrade --install crowdsec ... (no --force needed)
# 3. janitor-now right away (upgrade reverts init; new pods would
# sit in Init until the next hourly run otherwise).
#
# One-time bootstrap (order matters):
# 1. Create Secret + static machine (see commands in chat).
# 2. Apply this file, trigger janitor-now, wait for agent 1/1.
# 3. One-time orphan cleanup:
# kubectl exec -n crowdsec deploy/crowdsec-lapi -- \
# cscli machines prune --duration 1h --force
# 4. Only then `helm upgrade` crowdsec with the extraVolumes values.
# Upgrade reverts the DS patch; trigger janitor-now right after it
# (otherwise new pods sit in Init until the next hourly run, then
# self-heal anyway).
#
# Password rotation: update the Secret, delete the machine
# (`cscli machines delete crowdsec-agent-workstation`), trigger
# janitor-now (recreates it), then `kubectl rollout restart
# ds/crowdsec-agent -n crowdsec` (agent reads the file at startup only).
apiVersion: v1
kind: ServiceAccount
metadata:
name: crowdsec-janitor
namespace: crowdsec
labels:
app.kubernetes.io/part-of: crowdsec
---
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
name: crowdsec-janitor
namespace: crowdsec
labels:
app.kubernetes.io/part-of: crowdsec
rules:
- apiGroups: [""]
resources: ["pods"]
verbs: ["get", "list"]
- apiGroups: [""]
resources: ["pods/exec"]
verbs: ["create"]
- apiGroups: ["apps"]
resources: ["daemonsets"]
verbs: ["get", "patch"]
# `kubectl exec deploy/<name>` resolves deploy -> replicaset -> pod,
# which needs read access to these (exec itself is pods/exec above).
- apiGroups: ["apps"]
resources: ["deployments", "replicasets"]
verbs: ["get", "list"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: crowdsec-janitor
namespace: crowdsec
labels:
app.kubernetes.io/part-of: crowdsec
subjects:
- kind: ServiceAccount
name: crowdsec-janitor
namespace: crowdsec
roleRef:
kind: Role
name: crowdsec-janitor
apiGroup: rbac.authorization.k8s.io
---
apiVersion: batch/v1
kind: CronJob
metadata:
name: crowdsec-janitor
namespace: crowdsec
labels:
app.kubernetes.io/part-of: crowdsec
spec:
schedule: "17 * * * *"
concurrencyPolicy: Forbid
successfulJobsHistoryLimit: 3
failedJobsHistoryLimit: 3
jobTemplate:
spec:
activeDeadlineSeconds: 300
template:
metadata:
labels:
app.kubernetes.io/part-of: crowdsec
spec:
serviceAccountName: crowdsec-janitor
restartPolicy: OnFailure
containers:
- name: janitor
# Same image the chart itself uses for registration jobs;
# IfNotPresent so it works while the node is offline
# (layer cached from the chart install).
image: alpine/kubectl:latest
imagePullPolicy: IfNotPresent
env:
- name: AGENT_PASSWORD
valueFrom:
secretKeyRef:
name: crowdsec-agent-credentials
key: password
command:
- /bin/sh
- -c
- |
set -eu
LAPI_EXEC="kubectl exec -n crowdsec deploy/crowdsec-lapi --"
echo "== 1. enforce patched agent init =="
CUR=$(kubectl get ds crowdsec-agent -n crowdsec \
-o jsonpath='{.spec.template.spec.initContainers[0].command[2]}')
case "$CUR" in
*'-s /tmp_config'*)
echo "init already patched"
;;
*)
echo "patching init"
WAIT='until nc "$LAPI_HOST" "$LAPI_PORT" -z'
WAIT="$WAIT; do echo waiting for lapi to start; sleep 5; done"
LINK='ln -s /staging/etc/crowdsec /etc/crowdsec'
REG='cscli lapi register --machine "$USERNAME"'
REG="$REG -u \"\$LAPI_URL\" --token \"\$REGISTRATION_TOKEN\""
CREDS=/tmp_config/local_api_credentials.yaml
CMD="$WAIT; $LINK; [ -s $CREDS ] || {"
CMD="$CMD $REG && cp"
CMD="$CMD /etc/crowdsec/local_api_credentials.yaml $CREDS; }"
ESC=$(printf '%s' "$CMD" | sed 's/"/\\"/g')
PATCH='{"spec":{"template":{"spec":{"initContainers":'
PATCH=$PATCH'[{"name":"wait-for-lapi-and-register",'
PATCH=$PATCH'"command":["sh","-c","'$ESC'"]}]}}}}'
kubectl patch ds crowdsec-agent -n crowdsec \
--type strategic -p "$PATCH"
;;
esac
echo "== 2. prune orphan machines (no heartbeat for 2h) =="
$LAPI_EXEC cscli machines prune --duration 2h --force
echo "== 3. ensure static machine exists =="
if $LAPI_EXEC cscli machines inspect \
crowdsec-agent-workstation >/dev/null 2>&1; then
echo "static machine present"
else
echo "recreating static machine"
$LAPI_EXEC cscli machines add crowdsec-agent-workstation \
--password "$AGENT_PASSWORD" --force
fi
echo "== 4. prune stale bouncers (no pull for 30d) =="
$LAPI_EXEC cscli bouncers prune -d 720h --force
-6
View File
@@ -1,6 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: crowdsec
labels:
app.kubernetes.io/part-of: crowdsec
-34
View File
@@ -1,34 +0,0 @@
apiVersion: networking.k8s.io/v1
kind: NetworkPolicy
metadata:
name: crowdsec-lapi
namespace: crowdsec
spec:
podSelector:
matchLabels:
k8s-app: crowdsec
type: lapi
policyTypes:
- Ingress
ingress:
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: traefik
podSelector:
matchLabels:
app.kubernetes.io/name: traefik
- podSelector:
matchLabels:
k8s-app: crowdsec
type: agent
ports:
- protocol: TCP
port: 8080
- from:
- namespaceSelector:
matchLabels:
kubernetes.io/metadata.name: prometheus
ports:
- protocol: TCP
port: 6060
+45 -41
View File
@@ -1,46 +1,50 @@
services: services:
dockmon: dockmon:
image: darthnorse/dockmon:2.5.0 image: darthnorse/dockmon:latest
container_name: dockmon container_name: dockmon
restart: unless-stopped restart: unless-stopped
# ports: # ports:
# - 8000:443 # - 8000:443
volumes: volumes:
- data:/app/data - data:/app/data
- /var/run/docker.sock:/var/run/docker.sock - /var/run/docker.sock:/var/run/docker.sock
healthcheck: healthcheck:
test: ["CMD", "curl", "-k", "-f", "https://localhost:443/health"] test: [ "CMD", "curl", "-k", "-f", "https://localhost:443/health" ]
interval: 30s interval: 30s
timeout: 10s timeout: 10s
retries: 3 retries: 3
labels: labels:
- "traefik.enable=true" - "traefik.enable=true"
- "traefik.http.services.dockmon.loadbalancer.server.port=443" - "traefik.docker.network=proxy"
- "traefik.http.services.dockmon.loadbalancer.server.scheme=https" - "traefik.http.services.dockmon.loadbalancer.server.port=443"
- "traefik.http.services.dockmon.loadbalancer.serverstransport=insecureTransport@file" - "traefik.http.services.dockmon.loadbalancer.server.scheme=https"
- "traefik.http.services.dockmon.loadbalancer.serverstransport=insecureTransport@file"
# Prod Router # Prod Router
- "traefik.http.routers.dockmon.rule=Host(`dockmon.forust.xyz`)" - "traefik.http.routers.dockmon.rule=Host(`dockmon.forust.xyz`)"
- "traefik.http.routers.dockmon.entrypoints=websecure" - "traefik.http.routers.dockmon.entrypoints=websecure"
- "traefik.http.routers.dockmon.middlewares=security-headers@file" - "traefik.http.routers.dockmon.middlewares=security-chain@file"
- "traefik.http.routers.dockmon.tls.certresolver=letsencrypt" - "traefik.http.routers.dockmon.service=dockmon"
# Local Router - "traefik.http.routers.dockmon.tls=true"
- "traefik.http.routers.dockmon-local.rule=Host(`dockmon.workstation.internal`)" # Local Router
- "traefik.http.routers.dockmon-local.entrypoints=websecure" - "traefik.http.routers.dockmon-local.rule=Host(`dockmon.workstation.internal`)"
- "traefik.http.routers.dockmon-local.tls=true" - "traefik.http.routers.dockmon-local.entrypoints=websecure"
# Dev Router - "traefik.http.routers.dockmon-local.middlewares=security-headers@file"
- "traefik.http.routers.dockmon-dev.rule=Host(`dockmon.gigaforust.internal`)" - "traefik.http.routers.dockmon-local.tls=true"
- "traefik.http.routers.dockmon-dev.entrypoints=websecure" # Dev Router
- "traefik.http.routers.dockmon-dev.tls=true" - "traefik.http.routers.dockmon-dev.rule=Host(`dockmon.gigaforust.internal`)"
- "traefik.http.routers.dockmon-dev.entrypoints=websecure"
- "traefik.http.routers.dockmon-dev.middlewares=security-chain@file"
- "traefik.http.routers.dockmon-dev.tls=true"
# Glance Metadata # Glance Metadata
- glance.name=dockmon - glance.name=dockmon
- glance.url=https://dockmon.forust.xyz/ - glance.url=https://dockmon.forust.xyz/
- glance.description=Dockmon is a lightweight Docker container monitoring and management tool with a user-friendly web interface. - glance.description=Dockmon is a lightweight Docker container monitoring and management tool with a user-friendly web interface.
