feat(db): use pgautoupgrade instead of custom pg_upgrade entrypoint

Replace the hand-rolled entrypoint.postgres.sh.tmpl (which apt-installed
the old PG binaries and ran initdb + pg_upgrade --link by hand) with the
pgautoupgrade/pgautoupgrade:18-alpine image, matching the other recipes.
PGDATA is pinned to the legacy /var/lib/postgresql/data so the existing
cluster on the volume is upgraded in place rather than re-initialised.
Drops the db_entrypoint config and DB_ENTRYPOINT_VERSION.

.drone.yml

@@ -45,7 +45,7 @@ steps:
         from_secret: drone_abra-bot_token
       fork: true
       repositories:
-        - coop-cloud/auto-recipes-catalogue-json
+        - toolshed/auto-recipes-catalogue-json
 
 trigger:
   event: tag

abra.sh

@@ -1,4 +1,3 @@
 export CLICKHOUSE_CONF_VERSION=v2
 export CLICKHOUSE_USER_CONF_VERSION=v2
-export DB_ENTRYPOINT_VERSION=v1
-export CLICKHOUSE_ENTRYPOINT_VERSION=v2
+export CLICKHOUSE_ENTRYPOINT_VERSION=v3

compose.yml

@@ -12,8 +12,13 @@ services:
       - BASE_URL=https://$DOMAIN
       - SECRET_KEY_BASE
       - DATABASE_URL=postgres://plausible:plausible@${STACK_NAME}_db:5432/plausible
+      - CLICKHOUSE_DATABASE_URL=http://${STACK_NAME}_plausible_events_db:8123/plausible_events_db
       - SMTP_HOST_ADDR
       - MAILER_EMAIL
+      - SMTP_HOST_PORT
+      - SMTP_USER_NAME
+      - SMTP_USER_PWD
+      - SMTP_HOST_SSL_ENABLED
       - DISABLE_REGISTRATION
       - DISABLE_AUTH
     networks:
@@ -28,30 +33,32 @@ services:
         - "traefik.http.routers.${STACK_NAME}.rule=Host(`${DOMAIN}`${EXTRA_DOMAINS})"
         - "traefik.http.routers.${STACK_NAME}.entrypoints=web-secure"
         - "traefik.http.routers.${STACK_NAME}.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        - coop-cloud.${STACK_NAME}.version=3.0.1+v2.0.0
+        - coop-cloud.${STACK_NAME}.version=4.0.0+v2.0.0
   db:
-    image: postgres:13.12
-    configs:
-      - source: db_entrypoint
-        target: /docker-entrypoint.sh
-        mode: 0555
-    # Custom docker entrypoint to handle major Postgres version upgrades
+    image: pgautoupgrade/pgautoupgrade:18-alpine
     volumes:
       - db-data:/var/lib/postgresql/data
-    entrypoint: /docker-entrypoint.sh
     environment:
+      # pin legacy PGDATA so the existing cluster on the volume is upgraded in place, not re-init'd
+      - PGDATA=/var/lib/postgresql/data
       - POSTGRES_USER=plausible
       - POSTGRES_PASSWORD=plausible
       - POSTGRES_DB=plausible
     networks:
       - internal
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U plausible -d plausible"]
+      interval: 5s
+      timeout: 5s
+      retries: 60
     deploy:
       labels:
         backupbot.backup: "true"
         backupbot.backup.pre-hook: sh -c 'pg_dump -U "$$POSTGRES_USER" -Fc "$$POSTGRES_DB" | gzip > "/postgres.dump.gz"'
         backupbot.backup.path: "/postgres.dump.gz"
         backupbot.backup.post-hook: "rm -f /postgres.dump.gz"
-        backupbot.restore.post-hook: sh -c 'gzip -d /postgres.dump.gz && pg_restore -U "$$POSTGRES_USER" --dbname="$$PLAUSIBLE_DB" < /postgres.dump && rm /postgres.dump'
+        backupbot.restore: "true"
+        backupbot.restore.post-hook: sh -c 'gzip -d /postgres.dump.gz && pg_restore --clean -U "$$POSTGRES_USER" --dbname="$$PLAUSIBLE_DB" < /postgres.dump && rm -f /postgres.dump'
 
