fix(db): bump DB_ENTRYPOINT_VERSION to v3 so the entrypoint config reloads

The install-user fix changed the entrypoint content; swarm configs are
immutable, so the config name (which embeds DB_ENTRYPOINT_VERSION) must change
for a redeploy to pick up the new script.

.drone.yml

@@ -3,7 +3,7 @@ kind: pipeline
 name: deploy to swarm-test.autonomic.zone
 steps:
   - name: deployment
-    image: decentral1se/stack-ssh-deploy:latest
+    image: git.coopcloud.tech/coop-cloud/stack-ssh-deploy:latest
     settings:
       host: swarm-test.autonomic.zone
       stack: discourse
@@ -18,6 +18,23 @@ steps:
       STACK_NAME: discourse
       LETS_ENCRYPT_ENV: production
       SECRET_DB_PASSWORD_VERSION: v1
+      DB_ENTRYPOINT_VERSION: v1
 trigger:
   branch:
     - main
+---
+kind: pipeline
+name: generate recipe catalogue
+steps:
+  - name: release a new version
+    image: plugins/downstream
+    settings:
+      server: https://build.coopcloud.tech
+      token:
+        from_secret: drone_abra-bot_token
+      fork: true
+      repositories:
+        - toolshed/auto-recipes-catalogue-json
+
+trigger:
+  event: tag

README.md

@@ -7,7 +7,7 @@ A platform for community discussion
 <!-- metadata -->
 * **Category**: Apps
 * **Status**: 
-* **Image**: [`bitnami/discourse`](https://hub.docker.com/r/bitname/discourse)
+* **Image**: [`bitnami/discourse`](https://hub.docker.com/r/bitnami/discourse)
 * **Healthcheck**: yes
 * **Backups**: no
 * **Email**: yes
@@ -21,15 +21,15 @@ A platform for community discussion
 2. Deploy [`coop-cloud/traefik`]
 3. `abra app new discourse --secrets` (optionally with `--pass` if you'd like
    to save secrets in `pass`)
-4. `abra app YOURAPPDOMAIN config` - be sure to change `$DOMAIN` to something that resolves to
+4. `abra app config YOURAPPDOMAIN` - be sure to change `$DOMAIN` to something that resolves to
    your Docker swarm box
-5. `abra app YOURAPPDOMAIN deploy`
+5. `abra app deploy YOURAPPDOMAIN`
 6. Open the configured domain in your browser to finish set-up
 
 [`abra`]: https://git.autonomic.zone/autonomic-cooperative/abra
 [`coop-cloud/traefik`]: https://git.autonomic.zone/coop-cloud/traefik
 
-## To add a new Admin user
+## To add a new admin user
 
 1. Login to the instance `abra app run APPNAME app sh`
 2. `cd /opt/bitnami/discourse`
@@ -39,9 +39,34 @@ A platform for community discussion
 
 1. Login to instance `abra app run APPNAME app sh`
 2. `cd /bitnami/discourse/plugins/`
-3. `git clone plugingit` for example `https://github.com/discourse/discourse-openid-connect.git`
-4. `abra app restart APPNAME app`
+3. `git clone plugin.git` for example `https://github.com/discourse/discourse-openid-connect.git`
+4. `abra app restart YOURAPPDOMAIN app`
+
+### Events / calendar plugin
+
+We've had some luck running [discourse-events](https://github.com/paviliondev/discourse-events).
 
 ## Setup Notes
 
 Until issue #1 is fixed, the default user is `user` and the default password is `bitnami123`
+
+## Postgres major version upgrades
+
+Welcome to hell.
+
+1. `abra app run YOURAPPDOMAIN db pg_dumpall -U discourse | gzip > YOURAPPDOMAIN_db_DATE.sql.gz`
+2. `abra app volume ls YOURAPPDOMAIN`, find the name of the Postgres data volume
+3. `scp` the backup to your VPS
+4. `abra app undeploy YOURAPPDOMAIN`
+5. `abra app volume rm YOURAPPDOMAIN`, choose the Postgres data volume
+6. `abra app deploy YOURAPPDOMAIN`, then `abra app undeploy YOURAPPDOMAIN`
+7. `ssh` to the VPS, run (replacing `13-alpine` with the new Postgres version)
+   `docker run -v YOURDATAVOLUME:/var/lib/postgresql/data -e POSTGRES_HOST_AUTH_METHOD=trust -it postgres:13-alpine`
+8. In another SSH session on the server, run `docker ps` to find the ID of the
+   new Postgres container, then `docker exec -it CONTAINERID bash`
+9. In the shell you just launched, run `dropdb -U discourse discourse`, then
+   `createdb -U discourse discourse`, then Ctrl+D or run `exit`
+10. In the second SSH session, run `zcat YOURAPPDOMAIN_db_DATE.sql.gz | docker exec -it CONTAINERID psql -U discourse`
+11. Exit the second SSH session
+12. Back in the first SSH session, Ctrl+C to shut down the database
+13. `abra app deploy YOURAPPDOMAIN`

