add run_compressor command

Reviewed-on: #55

.env.sample

@@ -199,6 +199,14 @@ RETENTION_MAX_LIFETIME=4w
 #WEB_CLIENT_LOCATION=https://element-web.example.com
 
 
+## State compression (reduces database bloat from federation)
+## Runs synapse_auto_compressor daily, built from source on first start
+#COMPOSE_FILE="$COMPOSE_FILE:compose.compress-state.yml"
+# See https://github.com/matrix-org/rust-synapse-compress-state#running-options
+#STATE_COMPRESS_CHUNK_SIZE=500
+#STATE_COMPRESS_CHUNKS=100
+#STATE_COMPRESS_SCHEDULE=0 3 * * *
+
 ## Admin interface at /admin
 #COMPOSE_FILE="$COMPOSE_FILE:compose.admin.yml"
 #ADMIN_INTERFACE_ENABLED=1

README.md

@@ -52,6 +52,9 @@ For all Bridges:
 - include the registration in synapse, e.g. `APP_SERVICE_CONFIGS="[\"/telegram-data/registration.yaml\"]"`
 - and set yourself as admin, e.g.: `TELEGRAM_BRIDGE_PERMISSIONS="{ \"*\": \"relaybot\", \"@akadmin:example.com\": \"admin\"}"`
 
+> [!IMPORTANT]
+> The shared secret authenticator may break when matrix-synapse uses a newer python version with an error stating something like "module not found". You have to fix the path in the compose.shared_secret_auth.yml like [here](https://git.coopcloud.tech/coop-cloud/matrix-synapse/commit/3d1350533079ce1ad3bea92039fe003684589b95)
+
 ### Telegram bridging
 
 You need to get your bot setup on the telegram side first by creating a [telegram app](https://my.telegram.org/apps) and a [telegram bot](https://docs.mau.fi/bridges/python/telegram/relay-bot.html#setup) and have these values:

