Merge branch 'develop' of github.com:matrix-org/synapse into anoa/public_rooms_federate

7 files changed, 255 insertions, 26 deletions

diff --git a/contrib/docker/docker-compose.yml b/contrib/docker/docker-compose.yml
index 3a8dfbae34..1e4ee43758 100644
--- a/contrib/docker/docker-compose.yml
+++ b/contrib/docker/docker-compose.yml
@@ -6,9 +6,11 @@ version: '3'
 services:
 
   synapse:
-    build: ../..
+    build:
+        context: ../..
+        dockerfile: docker/Dockerfile
     image: docker.io/matrixdotorg/synapse:latest
-    # Since snyapse does not retry to connect to the database, restart upon
+    # Since synapse does not retry to connect to the database, restart upon
     # failure
     restart: unless-stopped
     # See the readme for a full documentation of the environment settings
@@ -35,7 +37,7 @@ services:
     labels:
       - traefik.enable=true
       - traefik.frontend.rule=Host:my.matrix.Host
-      - traefik.port=8448
+      - traefik.port=8008
 
   db:
     image: docker.io/postgres:10-alpine
@@ -47,4 +49,4 @@ services:
       # You may store the database tables in a local folder..
       - ./schemas:/var/lib/postgresql/data
       # .. or store them on some high performance storage for better results
-      # - /path/to/ssd/storage:/var/lib/postfesql/data
+      # - /path/to/ssd/storage:/var/lib/postgresql/data
diff --git a/contrib/prometheus/README b/contrib/prometheus/README.md
index 7b733172e6..e646cb7ea7 100644
--- a/contrib/prometheus/README
+++ b/contrib/prometheus/README.md
@@ -6,8 +6,10 @@ To use it, first install prometheus by following the instructions at
   http://prometheus.io/
 
 ### for Prometheus v1
+
 Add a new job to the main prometheus.conf file:
 
+```yaml
   job: {
     name: "synapse"
 
@@ -15,10 +17,12 @@ Add a new job to the main prometheus.conf file:
       target: "http://SERVER.LOCATION.HERE:PORT/_synapse/metrics"
     }
   }
+```
 
 ### for Prometheus v2
 Add a new job to the main prometheus.yml file:
 
+```yaml
   - job_name: "synapse"
     metrics_path: "/_synapse/metrics"
     # when endpoint uses https:
@@ -26,11 +30,14 @@ Add a new job to the main prometheus.yml file:
 