networks: networks:
- proxy - proxy
volumes: volumes:
data: data:
networks: networks:
proxy: proxy:
external: true external: true
-28
View File
@@ -1,28 +0,0 @@
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: dockmon-prod-tls
namespace: dockmon
spec:
secretName: dockmon-prod-tls
dnsNames:
- dockmon.forust.xyz
issuerRef:
name: letsencrypt-prod
kind: ClusterIssuer
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: internal-wildcard-tls
namespace: dockmon
spec:
secretName: internal-wildcard-tls
dnsNames:
- "*.workstation.internal"
- "*.gigaforust.internal"
- workstation.internal
- gigaforust.internal
issuerRef:
name: internal-ca
kind: ClusterIssuer
-68
View File
@@ -1,68 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: dockmon-service
namespace: dockmon
spec:
clusterIP: None
selector:
app: dockmon
ports:
- port: 443
targetPort: 443
---
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: dockmon-statefulset
namespace: dockmon
spec:
serviceName: dockmon-service
replicas: 1
selector:
matchLabels:
app: dockmon
template:
metadata:
labels:
app: dockmon
spec:
containers:
- name: dockmon
image: darthnorse/dockmon:2.5.0
ports:
- containerPort: 443
volumeMounts:
- name: data
mountPath: /app/data
- name: docker-sock
mountPath: /var/run/docker.sock
livenessProbe:
httpGet:
path: /health
port: 443
scheme: HTTPS
initialDelaySeconds: 30
periodSeconds: 30
timeoutSeconds: 10
failureThreshold: 3
resources:
requests:
memory: "512Mi"
cpu: "200m"
limits:
memory: "1.5Gi"
cpu: "700m "
volumes:
- name: docker-sock
hostPath:
path: /var/run/docker.sock
type: Socket
volumeClaimTemplates:
- metadata:
name: data
spec:
accessModes: ["ReadWriteOnce"]
resources:
requests:
storage: 1Gi
-45
View File
@@ -1,45 +0,0 @@
apiVersion: traefik.io/v1alpha1
kind: ServersTransport
metadata:
name: dockmon-transport
namespace: dockmon
spec:
insecureSkipVerify: true
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: dockmon-prod
namespace: dockmon
spec:
entryPoints:
- websecure
routes:
- match: Host(`dockmon.forust.xyz`)
kind: Rule
middlewares:
- name: security-headers@file
services:
- name: dockmon-service
port: 443
serversTransport: dockmon-transport
tls:
secretName: dockmon-prod-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: dockmon-local
namespace: dockmon
spec:
entryPoints:
- websecure
routes:
- match: Host(`dockmon.workstation.internal`) || Host(`dockmon.gigaforust.internal`)
kind: Rule
services:
- name: dockmon-service
port: 443
serversTransport: dockmon-transport
tls:
secretName: internal-wildcard-tls
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: dockmon
+17 -15
View File
@@ -1,29 +1,31 @@
services: services:
downtify: downtify:
container_name: downtify container_name: downtify
image: ghcr.io/henriquesebastiao/downtify:3.4.0 image: ghcr.io/henriquesebastiao/downtify:latest
restart: unless-stopped
# ports: # ports:
# - '7077:8000' # - '7077:8000'
volumes: volumes:
- ./Downtify_downloads:/downloads - ./Downtify_downloads:/downloads
labels: labels:
- "traefik.enable=true" - traefik.enable=true
- "traefik.http.services.downtify.loadbalancer.server.port=8000" - traefik.docker.network=proxy
- traefik.http.services.downtify.loadbalancer.server.port=8000
# Prod Router # Prod Router
- "traefik.http.routers.downtify.rule=Host(`downtify.forust.xyz`)" - traefik.http.routers.downtify.rule=Host(`downtify.forust.xyz`)
- "traefik.http.routers.downtify.entrypoints=websecure" - traefik.http.routers.downtify.entrypoints=websecure
- "traefik.http.routers.downtify.middlewares=security-chain@file" - traefik.http.routers.downtify.middlewares=security-chain@file
- "traefik.http.routers.downtify.tls.certresolver=letsencrypt" - traefik.http.routers.downtify.tls=true
# Local Router # Local Router
- "traefik.http.routers.downtify-local.rule=Host(`downtify.workstation.internal`)" - traefik.http.routers.downtify-local.rule=Host(`downtify.workstation.internal`) || Host(`downtify.internal`)
- "traefik.http.routers.downtify-local.entrypoints=websecure" - traefik.http.routers.downtify-local.entrypoints=websecure
- "traefik.http.routers.downtify-local.tls=true" - traefik.http.routers.downtify-local.middlewares=security-headers@file
- traefik.http.routers.downtify-local.tls=true
# Dev Router # Dev Router
- "traefik.http.routers.downtify-dev.rule=Host(`downtify.gigaforust.internal`)" - traefik.http.routers.downtify-dev.rule=Host(`downtify.gigaforust.internal`)
- "traefik.http.routers.downtify-dev.entrypoints=websecure" - traefik.http.routers.downtify-dev.entrypoints=websecure
- "traefik.http.routers.downtify-dev.tls=true" - traefik.http.routers.downtify-dev.middlewares=security-chain@file
- traefik.http.routers.downtify-dev.tls=true
networks: networks:
- proxy - proxy
networks: networks:
-60
View File
@@ -1,60 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: downtify-service
namespace: downtify
spec:
selector:
app: downtify
ports:
- port: 8000
targetPort: 8000
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: downtify-deployment
namespace: downtify
spec:
replicas: 1
selector:
matchLabels:
app: downtify
strategy:
type: Recreate
template:
metadata:
labels:
app: downtify
spec:
containers:
- name: downtify
image: ghcr.io/henriquesebastiao/downtify:3.4.0
ports:
- containerPort: 8000
volumeMounts:
- name: downloads
mountPath: /downloads
resources:
requests:
memory: "128Mi"
cpu: "200m"
limits:
memory: "1Gi"
cpu: "1"
volumes:
- name: downloads
persistentVolumeClaim:
claimName: downtify-downloads-pvc
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: downtify-downloads-pvc
namespace: downtify
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 10Gi
-35
View File
@@ -1,35 +0,0 @@
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: downtify-prod
namespace: downtify
spec:
entryPoints:
- websecure
routes:
- match: Host(`downtify.forust.xyz`)
kind: Rule
middlewares:
- name: security-chain@file
services:
- name: downtify-service
port: 8000
tls:
secretName: downtify-prod-tls
---
apiVersion: traefik.io/v1alpha1
kind: IngressRoute
metadata:
name: downtify-local
namespace: downtify
spec:
entryPoints:
- websecure
routes:
- match: Host(`downtify.workstation.internal`) || Host(`downtify.gigaforust.internal`)
kind: Rule
services:
- name: downtify-service
port: 8000
tls:
secretName: internal-wildcard-tls
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: downtify
+13
View File
@@ -0,0 +1,13 @@
FROM python:3.9-alpine
WORKDIR /app
# Установка зависимостей
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
# Копирование кода
COPY main.py .
COPY .env .
# Запуск бота
CMD ["python", "-u", "main.py"]
+373
View File
@@ -0,0 +1,373 @@
Mozilla Public License Version 2.0
==================================
1. Definitions
--------------
1.1. "Contributor"
means each individual or legal entity that creates, contributes to
the creation of, or owns Covered Software.
1.2. "Contributor Version"
means the combination of the Contributions of others (if any) used
by a Contributor and that particular Contributor's Contribution.
1.3. "Contribution"
means Covered Software of a particular Contributor.
