From 5121f9210c989fcc909e78195133876dff3bc9b9 Mon Sep 17 00:00:00 2001
From: Devon Hudson <devon.dmytro@gmail.com>
Date: Tue, 25 Feb 2025 16:25:39 +0000
Subject: Add background job to clear unreferenced state groups (#18154)

Fixes #18150

### Pull Request Checklist

<!-- Please read
https://element-hq.github.io/synapse/latest/development/contributing_guide.html
before submitting your pull request -->

* [X] Pull request is based on the develop branch
* [x] Pull request includes a [changelog
file](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#changelog).
The entry should:
- Be a short description of your change which makes sense to users.
"Fixed a bug that prevented receiving messages from other servers."
instead of "Moved X method from `EventStore` to `EventWorkerStore`.".
  - Use markdown where necessary, mostly for `code blocks`.
  - End with either a period (.) or an exclamation mark (!).
  - Start with a capital letter.
- Feel free to credit yourself, by adding a sentence "Contributed by
@github_username." or "Contributed by [Your Name]." to the end of the
entry.
* [X] [Code
style](https://element-hq.github.io/synapse/latest/code_style.html) is
correct
(run the
[linters](https://element-hq.github.io/synapse/latest/development/contributing_guide.html#run-the-linters))

---------

Co-authored-by: Erik Johnston <erikj@element.io>
---
 synapse/_scripts/synapse_port_db.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'synapse/_scripts')

diff --git a/synapse/_scripts/synapse_port_db.py b/synapse/_scripts/synapse_port_db.py
index 3f67a739a0..59065a0504 100755
--- a/synapse/_scripts/synapse_port_db.py
+++ b/synapse/_scripts/synapse_port_db.py
@@ -191,6 +191,11 @@ APPEND_ONLY_TABLES = [
 
 
 IGNORED_TABLES = {
+    # Porting the auto generated sequence in this table is non-trivial.
+    # None of the entries in this list are mandatory for Synapse to keep working.
+    # If state group disk space is an issue after the port, the
+    # `delete_unreferenced_state_groups_bg_update` background task can be run again.
+    "state_groups_pending_deletion",
     # We don't port these tables, as they're a faff and we can regenerate
     # them anyway.
     "user_directory",
@@ -216,6 +221,15 @@ IGNORED_TABLES = {
 }
 
 
+# These background updates will not be applied upon creation of the postgres database.
+IGNORED_BACKGROUND_UPDATES = {
+    # Reapplying this background update to the postgres database is unnecessary after
+    # already having waited for the SQLite database to complete all running background
+    # updates.
+    "delete_unreferenced_state_groups_bg_update",
+}
+
+
 # Error returned by the run function. Used at the top-level part of the script to
 # handle errors and return codes.
 end_error: Optional[str] = None
@@ -687,6 +701,20 @@ class Porter:
         # 0 means off. 1 means full. 2 means incremental.
         return autovacuum_setting != 0
 
+    async def remove_ignored_background_updates_from_database(self) -> None:
+        def _remove_delete_unreferenced_state_groups_bg_updates(
+            txn: LoggingTransaction,
+        ) -> None:
+            txn.execute(
+                "DELETE FROM background_updates WHERE update_name = ANY(?)",
+                (list(IGNORED_BACKGROUND_UPDATES),),
+            )
+
+        await self.postgres_store.db_pool.runInteraction(
+            "remove_delete_unreferenced_state_groups_bg_updates",
+            _remove_delete_unreferenced_state_groups_bg_updates,
+        )
+
     async def run(self) -> None:
         """Ports the SQLite database to a PostgreSQL database.
 
@@ -732,6 +760,8 @@ class Porter:
                 self.hs_config.database.get_single_database()
             )
 
+            await self.remove_ignored_background_updates_from_database()
+
             await self.run_background_updates_on_postgres()
 
             self.progress.set_state("Creating port tables")
-- 
cgit 1.5.1