Merge pull request 'switch app to official discourse/discourse image (with idempotent migration)' (#16) from discourse-official into main

Reviewed-on: https://git.coopcloud.tech/coop-cloud/discourse/pulls/16

.env.sample

@@ -21,3 +21,9 @@ DISCOURSE_DEVELOPER_EMAILS=admin@example.com
 #SECRET_SMTP_PASSWORD_VERSION=v1
 
 SECRET_DB_PASSWORD_VERSION=v1
+
+# Postgres bootstrap superuser (the cluster's "install user"). Defaults to
+# `postgres`, which matches fresh installs and bitnami-origin clusters. Only set
+# this if you are upgrading a cluster that was bootstrapped with a different
+# superuser (e.g. `discourse`) — a postgres major upgrade fails unless it matches.
+#POSTGRES_USER=postgres

README.md

@@ -47,10 +47,15 @@ abra app run YOURAPPDOMAIN app discourse admin create
 
 Handled automatically by the [`discourse/postgres`] image (pgvector + an
 auto-upgrade layer). On deploy it finds an older cluster, installs the old
-binaries and runs `pg_upgrade` into the new versioned data directory. The recipe
+binaries and runs `pg_upgrade` into the new versioned data directory. No manual
-adds a small entrypoint wrapper that injects the password secret and detects the
+dump/restore needed.
-old cluster's real install superuser (oid 10), so the upgrade works whether that
+
-user is `postgres` or `discourse`. No manual dump/restore needed.
+`pg_upgrade` must run as the old cluster's bootstrap superuser (its "install
+user"). The recipe uses `POSTGRES_USER`, which defaults to `postgres` — the right
+value for fresh installs and for clusters that came from the old bitnami recipe.
+If your cluster was bootstrapped with a different superuser (e.g. `discourse`),
+set `POSTGRES_USER` in the app `.env` before upgrading, otherwise `pg_upgrade`
+will refuse with an install-user mismatch.
 
 [`discourse/postgres`]: https://github.com/discourse/discourse-postgres
 

abra.sh

@@ -1,5 +1,4 @@
-export DB_ENTRYPOINT_VERSION=v6
+export PG_BACKUP_VERSION=v4
-export PG_BACKUP_VERSION=v3
 export APP_ENTRYPOINT_VERSION=v2
 export APP_INSTALL_SSL_VERSION=v1
 export APP_MIGRATE_UPLOADS_VERSION=v1