     static_configs:
     - targets: ['SERVER.LOCATION:PORT']
+```
 
 To use `synapse.rules` add
 
+```yaml
     rule_files:
       - "/PATH/TO/synapse-v2.rules"
+```
 
 Metrics are disabled by default when running synapse; they must be enabled
 with the 'enable-metrics' option, either in the synapse config file or as a
diff --git a/contrib/purge_api/README.md b/contrib/purge_api/README.md
new file mode 100644
index 0000000000..000bf35ca7
--- /dev/null
+++ b/contrib/purge_api/README.md
@@ -0,0 +1,16 @@
+Purge history API examples
+==========================
+
+# `purge_history.sh`
+
+A bash file, that uses the [purge history API](/docs/admin_api/README.rst) to 
+purge all messages in a list of rooms up to a certain event. You can select a 
+timeframe or a number of messages that you want to keep in the room.
+
+Just configure the variables DOMAIN, ADMIN, ROOMS_ARRAY and TIME at the top of
+the script.
+
+# `purge_remote_media.sh`
+
+A bash file, that uses the [purge history API](/docs/admin_api/README.rst) to 
+purge all old cached remote media.
diff --git a/contrib/purge_api/purge_history.sh b/contrib/purge_api/purge_history.sh
new file mode 100644
index 0000000000..e7dd5d6468
--- /dev/null
+++ b/contrib/purge_api/purge_history.sh
@@ -0,0 +1,141 @@
+#!/bin/bash
+
+# this script will use the api:
+#    https://github.com/matrix-org/synapse/blob/master/docs/admin_api/purge_history_api.rst
+# 
+# It will purge all messages in a list of rooms up to a cetrain event
+
+###################################################################################################
+# define your domain and admin user
+###################################################################################################
+# add this user as admin in your home server:
+DOMAIN=yourserver.tld
+# add this user as admin in your home server:
+ADMIN="@you_admin_username:$DOMAIN"
+
+API_URL="$DOMAIN:8008/_matrix/client/r0"
+
+###################################################################################################
+#choose the rooms to prune old messages from (add a free comment at the end)
+###################################################################################################
+# the room_id's you can get e.g. from your Riot clients "View Source" button on each message
+ROOMS_ARRAY=(
+'!DgvjtOljKujDBrxyHk:matrix.org#riot:matrix.org'
+'!QtykxKocfZaZOUrTwp:matrix.org#Matrix HQ'
+)
+
+# ALTERNATIVELY:
+# you can select all the rooms that are not encrypted and loop over the result:
+# SELECT room_id FROM rooms WHERE room_id NOT IN (SELECT DISTINCT room_id FROM events WHERE type ='m.room.encrypted')
+# or
+# select all rooms with at least 100 members:
+# SELECT q.room_id FROM (select count(*) as numberofusers, room_id FROM current_state_events WHERE type ='m.room.member'
+#   GROUP BY room_id) AS q LEFT JOIN room_aliases a ON q.room_id=a.room_id WHERE q.numberofusers > 100 ORDER BY numberofusers desc
+
+###################################################################################################
+# evaluate the EVENT_ID before which should be pruned
+###################################################################################################
+# choose a time before which the messages should be pruned:
+TIME='12 months ago'
+# ALTERNATIVELY:
+# a certain time:
+# TIME='2016-08-31 23:59:59'
+
+# creates a timestamp from the given time string:
+UNIX_TIMESTAMP=$(date +%s%3N --date='TZ="UTC+2" '"$TIME")
+
+# ALTERNATIVELY:
+# prune all messages that are older than 1000 messages ago:
+# LAST_MESSAGES=1000
+# SQL_GET_EVENT="SELECT event_id from events WHERE type='m.room.message' AND room_id ='$ROOM' ORDER BY received_ts DESC LIMIT 1 offset $(($LAST_MESSAGES - 1))"
+
+# ALTERNATIVELY:
+# select the EVENT_ID manually:
+#EVENT_ID='$1471814088343495zpPNI:matrix.org' # an example event from 21st of Aug 2016 by Matthew
+
+###################################################################################################
+# make the admin user a server admin in the database with
+###################################################################################################
+# psql -A -t --dbname=synapse -c "UPDATE users SET admin=1 WHERE name LIKE '$ADMIN'"
+
+###################################################################################################
+# database function
+###################################################################################################
+sql (){
+  # for sqlite3:
+  #sqlite3 homeserver.db "pragma busy_timeout=20000;$1" | awk '{print $2}'
+  # for postgres:
+  psql -A -t --dbname=synapse -c "$1" | grep -v 'Pager'
+}
+
+###################################################################################################
+# get an access token
+###################################################################################################
+# for example externally by watching Riot in your browser's network inspector
+# or internally on the server locally, use this:
+TOKEN=$(sql "SELECT token FROM access_tokens WHERE user_id='$ADMIN' ORDER BY id DESC LIMIT 1")
+AUTH="Authorization: Bearer $TOKEN"
+
+###################################################################################################
+# check, if your TOKEN works. For example this works: 
+###################################################################################################
+# $ curl --header "$AUTH" "$API_URL/rooms/$ROOM/state/m.room.power_levels" 
+
+###################################################################################################
+# finally start pruning the room:
+###################################################################################################
+POSTDATA='{"delete_local_events":"true"}' # this will really delete local events, so the messages in the room really disappear unless they are restored by remote federation
+
+for ROOM in "${ROOMS_ARRAY[@]}"; do
+    echo "########################################### $(date) ################# "
+    echo "pruning room: $ROOM ..."
+    ROOM=${ROOM%#*}
+    #set -x
+    echo "check for alias in db..."
+    # for postgres:
+    sql "SELECT * FROM room_aliases WHERE room_id='$ROOM'"
+    echo "get event..."
+    # for postgres:
+    EVENT_ID=$(sql "SELECT event_id FROM events WHERE type='m.room.message' AND received_ts<'$UNIX_TIMESTAMP' AND room_id='$ROOM' ORDER BY received_ts DESC LIMIT 1;")
