feat: Adds monitoring setup for prometheus push gateway

Reviewed-on: #49

.drone.yml

@@ -2,11 +2,16 @@
 kind: pipeline
 name: linters
 steps:
-  - name: run shellcheck
-    image: koalaman/shellcheck-alpine
-    commands:
-      - shellcheck backup.sh
-
-trigger:
-  branch:
-    - main
+  - name: publish image
+    image: plugins/docker
+    settings:
+      username: 3wordchant
+      password:
+        from_secret: git_coopcloud_tech_token_3wc
+      repo: git.coopcloud.tech/coop-cloud/backup-bot-two
+      tags: 2.0.0
+      registry: git.coopcloud.tech
+    when:
+      event:
+        exclude:
+          - pull_request

.env.sample

@@ -9,10 +9,16 @@ RESTIC_REPOSITORY=/backups/restic
 CRON_SCHEDULE='30 3 * * *'
 
 # Push Notifiactions
+#PUSH_PROMETHEUS_URL=https://pushgateway.example.com/metrics/job/backup
+# or
 #PUSH_URL_START=https://status.example.com/api/push/xxxxxxxxxx?status=up&msg=start
 #PUSH_URL_SUCCESS=https://status.example.com/api/push/xxxxxxxxxx?status=up&msg=OK
 #PUSH_URL_FAIL=https://status.example.com/api/push/xxxxxxxxxx?status=down&msg=fail
 
+# Push Basic Auth
+#COMPOSE_FILE="$COMPOSE_FILE:compose.pushbasicauth.yml"
+#SECRET_PUSH_BASICAUTH=v1
+
 # swarm-cronjob, instead of built-in cron
 #COMPOSE_FILE="$COMPOSE_FILE:compose.swarm-cronjob.yml"
 

Dockerfile

@@ -0,0 +1,11 @@
+FROM docker:24.0.7-dind
+
+RUN apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
+
+# Todo use requirements file with specific versions
+RUN pip install --break-system-packages resticpy==1.0.2
+
+COPY backupbot.py /usr/bin/backup
+COPY entrypoint.sh /entrypoint.sh
+
+ENTRYPOINT /entrypoint.sh

README.md

@@ -10,7 +10,7 @@ Automatically take backups from all volumes of running Docker Swarm services and
 
 * **Category**: Utilities
 * **Status**: 0, work-in-progress
-* **Image**: [`thecoopcloud/backup-bot-two`](https://hub.docker.com/r/thecoopcloud/backup-bot-two), 4, upstream
+* **Image**: [`git.coopcloud.tech/coop-cloud/backup-bot-two`](https://git.coopcloud.tech/coop-cloud/-/packages/container/backup-bot-two), 4, upstream
 * **Healthcheck**: No
 * **Backups**: N/A
 * **Email**: N/A
@@ -104,15 +104,38 @@ See [restic REST docs](https://restic.readthedocs.io/en/latest/030_preparing_a_n
 
 ## Push notifications
 
+It is possible to configure three push events, that may trigger on the backup cronjob. Those can be used to detect failures from mointoring systems.
+The events are:
+- start
+- success
+- fail
+
+### Using a Prometheus Push Gateway
+
+[A prometheus push gateway](https://git.coopcloud.tech/coop-cloud/monitoring-ng#setup-push-gateway) can be used by setting the following env variables:
+- `PUSH_PROMETHEUS_URL=pushgateway.example.com/metrics/job/backup`
+
+### Using custom URLs
+
 The following env variables can be used to setup push notifications for backups. `PUSH_URL_START` is requested just before the backups starts, `PUSH_URL_SUCCESS` is only requested if the backup was successful and if the backup fails `PUSH_URL_FAIL` will be requested.
 Each variable is optional and independent of the other.
-```
 