1.4. "Covered Software"
means Source Code Form to which the initial Contributor has attached
the notice in Exhibit A, the Executable Form of such Source Code
Form, and Modifications of such Source Code Form, in each case
including portions thereof.
1.5. "Incompatible With Secondary Licenses"
means
(a) that the initial Contributor has attached the notice described
in Exhibit B to the Covered Software; or
(b) that the Covered Software was made available under the terms of
version 1.1 or earlier of the License, but not also under the
terms of a Secondary License.
1.6. "Executable Form"
means any form of the work other than Source Code Form.
1.7. "Larger Work"
means a work that combines Covered Software with other material, in
a separate file or files, that is not Covered Software.
1.8. "License"
means this document.
1.9. "Licensable"
means having the right to grant, to the maximum extent possible,
whether at the time of the initial grant or subsequently, any and
all of the rights conveyed by this License.
1.10. "Modifications"
means any of the following:
(a) any file in Source Code Form that results from an addition to,
deletion from, or modification of the contents of Covered
Software; or
(b) any new file in Source Code Form that contains any Covered
Software.
1.11. "Patent Claims" of a Contributor
means any patent claim(s), including without limitation, method,
process, and apparatus claims, in any patent Licensable by such
Contributor that would be infringed, but for the grant of the
License, by the making, using, selling, offering for sale, having
made, import, or transfer of either its Contributions or its
Contributor Version.
1.12. "Secondary License"
means either the GNU General Public License, Version 2.0, the GNU
Lesser General Public License, Version 2.1, the GNU Affero General
Public License, Version 3.0, or any later versions of those
licenses.
1.13. "Source Code Form"
means the form of the work preferred for making modifications.
1.14. "You" (or "Your")
means an individual or a legal entity exercising rights under this
License. For legal entities, "You" includes any entity that
controls, is controlled by, or is under common control with You. For
purposes of this definition, "control" means (a) the power, direct
or indirect, to cause the direction or management of such entity,
whether by contract or otherwise, or (b) ownership of more than
fifty percent (50%) of the outstanding shares or beneficial
ownership of such entity.
2. License Grants and Conditions
--------------------------------
2.1. Grants
Each Contributor hereby grants You a world-wide, royalty-free,
non-exclusive license:
(a) under intellectual property rights (other than patent or trademark)
Licensable by such Contributor to use, reproduce, make available,
modify, display, perform, distribute, and otherwise exploit its
Contributions, either on an unmodified basis, with Modifications, or
as part of a Larger Work; and
(b) under Patent Claims of such Contributor to make, use, sell, offer
for sale, have made, import, and otherwise transfer either its
Contributions or its Contributor Version.
2.2. Effective Date
The licenses granted in Section 2.1 with respect to any Contribution
become effective for each Contribution on the date the Contributor first
distributes such Contribution.
2.3. Limitations on Grant Scope
The licenses granted in this Section 2 are the only rights granted under
this License. No additional rights or licenses will be implied from the
distribution or licensing of Covered Software under this License.
Notwithstanding Section 2.1(b) above, no patent license is granted by a
Contributor:
(a) for any code that a Contributor has removed from Covered Software;
or
(b) for infringements caused by: (i) Your and any other third party's
modifications of Covered Software, or (ii) the combination of its
Contributions with other software (except as part of its Contributor
Version); or
(c) under Patent Claims infringed by Covered Software in the absence of
its Contributions.
This License does not grant any rights in the trademarks, service marks,
or logos of any Contributor (except as may be necessary to comply with
the notice requirements in Section 3.4).
2.4. Subsequent Licenses
No Contributor makes additional grants as a result of Your choice to
distribute the Covered Software under a subsequent version of this
License (see Section 10.2) or under the terms of a Secondary License (if
permitted under the terms of Section 3.3).
2.5. Representation
Each Contributor represents that the Contributor believes its
Contributions are its original creation(s) or it has sufficient rights
to grant the rights to its Contributions conveyed by this License.
2.6. Fair Use
This License is not intended to limit any rights You have under
applicable copyright doctrines of fair use, fair dealing, or other
equivalents.
2.7. Conditions
Sections 3.1, 3.2, 3.3, and 3.4 are conditions of the licenses granted
in Section 2.1.
3. Responsibilities
-------------------
3.1. Distribution of Source Form
All distribution of Covered Software in Source Code Form, including any
Modifications that You create or to which You contribute, must be under
the terms of this License. You must inform recipients that the Source
Code Form of the Covered Software is governed by the terms of this
License, and how they can obtain a copy of this License. You may not
attempt to alter or restrict the recipients' rights in the Source Code
Form.
3.2. Distribution of Executable Form
If You distribute Covered Software in Executable Form then:
(a) such Covered Software must also be made available in Source Code
Form, as described in Section 3.1, and You must inform recipients of
the Executable Form how they can obtain a copy of such Source Code
Form by reasonable means in a timely manner, at a charge no more
than the cost of distribution to the recipient; and
(b) You may distribute such Executable Form under the terms of this
License, or sublicense it under different terms, provided that the
license for the Executable Form does not attempt to limit or alter
the recipients' rights in the Source Code Form under this License.
3.3. Distribution of a Larger Work
You may create and distribute a Larger Work under terms of Your choice,
provided that You also comply with the requirements of this License for
the Covered Software. If the Larger Work is a combination of Covered
Software with a work governed by one or more Secondary Licenses, and the
Covered Software is not Incompatible With Secondary Licenses, this
License permits You to additionally distribute such Covered Software
under the terms of such Secondary License(s), so that the recipient of
the Larger Work may, at their option, further distribute the Covered
Software under the terms of either this License or such Secondary
License(s).
3.4. Notices
You may not remove or alter the substance of any license notices
(including copyright notices, patent notices, disclaimers of warranty,
or limitations of liability) contained within the Source Code Form of
the Covered Software, except that You may alter any license notices to
the extent required to remedy known factual inaccuracies.
3.5. Application of Additional Terms
You may choose to offer, and to charge a fee for, warranty, support,
indemnity or liability obligations to one or more recipients of Covered
Software. However, You may do so only on Your own behalf, and not on
behalf of any Contributor. You must make it absolutely clear that any
such warranty, support, indemnity, or liability obligation is offered by
You alone, and You hereby agree to indemnify every Contributor for any
liability incurred by such Contributor as a result of warranty, support,
indemnity or liability terms You offer. You may include additional
disclaimers of warranty and limitations of liability specific to any
jurisdiction.
4. Inability to Comply Due to Statute or Regulation
---------------------------------------------------
If it is impossible for You to comply with any of the terms of this
License with respect to some or all of the Covered Software due to
statute, judicial order, or regulation then You must: (a) comply with
the terms of this License to the maximum extent possible; and (b)
describe the limitations and the code they affect. Such description must
be placed in a text file included with all distributions of the Covered
Software under this License. Except to the extent prohibited by statute
or regulation, such description must be sufficiently detailed for a
recipient of ordinary skill to be able to understand it.
5. Termination
--------------
5.1. The rights granted under this License will terminate automatically
if You fail to comply with any of its terms. However, if You become
compliant, then the rights granted under this License from a particular
Contributor are reinstated (a) provisionally, unless and until such
Contributor explicitly and finally terminates Your grants, and (b) on an
ongoing basis, if such Contributor fails to notify You of the
non-compliance by some reasonable means prior to 60 days after You have
come back into compliance. Moreover, Your grants from a particular
Contributor are reinstated on an ongoing basis if such Contributor
notifies You of the non-compliance by some reasonable means, this is the
first time You have received notice of non-compliance with this License
from such Contributor, and You become compliant prior to 30 days after
Your receipt of the notice.
5.2. If You initiate litigation against any entity by asserting a patent
infringement claim (excluding declaratory judgment actions,
counter-claims, and cross-claims) alleging that a Contributor Version
directly or indirectly infringes any patent, then the rights granted to
You by any and all Contributors for the Covered Software under Section
2.1 of this License shall terminate.
5.3. In the event of termination under Sections 5.1 or 5.2 above, all
end user license agreements (excluding distributors and resellers) which
have been validly granted by You or Your distributors under this License
prior to termination shall survive termination.