   plausible_events_db:
     image: clickhouse/clickhouse-server:23.4.2.11-alpine
@@ -74,8 +81,8 @@ services:
         backupbot.backup.pre-hook: clickhouse-backup create events
         backupbot.backup.path: "/var/lib/clickhouse/backup/events"
         backupbot.backup.post-hook: "rm -rf /var/lib/clickhouse/backup/events"
-        backupbot.restore.post-hook: clickhouse-backup restore events
-        backupbot.resoter.post-hook: "rm -rf /var/lib/clickhouse/backup/events"
+        backupbot.restore: "true"
+        backupbot.restore.post-hook: clickhouse-backup restore --rm events && rm -rf /var/lib/clickhouse/backup/events"
 
 volumes:
   db-data:
@@ -93,10 +100,6 @@ configs:
   clickhouse-user-config:
     name: ${STACK_NAME}_clickhouse_user_config_${CLICKHOUSE_USER_CONF_VERSION}
     file: clickhouse-user-config.xml
-  db_entrypoint:
-    name: ${STACK_NAME}_db_entrypoint_${DB_ENTRYPOINT_VERSION}
-    file: entrypoint.postgres.sh.tmpl
-    template_driver: golang
   clickhouse_entrypoint:
     name: ${STACK_NAME}_clickhouse_entrypoint_${CLICKHOUSE_ENTRYPOINT_VERSION}
     file: entrypoint.clickhouse.sh

entrypoint.clickhouse.sh

@@ -1,6 +1,23 @@
 #!/bin/bash
+# clickhouse entrypoint (cc-ci Q4.7b hardening — recipe-PR for recipe-maintainers/plausible).
+#
+# clickhouse-backup is the BACKUP tool (backupbot pre/post-hooks: `clickhouse-backup create/restore`).
+# It is NOT required for clickhouse-SERVER (`/entrypoint.sh`) to run. The published recipe fetched it
+# with `set -ex` + a single silenced no-retry wget to ephemeral /tmp, so ANY transient failure of the
+# 22 MB GitHub download (rate-limit / network) exited the container BEFORE the server started → swarm
+# restarted it → re-downloaded → amplified the throttle → crash-loop → deploy timeout (cc-ci Q4.7).
+#
+# Hardening (no behaviour change when the download succeeds first try):
+#   - cache the binary on the PERSISTENT clickhouse data volume (/var/lib/clickhouse) so it is fetched
+#     at most once and reused on every container restart (no re-download amplification);
+#   - retry with backoff to ride out transient GitHub failures;
+#   - un-silenced so a failure is diagnosable in `docker service logs`.
+#
+# Policy: clickhouse-backup is REQUIRED. If it cannot be installed after all retries the entrypoint
+# aborts (non-zero exit) and the server is NOT started — we deliberately fail the deploy loudly rather
+# than come up silently without backup/restore capability.
 
-set -ex
+set -e
 
 CLICKHOUSE_BACKUP_VERSION=2.4.2
 
@@ -17,13 +34,34 @@ elif [[ $ARCH =~ "x86_64" ]]; then
   ARCH="amd64"
 fi
 
-wget \
-    --quiet \
-    --continue \
-    --no-clobber \
-    --output-document=/tmp/clickhouse-backup.tar.gz \
-    "https://github.com/AlexAkulov/clickhouse-backup/releases/download/v${CLICKHOUSE_BACKUP_VERSION}/clickhouse-backup-linux-${ARCH}.tar.gz" 2>/dev/null
+CACHE_DIR=/var/lib/clickhouse/.ccci-bin
+CACHED="${CACHE_DIR}/clickhouse-backup"
+BIN=/usr/local/bin/clickhouse-backup
+URL="https://github.com/AlexAkulov/clickhouse-backup/releases/download/v${CLICKHOUSE_BACKUP_VERSION}/clickhouse-backup-linux-${ARCH}.tar.gz"
 
