From daf13107a03e5047ff30bceb57edfa76fd449eda Mon Sep 17 00:00:00 2001 From: Slavi Pantaleev Date: Fri, 21 Aug 2020 13:52:16 +0300 Subject: [PATCH] Add support for rust-synapse-compress-state --- CHANGELOG.md | 9 ++ docs/maintenance-postgres.md | 4 +- docs/maintenance-synapse.md | 87 +++++++------ roles/matrix-base/defaults/main.yml | 1 + roles/matrix-synapse/defaults/main.yml | 7 ++ roles/matrix-synapse/tasks/main.yml | 5 + .../compress_room.yml | 48 +++++++ .../rust-synapse-compress-state/main.yml | 118 ++++++++++++++++++ 8 files changed, 234 insertions(+), 45 deletions(-) create mode 100644 roles/matrix-synapse/tasks/rust-synapse-compress-state/compress_room.yml create mode 100644 roles/matrix-synapse/tasks/rust-synapse-compress-state/main.yml diff --git a/CHANGELOG.md b/CHANGELOG.md index 140c4f702..674721cbc 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,12 @@ +# 2020-08-21 + +## rust-synapse-compress-state support + +The playbook can now help you use [rust-synapse-compress-state](https://github.com/matrix-org/rust-synapse-compress-state) to compress the state groups in your Synapse database. + +See our [Compressing state with rust-synapse-compress-state](docs/maintenance-synapse.md#compressing-state-with-rust-synapse-compress-state) documentation page to get started. + + # 2020-07-22 ## Synapse Admin support diff --git a/docs/maintenance-postgres.md b/docs/maintenance-postgres.md index da62509b0..6f599de19 100644 --- a/docs/maintenance-postgres.md +++ b/docs/maintenance-postgres.md @@ -22,6 +22,8 @@ If you are using an [external Postgres server](configuring-playbook-external-pos ## Vacuuming PostgreSQL +Deleting lots data from Postgres does not make it release disk space, until you perform a `VACUUM` operation. + To perform a `FULL` Postgres [VACUUM](https://www.postgresql.org/docs/current/sql-vacuum.html), run the playbook with `--tags=run-postgres-vacuum`. Example: @@ -42,7 +44,7 @@ docker run \ --rm \ --network=matrix \ --env-file=/matrix/postgres/env-postgres-psql \ -postgres:12.1-alpine \ +postgres:12.4-alpine \ pg_dumpall -h matrix-postgres \ | gzip -c \ > /postgres.sql.gz diff --git a/docs/maintenance-synapse.md b/docs/maintenance-synapse.md index afbf86edc..799982990 100644 --- a/docs/maintenance-synapse.md +++ b/docs/maintenance-synapse.md @@ -9,14 +9,54 @@ Table of contents: - [Purging old data with the Purge History API](#purging-old-data-with-the-purge-history-api), for when you wish to delete in-use (but old) data from the Synapse database - [Synapse maintenance](#synapse-maintenance) - - [Purging unused data with synapse-janitor](#purging-unused-data-with-synapse-janitor) - - [Vacuuming Postgres](#vacuuming-postgres) - [Purging old data with the Purge History API](#purging-old-data-with-the-purge-history-api) - [Compressing state with rust-synapse-compress-state](#compressing-state-with-rust-synapse-compress-state) + - [Purging unused data with synapse-janitor](#purging-unused-data-with-synapse-janitor) - [Browse and manipulate the database](#browse-and-manipulate-the-database) - [Browse and manipulate the database](#browse-and-manipulate-the-database), for when you really need to take matters into your own hands + +## Purging old data with the Purge History API + +You can use the **Purge History API** to delete in-use (but old) data. + +**This is destructive** (especially for non-federated rooms), because it means **people will no longer have access to history past a certain point**. + +Synapse's [Purge History API](https://github.com/matrix-org/synapse/blob/master/docs/admin_api/purge_history_api.rst) can be used to purge on a per-room basis. + +To make use of this API, **you'll need an admin access token** first. You can find your access token in the setting of some clients (like Element). +Alternatively, you can log in and