abra.sh

@@ -0,0 +1,2 @@
+export DB_ENTRYPOINT_VERSION=v3
+export PG_BACKUP_VERSION=v2

compose.yml

@@ -3,24 +3,25 @@ version: "3.8"
 
 services:
   app:
-    image: bitnami/discourse:2.8.9
+    image: bitnamilegacy/discourse:3.5.0
     networks:
       - proxy
       - internal
     # entrypoint: ['tail', '-f', '/dev/null']
     environment:
       - ALLOW_EMPTY_PASSWORD=yes
-      - DISCOURSE_HOST=${DOMAIN}
-      - DISCOURSE_DATABASE_HOST=db
-      - DISCOURSE_DATABASE_USER=discourse
+      - DISCOURSE_DATABASE_HOST=${STACK_NAME}_db
       - DISCOURSE_DATABASE_NAME=discourse
       - DISCOURSE_DATABASE_PASSWORD_FILE=/run/secrets/db_password
+      - DISCOURSE_DATABASE_USER=discourse
+      - DISCOURSE_HOST=${DOMAIN}
+      - DISCOURSE_NOTIFICATION_EMAIL
+      - DISCOURSE_SMTP_AUTH
       - DISCOURSE_SMTP_HOST
       - DISCOURSE_SMTP_PORT
-      - DISCOURSE_SMTP_USER
       - DISCOURSE_SMTP_PROTOCOL
-      - DISCOURSE_SMTP_AUTH
-      - DISCOURSE_NOTIFICATION_EMAIL
+      - DISCOURSE_SMTP_USER
+      - PASSENGER_COMPILE_NATIVE_SUPPORT_BINARY=0
     volumes:
       - 'discourse_data:/bitnami/discourse'
     secrets:
@@ -42,60 +43,76 @@ services:
         #- "traefik.http.routers.${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.${STACK_NAME}.version=0.3.1+2.8.9"
-    # healthcheck:
-    #   test: ["CMD", "curl", "-f", "http://localhost:3000"]
-    #   interval: 30s
-    #   timeout: 10s
-    #   retries: 10
-    #   start_period: 1m
+        - "coop-cloud.${STACK_NAME}.version=0.10.0+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
+      timeout: 10s
+      retries: 6
+      start_period: 20m
 
   db:
-    image: postgres:13-alpine
+    image: pgvector/pgvector:pg17
     networks:
       - internal
     secrets:
       - db_password
     volumes:
       - 'postgresql_data:/var/lib/postgresql/data'
+    configs:
+      - source: db_entrypoint
+        target: /docker-entrypoint.sh
+        mode: 0555
+      - source: pg_backup
+        target: /pg_backup.sh
+        mode: 0555
+    entrypoint: /docker-entrypoint.sh
     environment:
       - POSTGRES_HOST_AUTH_METHOD=trust
       - POSTGRES_USER=discourse
       - POSTGRES_DB=discourse
       - POSTGRES_PASSWORD_FILE=/run/secrets/db_password
+    deploy:
+      labels:
+        backupbot.backup: "true"
+        backupbot.backup.pre-hook: "/pg_backup.sh backup"
+        backupbot.backup.volumes.postgresql_data.path: "backup.sql"
+        backupbot.restore.post-hook: "/pg_backup.sh restore"
 
   redis:
-    image: redis:7.0-alpine
+    image: redis:8.8-alpine
     networks:
       - internal
     volumes:
       - 'redis_data:/data'
 
   sidekiq:
-    image: bitnami/discourse:2.8.9
+    image: bitnamilegacy/discourse:3.5.0
     networks:
+      - proxy
       - internal
     depends_on:
       - discourse
     volumes:
-      - 'sidekiq_data:/bitnami/discourse'
+      - 'discourse_data:/bitnami/discourse'
     command: /opt/bitnami/scripts/discourse-sidekiq/run.sh
     secrets:
       - db_password
     environment:
       - ALLOW_EMPTY_PASSWORD=yes
-      - DISCOURSE_HOST=${DOMAIN}
       - DISCOURSE_DATABASE_HOST=db
+      - DISCOURSE_DATABASE_NAME=discourse
+      - DISCOURSE_DATABASE_PASSWORD_FILE=/run/secrets/db_password
       - DISCOURSE_DATABASE_PORT_NUMBER=5432
       - DISCOURSE_DATABASE_USER=discourse
-      - DISCOURSE_DATABASE_NAME=discourse
+      - DISCOURSE_HOST=${DOMAIN}
       - DISCOURSE_REDIS_HOST=redis
       - DISCOURSE_REDIS_PORT_NUMBER=6379
-      - DISCOURSE_DATABASE_PASSWORD_FILE=/run/secrets/db_password
       - DISCOURSE_SMTP_HOST
       - DISCOURSE_SMTP_PORT
-      - DISCOURSE_SMTP_USER
       - DISCOURSE_SMTP_PROTOCOL
+      - DISCOURSE_SMTP_USER
+      - PASSENGER_COMPILE_NATIVE_SUPPORT_BINARY=0
       - DISCOURSE_SMTP_AUTH
 