-tar -xf /tmp/clickhouse-backup.tar.gz --directory=/usr/local/bin --strip-components=3
+install_clickhouse_backup() {
+  mkdir -p "$CACHE_DIR"
+  if [ -x "$CACHED" ]; then
+    cp -f "$CACHED" "$BIN"
+    echo "clickhouse-backup: restored from persistent cache ($CACHED)"
+    return 0
+  fi
+  for attempt in 1 2 3 4 5; do
+    if wget --continue --output-document=/tmp/clickhouse-backup.tar.gz "$URL" \
+       && tar -xf /tmp/clickhouse-backup.tar.gz --directory=/usr/local/bin --strip-components=3; then
+      cp -f "$BIN" "$CACHED" 2>/dev/null || true
+      echo "clickhouse-backup: downloaded + cached (attempt ${attempt})"
+      return 0
+    fi
+    echo "clickhouse-backup: fetch attempt ${attempt} failed; backing off $((attempt * 10))s" >&2
+    sleep $((attempt * 10))
+  done
+  echo "clickhouse-backup: fetch FAILED after all retries — aborting; clickhouse-server will NOT start (backup tool is required)" >&2
+  return 1
+}
 
-/entrypoint.sh
+# Required: if the backup tool cannot be installed after retries, abort (set -e) so the deploy fails
+# loudly instead of coming up without backup/restore capability.
+install_clickhouse_backup
+
+exec /entrypoint.sh

entrypoint.postgres.sh.tmpl

@@ -1,44 +0,0 @@
-#!/bin/bash
-
-set -e
-
-MIGRATION_MARKER=$PGDATA/migration_in_progress
-OLDDATA=$PGDATA/old_data
-NEWDATA=$PGDATA/new_data
-
-if [ -e $MIGRATION_MARKER ]; then
-  echo "FATAL: migration was started but did not complete in a previous run. manual recovery necessary"
-  exit 1
-fi
-
-if [ -f $PGDATA/PG_VERSION ]; then
-  DATA_VERSION=$(cat $PGDATA/PG_VERSION)
-
-  if [ -n "$DATA_VERSION" -a "$PG_MAJOR" != "$DATA_VERSION" ]; then
-    echo "postgres data version $DATA_VERSION found, but need $PG_MAJOR. Starting migration"
-    echo "Installing postgres $DATA_VERSION"
-    sed -i "s/$/ $DATA_VERSION/" /etc/apt/sources.list.d/pgdg.list
-    apt-get update && apt-get install -y --no-install-recommends \
-      postgresql-$DATA_VERSION \
-      && rm -rf /var/lib/apt/lists/*
-    echo "shuffling around"
-    gosu postgres mkdir $OLDDATA $NEWDATA
-    chmod 700 $OLDDATA $NEWDATA
-    mv $PGDATA/* $OLDDATA/ || true
-    touch $MIGRATION_MARKER
-    echo "running initdb"
-    # abuse entrypoint script for initdb by making server error out
-    gosu postgres bash -c "export PGDATA=$NEWDATA ; /usr/local/bin/docker-entrypoint.sh --invalid-arg || true"
-    echo "running pg_upgrade"
-    cd /tmp
-    gosu postgres pg_upgrade --link -b /usr/lib/postgresql/$DATA_VERSION/bin -d $OLDDATA -D $NEWDATA -U $POSTGRES_USER
-    cp $OLDDATA/pg_hba.conf $NEWDATA/
-    mv $NEWDATA/* $PGDATA
-    rm -rf $OLDDATA
-    rmdir $NEWDATA
-    rm $MIGRATION_MARKER
-    echo "migration complete"
-  fi
-fi
-
-/usr/local/bin/docker-entrypoint.sh postgres

release/3.0.0+v2.0.0

@@ -0,0 +1,8 @@
+⚠ WARNING! ⚠
+
+This major version upgrade of Plausible requires running a manual data migration
+-- otherwise you'll see all historical data disappear (don't worry, it's
+"probably" still there). 
+
+Take a manual docker volume backup, then see here, and strap in: 
+https://github.com/plausible/analytics/discussions/3132