************************************************************************
* *
* 6. Disclaimer of Warranty *
* ------------------------- *
* *
* Covered Software is provided under this License on an "as is" *
* basis, without warranty of any kind, either expressed, implied, or *
* statutory, including, without limitation, warranties that the *
* Covered Software is free of defects, merchantable, fit for a *
* particular purpose or non-infringing. The entire risk as to the *
* quality and performance of the Covered Software is with You. *
* Should any Covered Software prove defective in any respect, You *
* (not any Contributor) assume the cost of any necessary servicing, *
* repair, or correction. This disclaimer of warranty constitutes an *
* essential part of this License. No use of any Covered Software is *
* authorized under this License except under this disclaimer. *
* *
************************************************************************
************************************************************************
* *
* 7. Limitation of Liability *
* -------------------------- *
* *
* Under no circumstances and under no legal theory, whether tort *
* (including negligence), contract, or otherwise, shall any *
* Contributor, or anyone who distributes Covered Software as *
* permitted above, be liable to You for any direct, indirect, *
* special, incidental, or consequential damages of any character *
* including, without limitation, damages for lost profits, loss of *
* goodwill, work stoppage, computer failure or malfunction, or any *
* and all other commercial damages or losses, even if such party *
* shall have been informed of the possibility of such damages. This *
* limitation of liability shall not apply to liability for death or *
* personal injury resulting from such party's negligence to the *
* extent applicable law prohibits such limitation. Some *
* jurisdictions do not allow the exclusion or limitation of *
* incidental or consequential damages, so this exclusion and *
* limitation may not apply to You. *
* *
************************************************************************
8. Litigation
-------------
Any litigation relating to this License may be brought only in the
courts of a jurisdiction where the defendant maintains its principal
place of business and such litigation shall be governed by laws of that
jurisdiction, without reference to its conflict-of-law provisions.
Nothing in this Section shall prevent a party's ability to bring
cross-claims or counter-claims.
9. Miscellaneous
----------------
This License represents the complete agreement concerning the subject
matter hereof. If any provision of this License is held to be
unenforceable, such provision shall be reformed only to the extent
necessary to make it enforceable. Any law or regulation which provides
that the language of a contract shall be construed against the drafter
shall not be used to construe this License against a Contributor.
10. Versions of the License
---------------------------
10.1. New Versions
Mozilla Foundation is the license steward. Except as provided in Section
10.3, no one other than the license steward has the right to modify or
publish new versions of this License. Each version will be given a
distinguishing version number.
10.2. Effect of New Versions
You may distribute the Covered Software under the terms of the version
of the License under which You originally received the Covered Software,
or under the terms of any subsequent version published by the license
steward.
10.3. Modified Versions
If you create software not governed by this License, and you want to
create a new license for such software, you may create and use a
modified version of this License if you rename the license and remove
any references to the name of the license steward (except to note that
such modified license differs from this License).
10.4. Distributing Source Code Form that is Incompatible With Secondary
Licenses
If You choose to distribute Source Code Form that is Incompatible With
Secondary Licenses under the terms of this version of the License, the
notice described in Exhibit B of this License must be attached.
Exhibit A - Source Code Form License Notice
-------------------------------------------
This Source Code Form is subject to the terms of the Mozilla Public
License, v. 2.0. If a copy of the MPL was not distributed with this
file, You can obtain one at https://mozilla.org/MPL/2.0/.
If it is not possible or desirable to put the notice in a particular
file, then You may include the notice in a location (such as a LICENSE
file in a relevant directory) where a recipient would be likely to look
for such a notice.
You may add additional accurate notices of copyright ownership.
Exhibit B - "Incompatible With Secondary Licenses" Notice
---------------------------------------------------------
This Source Code Form is "Incompatible With Secondary Licenses", as
defined by the Mozilla Public License, v. 2.0.
+14
View File
@@ -0,0 +1,14 @@
services:
dtek_notif:
build:
context: .
dockerfile: Dockerfile
restart: unless-stopped
environment:
- TZ=Europe/Kyiv
dns:
- 1.1.1.1
- 8.8.8.8
networks:
- default
+778
View File
@@ -0,0 +1,778 @@
import requests
import json
import asyncio
from bs4 import BeautifulSoup
from datetime import datetime, timedelta
from aiogram import Bot, Dispatcher, types
from aiogram.filters import Command
from aiogram.types import Message, KeyboardButton
from aiogram.utils.keyboard import ReplyKeyboardBuilder
import logging
import os
from dotenv import load_dotenv
from typing import Optional, List, Dict
# Загрузка переменных окружения
load_dotenv()
# Настройки
TELEGRAM_TOKEN = os.getenv("TELEGRAM_TOKEN", "YOUR_TOKEN_HERE")
ALLOWED_CHAT_IDS = list(map(int, os.getenv("ALLOWED_CHAT_IDS", "").split(","))) if os.getenv("ALLOWED_CHAT_IDS") else []
CHECK_INTERVAL = int(os.getenv("CHECK_INTERVAL", "120"))
# Параметры для запроса
VOE_CITY_ID = int(os.getenv("VOE_CITY_ID", "VOE_CITY_ID"))
VOE_STREET_ID = int(os.getenv("VOE_STREET_ID", "VOE_STREET_ID"))
VOE_HOUSE_ID = int(os.getenv("VOE_HOUSE_ID", "VOE_HOUSE_ID"))
# Настройка логирования
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)
# Глобальные переменные
bot = Bot(token=TELEGRAM_TOKEN)
dp = Dispatcher()
last_schedule: Optional[List[Dict]] = None
last_notification_time: Dict[str, datetime] = {}
# ============================================================================
# УТИЛИТЫ
# ============================================================================
def format_time_duration(minutes: int) -> str:
"""Форматирует время из минут в часы и минуты"""
hours = minutes // 60
mins = minutes % 60
if hours == 0:
return f"{mins}м"
elif mins == 0:
return f"{hours}ч"
return f"{hours}ч {mins}м"
def get_day_statistics(day_blocks: List[Dict]) -> Dict[str, int]:
"""Получает статистику по дню"""
total_minutes = 0
confirmed_minutes = 0
possible_minutes = 0
for block in day_blocks:
for half in [block["first_half"], block["second_half"]]:
if half["status"] == "off":
total_minutes += 30
if half["confirmed"]:
confirmed_minutes += 30
else:
possible_minutes += 30
return {
"total": total_minutes,
"confirmed": confirmed_minutes,
"possible": possible_minutes
}
# ============================================================================
# ПАРСИНГ ДАННЫХ
# ============================================================================
def parse_html(html: str) -> List[Dict]:
"""Парсит HTML с графиком отключений (логика от 15.11.2024)"""
soup = BeautifulSoup(html, "html.parser")
cells = soup.select(".disconnection-detailed-table-cell.cell")
schedule = []
current_hour = 0
current_day = 0
for cell in cells:
if 'legend' in cell.get('class', []) or 'head' in cell.get('class', []):
continue
cell_classes = cell.get('class', [])
# ПРоверка статуса отключения на весь час
full_hour_off = 'has_disconnection' in cell_classes and 'full_hour' in cell_classes
no_disconnection_cell = 'no_disconnection' in cell_classes
hour_block = cell.select_one(".hour_block")
if not hour_block:
continue
# Проверка подтверждённости отключения для всего часа
cell_confirmed = None
if 'confirm_1' in cell_classes:
cell_confirmed = True
elif 'confirm_0' in cell_classes:
cell_confirmed = False
# Проверка половин часа
left = hour_block.select_one(".half.left")
right = hour_block.select_one(".half.right")
def parse_half(half, is_full_hour_off: bool) -> Dict:
"""Парсит половину часа"""
if not half:
return {"status": "on", "queue": None, "confirmed": None}
half_classes = half.get('class', [])
# Если вся ячейка full_hour - используем статус ячейки
if is_full_hour_off:
return {"status": "off", "queue": None, "confirmed": cell_confirmed}
# Определяем статус половины
if 'has_disconnection' in half_classes:
status = "off"