abra.sh

@@ -1,15 +1,188 @@
 export DISCORD_BRIDGE_YAML_VERSION=v2
 export ENTRYPOINT_CONF_VERSION=v3
-export HOMESERVER_YAML_VERSION=v32
+export HOMESERVER_YAML_VERSION=v35
 export LOG_CONFIG_VERSION=v2
 export SHARED_SECRET_AUTH_VERSION=v2
 export SIGNAL_BRIDGE_YAML_VERSION=v6
 export TELEGRAM_BRIDGE_YAML_VERSION=v6
-export NGINX_CONFIG_VERSION=v8
+export NGINX_CONFIG_VERSION=v12
 export WK_SERVER_VERSION=v1
 export WK_CLIENT_VERSION=v1
-export PG_BACKUP_VERSION=v1
+export PG_BACKUP_VERSION=v2
 export ADMIN_CONFIG_VERSION=v1
+export COMPRESS_STATE_ENTRYPOINT_VERSION=v5
+
+# See https://levans.fr/shrink-synapse-database.html
+db_size() {
+    echo "=== Database size ==="
+    psql -U synapse -d synapse -c "SELECT pg_size_pretty(pg_database_size('synapse')) AS db_size;"
+    echo ""
+    echo "=== Top 10 largest tables ==="
+    psql -U synapse -d synapse -c "
+        SELECT nspname || '.' || relname AS table,
+               pg_size_pretty(pg_total_relation_size(C.oid)) AS total_size
+        FROM pg_class C
+        LEFT JOIN pg_namespace N ON (N.oid = C.relnamespace)
+        WHERE nspname NOT IN ('pg_catalog', 'information_schema')
+        ORDER BY pg_total_relation_size(C.oid) DESC
+        LIMIT 10;"
+}
+
+state_bloat() {
+    echo "=== Rooms with most state bloat ==="
+    psql -U synapse -d synapse -c "
+        SELECT room_id, count(*) AS state_entries
+        FROM state_groups_state
+        GROUP BY room_id
+        ORDER BY state_entries DESC
+        LIMIT 20;"
+}
+
+empty_rooms() {
+    echo "=== Rooms with no local members ==="
+    psql -U synapse -d synapse -c "
+        SELECT room_id, room_version
+        FROM rooms
+        WHERE room_id NOT IN (
+            SELECT room_id FROM local_current_membership WHERE membership = 'join'
+        );"
+}
+
+reindex() {
+    echo "WARNING: REINDEX locks tables. Synapse should be stopped before running this."
+    echo "Running REINDEX on synapse database..."
+    psql -U synapse -d synapse -c "REINDEX (VERBOSE) DATABASE synapse;"
+    echo "REINDEX complete."
+    psql -U synapse -d synapse -c "SELECT pg_size_pretty(pg_database_size('synapse')) AS db_size;"
+}
+
+# Run via: abra app cmd <domain> compress-state run_compressor
+run_compressor() {
+    CHUNK_SIZE="${1:-${STATE_COMPRESS_CHUNK_SIZE:-500}}"
+    CHUNKS="${2:-${STATE_COMPRESS_CHUNKS:-100}}"
+    DB_PASS=$(cat /run/secrets/db_password)
+    echo "Running synapse_auto_compressor (chunk_size=$CHUNK_SIZE, chunks=$CHUNKS)..."
+    /build/synapse_auto_compressor \
+        -p "postgresql://synapse:${DB_PASS}@db:5432/synapse" \
+        -c "$CHUNK_SIZE" -n "$CHUNKS"
+}
+
+vacuum_full() {
+    echo "WARNING: VACUUM FULL locks tables and requires temporary disk space."
+    echo "Synapse should be stopped before running this."
+    echo "Running VACUUM FULL on synapse database..."
+    psql -U synapse -d synapse -c "VACUUM FULL;"
+    echo "VACUUM FULL complete."
+    psql -U synapse -d synapse -c "SELECT pg_size_pretty(pg_database_size('synapse')) AS db_size;"
+}
+
+# Purge commands — run via: abra app cmd <domain> app <command>
+# These use the Synapse admin API and require an admin access token.
+
+register_admin() {
+    USER="${1}"
+    PASS="${2}"
+    if [ -z "$USER" ] || [ -z "$PASS" ]; then
+        echo "Usage: register_admin <username> <password>"
