From 902498ec4ff572ff289b875f62bb304df8cbf21e Mon Sep 17 00:00:00 2001
From: Alex Vandiver <alexmv@zulip.com>
Date: Wed, 13 Sep 2023 16:29:06 +0000
Subject: [PATCH] zilencer: Update remoterealm indexes.

There is no reason to have an index on just `realm_id` or `remote_id`,
as those values mean nothing outside of the scope of a specific
`server_id`.  Remove those never-used single-column indexes from the
two tables that have them.

By contrast, the pair of `server_id` and `remote_id` is quite useful
and specific -- it is a unique pair, and every POST of statistics from
a remote host requires looking up the highest `remote_id` for a given
`server_id`, which (without this index) is otherwise a quite large
scan.

Add a unique constraint, which (in PostgreSQL) is implemented as a
unique index.
---
 .../0029_update_remoterealm_indexes.py        | 45 +++++++++++++++++++
 zilencer/models.py                            | 22 +++++++--
 2 files changed, 63 insertions(+), 4 deletions(-)
 create mode 100644 zilencer/migrations/0029_update_remoterealm_indexes.py

diff --git a/zilencer/migrations/0029_update_remoterealm_indexes.py b/zilencer/migrations/0029_update_remoterealm_indexes.py
new file mode 100644
index 0000000000..ad510c7291
--- /dev/null
+++ b/zilencer/migrations/0029_update_remoterealm_indexes.py
@@ -0,0 +1,45 @@
+# Generated by Django 4.2.5 on 2023-09-13 05:02
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("zilencer", "0028_rename_extradatajson_remoteauditlog_extra_data"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="remoterealmauditlog",
+            name="realm_id",
+            field=models.IntegerField(),
+        ),
+        migrations.AlterField(
+            model_name="remoterealmauditlog",
+            name="remote_id",
+            field=models.IntegerField(),
+        ),
+        migrations.AlterField(
+            model_name="remoterealmcount",
+            name="realm_id",
+            field=models.IntegerField(),
+        ),
+        migrations.AlterField(
+            model_name="remoterealmcount",
+            name="remote_id",
+            field=models.IntegerField(),
+        ),
+        migrations.AddConstraint(
+            model_name="remoterealmauditlog",
+            constraint=models.UniqueConstraint(
+                fields=("server", "remote_id"), name="zilencer_remoterealmauditlog_server_remote"
+            ),
+        ),
+        migrations.AddIndex(
+            model_name="remoterealmauditlog",
+            index=models.Index(
+                fields=["server", "realm_id", "remote_id"],
+                name="zilencer_remoterealmauditlog_server_realm_remote",
+            ),
+        ),
+    ]
diff --git a/zilencer/models.py b/zilencer/models.py
index c646516429..af6682eb76 100644
--- a/zilencer/models.py
+++ b/zilencer/models.py
@@ -100,13 +100,27 @@ class RemoteRealmAuditLog(AbstractRealmAuditLog):
     """
 
     server = models.ForeignKey(RemoteZulipServer, on_delete=models.CASCADE)
-    realm_id = models.IntegerField(db_index=True)
+    realm_id = models.IntegerField()
     # The remote_id field lets us deduplicate data from the remote server
-    remote_id = models.IntegerField(db_index=True)
+    remote_id = models.IntegerField()
 
     def __str__(self) -> str:
         return f"{self.server!r} {self.event_type} {self.event_time} {self.id}"
 
+    class Meta:
+        constraints = [
+            models.UniqueConstraint(
+                fields=["server", "remote_id"],
+                name="zilencer_remoterealmauditlog_server_remote",
+            ),
+        ]
+        indexes = [
+            models.Index(
+                fields=["server", "realm_id", "remote_id"],
+                name="zilencer_remoterealmauditlog_server_realm_remote",
+            ),
+        ]
+
 
 class RemoteInstallationCount(BaseCount):
     server = models.ForeignKey(RemoteZulipServer, on_delete=models.CASCADE)
@@ -129,9 +143,9 @@ class RemoteInstallationCount(BaseCount):
 # We can't subclass RealmCount because we only have a realm_id here, not a foreign key.
 class RemoteRealmCount(BaseCount):
     server = models.ForeignKey(RemoteZulipServer, on_delete=models.CASCADE)
-    realm_id = models.IntegerField(db_index=True)
+    realm_id = models.IntegerField()
     # The remote_id field lets us deduplicate data from the remote server
-    remote_id = models.IntegerField(db_index=True)
+    remote_id = models.IntegerField()
 
     class Meta:
         unique_together = ("server", "realm_id", "property", "subgroup", "end_time")