elif 'no_disconnection' in half_classes:
status = "on"
else:
status = "on" # По умолчанию считаем включенным
# Если выключено - ищем подробности
queue = None
confirmed = None
if status == "off":
disconnection_div = half.select_one(".disconnection")
if disconnection_div:
# Ищем номер черги в title
if disconnection_div.has_attr("title"):
title = disconnection_div["title"]
if "Номер черги" in title or "Номер черги:" in title:
try:
queue = title.split(":")[-1].strip()
except:
pass
# Определяем подтверждение
disc_classes = disconnection_div.get('class', [])
if 'disconnection_confirm_1' in disc_classes:
confirmed = True
elif 'disconnection_confirm_0' in disc_classes:
confirmed = False
return {"status": status, "queue": queue, "confirmed": confirmed}
first_half_data = parse_half(left, full_hour_off)
second_half_data = parse_half(right, full_hour_off)
schedule.append({
"hour": current_hour,
"day": current_day,
"first_half": first_half_data,
"second_half": second_half_data,
})
current_hour += 1
if current_hour >= 24:
current_hour = 0
current_day += 1
return schedule
def get_voe_html(city_id: int, street_id: int, house_id: int) -> str:
"""Получает HTML с сайта VOE"""
url = "https://www.voe.com.ua/disconnection/detailed?ajax_form=1&_wrapper_format=drupal_ajax"
headers = {
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
"X-Requested-With": "XMLHttpRequest",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
}
data = {
"search_type": 0,
"city_id": city_id,
"street_id": street_id,
"house_id": house_id,
"form_build_id": "form-Irv5aHw1R2FT_Ik2apyHOZ47hTH5xPNH_LQnBrmpSTc",
"form_id": "disconnection_detailed_search_form",
"_triggering_element_name": "search",
"_triggering_element_value": "Показати",
"_drupal_ajax": 1,
}
try:
response = requests.post(url, headers=headers, data=data, timeout=10)
response.raise_for_status()
resp_json = response.json()
insert_html = next(
(item["data"] for item in resp_json if item.get("command") == "insert"),
None
)
if not insert_html:
raise ValueError("HTML не найден в ответе")
return insert_html
except requests.exceptions.RequestException as e:
logger.error(f"Ошибка запроса VOE: {e}")
raise
# ============================================================================
# ФОРМАТИРОВАНИЕ СООБЩЕНИЙ
# ============================================================================
def get_main_keyboard():
"""Создает главную клавиатуру"""
builder = ReplyKeyboardBuilder()
builder.row(
KeyboardButton(text="📊 Графік"),
KeyboardButton(text="🔄 Оновити")
)
builder.row(
KeyboardButton(text="📅 Сьогодні"),
KeyboardButton(text="📅 Завтра")
)
builder.row(KeyboardButton(text="ℹ️ Про бота"))
return builder.as_markup(resize_keyboard=True)
def format_schedule_message(schedule: List[Dict], days_to_show: int = 2) -> str:
"""Форматирует полный график на несколько дней"""
lines = [
"⚡️ <b>Графік відключень світла</b>",
f"🕐 Оновлено: {datetime.now().strftime('%d.%m.%Y %H:%M:%S')}",
"─" * 30,
""
]
start_date = datetime.now()
for day in range(min(days_to_show, 2)):
day_blocks = [b for b in schedule if b["day"] == day]
if not day_blocks:
continue
date_str = (start_date + timedelta(days=day)).strftime('%d.%m.%Y')
day_name = "🌅 <b>Сьогодні</b>" if day == 0 else "🌄 <b>Завтра</b>"
lines.append(f"{day_name} ({date_str})")
# Статистика
stats = get_day_statistics(day_blocks)
if stats["total"] > 0:
lines.append(f"⏱ Всього: <code>{format_time_duration(stats['total'])}</code>")
if stats["confirmed"] > 0:
lines.append(f"🔴 Підтверджено: <code>{format_time_duration(stats['confirmed'])}</code>")
if stats["possible"] > 0:
lines.append(f"🟠 Можливо: <code>{format_time_duration(stats['possible'])}</code>")
else:
lines.append("🟢 <b>Відключень немає!</b>")
lines.append("")
# Детальный список отключений
disconnections = []
current_status = None
start_time = None
current_confirmed = None
current_queue = None
for block in day_blocks:
hour = block["hour"]
for half_idx, half in enumerate([block["first_half"], block["second_half"]]):
time_str = f"{hour:02d}:00" if half_idx == 0 else f"{hour:02d}:30"
if half["status"] == "off":
if current_status != "off":
start_time = time_str
current_confirmed = half["confirmed"]
current_queue = half["queue"]
current_status = "off"
else:
if current_status == "off":
icon = "🔴" if current_confirmed else "🟠"
queue_text = f" (Ч{current_queue})" if current_queue else ""
disconnections.append(f"{icon} <code>{start_time} - {time_str}</code>{queue_text}")
current_status = half["status"]
# Если день закончился на отключении
if current_status == "off":
icon = "🔴" if current_confirmed else "🟠"
queue_text = f" (Ч{current_queue})" if current_queue else ""
next_hour = (day_blocks[-1]["hour"] + 1) % 24
end_time = f"{next_hour:02d}:00"
disconnections.append(f"{icon} <code>{start_time} - {end_time}</code>{queue_text}")
if disconnections:
for idx, disc in enumerate(disconnections, 1):
lines.append(f"{idx}. {disc}")
lines.append("")
lines.append("<i>🔴 = підтверджено • 🟠 = можливо • 🟢 = світло</i>")
return "\n".join(lines)
def format_single_day_schedule(schedule: List[Dict], day: int) -> str:
"""Форматирует график на один день"""
day_blocks = [b for b in schedule if b["day"] == day]
if not day_blocks:
return "❌ Немає даних для цього дня"
start_date = datetime.now()
date_str = (start_date + timedelta(days=day)).strftime('%d.%m.%Y')
day_name = "🟠 <b>Сьогодні</b>" if day == 0 else "🔶 <b>Завтра</b>"
lines = [
f"{day_name} • {date_str}",
""
]
# Статистика
lines.append("<b>📊 Статистика</b>")
stats = get_day_statistics(day_blocks)
if stats["total"] == 0:
lines.append("└ 🟢 <b>Відключень немає!</b>")
else:
total_time = format_time_duration(stats["total"])
lines.append(f"├ ⏱ Всього: <code>{total_time}</code>")
if stats["confirmed"] > 0:
confirmed_time = format_time_duration(stats["confirmed"])
lines.append(f"├ 🔴 Підтверджено: <code>{confirmed_time}</code>")
if stats["possible"] > 0:
possible_time = format_time_duration(stats["possible"])
lines.append(f"└ 🟠 Можливо: <code>{possible_time}</code>")
else:
lines.append(f"└ 🟢 Решта часу світло")
lines.append("")
# Детальный список отключений
disconnections = []
current_status = None
start_time = None
current_confirmed = None
current_queue = None
for block in day_blocks:
hour = block["hour"]
for half_idx, half in enumerate([block["first_half"], block["second_half"]]):
time_str = f"{hour:02d}:00" if half_idx == 0 else f"{hour:02d}:30"
if half["status"] == "off":
if current_status != "off":
start_time = time_str
current_confirmed = half["confirmed"]
current_queue = half["queue"]
current_status = "off"
else:
if current_status == "off":
icon = "🔴" if current_confirmed else "🟠"
queue_text = f" (Ч.{current_queue})" if current_queue else ""
disconnections.append(f"{icon} <code>{start_time} - {time_str}</code>{queue_text}")
current_status = half["status"]
# Если день закончился на отключении
if current_status == "off":
icon = "🔴" if current_confirmed else "🟠"
queue_text = f" (Ч.{current_queue})" if current_queue else ""
next_hour = (day_blocks[-1]["hour"] + 1) % 24
end_time = f"{next_hour:02d}:00"
disconnections.append(f"{icon} <code>{start_time} - {end_time}</code>{queue_text}")
if disconnections:
lines.append("<b>⚡️ Розклад відключень</b>")
for idx, disc in enumerate(disconnections, 1):
lines.append(f"{idx}. {disc}")
lines.append("")
lines.append("<i>🔴 підтверджено • 🟠 можливо • 🟢 світло</i>")
return "\n".join(lines)
def schedules_differ(old_schedule: Optional[List[Dict]], new_schedule: Optional[List[Dict]]) -> bool:
"""Проверяет отличия между графиками"""
if old_schedule is None or new_schedule is None:
return True
if len(old_schedule) != len(new_schedule):
return True
for old, new in zip(old_schedule, new_schedule):
if old["day"] >= 2:
break
if (old["first_half"] != new["first_half"] or
old["second_half"] != new["second_half"]):
return True
return False
# ============================================================================
# УВЕДОМЛЕНИЯ
# ============================================================================
async def send_to_all_users(message_text: str, parse_mode: str = "HTML"):
"""Отправляет сообщение всем пользователям"""
if not ALLOWED_CHAT_IDS:
logger.warning("Нет допущенных ID чатов для отправки уведомлений")
return
for chat_id in ALLOWED_CHAT_IDS:
try:
await bot.send_message(chat_id, message_text, parse_mode=parse_mode)
logger.info(f"✅ Сообщение отправлено пользователю {chat_id}")
except Exception as e:
logger.error(f"❌ Ошибка отправки пользователю {chat_id}: {e}")
await asyncio.sleep(0.5)
async def check_schedule():
"""Проверяет график и отправляет уведомления"""
global last_schedule
try:
logger.info("🔍 Проверка графика...")
html = get_voe_html(VOE_CITY_ID, VOE_STREET_ID, VOE_HOUSE_ID)
new_schedule = parse_html(html)
if schedules_differ(last_schedule, new_schedule):
logger.info("✨ Обнаружены изменения!")