+```
 PUSH_URL_START=https://status.example.com/api/push/xxxxxxxxxx?status=up&msg=start
 PUSH_URL_SUCCESS=https://status.example.com/api/push/xxxxxxxxxx?status=up&msg=OK
 PUSH_URL_FAIL=https://status.example.com/api/push/xxxxxxxxxx?status=down&msg=fail
 ```
 
+### Push endpoint behind basic auth
+
+Insert the basic auth secret
+`abra app secret insert <backupbot_name> push_basicauth v1 "user:password"`
+
+Enable basic auth in the env file, by uncommenting the following line:
+```
+#COMPOSE_FILE="$COMPOSE_FILE:compose.pushbasicauth.yml"
+#SECRET_PUSH_BASICAUTH=v1
+```
 
 ## Usage
 

abra.sh

@@ -1,6 +1,7 @@
-export ENTRYPOINT_VERSION=v1
 export BACKUPBOT_VERSION=v1
 export SSH_CONFIG_VERSION=v1
+export ENTRYPOINT_VERSION=v17
+export CRONJOB_VERSION=v2
 
 run_cron () {
     schedule="$(crontab -l | tr -s " " | cut -d ' ' -f-5)"

backupbot.py

@@ -42,7 +42,7 @@ sys.excepthook = handle_exception
 @click.option('-l', '--log', 'loglevel')
 @click.option('-m', '--machine-logs', 'machine_logs', is_flag=True)
 @click.option('service', '--host', '-h', envvar='SERVICE')
-@click.option('repository', '--repo', '-r', envvar='RESTIC_REPOSITORY', required=True)
+@click.option('repository', '--repo', '-r', envvar='RESTIC_REPOSITORY')
 def cli(loglevel, service, repository, machine_logs):
     global SERVICE
     if service:
@@ -54,21 +54,25 @@ def cli(loglevel, service, repository, machine_logs):
         if not isinstance(numeric_level, int):
             raise ValueError('Invalid log level: %s' % loglevel)
         logger.setLevel(numeric_level)
+    logHandler = logging.StreamHandler()
     if machine_logs:
-        logHandler = logging.StreamHandler()
         formatter = jsonlogger.JsonFormatter(
             "%(levelname)s %(filename)s %(lineno)s %(process)d %(message)s", rename_fields={"levelname": "message_type"})
         logHandler.setFormatter(formatter)
-        logger.addHandler(logHandler)
+    logger.addHandler(logHandler)
 
     export_secrets()
     init_repo()
 
 
 def init_repo():
-    repo = os.environ['RESTIC_REPOSITORY']
+    if repo:= os.environ.get('RESTIC_REPOSITORY_FILE'):
+        # RESTIC_REPOSITORY_FILE and RESTIC_REPOSITORY are mutually exclusive
+        del os.environ['RESTIC_REPOSITORY']
+    else:
+        repo = os.environ['RESTIC_REPOSITORY']
+        restic.repository = repo
     logger.debug(f"set restic repository location: {repo}")
-    restic.repository = repo
     restic.password_file = '/var/run/secrets/restic_password'
     try:
         restic.cat.config()
@@ -104,7 +108,7 @@ def create(retries):
 def get_backup_cmds():
     client = docker.from_env()
     container_by_service = {
-        c.labels['com.docker.swarm.service.name']: c for c in client.containers.list()}
+        c.labels.get('com.docker.swarm.service.name'): c for c in client.containers.list()}
     backup_paths = set()
     backup_apps = set()
     pre_commands = {}
@@ -139,14 +143,14 @@ def copy_secrets(apps):
     os.mkdir(SECRET_PATH)
     client = docker.from_env()
     container_by_service = {
-        c.labels['com.docker.swarm.service.name']: c for c in client.containers.list()}
+        c.labels.get('com.docker.swarm.service.name'): c for c in client.containers.list()}
     services = client.services.list()
     for s in services:
         app_name = s.attrs['Spec']['Labels']['com.docker.stack.namespace']
         if (app_name in apps and
                 (app_secs := s.attrs['Spec']['TaskTemplate']['ContainerSpec'].get('Secrets'))):
             if not container_by_service.get(s.name):
-                logger.error(
+                logger.warning(
                     f"Container {s.name} is not running, secrets can not be copied.")
                 continue
             container_id = container_by_service[s.name].id
@@ -157,6 +161,7 @@ def copy_secrets(apps):
                         f"For the secret {sec['SecretName']} the file {src} does not exist for {s.name}")
                     continue
                 dst = SECRET_PATH + sec['SecretName']
+                logger.debug("Copy Secret {sec['SecretName']}")
                 copyfile(src, dst)
 
 
@@ -184,6 +189,8 @@ def run_commands(commands):
 def backup_volumes(backup_paths, apps, retries, dry_run=False):
     while True:
         try:
+            logger.info("Start volume backup")
+            logger.debug(backup_paths)
             result = restic.backup(backup_paths, dry_run=dry_run, tags=apps)
             logger.summary("backup finished", extra=result)
             return

compose.pushbasicauth.yml

@@ -0,0 +1,11 @@
+---
+version: "3.8"
+services:
+  app:
+    secrets:
+      - push_basicauth
+
+secrets:
+  push_basicauth:
+    external: true
+    name: ${STACK_NAME}_push_basicauth_${SECRET_PUSH_BASICAUTH}

compose.yml

@@ -2,7 +2,7 @@
 version: "3.8"
 services:
   app:
-    image: docker:24.0.7-dind
+    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.0.0
     volumes:
       - "/var/run/docker.sock:/var/run/docker.sock"
       - "/var/lib/docker/volumes/:/var/lib/docker/volumes/"
@@ -14,20 +14,19 @@ services:
       - RESTIC_PASSWORD_FILE=/run/secrets/restic_password
     secrets:
       - restic_password
+    configs:
+      - source: entrypoint
+        target: /entrypoint.sh
+        mode: 666
+      - source: cronjob
+        target: /cronjob.sh
+        mode: 666
     deploy:
       labels:
         - coop-cloud.${STACK_NAME}.version=0.1.0+latest
         - coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-300}
         - coop-cloud.backupbot.enabled=true
-    configs:
-      - source: entrypoint
-        target: /entrypoint.sh
-        mode: 0555
-      - source: backupbot
-        target: /usr/bin/backup
-        mode: 0555
-    entrypoint: ['/entrypoint.sh']
-   #entrypoint: ['tail', '-f','/dev/null']
+    #entrypoint: ['tail', '-f','/dev/null']
     healthcheck:
       test: "pgrep crond"
       interval: 30s
@@ -39,14 +38,14 @@ secrets:
   restic_password:
     external: true
     name: ${STACK_NAME}_restic_password_${SECRET_RESTIC_PASSWORD_VERSION}
-    
-volumes:
-  backups:
 
 configs:
   entrypoint:
     name: ${STACK_NAME}_entrypoint_${ENTRYPOINT_VERSION}
     file: entrypoint.sh
-  backupbot:
-    name: ${STACK_NAME}_backupbot_${BACKUPBOT_VERSION}
-    file: backupbot.py
+  cronjob:
+    name: ${STACK_NAME}_cronjob_${CRONJOB_VERSION}
+    file: cronjob.sh
+
+volumes:
+  backups:

cronjob.sh

@@ -0,0 +1,40 @@
+#!/bin/sh
+
+set -e
+
+CURL_OPTS="-s"
+# Check for basic auth
+if [ -n "$(cat /run/secrets/push_basicauth)" ]
+then
+    CURL_OPTS="$CURL_OPTS -u $(cat /run/secrets/push_basicauth)"
+fi
+
+if [ -n "$PUSH_PROMETHEUS_URL" ]
+then
+    push_start_notification="(echo 'backup 1' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
+    push_success_notification="(echo 'backup 0' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
+    push_fail_notification="(echo 'backup -1' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
+else
+    if [ -n "$PUSH_URL_START" ]
+    then
+        push_start_notification="curl $CURL_OPTS '$PUSH_URL_START'"
+    fi
+
+    if [ -n "$PUSH_URL_FAIL" ]
+    then
+        push_fail_notification="curl $CURL_OPTS '$PUSH_URL_FAIL'"
+    fi
+
+    if [ -n "$PUSH_URL_SUCCESS" ]
+    then
+        push_success_notification="curl $CURL_OPTS '$PUSH_URL_SUCCESS'"
+    fi
+fi
+
+eval "$push_start_notification"
+if [ "$(backup --machine-logs create  2>&1 | tee /tmp/backup.log && (grep -q 'backup finished' /tmp/backup.log))" ]
+then
+    eval "$push_success_notification"
+else
+    eval "$push_fail_notification"
+fi

entrypoint.sh

@@ -1,11 +1,6 @@
 #!/bin/sh
 
-set -e -o pipefail
-
-apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
-
-# Todo use requirements file with specific versions
-pip install --break-system-packages resticpy==1.0.2
+set -e
 
 if [ -n "$SSH_HOST_KEY" ]
 then
@@ -14,22 +9,7 @@ fi
 
 cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
 
-if [ -n "$PUSH_URL_START" ]
-then
-    push_start_notification="curl -s '$PUSH_URL_START' &&"
-fi
-
-if [ -n "$PUSH_URL_FAIL" ]
-then
-    push_fail_notification="|| curl -s '$PUSH_URL_FAIL'"
-fi
-
-if [ -n "$PUSH_URL_SUCCESS" ]
-then
-    push_notification=" && (grep -q 'backup finished' /tmp/backup.log && curl -s '$PUSH_URL_SUCCESS' $push_fail_notification)"
-fi
-
-echo "$cron_schedule $push_start_notification backup --machine-logs create  2>&1 | tee /tmp/backup.log $push_notification" | crontab -
+echo "$cron_schedule /cronjob.sh" | crontab -
 crontab -l
 
 crond -f -d8 -L /dev/stdout