fix(app): use stack-prefixed hostnames for redis and db

The app service was missing DISCOURSE_REDIS_HOST entirely, so the
bitnami image defaulted to the bare hostname 'redis', which does not
resolve when the service is attached to multiple overlay networks
(proxy + internal) — causing a restart loop.

sidekiq had the same problem worse: both DISCOURSE_DATABASE_HOST=db
and DISCOURSE_REDIS_HOST=redis used bare hostnames instead of the
stack-prefixed service names. On a swarm stack the reliable DNS name
is ${STACK_NAME}_db / ${STACK_NAME}_redis.

abra.sh

@@ -1,2 +1,2 @@
-export DB_ENTRYPOINT_VERSION=v1
+export DB_ENTRYPOINT_VERSION=v3
 export PG_BACKUP_VERSION=v2

compose.yml

@@ -16,6 +16,8 @@ services:
       - DISCOURSE_DATABASE_USER=discourse
       - DISCOURSE_HOST=${DOMAIN}
       - DISCOURSE_NOTIFICATION_EMAIL
+      # bare "redis" doesn't resolve when app is on multiple networks; use stack-prefixed name
+      - DISCOURSE_REDIS_HOST=${STACK_NAME}_redis
       - DISCOURSE_SMTP_AUTH
       - DISCOURSE_SMTP_HOST
       - DISCOURSE_SMTP_PORT
@@ -43,7 +45,7 @@ services:
         #- "traefik.http.routers.${STACK_NAME}.middlewares=${STACK_NAME}-redirect"
         #- "traefik.http.middlewares.${STACK_NAME}-redirect.headers.SSLForceHost=true"
         #- "traefik.http.middlewares.${STACK_NAME}-redirect.headers.SSLHost=${DOMAIN}"
-        - "coop-cloud.${STACK_NAME}.version=0.8.0+3.5.0"
+        - "coop-cloud.${STACK_NAME}.version=0.8.1+3.5.0"
     healthcheck:
       test: "ruby -e \"require 'uri'; require 'net/http'; uri = URI('http://localhost:3000/srv/status'); res = Net::HTTP.get_response(uri); if res.is_a?(Net::HTTPSuccess) then exit (0) else exit (1) end\""
       interval: 30s
@@ -100,13 +102,13 @@ services:
       - db_password
     environment:
       - ALLOW_EMPTY_PASSWORD=yes
-      - DISCOURSE_DATABASE_HOST=db
+      - DISCOURSE_DATABASE_HOST=${STACK_NAME}_db
       - DISCOURSE_DATABASE_NAME=discourse
       - DISCOURSE_DATABASE_PASSWORD_FILE=/run/secrets/db_password
       - DISCOURSE_DATABASE_PORT_NUMBER=5432
       - DISCOURSE_DATABASE_USER=discourse
       - DISCOURSE_HOST=${DOMAIN}
-      - DISCOURSE_REDIS_HOST=redis
+      - DISCOURSE_REDIS_HOST=${STACK_NAME}_redis
       - DISCOURSE_REDIS_PORT_NUMBER=6379
       - DISCOURSE_SMTP_HOST
       - DISCOURSE_SMTP_PORT

entrypoint.postgres.sh.tmpl

@@ -2,16 +2,23 @@
 
 set -e
 
-MIGRATION_MARKER=$PGDATA/migration_in_progress
 OLDDATA=$PGDATA/old_data
 NEWDATA=$PGDATA/new_data
 
 echo "Running as $(id)"
 
-if [ -e $MIGRATION_MARKER ]; then
+# The migration uses $OLDDATA/$NEWDATA as scratch and removes them when it
-  echo "FATAL: migration was started but did not complete in a previous run. manual recovery necessary"
+# finishes; a leftover *empty* one means a run was interrupted before any data
-  exit 1
+# moved (data still intact at $PGDATA) so we clear it and retry, while a
-fi
+# *non-empty* one means data may live only there, so we stop for manual recovery.
+for scratch in $OLDDATA $NEWDATA; do
+  if [ -d "$scratch" ] && [ -n "$(ls -A "$scratch")" ]; then
+    echo "FATAL: $scratch exists and is not empty - a previous migration did not"
+    echo "complete and the data may only exist there. manual recovery necessary."
+    exit 1
+  fi
+done
+rm -rf $OLDDATA $NEWDATA
 
 if [ -f $PGDATA/PG_VERSION ]; then
   DATA_VERSION=$(cat $PGDATA/PG_VERSION)
@@ -23,22 +30,33 @@ if [ -f $PGDATA/PG_VERSION ]; then
     apt-get update && apt-get install -y --no-install-recommends \
       postgresql-$DATA_VERSION \
       && rm -rf /var/lib/apt/lists/*
+    # pg_upgrade must run as the old cluster's bootstrap superuser (the "install
+    # user", oid 10), and the new cluster must be initialised with that same
+    # user. It is not necessarily $POSTGRES_USER (e.g. clusters created with the
+    # default "postgres" superuser and a separate app role), so read it from the
+    # old cluster: briefly start it and ask, connecting as the app role we know.
+    PGBIN=/usr/lib/postgresql/$DATA_VERSION/bin
+    gosu postgres $PGBIN/pg_ctl -D $PGDATA -w \
+      -o "-c listen_addresses= -c unix_socket_directories=/tmp" start
+    INSTALL_USER=$(gosu postgres psql -h /tmp -U "$POSTGRES_USER" -d postgres -tAc \
+      "select rolname from pg_roles where oid = 10")
+    gosu postgres $PGBIN/pg_ctl -D $PGDATA -w stop
+    echo "old cluster install user: $INSTALL_USER"
     echo "shuffling around"
     gosu postgres mkdir $OLDDATA $NEWDATA
     chmod 700 $OLDDATA $NEWDATA
     mv $PGDATA/* $OLDDATA/ || true
-    touch $MIGRATION_MARKER
     echo "running initdb"
-    # abuse entrypoint script for initdb by making server error out
+    # abuse entrypoint script for initdb by making server error out; initialise
-    gosu postgres bash -c "export PGDATA=$NEWDATA ; /usr/local/bin/docker-entrypoint.sh --invalid-arg || true"
+    # the new cluster with the same superuser as the old one so pg_upgrade matches
+    gosu postgres bash -c "export PGDATA=$NEWDATA POSTGRES_USER=$INSTALL_USER ; /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 $POSTGRES_USER
+    gosu postgres pg_upgrade --link -b /usr/lib/postgresql/$DATA_VERSION/bin -d $OLDDATA -D $NEWDATA -U $INSTALL_USER
     cp $OLDDATA/pg_hba.conf $NEWDATA/
     mv $NEWDATA/* $PGDATA
     rm -rf $OLDDATA
     rmdir $NEWDATA
-    rm $MIGRATION_MARKER
     echo "migration complete"
   fi
 fi