cc-db-entrypoint.sh

@@ -1,87 +0,0 @@
-#!/bin/bash
-# Co-op Cloud entrypoint wrapper for the discourse/postgres image.
-#
-# discourse/postgres (https://github.com/discourse/discourse-postgres) is pgvector
-# plus a management layer that auto-upgrades an older cluster on boot. It does the
-# heavy lifting (apt-installs the old binaries, runs pg_upgrade, writes the new
-# cluster to the versioned PGDATA). This wrapper only fills the two gaps it leaves:
-#
-#   1. Secrets: the image reads DB_PASSWORD / POSTGRES_PASSWORD from the process
-#      env (no *_FILE support), so inject them from the docker secret.
-#   2. Install user: the image runs `pg_upgrade --username="$POSTGRES_USER"` and
-#      initdb's the new cluster with $POSTGRES_USER, but never detects the OLD
-#      cluster's real bootstrap superuser (the install user, oid 10). pg_upgrade
-#      aborts unless the new cluster's install-user name matches the old one. Real
-#      deployments differ: some were bootstrapped with `postgres` as the install
-#      user (+ a separate `discourse` app role), others with `discourse` itself.
-#      So detect oid 10 from the old cluster and export POSTGRES_USER to match
-#      before handing off to the image's run-postgres.sh.
-set -e
-
-# --- 1. secret injection -----------------------------------------------------
-if [ -f /run/secrets/db_password ]; then
-  pw="$(cat /run/secrets/db_password)"
-  export DB_PASSWORD="$pw"
-  export POSTGRES_PASSWORD="$pw"
-fi
-
-# --- 2. install-user detection (only matters on the upgrade path) ------------
-NEW_MAJOR="$(postgres --version | sed -rn 's/^[^0-9]*([0-9]+).*/\1/p')"
-
-# Newest existing cluster under the data mount (same search the image uses).
-PGVER_FILE="$(find /var/lib/postgresql -maxdepth 3 -type f -name PG_VERSION 2>/dev/null \
-  | xargs -I{} sh -c 'printf "%s " "{}"; cat "{}"' \
-  | sort -nk2,2 | tail -n1 | awk '{print $1}')"
-
-if [ -n "$PGVER_FILE" ]; then
-  OLD_DIR="$(dirname "$PGVER_FILE")"
-  OLD_MAJOR="$(cat "$PGVER_FILE")"
-  if [ "$OLD_MAJOR" != "$NEW_MAJOR" ]; then
-    echo "cc-db-entrypoint: existing pg${OLD_MAJOR} cluster at ${OLD_DIR}, image is pg${NEW_MAJOR} -> detecting install user"
-    OLD_BIN="/usr/lib/postgresql/${OLD_MAJOR}/bin"
-    if [ ! -x "$OLD_BIN/pg_ctl" ]; then
-      echo "cc-db-entrypoint: installing postgresql-${OLD_MAJOR} to read the old cluster"
-      apt-get update
-      apt-get install -y --no-install-recommends "postgresql-${OLD_MAJOR}" >/dev/null
-    fi
-    chown -R postgres "$OLD_DIR" 2>/dev/null || true
-
-    # Briefly start the old cluster on a local socket only, ask it for oid 10.
-    gosu postgres "$OLD_BIN/pg_ctl" -D "$OLD_DIR" -w \
-      -o "-c listen_addresses= -c unix_socket_directories=/tmp" start >/dev/null 2>&1 || true
-    detected=""
-    for login_role in discourse postgres; do
-      detected="$(gosu postgres psql -h /tmp -U "$login_role" -d postgres -tAc \
-        'select rolname from pg_roles where oid = 10' 2>/dev/null | tr -d '[:space:]')"
-      [ -n "$detected" ] && break
-    done
-    gosu postgres "$OLD_BIN/pg_ctl" -D "$OLD_DIR" -w stop >/dev/null 2>&1 || true
-
-    if [ -n "$detected" ]; then
-      echo "cc-db-entrypoint: old cluster install user is '$detected' -> POSTGRES_USER=$detected"
-      export POSTGRES_USER="$detected"
-    else
-      echo "cc-db-entrypoint: WARNING could not detect old install user; leaving POSTGRES_USER=${POSTGRES_USER:-<image default>}"
-    fi
-
-    # pg_upgrade refuses to run if the old and new clusters disagree on data
-    # checksums. PostgreSQL 18's initdb enables checksums by default, but the
-    # older clusters in this recipe's lineage (pg13-17) were created without
-    # them, so initdb the new cluster to match. Default to OFF (the lineage
-    # reality) and only enable when the old cluster positively reports them on.
-    csum=""
-    if [ -x "$OLD_BIN/pg_controldata" ]; then
-      csum="$("$OLD_BIN/pg_controldata" "$OLD_DIR" 2>/dev/null \
-        | awk -F: '/checksum version/{gsub(/[^0-9]/,"",$2); print $2}')"
-    fi
-    if [ "$csum" = "1" ]; then
-      echo "cc-db-entrypoint: old cluster data checksums ON -> initdb new cluster --data-checksums"
-      export POSTGRES_INITDB_ARGS="${POSTGRES_INITDB_ARGS:+$POSTGRES_INITDB_ARGS }--data-checksums"
-    else
-      echo "cc-db-entrypoint: old cluster data checksums OFF (version='${csum:-unknown}') -> initdb new cluster --no-data-checksums"
-      export POSTGRES_INITDB_ARGS="${POSTGRES_INITDB_ARGS:+$POSTGRES_INITDB_ARGS }--no-data-checksums"
-    fi
-  fi
-fi
-
-exec run-postgres.sh postgres

compose.yml

@@ -65,8 +65,7 @@ services:
   db:
     # discourse/postgres = pgvector + discourse's postgres management layer, which
     # auto-upgrades an older cluster in place on boot (pg_upgrade into the versioned
-    # PGDATA /var/lib/postgresql/${MAJOR}/docker). The cc-db-entrypoint wrapper
+    # PGDATA /var/lib/postgresql/${MAJOR}/docker); everything is driven by the env below.
-    # injects the password secret and detects the old cluster's install user.
     image: discourse/postgres:pg18
     networks:
       - internal
@@ -77,27 +76,37 @@ services:
       # an existing pg17 cluster at the volume root is found and upgraded into /18/docker
       - 'postgresql_data:/var/lib/postgresql'
     configs:
-      - source: db_entrypoint
-        target: /usr/local/bin/cc-db-entrypoint.sh
-        mode: 0555
       - source: pg_backup
         target: /pg_backup.sh
         mode: 0555
-    entrypoint: /usr/local/bin/cc-db-entrypoint.sh
+    entrypoint:
+      - /bin/bash
+      - -c
+      - |
+        if [ -f /run/secrets/db_password ]; then
+          DB_PASSWORD="$$(cat /run/secrets/db_password)"
+          export DB_PASSWORD POSTGRES_PASSWORD="$$DB_PASSWORD"
+        fi
+        exec run-postgres.sh postgres
     environment:
       # internal-only overlay network; keep all-trust so the app and the
       # backup/restore hooks connect without juggling the superuser password
       - POSTGRES_HOST_AUTH_METHOD=trust
       - POSTGRES_DB=discourse
       - DB_USER=discourse
+      # pg_upgrade runs as this role and initdb's the new cluster with it; it must
+      # match the OLD cluster's bootstrap superuser (oid 10). The image default
+      # `postgres` matches fresh installs and bitnami-origin clusters. Override in
+      # the app .env (POSTGRES_USER=...) only for a cluster bootstrapped differently.
+      - POSTGRES_USER=${POSTGRES_USER:-postgres}
+      # pg18's initdb enables data checksums by default, but pg13-17 clusters here
+      # have them off and pg_upgrade requires a match -> initialise without them.
+      - POSTGRES_INITDB_ARGS=--no-data-checksums
     healthcheck:
       test: "pg_isready -U discourse -d discourse"
       interval: 30s
       timeout: 10s
       retries: 5
-      # generous: a postgres major-version upgrade (apt install old binaries +
-      # pg_upgrade) runs in the entrypoint before the server accepts connections —
-      # don't let the healthcheck kill an in-progress migration
       start_period: 15m
     deploy:
       labels:
@@ -145,9 +154,6 @@ configs:
   app_migrate_uploads:
     name: ${STACK_NAME}_app_migrate_uploads_${APP_MIGRATE_UPLOADS_VERSION}
     file: migrate-uploads.sh
-  db_entrypoint:
-    name: ${STACK_NAME}_db_entrypoint_${DB_ENTRYPOINT_VERSION}
-    file: cc-db-entrypoint.sh
   pg_backup:
     name: ${STACK_NAME}_pg_backup_${PG_BACKUP_VERSION}
     file: pg_backup.sh