+        return 1
+    fi
+    register_new_matrix_user -u "$USER" -p "$PASS" -a -c /data/homeserver.yaml http://localhost:8008
+}
+
+get_token() {
+    USER="${1}"
+    PASS="${2}"
+    if [ -z "$USER" ] || [ -z "$PASS" ]; then
+        echo "Usage: get_token <username> <password>"
+        echo "Returns an admin access token for use with purge commands."
+        return 1
+    fi
+    curl -s -X POST "http://localhost:8008/_matrix/client/r0/login" \
+        -H "Content-Type: application/json" \
+        -d "{\"type\":\"m.login.password\",\"user\":\"$USER\",\"password\":\"$PASS\"}" \
+        | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('access_token', d.get('error', 'unknown error')))"
+}
+
+purge_remote_media() {
+    DAYS="${1:-30}"
+    TOKEN="${2}"
+    if [ -z "$TOKEN" ]; then
+        echo "Usage: purge_remote_media <days> <admin_token>"
+        return 1
+    fi
+    BEFORE_TS=$(( $(date +%s) * 1000 - DAYS * 86400000 ))
+    echo "Purging remote media older than $DAYS days..."
+    curl -s -X POST "http://localhost:8008/_synapse/admin/v1/purge_media_cache?before_ts=$BEFORE_TS" \
+        -H "Authorization: Bearer $TOKEN"
+    echo ""
+}
+
+purge_room() {
+    ROOM_ID="${1}"
+    TOKEN="${2}"
+    if [ -z "$ROOM_ID" ] || [ -z "$TOKEN" ]; then
+        echo "Usage: purge_room <room_id> <admin_token>"
+        return 1
+    fi
+    echo "Purging room $ROOM_ID..."
+    curl -s -X DELETE "http://localhost:8008/_synapse/admin/v1/rooms/$ROOM_ID" \
+        -H "Authorization: Bearer $TOKEN" \
+        -H "Content-Type: application/json" \
+        -d '{"purge": true}'
+    echo ""
+}
+
+purge_history() {
+    ROOM_ID="${1}"
+    DAYS="${2:-90}"
+    TOKEN="${3}"
+    if [ -z "$ROOM_ID" ] || [ -z "$TOKEN" ]; then
+        echo "Usage: purge_history <room_id> <days> <admin_token>"
+        return 1
+    fi
+    BEFORE_TS=$(( $(date +%s) * 1000 - DAYS * 86400000 ))
+    echo "Purging history older than $DAYS days from $ROOM_ID..."
+    curl -s -X POST "http://localhost:8008/_synapse/admin/v1/purge_history/$ROOM_ID" \
+        -H "Authorization: Bearer $TOKEN" \
+        -H "Content-Type: application/json" \
+        -d "{\"purge_up_to_ts\": $BEFORE_TS}"
+    echo ""
+}
+
+purge_empty_rooms() {
+    TOKEN="${1}"
+    if [ -z "$TOKEN" ]; then
+        echo "Usage: purge_empty_rooms <admin_token>"
+        return 1
+    fi
+    echo "Fetching rooms with no local members..."
+    ROOMS=$(curl -s "http://localhost:8008/_synapse/admin/v1/rooms?limit=1000" \
+        -H "Authorization: Bearer $TOKEN" \
+        | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+for r in data.get('rooms', []):
+    if r.get('joined_local_members', 0) == 0:
+        print(r['room_id'])
+")
+    COUNT=$(echo "$ROOMS" | grep -c '.' || true)
+    echo "Found $COUNT empty rooms."
+    if [ "$COUNT" -eq 0 ]; then
+        echo "Nothing to purge."
+        return 0
+    fi
+    echo "$ROOMS"
+    echo ""
+    echo "Purging..."
+    for ROOM_ID in $ROOMS; do
+        echo "  Purging $ROOM_ID"
+        curl -s -X DELETE "http://localhost:8008/_synapse/admin/v1/rooms/$ROOM_ID" \
+            -H "Authorization: Bearer $TOKEN" \
+            -H "Content-Type: application/json" \
+            -d '{"purge": true}' > /dev/null
+    done
+    echo "Done."
+}
 