+    if [ "$EVENT_ID" == "" ]; then
+      echo "no event $TIME"
+    else
+      echo "event: $EVENT_ID"
+      SLEEP=2
+      set -x
+      # call purge
+      OUT=$(curl --header "$AUTH" -s -d $POSTDATA POST "$API_URL/admin/purge_history/$ROOM/$EVENT_ID")
+      PURGE_ID=$(echo "$OUT" |grep purge_id|cut -d'"' -f4 )
+      if [ "$PURGE_ID" == "" ]; then
+        # probably the history purge is already in progress for $ROOM
+        : "continuing with next room"
+      else
+        while : ; do
+          # get status of purge and sleep longer each time if still active
+          sleep $SLEEP
+          STATUS=$(curl --header "$AUTH" -s GET "$API_URL/admin/purge_history_status/$PURGE_ID" |grep status|cut -d'"' -f4)
+          : "$ROOM --> Status: $STATUS"
+          [[ "$STATUS" == "active" ]] || break 
+          SLEEP=$((SLEEP + 1))
+        done 
+      fi
+      set +x
+      sleep 1
+    fi  
+done
+
+
+###################################################################################################
+# additionally
+###################################################################################################
+# to benefit from pruning large amounts of data, you need to call VACUUM to free the unused space.
+# This can take a very long time (hours) and the client have to be stopped while you do so:
+# $ synctl stop
+# $ sqlite3 -line homeserver.db "vacuum;"
+# $ synctl start
+
+# This could be set, so you don't need to prune every time after deleting some rows:
+# $ sqlite3 homeserver.db "PRAGMA auto_vacuum = FULL;"
+# be cautious, it could make the database somewhat slow if there are a lot of deletions
+
+exit
diff --git a/contrib/purge_api/purge_remote_media.sh b/contrib/purge_api/purge_remote_media.sh
new file mode 100644
index 0000000000..99c07c663d
--- /dev/null
+++ b/contrib/purge_api/purge_remote_media.sh
@@ -0,0 +1,54 @@
+#!/bin/bash
+
+DOMAIN=yourserver.tld
+# add this user as admin in your home server:
+ADMIN="@you_admin_username:$DOMAIN"
+
+API_URL="$DOMAIN:8008/_matrix/client/r0"
+
+# choose a time before which the messages should be pruned:
+# TIME='2016-08-31 23:59:59'
+TIME='12 months ago'
+
+# creates a timestamp from the given time string:
+UNIX_TIMESTAMP=$(date +%s%3N --date='TZ="UTC+2" '"$TIME")
+
+
+###################################################################################################
+# database function
+###################################################################################################
+sql (){
+  # for sqlite3:
+  #sqlite3 homeserver.db "pragma busy_timeout=20000;$1" | awk '{print $2}'
+  # for postgres:
+  psql -A -t --dbname=synapse -c "$1" | grep -v 'Pager'
+}
+
+###############################################################################
+# make the admin user a server admin in the database with
+###############################################################################
+# sql "UPDATE users SET admin=1 WHERE name LIKE '$ADMIN'"
+
+###############################################################################
+# get an access token
+###############################################################################
+# for example externally by watching Riot in your browser's network inspector
+# or internally on the server locally, use this:
+TOKEN=$(sql "SELECT token FROM access_tokens WHERE user_id='$ADMIN' ORDER BY id DESC LIMIT 1")
+
+###############################################################################
+# check, if your TOKEN works. For example this works: 
+###############################################################################
+# curl --header "Authorization: Bearer $TOKEN" "$API_URL/rooms/$ROOM/state/m.room.power_levels"
+
+###############################################################################
+# optional check size before
+###############################################################################
+# echo calculate used storage before ...
+# du -shc ../.synapse/media_store/*
+
+###############################################################################
+# finally start pruning media:
+###############################################################################
+set -x # for debugging the generated string
+curl --header "Authorization: Bearer $TOKEN" -v POST "$API_URL/admin/purge_media_cache/?before_ts=$UNIX_TIMESTAMP"
diff --git a/contrib/systemd/matrix-synapse.service b/contrib/systemd/matrix-synapse.service
new file mode 100644
index 0000000000..efb157e941
--- /dev/null
+++ b/contrib/systemd/matrix-synapse.service
@@ -0,0 +1,31 @@
+# Example systemd configuration file for synapse. Copy into
+#    /etc/systemd/system/, update the paths if necessary, then:
+#
+#    systemctl enable matrix-synapse
+#    systemctl start matrix-synapse
+#
+# This assumes that Synapse has been installed in a virtualenv in
+# /opt/synapse/env.
+#
+# **NOTE:** This is an example service file that may change in the future. If you
+# wish to use this please copy rather than symlink it.
+
+[Unit]
+Description=Synapse Matrix homeserver
+
+[Service]
+Type=simple
+Restart=on-abort
+
+User=synapse
+Group=nogroup
+
+WorkingDirectory=/opt/synapse
+ExecStart=/opt/synapse/env/bin/python -m synapse.app.homeserver --config-path=/opt/synapse/homeserver.yaml
+
+# adjust the cache factor if necessary
+# Environment=SYNAPSE_CACHE_FACTOR=2.0
+
+[Install]
+WantedBy=multi-user.target
+
diff --git a/contrib/systemd/synapse.service b/contrib/systemd/synapse.service
deleted file mode 100644
index b81ce3915d..0000000000
--- a/contrib/systemd/synapse.service
+++ /dev/null
@@ -1,22 +0,0 @@
-# This assumes that Synapse has been installed as a system package
-# (e.g. https://www.archlinux.org/packages/community/any/matrix-synapse/ for ArchLinux)
-# rather than in a user home directory or similar under virtualenv.
-
-# **NOTE:** This is an example service file that may change in the future. If you
-# wish to use this please copy rather than symlink it.
-
-[Unit]
-Description=Synapse Matrix homeserver
-
-[Service]
-Type=simple
-User=synapse
-Group=synapse
-WorkingDirectory=/var/lib/synapse
-ExecStart=/usr/bin/python2.7 -m synapse.app.homeserver --config-path=/etc/synapse/homeserver.yaml
-ExecStop=/usr/bin/synctl stop /etc/synapse/homeserver.yaml
-# EnvironmentFile=-/etc/sysconfig/synapse  # Can be used to e.g. set SYNAPSE_CACHE_FACTOR 
-
-[Install]
-WantedBy=multi-user.target
-