message = format_schedule_message(new_schedule, days_to_show=2)
if last_schedule is not None:
await send_to_all_users(f"🔄 <b>Графік оновлено!</b>\n\n{message}")
last_schedule = new_schedule
else:
logger.info("✓ Графік без змін")
except Exception as e:
logger.error(f"❌ Ошибка при проверке графика: {e}")
async def check_upcoming_disconnections():
"""Проверяет предстоящие события и отправляет предупреждения за 5 минут"""
global last_notification_time
if last_schedule is None:
return
now = datetime.now()
today_blocks = [b for b in last_schedule if b["day"] == 0]
# Создаем список всех переходов (off -> on или on -> off)
transitions = []
prev_status = None
for block in today_blocks:
hour = block["hour"]
for half_idx, half in enumerate([block["first_half"], block["second_half"]]):
minute = 0 if half_idx == 0 else 30
time_str = f"{hour:02d}:{minute:02d}"
current_status = half["status"]
# Если статус изменился - это переход
if prev_status is not None and prev_status != current_status:
transitions.append({
"hour": hour,
"minute": minute,
"time_str": time_str,
"from_status": prev_status,
"to_status": current_status,
"confirmed": half.get("confirmed"),
"queue": half.get("queue")
})
prev_status = current_status
# Проверяем переходы
for transition in transitions:
event_time = now.replace(
hour=transition["hour"],
minute=transition["minute"],
second=0,
microsecond=0
)
time_until = (event_time - now).total_seconds() / 60
notification_key = f"{transition['hour']}:{transition['minute']}_{transition['to_status']}"
# Если за 5 минут до события (±1 минута) и еще не отправляли
if 4 <= time_until <= 6:
# Проверяем, не отправляли ли уже уведомление сегодня
if notification_key in last_notification_time:
last_notif_time = last_notification_time[notification_key]
if last_notif_time.date() == now.date():
continue # Уже отправляли сегодня
# Переход на ОТКЛЮЧЕНИЕ (on -> off)
if transition["from_status"] == "on" and transition["to_status"] == "off":
icon = "🔴" if transition["confirmed"] else "🟠"
status = "підтверджено" if transition["confirmed"] else "можливе"
queue_info = f" (Черга {transition['queue']})" if transition['queue'] else ""
warning = (
f"⚠️ <b>УВАГА! ВІДКЛЮЧЕННЯ</b>\n\n"
f"Через ~5 хвилин\n"
f"Час: <code>{transition['time_str']}</code>\n"
f"Статус: {icon} {status}{queue_info}"
)
await send_to_all_users(warning)
last_notification_time[notification_key] = now
logger.info(f"📢 Відправлено попередження про ВІДКЛЮЧЕННЯ в {transition['time_str']}")
# Переход на ВКЛЮЧЕНИЕ (off -> on)
elif transition["from_status"] == "off" and transition["to_status"] == "on":
warning = (
f"✅ <b>УВАГА! ВКЛЮЧЕННЯ</b>\n\n"
f"Через ~5 хвилин буде світло\n"
f"Час: <code>{transition['time_str']}</code>"
)
await send_to_all_users(warning)
last_notification_time[notification_key] = now
logger.info(f"📢 Відправлено попередження про ВКЛЮЧЕННЯ в {transition['time_str']}")
async def monitoring_loop():
"""Основной цикл мониторинга"""
await check_schedule()
while True:
try:
await asyncio.sleep(CHECK_INTERVAL)
await check_schedule()
await check_upcoming_disconnections()
except Exception as e:
logger.error(f"Ошибка в цикле мониторинга: {e}")
await asyncio.sleep(5)
# ============================================================================
# ОБРАБОТЧИКИ КОМАНД
# ============================================================================
@dp.message(Command("start"))
async def cmd_start(message: Message):
"""Обработчик /start"""
if message.chat.id not in ALLOWED_CHAT_IDS:
await message.answer("❌ У вас немає доступу до цього бота.")
return
await message.answer(
"👋 <b>Ласкаво просимо!</b>\n\n"
"🤖 <b>Бот для моніторингу графіку відключень світла</b>\n\n"
"✨ <b>Можливості:</b>\n"
"• 📊 Перегляд графіку на сьогодні і завтра\n"
"• 🔔 Автоматичні сповіщення за 5 хвилин до подій\n"
"• 🔄 Моніторинг змін графіку\n\n"
"Використовуйте кнопки нижче 👇",
parse_mode="HTML",
reply_markup=get_main_keyboard()
)
@dp.message(lambda msg: msg.text == "ℹ️ Про бота")
async def cmd_info(message: Message):
"""Показывает информацию о боте"""
if message.chat.id not in ALLOWED_CHAT_IDS:
return
await message.answer(
"<b>ℹ️ Про бота</b>\n\n"
"🚀 <b>Версія:</b> 2.2 (Стабільна)\n\n"
"📝 <b>Реліз-ноути:</b>\n"
"├ 15.11.2024: Адаптація під оновлену логіку сайту VOE\n"
"├ Виправлено парсинг half.left та half.right\n"
"├ Покращено визначення підтвердження відключень\n"
"└ Оптимізовано обробку статусу для всієї години\n\n"
"⚡ <b>Функціональність:</b>\n"
"├ Моніторинг графіку 24/7\n"
"├ Сповіщення за 5 хвилин\n"
"├ Детальна статистика дня\n"
"└ Красива візуалізація\n\n"
"🔐 <b>Безпека:</b> Використовуються .env файли\n"
"💾 <b>Джерело:</b> voe.com.ua",
parse_mode="HTML",
reply_markup=get_main_keyboard()
)
@dp.message(Command("schedule"))
async def cmd_schedule(message: Message):
"""Показывает полный график"""
if message.chat.id not in ALLOWED_CHAT_IDS:
await message.answer("❌ У вас немає доступу.")
return
try:
await message.answer("⏳ Завантаження графіку...")
html = get_voe_html(VOE_CITY_ID, VOE_STREET_ID, VOE_HOUSE_ID)
schedule = parse_html(html)
text = format_schedule_message(schedule, days_to_show=2)
await message.answer(text, parse_mode="HTML", reply_markup=get_main_keyboard())
except Exception as e:
await message.answer(
f"❌ <b>Помилка:</b> {str(e)}",
parse_mode="HTML",
reply_markup=get_main_keyboard()
)
@dp.message(Command("today"))
async def cmd_today(message: Message):
"""Показывает график на сегодня"""
if message.chat.id not in ALLOWED_CHAT_IDS:
await message.answer("❌ У вас немає доступу.")
return
try:
await message.answer("⏳ Завантаження графіку сьогодні...")
html = get_voe_html(VOE_CITY_ID, VOE_STREET_ID, VOE_HOUSE_ID)
schedule = parse_html(html)
text = format_single_day_schedule(schedule, 0)
await message.answer(text, parse_mode="HTML", reply_markup=get_main_keyboard())
except Exception as e:
await message.answer(
f"❌ <b>Помилка:</b> {str(e)}",
parse_mode="HTML",
reply_markup=get_main_keyboard()
)
@dp.message(Command("tomorrow"))
async def cmd_tomorrow(message: Message):
"""Показывает график на завтра"""
if message.chat.id not in ALLOWED_CHAT_IDS:
await message.answer("❌ У вас немає доступу.")
return
try:
await message.answer("⏳ Завантаження графіку завтра...")
html = get_voe_html(VOE_CITY_ID, VOE_STREET_ID, VOE_HOUSE_ID)
schedule = parse_html(html)
text = format_single_day_schedule(schedule, 1)
await message.answer(text, parse_mode="HTML", reply_markup=get_main_keyboard())
# await message.answer("❌ Функція тимчасово недоступна. Чекаємо на оновлення сайту", parse_mode="HTML", reply_markup=get_main_keyboard())
except Exception as e:
await message.answer(
f"❌ <b>Помилка:</b> {str(e)}",
parse_mode="HTML",
reply_markup=get_main_keyboard()
)
@dp.message(Command("check"))
async def cmd_check(message: Message):
"""Принудительная проверка графика"""
if message.chat.id not in ALLOWED_CHAT_IDS:
await message.answer("❌ У вас немає доступу.")