 set_admin () {
     admin=akadmin

compose.admin.yml

@@ -3,13 +3,13 @@ version: "3.8"
 
 services:
   admin:
-    image: awesometechnologies/synapse-admin:0.11.1
+    image: awesometechnologies/synapse-admin:0.11.4
     networks:
       - proxy
     deploy:
       labels:
         - "traefik.enable=true"
-        - "traefik.docker.network=proxy"
+        - "traefik.swarm.network=proxy"
         - "traefik.http.services.${STACK_NAME}_admin.loadbalancer.server.port=80"
         - "traefik.http.routers.${STACK_NAME}_admin.rule=Host(`${DOMAIN}`${EXTRA_DOMAINS})&&PathPrefix(`/admin`)"
         - "traefik.http.routers.${STACK_NAME}_admin.entrypoints=web-secure"

compose.compress-state.yml

@@ -0,0 +1,31 @@
+version: "3.8"
+
+services:
+  compress-state:
+    image: rust:1-alpine
+    entrypoint: /compress_state_entrypoint.sh
+    environment:
+      - STATE_COMPRESS_CHUNK_SIZE=${STATE_COMPRESS_CHUNK_SIZE:-500}
+      - STATE_COMPRESS_CHUNKS=${STATE_COMPRESS_CHUNKS:-100}
+      - STATE_COMPRESS_SCHEDULE=${STATE_COMPRESS_SCHEDULE:-0 3 * * *}
+    secrets:
+      - db_password
+    configs:
+      - source: compress_entrypoint
+        target: /compress_state_entrypoint.sh
+        mode: 0555
+    volumes:
+      - compress_state_build:/build
+    networks:
+      - internal
+    deploy:
+      restart_policy:
+        condition: on-failure
+
+volumes:
+  compress_state_build:
+
+configs:
+  compress_entrypoint:
+    name: ${STACK_NAME}_compress_ep_${COMPRESS_STATE_ENTRYPOINT_VERSION}
+    file: compress_state_entrypoint.sh

compose.shared_secret_auth.yml

@@ -9,7 +9,7 @@ services:
       - shared_secret_auth
     configs:
       - source: shared_secret_auth
-        target: /usr/local/lib/python3.12/site-packages/shared_secret_authenticator.py
+        target: /usr/local/lib/python3.13/site-packages/shared_secret_authenticator.py
 
 configs:
   shared_secret_auth:

compose.signal.yml

@@ -10,7 +10,7 @@ services:
       - signal-data:/signal-data
 
   signalbridge:
-    image: dock.mau.dev/mautrix/signal:v0.8.4
+    image: dock.mau.dev/mautrix/signal:v0.8.7
     depends_on:
       - signaldb
     configs:

compose.telegram.yml

@@ -10,7 +10,7 @@ services:
       - telegram-data:/telegram-data
 
   telegrambridge:
-    image: dock.mau.dev/mautrix/telegram:v0.15.2
+    image: dock.mau.dev/mautrix/telegram:v0.15.3
     depends_on:
       - telegramdb
     configs:

compose.yml

@@ -3,7 +3,7 @@ version: "3.8"
 
 services:
   web:
-    image: nginx:1.29.0
+    image: nginx:1.29.6
     networks:
       - proxy
       - internal
@@ -12,6 +12,7 @@ services:
       - STACK_NAME
       - NGINX_ACCESS_LOG_LOCATION
       - NGINX_ERROR_LOG_LOCATION
+      - MAX_UPLOAD_SIZE
     configs:
       - source: nginx_config
         target: /etc/nginx/nginx.conf
@@ -21,7 +22,7 @@ services:
         target: /var/www/.well-known/matrix/client
     deploy:
       restart_policy:
-        condition: on-failure
+        condition: any
       labels:
         - "traefik.enable=true"
         - "traefik.http.services.${STACK_NAME}.loadbalancer.server.port=80"
@@ -30,12 +31,13 @@ services:
         - "traefik.http.routers.${STACK_NAME}.tls.certresolver=${LETS_ENCRYPT_ENV}"
     healthcheck:
       test: curl -f http://${STACK_NAME}_app:8008/health || exit 1
-      interval: 20s
+      interval: 30s
       timeout: 15s
-      retries: 20
+      retries: 90
+      start_period: 2m
 
   app:
-    image: "matrixdotorg/synapse:v1.133.0"
+    image: "matrixdotorg/synapse:v1.149.1"
     volumes:
       - "data:/data"
     secrets:
@@ -104,34 +106,33 @@ services:
       restart_policy:
         condition: on-failure
       labels:
-        - "coop-cloud.${STACK_NAME}.version=6.7.0+v1.133.0"
-        - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-120}"
+        - "coop-cloud.${STACK_NAME}.version=7.0.2+v1.149.1"
+        - "coop-cloud.${STACK_NAME}.timeout=${TIMEOUT}"
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8008/health"]
       interval: 30s
       timeout: 10s
-      retries: 10
+      retries: 30
       start_period: 1m
 