obtain a new access token like this: + +``` +curl \ +--data '{"identifier": {"type": "m.id.user", "user": "YOUR_MATRIX_USERNAME" }, "password": "YOUR_MATRIX_PASSWORD", "type": "m.login.password", "device_id": "Synapse-Purge-History-API"}' \ +https://matrix.DOMAIN/_matrix/client/r0/login +``` + +Follow the [Purge History API](https://github.com/matrix-org/synapse/blob/master/docs/admin_api/purge_history_api.rst) documentation page for the actual purging instructions. + +After deleting data, you may wish to run a [`FULL` Postgres `VACUUM`](./maintenance-postgres.md#vacuuming-postgresql). + + +## Compressing state with rust-synapse-compress-state + +[rust-synapse-compress-state](https://github.com/matrix-org/rust-synapse-compress-state) can be used to optimize some `_state` tables used by Synapse. + +This tool should be safe to use (even when Synapse is running), but it's always a good idea to [make Postgres backups](./maintenance-postgres.md#backing-up-postgresql) first. + +To ask the playbook to run rust-synapse-compress-state, execute: + +``` +ansible-playbook -i inventory/hosts setup.yml --tags=rust-synapse-compress-state +``` + +By default, all rooms with more than `100000` state group rows will be compressed. +If you need to adjust this, pass: `--extra-vars='matrix_synapse_rust_synapse_compress_state_min_state_groups_required=SOME_NUMBER_HERE'` to the command above. + +After state compression, you may wish to run a [`FULL` Postgres `VACUUM`](./maintenance-postgres.md#vacuuming-postgresql). + + ## Purging unused data with synapse-janitor **NOTE**: There are [reports](https://github.com/spantaleev/matrix-docker-ansible-deploy/issues/465) that **synapse-janitor is dangerous to use and causes database corruption**. You may wish to refrain from using it. @@ -34,50 +74,9 @@ ansible-playbook -i inventory/hosts setup.yml --tags=run-postgres-synapse-janito **Note**: this will automatically stop Synapse temporarily and restart it later. - -### Vacuuming Postgres - Running synapse-janitor potentially deletes a lot of data from the Postgres database. -However, disk space only ever gets released after a [`FULL` Postgres `VACUUM`](./maintenance-postgres.md#vacuuming-postgresql). +You may wish to run a [`FULL` Postgres `VACUUM`](./maintenance-postgres.md#vacuuming-postgresql) after that. -It's easiest if you ask the playbook to run both synapse-janitor and a `VACUUM FULL` in one call: - -```bash -ansible-playbook -i inventory/hosts setup.yml --tags=run-postgres-synapse-janitor,run-postgres-vacuum,start -``` - -**Note**: this will automatically stop Synapse temporarily and restart it later. You'll also need plenty of available disk space in your Postgres data directory (usually `/matrix/postgres/data`). - - -## Purging old data with the Purge History API - -If [purging unused and unreachable data](#purging-unused-data-with-synapse-janitor) is not enough for you, you can start deleting in-use (but old) data. - -**This is destructive** (especially for non-federated rooms), because it means **people will no longer have access to history past a certain point**. - -Synapse provides a [Purge History API](https://github.com/matrix-org/synapse/blob/master/docs/admin_api/purge_history_api.rst) that you can use to purge on a per-room basis. - -To make use of this API, **you'll need an admin access token** first. You can find your access token in the setting of some clients (like Element). -Alternatively, you can log in and obtain a new access token like this: - -``` -curl \ ---data '{"identifier": {"type": "m.id.user", "user": "YOUR_MATRIX_USERNAME" }, "password": "YOUR_MATRIX_PASSWORD", "type": "m.login.password", "device_id": "Synapse-Purge-History-API"}' \ -https://matrix.DOMAIN/_matrix/client/r0/login -``` - -Follow the [Purge History