return
try:
await message.answer("🔄 <b>Перевіряю графік...</b>", parse_mode="HTML")
html = get_voe_html(VOE_CITY_ID, VOE_STREET_ID, VOE_HOUSE_ID)
new_schedule = parse_html(html)
prefix = "✅ <b>Знайдено зміни!</b>\n\n" if schedules_differ(last_schedule, new_schedule) else "✓ <b>Графік без змін</b>\n\n"
result = prefix + format_schedule_message(new_schedule, days_to_show=2)
await message.answer(result, parse_mode="HTML", reply_markup=get_main_keyboard())
except Exception as e:
await message.answer(
f"❌ <b>Помилка:</b> {str(e)}",
parse_mode="HTML",
reply_markup=get_main_keyboard()
)
@dp.message()
async def handle_text(message: Message):
"""Обработчик текстовых сообщений и кнопок"""
if message.chat.id not in ALLOWED_CHAT_IDS:
return
text = message.text
# Кнопка "Графік"
if text == "📊 Графік":
await cmd_schedule(message)
# Кнопка "Сьогодні"
elif text == "📅 Сьогодні":
await cmd_today(message)
# Кнопка "Завтра"
elif text == "📅 Завтра":
await cmd_tomorrow(message)
# Кнопка "Оновити"
elif text == "🔄 Оновити":
await cmd_check(message)
# Кнопка "Про бота"
elif text == "ℹ️ Про бота":
await cmd_info(message)
# Неизвестная команда
else:
await message.answer(
"❓ <b>Команда не розпізнана</b>\n\n"
"Використовуйте кнопки на клавіатурі або команди:\n"
"/start • /today • /tomorrow • /schedule • /check",
parse_mode="HTML",
reply_markup=get_main_keyboard()
)
# ============================================================================
# ГЛАВНАЯ ФУНКЦИЯ
# ============================================================================
async def main():
"""Главная функция"""
logger.info("=" * 50)
logger.info("ЗАПУСК БОТА V2.2 (stable 2.2, 15.11.2025)")
logger.info("=" * 50)
if not TELEGRAM_TOKEN or TELEGRAM_TOKEN = os.getenv("TELEGRAM_TOKEN", "YOUR_TOKEN_HERE")
logger.error("❌ TELEGRAM_TOKEN не конфігурований! Напишіть токен в .env файл")
return
if not ALLOWED_CHAT_IDS:
logger.error("❌ ALLOWED_CHAT_IDS не конфігуровані! Напишіть ID в .env файл")
return
logger.info(f"📌 Allowed chat ids: {ALLOWED_CHAT_IDS}")
logger.info(f"⏱ Інтервал перевірки: {CHECK_INTERVAL} сек")
logger.info("=" * 50)
# Запускаем мониторинг
monitoring_task = asyncio.create_task(monitoring_loop())
try:
await dp.start_polling(bot)
except KeyboardInterrupt:
logger.info("⏹ Бот зупинений користувачем")
finally:
monitoring_task.cancel()
await bot.session.close()
logger.info("✓ Підключення закрито")
if __name__ == "__main__":
try:
asyncio.run(main())
except KeyboardInterrupt:
logger.info("⏹ Завершено")
+7
View File
@@ -0,0 +1,7 @@
[project]
name = "dtek-notif"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.13"
dependencies = []
+5
View File
@@ -0,0 +1,5 @@
requests>=2.31.0
beautifulsoup4>=4.12.0
aiogram>=3.3.0
python-dotenv>=1.0.0
aiohttp>=3.9.0
-1
View File
@@ -9,6 +9,5 @@ WEBINAR_CHECK_INTERVAL=60
REDIS_HOST=redis REDIS_HOST=redis
REDIS_PORT=6379 REDIS_PORT=6379
PLAYWRIGHT_WS=ws://playwright-service:3000/ws PLAYWRIGHT_WS=ws://playwright-service:3000/ws
TZ=Europe/Kyiv
WEBINAR_TELEGRAM_TOKEN=your_telegram_bot_token_here WEBINAR_TELEGRAM_TOKEN=your_telegram_bot_token_here
WEBINAR_ADMIN_ID=123456789 WEBINAR_ADMIN_ID=123456789
-1
View File
@@ -1 +0,0 @@
1.56.0
+3 -7
View File
@@ -1,11 +1,11 @@
services: services:
redis: redis:
image: redis:8.10.2-alpine image: redis:alpine
restart: unless-stopped restart: unless-stopped
volumes: volumes:
- redis-data:/data - redis-data:/data
healthcheck: healthcheck:
test: ["CMD", "redis-cli", "ping"] test: [ "CMD", "redis-cli", "ping" ]
interval: 5s interval: 5s
timeout: 3s timeout: 3s
retries: 5 retries: 5
@@ -17,15 +17,13 @@ services:
session-keeper: session-keeper:
build: ./phpsessid-bot build: ./phpsessid-bot
image: gcr.forust.xyz/forust/session-keeper:prod
pull_policy: build
env_file: .env env_file: .env
restart: unless-stopped restart: unless-stopped
depends_on: depends_on:
redis: redis:
condition: service_healthy condition: service_healthy
healthcheck: healthcheck:
test: ["CMD-SHELL", "redis-cli -h redis EXISTS EDU_PHPSESSID | grep -q 1"] test: [ "CMD-SHELL", "redis-cli -h redis EXISTS EDU_PHPSESSID | grep -q 1" ]
interval: 30s interval: 30s
timeout: 5s timeout: 5s
retries: 10 retries: 10
@@ -33,8 +31,6 @@ services:
webinar-checker: webinar-checker:
build: ./webinar-checker build: ./webinar-checker
image: gcr.forust.xyz/forust/webinar-checker:prod
pull_policy: build
env_file: .env env_file: .env
restart: unless-stopped restart: unless-stopped
depends_on: depends_on:
View File
Whitespace-only changes.
-96
View File
@@ -1,96 +0,0 @@
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: edu-master-webinar
namespace: edu-master
labels:
release: prometheus-stack
spec:
groups:
- name: edu_master.webinar
rules:
# No successful webinar check for 5m (~2-3 missed 2-min checks).
# Catches: playwright hangs/timeouts, version skew, site changes, hung job.
# The last_success > 0 guard is mandatory: checker.py initialises
# last_success to 0, so without it `time() - 0` equals the current epoch
# and humanizeDuration renders ~20722d on every pod restart. Keep the
# duration expression on the left so $value stays the real gap.
- alert: WebinarCheckerNoSuccessfulCheck
expr: |
((time() - webinar_check_last_success_timestamp_seconds) > 300)
and (webinar_check_last_success_timestamp_seconds > 0)
and (webinar_check_last_run_timestamp_seconds > 0)
for: 2m
labels:
severity: critical
annotations:
summary: "Webinar checker has no successful check for 5m"
description: "edu-master/webinar-checker: last successful webinar check was {{ $value | humanizeDuration }} ago. Checks are failing or hanging (see consecutive failures alert). Notifications about new webinars are NOT being sent."
# Checks are running but none has ever succeeded since pod start.
# Split out from the rule above so a zeroed gauge never feeds
# humanizeDuration.
- alert: WebinarCheckerNeverSucceeded
expr: |
(webinar_check_last_success_timestamp_seconds == 0)
and (webinar_check_last_run_timestamp_seconds > 0)
for: 10m
labels:
severity: critical
annotations:
summary: "Webinar checker has never completed a successful check"
description: 'edu-master/webinar-checker: checks have been running for 10m but not one has ever succeeded since the pod started, so every check is failing. Check pod logs (Loki: {namespace="edu-master", container="webinar-checker"}).'
# Fast path: 3 consecutive failures (~6+ min at 2-min interval).
- alert: WebinarCheckerConsecutiveFailures
expr: |
webinar_check_consecutive_failures >= 3
for: 5m
labels:
severity: critical
annotations:
summary: "Webinar checker failing consecutively"
description: 'edu-master/webinar-checker: {{ $value }} consecutive webinar check failures (timeout / playwright error / page error). Check pod logs (Loki: {namespace="edu-master", container="webinar-checker"}).'
# Metrics endpoint not scraped for 10m: pod down, metrics server dead, or ServiceMonitor broken.
- alert: WebinarCheckerScrapeDown
expr: |
absent(webinar_check_last_run_timestamp_seconds) == 1
for: 10m
labels:
severity: critical
annotations:
summary: "Webinar checker metrics missing"
description: "edu-master/webinar-checker: no metrics series for 10m. Pod may be down, metrics server dead, or ServiceMonitor/Service broken. Webinar checks are unobserved."
# EDU session lost: session-keeper down or credentials expired. Without PHPSESSID every check is skipped.
- alert: EduPhpsessidMissing
expr: |
edu_phpsessid_present == 0
for: 10m
labels:
severity: critical
annotations:
summary: "EDU_PHPSESSID missing"
description: "edu-master: EDU_PHPSESSID absent from redis for 10m. Webinar/diari/schedule checks are all skipped. Check session-keeper logs and EDU credentials."