pg_backup.sh

@@ -4,25 +4,13 @@
 
 set -e
 
-# discourse/postgres keeps the live cluster at a versioned PGDATA under the
+# dump goes at the volume root so backupbot's backup.sql label finds it
-# /var/lib/postgresql mount. Write the dump at the volume root so backupbot's
-# `postgresql_data.path: backup.sql` label captures it.
 BACKUP_FILE='/var/lib/postgresql/backup.sql'
 DATADIR="${PGDATA:-/var/lib/postgresql/18/docker}"
 DB_NAME="${POSTGRES_DB:-discourse}"
 
-# The bootstrap superuser (install user, oid 10) differs between deployments
+# bootstrap superuser for the dump/drop/recreate; same POSTGRES_USER the db service sets
-# (`postgres` on bitnami-origin clusters, `discourse` on others). Detect it at
+SU="${POSTGRES_USER:-postgres}"
-# runtime over the local trust socket rather than hard-coding a name.
-detect_superuser() {
-  local u name
-  for u in discourse postgres; do
-    name="$(psql -U "$u" -d "$DB_NAME" -tAc 'select rolname from pg_roles where oid = 10' 2>/dev/null | tr -d '[:space:]')"
-    if [ -n "$name" ]; then echo "$name"; return 0; fi
-  done
-  echo postgres
-}
-SU="$(detect_superuser)"
 
 function backup {
   pg_dump -U "$SU" "$DB_NAME" | gzip > "$BACKUP_FILE"

release/1.0.0+3.5.3

@@ -1,10 +0,0 @@
-This release switches from the bitnami image to the official discourse/discourse
-image. Some env vars need to be renamed for this migration; everything else
-should happen automatically.
-
-Rename these in your app's .env (the values carry over):
-
-  DISCOURSE_SMTP_HOST     --> DISCOURSE_SMTP_ADDRESS
-  DISCOURSE_SMTP_USER     --> DISCOURSE_SMTP_USER_NAME
-  DISCOURSE_SMTP_AUTH     --> DISCOURSE_SMTP_AUTHENTICATION
-  DISCOURSE_SMTP_PROTOCOL --> DISCOURSE_SMTP_ENABLE_START_TLS (takes a boolean true/false, not the old tls/ssl value, so translate it rather than copying it straight across)

release/next

@@ -0,0 +1,31 @@
+This release switches from the bitnami image to the official discourse/discourse
+image. Some env vars need to be renamed for this migration; everything else
+should happen automatically.
+
+** WARNING A: renaming env vars
+
+Rename these in your app's .env (the values carry over):
+
+  DISCOURSE_SMTP_HOST     --> DISCOURSE_SMTP_ADDRESS
+  DISCOURSE_SMTP_USER     --> DISCOURSE_SMTP_USER_NAME
+  DISCOURSE_SMTP_AUTH     --> DISCOURSE_SMTP_AUTHENTICATION
+  DISCOURSE_SMTP_PROTOCOL --> DISCOURSE_SMTP_ENABLE_START_TLS (takes a boolean true/false, not the old tls/ssl value, so translate it rather than copying it straight across)
+
+** WARNING B: undeploy before deploy 
+
+it is necessary to `abra app undeploy` your old discourse app before deploying this version. otherwise the database will get killed and be in a bad state before the migration. 
+this was a non-fatal error in testing, but still a huge pain. 
+
+`abra app undeploy YOURDOMAIN` # cleaning stops your discourse
+`abra app deploy YOURDOMAIN` # with the new version 
+
+** WARNING C: install user
+
+if your deployment's database has an "install user" other than `postgres`
+(some older deployments do), you must set the POSTGRES_USER env var in your .env
+for this migration, otherwise the postgres upgrade aborts with an install-user
+mismatch.
+
+Check your old deployment's install user before upgrading (if this command returns postgres, then you do not need to set this env):
+
+  abra app run YOURAPPDOMAIN db -- psql -U discourse -tAc 'select rolname from pg_roles where oid = 10'