   db:
-    image: postgres:13-alpine
+    image: pgautoupgrade/pgautoupgrade:17-alpine
     secrets:
       - db_password
     environment:
       - LC_COLLATE=C
       - LC_CTYPE=C
       - POSTGRES_DB=synapse
-      - POSTGRES_INITDB_ARGS="-E \"UTF8\""
+      - POSTGRES_INITDB_ARGS=-E UTF8
       - POSTGRES_PASSWORD_FILE=/run/secrets/db_password
       - POSTGRES_USER=synapse
       - DOMAIN
     networks:
       - internal
     healthcheck:
-      test: ["CMD", "pg_isready", "-U", "synapse"]
       interval: 30s
       timeout: 10s
-      retries: 10
+      retries: 20
       start_period: 1m
     volumes:
       - postgres:/var/lib/postgresql/data
@@ -140,11 +141,11 @@ services:
         backupbot.backup: "${ENABLE_BACKUPS:-true}"
         backupbot.backup.pre-hook: "/pg_backup.sh backup"
         backupbot.backup.volumes.postgres.path: "backup.sql"
-        backupbot.restore.post-hook: '/pg_backup.sh restore'
+        backupbot.restore.post-hook: "/pg_backup.sh restore"
     configs:
-        - source: pg_backup
-          target: /pg_backup.sh
-          mode: 0555
+      - source: pg_backup
+        target: /pg_backup.sh
+        mode: 0555
 
 volumes:
   data:

compress_state_entrypoint.sh

@@ -0,0 +1,46 @@
+#!/bin/sh
+set -e
+
+BINARY="/build/synapse_auto_compressor"
+REPO_DIR="/build/rust-synapse-compress-state"
+DB_PASS=$(cat /run/secrets/db_password)
+CONN="postgresql://synapse:${DB_PASS}@db:5432/synapse"
+CHUNK_SIZE="${STATE_COMPRESS_CHUNK_SIZE:-500}"
+CHUNKS="${STATE_COMPRESS_CHUNKS:-100}"
+SCHEDULE="${STATE_COMPRESS_SCHEDULE:-0 3 * * *}"
+
+# Build from source if binary doesn't exist
+if [ ! -f "$BINARY" ]; then
+  echo "[compress-state] Binary not found, building from source..."
+  apk add --no-cache git openssl-dev openssl-libs-static perl make musl-dev jemalloc-dev
+  rm -rf "$REPO_DIR"
+  git clone https://github.com/matrix-org/rust-synapse-compress-state "$REPO_DIR"
+  cd "$REPO_DIR"
+  cargo build --release -p synapse_auto_compressor
+  cp target/release/synapse_auto_compressor "$BINARY"
+  echo "[compress-state] Build complete"
+  # Clean up source to save space
+  rm -rf "$REPO_DIR"
+else
+  echo "[compress-state] Using cached binary"
+fi
+
+# Run once at startup
+echo "[compress-state] Running initial compression at $(date)"
+"$BINARY" -p "$CONN" -c "$CHUNK_SIZE" -n "$CHUNKS" || echo "[compress-state] Error: $?"
+
+# Set up cron job
+CRON_SCRIPT="/build/run_compressor.sh"
+cat > "$CRON_SCRIPT" <<EOF
+#!/bin/sh
+echo "[compress-state] Running at \$(date)"
+$BINARY -p "$CONN" -c $CHUNK_SIZE -n $CHUNKS || echo "[compress-state] Error: \$?"
+echo "[compress-state] Done at \$(date)"
+EOF
+chmod +x "$CRON_SCRIPT"
+
+echo "$SCHEDULE $CRON_SCRIPT" | crontab -
+echo "[compress-state] Cron scheduled: $SCHEDULE"
+
+# Run crond in the foreground
+exec crond -f -l 2

homeserver.yaml.tmpl

@@ -157,8 +157,15 @@ registration_shared_secret: {{ secret "registration" }}
 
 {{ if eq (env "AUTO_JOIN_ROOM_ENABLED") "1" }}
 # https://matrix-org.github.io/synapse/latest/usage/configuration/config_documentation.html#auto_join_rooms
+
+# AUTO_JOIN_ROOM only for backwards compatibility
+{{ if (env "AUTO_JOIN_ROOM") }}
 auto_join_rooms:
   - "{{ env "AUTO_JOIN_ROOM" }}"
+{{ else }}
+auto_join_rooms: {{ env "AUTO_JOIN_ROOM_LIST" }}
+{{ end }}
+
 {{ end }}
 