 secrets:
@@ -107,9 +124,17 @@ volumes:
   postgresql_data:
   redis_data:
   discourse_data:
-  sidekiq_data:
 
 networks:
   proxy:
     external: true
   internal:
+
+configs:
+  db_entrypoint:
+    name: ${STACK_NAME}_db_entrypoint_${DB_ENTRYPOINT_VERSION}
+    file: entrypoint.postgres.sh.tmpl
+    template_driver: golang
+  pg_backup:
+    name: ${STACK_NAME}_pg_backup_${PG_BACKUP_VERSION}
+    file: pg_backup.sh

entrypoint.postgres.sh.tmpl

@@ -0,0 +1,64 @@
+#!/bin/bash
+
+set -e
+
+OLDDATA=$PGDATA/old_data
+NEWDATA=$PGDATA/new_data
+
+echo "Running as $(id)"
+
+# The migration uses $OLDDATA/$NEWDATA as scratch and removes them when it
+# finishes; a leftover *empty* one means a run was interrupted before any data
+# moved (data still intact at $PGDATA) so we clear it and retry, while a
+# *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 $PGDATA/PG_VERSION)
+
+  if [ -n "$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/*
+    # 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/* $OLDDATA/ || true
+    echo "running initdb"
+    # abuse entrypoint script for initdb by making server error out; initialise
+    # the new cluster with the same superuser as the old one so pg_upgrade matches
+    gosu postgres bash -c "export PGDATA=$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 $INSTALL_USER
+    cp $OLDDATA/pg_hba.conf $NEWDATA/
+    mv $NEWDATA/* $PGDATA
+    rm -rf $OLDDATA
+    rmdir $NEWDATA
+    echo "migration complete"
+  fi
+fi
+
+/usr/local/bin/docker-entrypoint.sh postgres

pg_backup.sh

@@ -0,0 +1,44 @@
+#!/bin/bash
+
+# Postgres backup/restore hook for the discourse `db` service.
+
+set -e
+
+BACKUP_FILE='/var/lib/postgresql/data/backup.sql'
+export PGPASSWORD=$(cat "${POSTGRES_PASSWORD_FILE:-/run/secrets/db_password}")
+DB_USER="${POSTGRES_USER:-discourse}"
+DB_NAME="${POSTGRES_DB:-discourse}"
+
+function backup {
+  pg_dump -U "$DB_USER" "$DB_NAME" | gzip > "$BACKUP_FILE"
+}
+
+function restore {
+  cd /var/lib/postgresql/data/
+
+  # Block all non-local connections so the running discourse app + sidekiq cannot reconnect and
+  # interfere with the drop/recreate/reimport. Restored on exit.
+  restore_hba() {
+    cat pg_hba.conf.bak > pg_hba.conf
+    rm -f pg_hba.conf.bak
+    su postgres -c 'pg_ctl reload'
+  }
+  cp pg_hba.conf pg_hba.conf.bak
+  echo 'local all all trust' > pg_hba.conf
+  su postgres -c 'pg_ctl reload'
+  trap restore_hba EXIT INT TERM
+
+  # terminate any lingering local sessions before recreate
+  # see https://stackoverflow.com/questions/5108876/kill-a-postgresql-session-connection
+  psql -U "$DB_USER" -d postgres -c \
+    "SELECT pg_terminate_backend(pid) FROM pg_stat_activity WHERE datname='${DB_NAME}' AND pid<>pg_backend_pid();"
+
+  # drop database and then recreate it
+  psql -U "$DB_USER" -d postgres -c "DROP DATABASE ${DB_NAME} WITH (FORCE);"
+  createdb -U "$DB_USER" "$DB_NAME"
+
+  # reimport data 
+  gunzip -c "$BACKUP_FILE" | psql -U "$DB_USER" -d "$DB_NAME" -1 -v ON_ERROR_STOP=1 -f -
+}
+
+$@