API](https://github.com/matrix-org/synapse/blob/master/docs/admin_api/purge_history_api.rst) documentation page for the actual purging instructions. - -Don't forget that disk space only ever gets released after a [`FULL` Postgres `VACUUM`](./maintenance-postgres.md#vacuuming-postgresql) - something the playbook can help you with. - - -## Compressing state with rust-synapse-compress-state - -[rust-synapse-compress-state](https://github.com/matrix-org/rust-synapse-compress-state) can be used to optimize some `_state` tables used by Synapse. - -Unfortunately, at this time the playbook can't help you run this **experimental tool**. - -Since it's also experimental, you may wish to stay away from it, or at least [make Postgres backups](./maintenance-postgres.md#backing-up-postgresql) first. ## Browse and manipulate the database diff --git a/roles/matrix-base/defaults/main.yml b/roles/matrix-base/defaults/main.yml index 9ab8bb3ce..c70781b31 100644 --- a/roles/matrix-base/defaults/main.yml +++ b/roles/matrix-base/defaults/main.yml @@ -101,6 +101,7 @@ run_postgres_vacuum: true run_synapse_register_user: true run_synapse_update_user_password: true run_synapse_import_media_store: true +run_synapse_rust_synapse_compress_state: true run_setup: true run_self_check: true run_start: true diff --git a/roles/matrix-synapse/defaults/main.yml b/roles/matrix-synapse/defaults/main.yml index 8b2186a59..24dee1e20 100644 --- a/roles/matrix-synapse/defaults/main.yml +++ b/roles/matrix-synapse/defaults/main.yml @@ -364,6 +364,13 @@ matrix_synapse_redaction_retention_period: 7d matrix_synapse_user_ips_max_age: 28d + +matrix_synapse_rust_synapse_compress_state_docker_image: "devture/rust-synapse-compress-state:v0.1.0" +matrix_synapse_rust_synapse_compress_state_docker_image_force_pull: "{{ matrix_synapse_rust_synapse_compress_state_docker_image.endswith(':latest') }}" + +matrix_synapse_rust_synapse_compress_state_base_path: "{{ matrix_base_data_path }}/rust-synapse-compress-state" + + # Default Synapse configuration template which covers the generic use case. # You can customize it by controlling the various variables inside it. # diff --git a/roles/matrix-synapse/tasks/main.yml b/roles/matrix-synapse/tasks/main.yml index 585a95bbb..48e72acec 100644 --- a/roles/matrix-synapse/tasks/main.yml +++ b/roles/matrix-synapse/tasks/main.yml @@ -43,6 +43,11 @@ tags: - update-user-password +- import_tasks: "{{ role_path }}/tasks/rust-synapse-compress-state/main.yml" + when: run_synapse_rust_synapse_compress_state|bool + tags: + - rust-synapse-compress-state + - name: Mark matrix-synapse role as executed set_fact: matrix_synapse_role_executed: true diff --git a/roles/matrix-synapse/tasks/rust-synapse-compress-state/compress_room.yml b/roles/matrix-synapse/tasks/rust-synapse-compress-state/compress_room.yml new file mode 100644 index 000000000..ad7b91b4f --- /dev/null +++ b/roles/matrix-synapse/tasks/rust-synapse-compress-state/compress_room.yml @@ -0,0 +1,48 @@ +- debug: + msg: "Compressing room `{{ room_details.room_id }}` having {{ room_details.count }} state group rows" + +- name: Generate rust-synapse-compress-state room compression command + set_fact: + matrix_synapse_rust_synapse_compress_state_compress_room_command: >- + {{ matrix_host_command_docker }} run --rm --name matrix-rust-synapse-compress-state-compress-room + --user={{ matrix_user_uid }}:{{ matrix_user_gid }} + --cap-drop=ALL + --network={{ matrix_docker_network }} + -v {{ matrix_synapse_rust_synapse_compress_state_base_path }}:/work + {{ matrix_synapse_rust_synapse_compress_state_docker_image }} + /synapse-compress-state -t -o /work/state-compressor.sql + -p "host={{ matrix_synapse_database_host }} user={{ matrix_synapse_database_user }} password={{ matrix_synapse_database_password }} dbname={{ matrix_synapse_database_database }}" + -r '{{ room_details.room_id }}' + +- name: Run rust-synapse-compress-state room compression command (SQL generation) + command: "{{ matrix_synapse_rust_synapse_compress_state_compress_room_command }}" + async: "{{ matrix_synapse_rust_synapse_compress_state_compress_room_time }}" + poll: 10 + register: matrix_synapse_rust_synapse_compress_state_compress_room_command_result + +- debug: var="matrix_synapse_rust_synapse_compress_state_compress_room_command_result" + +- name: Generate Postgres compression SQL import command + set_fact: + matrix_synapse_rust_synapse_compress_state_psql_import_command: >- + {{ matrix_host_command_docker }} run --rm --name matrix-rust-synapse-compress-state-psql-import + --user={{ matrix_user_uid }}:{{ matrix_user_gid }} + --cap-drop=ALL + --network={{ matrix_docker_network }} + --env-file={{ matrix_postgres_base_path }}/env-postgres-psql + -v {{ matrix_synapse_rust_synapse_compress_state_base_path }}:/work:ro + --entrypoint=/bin/sh + {{ matrix_postgres_docker_image_latest }} + -c "cat /work/state-compressor.sql | + psql -v ON_ERROR_STOP=1 -h matrix-postgres" + +- name: Import compression SQL into Postgres + command: "{{ matrix_synapse_rust_synapse_compress_state_psql_import_command }}" + async: "{{ matrix_synapse_rust_synapse_compress_state_psql_import_time }}" + poll: 10 + register: matrix_synapse_rust_synapse_compress_state_psql_import_command_result + +- name: Clean up + file: + path: "{{ matrix_synapse_rust_synapse_compress_state_base_path }}/state-compressor.sql" + state: absent diff --git a/roles/matrix-synapse/tasks/rust-synapse-compress-state/main.yml b/roles/matrix-synapse/tasks/rust-synapse-compress-state/main.yml new file mode 100644 index 000000000..4ce02bc4c --- /dev/null +++ b/roles/matrix-synapse/tasks/rust-synapse-compress-state/main.yml @@ -0,0 +1,118 @@ +# Pre-checks + +- name: Fail if Postgres not enabled + fail: + msg: "Postgres via the matrix-postgres role is not enabled (`matrix_postgres_enabled`). Cannot use rust-synapse-compress-state." + when: "not matrix_postgres_enabled|bool" + + +# Defaults + +- name: Set matrix_synapse_rust_synapse_compress_state_find_rooms_command_wait_time, if not provided + set_fact: + matrix_synapse_rust_synapse_compress_state_find_rooms_command_wait_time: 15 + when: "matrix_synapse_rust_synapse_compress_state_find_rooms_command_wait_time|default('') == ''" + +- name: Set matrix_synapse_rust_synapse_compress_state_compress_room_time, if not provided + set_fact: + matrix_synapse_rust_synapse_compress_state_compress_room_time: 1800 + when: "matrix_synapse_rust_synapse_compress_state_compress_room_time|default('') == ''" + +- name: Set matrix_synapse_rust_synapse_compress_state_psql_import_time, if not provided + set_fact: + matrix_synapse_rust_synapse_compress_state_psql_import_time: 1800 + when: "matrix_synapse_rust_synapse_compress_state_psql_import_time|default('') == ''" + +- name: Set matrix_synapse_rust_synapse_compress_state_min_state_groups_required, if not provided + set_fact: + # The minimum number of state groups we're looking for before we consider a room eligible for compression. + # Rooms with a smaller state groups count will not be compressed. + matrix_synapse_rust_synapse_compress_state_min_state_groups_required: 100000 + when: "matrix_synapse_rust_synapse_compress_state_min_state_groups_required|default('') == ''" + + +# Actual compression work + +- name: Ensure rust-synapse-compress-state paths exist + file: + path: "{{ matrix_synapse_rust_synapse_compress_state_base_path }}" + state: directory + mode: 0750 + owner: "{{ matrix_user_username }}" + group: "{{ matrix_user_groupname }}" + +- name: Ensure rust-synapse-compress-state image is pulled + docker_image: + name: "{{ matrix_synapse_rust_synapse_compress_state_docker_image }}" + source: "{{ 'pull' if ansible_version.major > 2 or ansible_version.minor > 7 else omit }}" + force_source: "{{ matrix_synapse_rust_synapse_compress_state_docker_image_force_pull if ansible_version.major > 2 or ansible_version.minor >= 8 else omit }}" + force: "{{ omit if ansible_version.major > 2 or ansible_version.minor >= 8 else matrix_synapse_rust_synapse_compress_state_docker_image_force_pull }}" + +- name: Generate rust-synapse-compress-state room find command + set_fact: + matrix_synapse_rust_synapse_compress_state_find_rooms_command: >- + {{ matrix_host_command_docker }} run --rm --name matrix-rust-synapse-compress-state-find-rooms + --user={{ matrix_user_uid }}:{{ matrix_user_gid }} + --cap-drop=ALL + --network={{ matrix_docker_network }} + --env-file={{ matrix_postgres_base_path }}/env-postgres-psql + {{ matrix_postgres_docker_image_latest }} + psql -v ON_ERROR_STOP=1 -h matrix-postgres {{ matrix_synapse_database_database }} -c + 'SELECT array_to_json(array_agg(row_to_json (r))) FROM (SELECT room_id, count(*) AS count FROM state_groups_state GROUP BY room_id HAVING count(*) > {{ matrix_synapse_rust_synapse_compress_state_min_state_groups_required }} ORDER BY count DESC) r;' + +- name: Find rooms eligible for compression with rust-synapse-compress-state + command: "{{ matrix_synapse_rust_synapse_compress_state_find_rooms_command }}" + async: "{{ matrix_synapse_rust_synapse_compress_state_find_rooms_command_wait_time }}" + poll: 10 + register: matrix_synapse_rust_synapse_compress_state_find_rooms_command_result + +# We expect the output to be like this: +# +# "stdout_lines": [ +# " array_to_json ", +# "----------------------------------------------------------------------------------------------------------------------------", +# " [{\"room_id\":\"!some-id\",\"count\":2461329},{\"room_id\":\"!another-id\",\"count\":512017}]", +# "(1 row)" +# ] +# +# Row 3 (out of 4) contains the actual result. +# +# Row 3 contains a space when there's no result. + +- block: + - debug: var="matrix_synapse_rust_synapse_compress_state_find_rooms_command_result" + + - name: Fail if room find result is not what we expect + fail: + msg: >- + Expecting 4 lines in the "find rooms" result. + when: "matrix_synapse_rust_synapse_compress_state_find_rooms_command_result.failed or matrix_synapse_rust_synapse_compress_state_find_rooms_command_result.stdout_lines|length != 4" + +- block: + # matrix_synapse_rust_synapse_compress_state_eligible_rooms is a list + # of dictionaries like this: {'room_id': '!some-id', 'count': 2461329} + - set_fact: + matrix_synapse_rust_synapse_compress_state_eligible_rooms: "{{ matrix_synapse_rust_synapse_compress_state_find_rooms_command_result.stdout_lines[2] | from_json }}" + + - name: Display rooms that will be compressed + debug: + msg: >- + The following rooms contain more than {{ matrix_synapse_rust_synapse_compress_state_min_state_groups_required }} state group rows + (configurable via `matrix_synapse_rust_synapse_compress_state_min_state_groups_required`) + and will be compressed: + {{ matrix_synapse_rust_synapse_compress_state_eligible_rooms }} + + - name: Compress room state + include_tasks: "{{ role_path }}/tasks/rust-synapse-compress-state/compress_room.yml" + with_items: "{{ matrix_synapse_rust_synapse_compress_state_eligible_rooms }}" + loop_control: + loop_var: room_details + when: "matrix_synapse_rust_synapse_compress_state_find_rooms_command_result.stdout_lines[2] != ' '" + +- name: Show notice about lack of rooms to compress + debug: + msg: >- + No rooms were found to contain more than {{ matrix_synapse_rust_synapse_compress_state_min_state_groups_required }} state group rows + (configurable via `matrix_synapse_rust_synapse_compress_state_min_state_groups_required`), + so there's nothing to compress. + when: "matrix_synapse_rust_synapse_compress_state_find_rooms_command_result.stdout_lines[2] == ' '"