 # https://element-hq.github.io/synapse/latest/usage/configuration/config_documentation.html#session_lifetime

nginx.conf.tmpl

@@ -5,6 +5,16 @@ events {
 }
 
 http {
+
+  resolver 127.0.0.11 valid=30s ipv6=off;
+  resolver_timeout 5s;
+
+  upstream matrix_upstream {
+    zone matrix_upstream 64k;
+    server {{ env "STACK_NAME"}}_app:8008 resolve;
+    keepalive 16;
+  }
+
   server {
     listen 80;
 
@@ -14,7 +24,7 @@ http {
     server_name {{ env "DOMAIN" }};
 
     location = / {
-      proxy_pass http://{{ env "STACK_NAME"}}_app:8008;
+      proxy_pass http://matrix_upstream;
       proxy_set_header X-Forwarded-For $remote_addr;
       proxy_set_header X-Forwarded-Proto https;
       proxy_set_header Host $host;
@@ -23,7 +33,7 @@ http {
     }
     
     location ~* ^(\/_matrix|\/_synapse\/client) {
-      proxy_pass http://{{ env "STACK_NAME"}}_app:8008;
+      proxy_pass http://matrix_upstream;
       proxy_set_header X-Forwarded-For $remote_addr;
       proxy_set_header X-Forwarded-Proto https;
       proxy_set_header Host $host;
@@ -42,7 +52,7 @@ http {
       if ($http_referer !~ "^https://{{ env "DOMAIN" }}/admin/") {
         return 403;
       }
-      proxy_pass http://{{ env "STACK_NAME"}}_app:8008;
+      proxy_pass http://matrix_upstream;
       proxy_set_header X-Forwarded-For $remote_addr;
       proxy_set_header X-Forwarded-Proto https;
       proxy_set_header Host $host;

pg_backup.sh

@@ -6,7 +6,7 @@ BACKUP_FILE='/var/lib/postgresql/data/backup.sql'
 
 function backup {
   export PGPASSWORD=$(cat $POSTGRES_PASSWORD_FILE)
-  pg_dump -U ${POSTGRES_USER} ${POSTGRES_DB} > $BACKUP_FILE
+  pg_dump -U ${POSTGRES_USER} ${POSTGRES_DB} | gzip > $BACKUP_FILE
 }
 
 function restore {
@@ -25,7 +25,7 @@ function restore {
     # Recreate Database
     psql -U ${POSTGRES_USER} -d postgres -c "DROP DATABASE ${POSTGRES_DB} WITH (FORCE);" 
     createdb -U ${POSTGRES_USER} ${POSTGRES_DB}
-    psql -U ${POSTGRES_USER} -d ${POSTGRES_DB} -1 -f $BACKUP_FILE
+    gunzip -c $BACKUP_FILE | psql -U ${POSTGRES_USER} -d ${POSTGRES_DB} -1 -f -
 
     trap - EXIT INT TERM
     restore_config

release/6.7.1+v1.133.0

@@ -0,0 +1 @@
+This patch contains a critical nginx fix, to allow resolving docker internal hosts.

release/6.8.2+v1.139.2

@@ -0,0 +1 @@
+this patch is a reset to the state of the last known deploying version 6.8.0 – so better skip 6.8.1

release/7.0.0+v1.149.1

@@ -0,0 +1,2 @@
+WARNING: Backup your database!
+This upgrade switches the database image from postgres to pgautoupgrade and performs an in-place database upgrades from version 13 to 17.