# Hard deps: checker and playwright deployments unavailable.
- alert: WebinarCheckerDeploymentDown
expr: |
kube_deployment_status_replicas_unavailable{deployment="webinar-checker", namespace="edu-master"} > 0
for: 10m
labels:
severity: critical
annotations:
summary: "Webinar checker deployment unavailable"
description: "edu-master/webinar-checker deployment has {{ $value }} unavailable replica(s) for 10m."
- alert: PlaywrightServiceDown
expr: |
kube_deployment_status_replicas_unavailable{deployment="playwright-service", namespace="edu-master"} > 0
for: 10m
labels:
severity: critical
annotations:
summary: "Playwright service unavailable"
description: "edu-master/playwright-service deployment has {{ $value }} unavailable replica(s) for 10m. All webinar/diari/schedule checks fail without it."
-4
View File
@@ -1,4 +0,0 @@
apiVersion: v1
kind: Namespace
metadata:
name: edu-master
-69
View File
@@ -1,69 +0,0 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: playwright-service
namespace: edu-master
labels:
app: edu-master-playwright
spec:
replicas: 1
selector:
matchLabels:
app: edu-master-playwright
strategy:
type: Recreate
template:
metadata:
labels:
app: edu-master-playwright
spec:
containers:
- name: playwright
# renovate: datasource=docker depName=mcr.microsoft.com/playwright versioning=docker
image: mcr.microsoft.com/playwright:v1.56.0-jammy
imagePullPolicy: IfNotPresent
# p95 412M, max 478M over 7 days, no limit before. Request is set at p95
# so the pod is not an eviction candidate; the limit stays above 2x the
# request because browser page lifetimes are unpredictable.
resources:
requests:
cpu: "200m"
memory: "416Mi"
limits:
memory: "1Gi"
command:
- npx
- -y
- playwright@1.56.0
- run-server
- --port
- "3000"
- --path
- /ws
ports:
- containerPort: 3000
readinessProbe:
tcpSocket:
port: 3000
initialDelaySeconds: 5
periodSeconds: 10
timeoutSeconds: 3
livenessProbe:
tcpSocket:
port: 3000
initialDelaySeconds: 15
periodSeconds: 20
timeoutSeconds: 3
---
apiVersion: v1
kind: Service
metadata:
name: playwright-service
namespace: edu-master
spec:
selector:
app: edu-master-playwright
ports:
- name: ws
port: 3000
targetPort: 3000
-75
View File
@@ -1,75 +0,0 @@
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: redis
namespace: edu-master
labels:
app: edu-master-redis
spec:
serviceName: redis
replicas: 1
selector:
matchLabels:
app: edu-master-redis
template:
metadata:
labels:
app: edu-master-redis
spec:
containers:
- name: redis
image: redis:8.10.2-alpine
imagePullPolicy: IfNotPresent
ports:
- containerPort: 6379
volumeMounts:
- name: redis-data
mountPath: /data
resources:
requests:
cpu: 25m
memory: 32Mi
limits:
cpu: 250m
memory: 128Mi
readinessProbe:
exec:
command: ["redis-cli", "ping"]
initialDelaySeconds: 5
periodSeconds: 5
timeoutSeconds: 3
livenessProbe:
exec:
command: ["redis-cli", "ping"]
initialDelaySeconds: 10
periodSeconds: 10
timeoutSeconds: 3
volumes:
- name: redis-data
persistentVolumeClaim:
claimName: redis-data-pvc
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: redis-data-pvc
namespace: edu-master
spec:
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 1Gi
---
apiVersion: v1
kind: Service
metadata:
name: redis
namespace: edu-master
spec:
selector:
app: edu-master-redis
ports:
- name: redis
port: 6379
targetPort: 6379
@@ -1,50 +0,0 @@
# One-time Job to migrate redis state from docker compose to k8s (maintenance window).
# The .example file is not applied by the deploy pipeline (mask *.example.yaml).
#
# Runbook:
# 1. docker compose -f <repo>/edu_master/compose.yaml stop # SIGTERM -> redis will flush dump.rdb
# 2. docker run --rm -v edu_master_redis-data:/data \
# -v /tmp/edu-master-backup:/backup \
# redis:alpine sh -c "cp /data/dump.rdb /backup/ && ls -la /backup"
# 3. kubectl apply -f edu_master/k8s/namespace.yaml
# 4. kubectl apply -f <only the PVC from redis.yaml> # seed must come BEFORE redis pod starts
# 5. kubectl apply -f edu_master/k8s/restore-seed-job.yaml.example
# kubectl wait --for=condition=complete job/redis-restore-seed -n edu-master --timeout=120s
# 6. kubectl delete job redis-restore-seed -n edu-master
# 7. kubectl apply -f edu_master/k8s/ -R # apply remaining manifests
apiVersion: batch/v1
kind: Job
metadata:
name: redis-restore-seed
namespace: edu-master
spec:
backoffLimit: 2
ttlSecondsAfterFinished: 3600
template:
spec:
restartPolicy: Never
containers:
- name: seed
image: redis:alpine
command:
- /bin/sh
- -ec
- |
ls -la /backup
cp /backup/dump.rdb /data/dump.rdb
chmod 644 /data/dump.rdb
ls -la /data
volumeMounts:
- name: redis-data
mountPath: /data
- name: backup
mountPath: /backup
readOnly: true
volumes:
- name: redis-data
persistentVolumeClaim:
claimName: redis-data-pvc
- name: backup
hostPath:
path: /tmp/edu-master-backup
type: DirectoryOrCreate
-29
View File
@@ -1,29 +0,0 @@
apiVersion: v1
kind: Secret
metadata:
name: edu-master-secrets
namespace: edu-master
type: Opaque
stringData:
# Session keeper credentials
KEEPER_LOGIN: ""
KEEPER_PASSWORD: ""
KEEPER_INTERVAL: "10"
# EDU links
EDU_URL_BASE: "https://edu.edu.vn.ua"
EDU_URL_LOGIN: "/user/login"
EDU_URL_COURSES: "/course/userlist"
EDU_URL_WEBINAR: "/webinar/useractive"
# Playwright
USER_AGENT: ""
PLAYWRIGHT_WS: "ws://playwright-service:3000/ws"
# Webinar-checker
WEBINAR_TELEGRAM_TOKEN: ""
WEBINAR_ADMIN_ID: ""
WEBINAR_CHECK_INTERVAL: "60"
# Prometheus metrics endpoint (scraped via ServiceMonitor, alerts in k8s/alerts.yaml)
METRICS_PORT: "8000"
# Database
REDIS_HOST: "redis"
REDIS_PORT: "6379"
TZ: "Europe/Kyiv"
-15
View File
@@ -1,15 +0,0 @@
apiVersion: v1
kind: Service
metadata:
name: webinar-checker
namespace: edu-master
labels:
app: edu-master-webinar-checker
spec:
selector:
app: edu-master-webinar-checker
ports:
- name: metrics
port: 8000
targetPort: metrics
protocol: TCP
-16
View File
@@ -1,16 +0,0 @@
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: webinar-checker
namespace: edu-master
labels:
release: prometheus-stack
spec:
selector:
matchLabels:
app: edu-master-webinar-checker
endpoints:
- port: metrics
path: /metrics
interval: 30s
scrapeTimeout: 10s
-55
View File
@@ -1,55 +0,0 @@
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
reloader.stakater.com/auto: "true"
name: session-keeper
namespace: edu-master
labels:
app: edu-master-session-keeper
spec:
replicas: 1
selector:
matchLabels:
app: edu-master-session-keeper
strategy:
type: Recreate
template:
metadata:
labels:
app: edu-master-session-keeper
spec:
initContainers:
- name: wait-redis
image: redis:8.10.2-alpine
command:
- /bin/sh
- -ec
- |
i=0
until redis-cli -h redis ping | grep -q PONG; do
i=$((i+1))
[ "$i" -ge 300 ] && echo "TIMEOUT: redis not ready" && exit 1
sleep 2
done
echo "redis is ready"
containers:
- name: session-keeper
image: gcr.forust.xyz/forust/session-keeper:prod
envFrom:
- secretRef:
name: edu-master-secrets
resources:
requests:
cpu: 25m
memory: 32Mi
limits:
cpu: 250m
memory: 128Mi
readinessProbe:
exec:
command: ["/bin/sh", "-ec", "redis-cli -h redis EXISTS EDU_PHPSESSID | grep -q 1"]
initialDelaySeconds: 15
periodSeconds: 30
timeoutSeconds: 5
failureThreshold: 10
Loaded 100 of 474 files, more files were not shown because too many files have changed in this diff. Show more