migration(crons): Add MonitorIncident table (#56435)

Adds `MonitorIncidentTable` to keep track of open monitor incidents +
display them on the timeline view.

If a `failure` threshold is set, we will open an `incident` and tag it
with the appropriate `hash` and reference the `checkin` that caused it
to pass the threshold.

If a `recovery` threshold is set, we will find any `incident` with the
appropriate `hash` and set it as the `closing_checkin`.

In the future, if no thresholds are set, we will move to this behavior.
But for now, we will keep existing behavior as-is.

The `thresholds` can be derived from the `checkin` configs, though we
may want to add them as top level fields.

Author: rjo100

fixtures/backup/model_dependencies/detailed.json

@@ -1830,6 +1830,31 @@
       "Region"
     ]
   },
+  "sentry.MonitorIncident": {
+    "foreign_keys": {
+      "monitor": {
+        "kind": "FlexibleForeignKey",
+        "model": "sentry.Monitor"
+      },
+      "monitor_environment": {
+        "kind": "FlexibleForeignKey",
+        "model": "sentry.MonitorEnvironment"
+      },
+      "resolving_checkin": {
+        "kind": "FlexibleForeignKey",
+        "model": "sentry.MonitorCheckIn"
+      },
+      "starting_checkin": {
+        "kind": "FlexibleForeignKey",
+        "model": "sentry.MonitorCheckIn"
+      }
+    },
+    "model": "sentry.MonitorIncident",
+    "relocation_scope": "Excluded",
+    "silos": [
+      "Region"
+    ]
+  },
   "sentry.MonitorLocation": {
     "foreign_keys": {},
     "model": "sentry.MonitorLocation",

fixtures/backup/model_dependencies/flat.json

@@ -412,6 +412,11 @@
     "sentry.Environment",
     "sentry.Monitor"
   ],
+  "sentry.MonitorIncident": [
+    "sentry.Monitor",
+    "sentry.MonitorCheckIn",
+    "sentry.MonitorEnvironment"
+  ],
   "sentry.MonitorLocation": [],
   "sentry.NeglectedRule": [
     "sentry.Organization",

fixtures/backup/model_dependencies/sorted.json

@@ -212,5 +212,6 @@
   "sentry.IncidentSnapshot",
   "sentry.IncidentActivity",
   "sentry.IncidentSubscription",
-  "sentry.IncidentTrigger"
+  "sentry.IncidentTrigger",
+  "sentry.MonitorIncident"
 ]

migrations_lockfile.txt

@@ -8,5 +8,5 @@ will then be regenerated, and you should be able to merge without conflicts.
 feedback: 0002_feedback_add_org_id_and_rename_event_id
 nodestore: 0002_nodestore_no_dictfield
 replays: 0003_add_size_to_recording_segment
-sentry: 0559_custom_dynamic_sampling_rule
+sentry: 0560_add_monitorincident_table
 social_auth: 0002_default_auto_field

src/sentry/migrations/0560_add_monitorincident_table.py

@@ -0,0 +1,78 @@
+# Generated by Django 3.2.20 on 2023-09-18 23:09
+
+import django.db.models.deletion
+import django.utils.timezone
+from django.db import migrations, models
+
+import sentry.db.models.fields.bounded
+import sentry.db.models.fields.foreignkey
+from sentry.new_migrations.migrations import CheckedMigration
+
+
+class Migration(CheckedMigration):
+    # This flag is used to mark that a migration shouldn't be automatically run in production. For
+    # the most part, this should only be used for operations where it's safe to run the migration
+    # after your code has deployed. So this should not be used for most operations that alter the
+    # schema of a table.
+    # Here are some things that make sense to mark as dangerous:
+    # - Large data migrations. Typically we want these to be run manually by ops so that they can
+    #   be monitored and not block the deploy for a long period of time while they run.
+    # - Adding indexes to large tables. Since this can take a long time, we'd generally prefer to
+    #   have ops run this and not block the deploy. Note that while adding an index is a schema
+    #   change, it's completely safe to run the operation after the code has deployed.
+    is_dangerous = False
+
+    dependencies = [
+        ("sentry", "0559_custom_dynamic_sampling_rule"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="MonitorIncident",
+            fields=[
+                (
+                    "id",
+                    sentry.db.models.fields.bounded.BoundedBigAutoField(
+                        primary_key=True, serialize=False
+                    ),
+                ),
+                ("starting_timestamp", models.DateTimeField(null=True)),
+                ("resolving_timestamp", models.DateTimeField(null=True)),
+                ("grouphash", models.CharField(max_length=32)),
+                ("date_added", models.DateTimeField(default=django.utils.timezone.now)),
+                (
+                    "monitor",
+                    sentry.db.models.fields.foreignkey.FlexibleForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="sentry.monitor"
+                    ),
+                ),
+                (
+                    "monitor_environment",
+                    sentry.db.models.fields.foreignkey.FlexibleForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to="sentry.monitorenvironment"
+                    ),
+                ),
+                (
+                    "resolving_checkin",
+                    sentry.db.models.fields.foreignkey.FlexibleForeignKey(
+                        null=True,
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="resolved_incidents",
+                        to="sentry.monitorcheckin",
+                    ),
+                ),
+                (
+                    "starting_checkin",
+                    sentry.db.models.fields.foreignkey.FlexibleForeignKey(
+                        null=True,
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="created_incidents",
+                        to="sentry.monitorcheckin",
+                    ),
+                ),
+            ],
+            options={
+                "db_table": "sentry_monitorincident",
+            },
+        ),
+    ]

src/sentry/monitors/models.py

@@ -591,3 +591,25 @@ def check_monitor_environment_limits(sender, instance, **kwargs):
         raise MonitorEnvironmentLimitsExceeded(
             f"You may not exceed {settings.MAX_ENVIRONMENTS_PER_MONITOR} environments per monitor"
         )
+
+
+@region_silo_only_model
+class MonitorIncident(Model):
+    __relocation_scope__ = RelocationScope.Excluded
+
+    monitor = FlexibleForeignKey("sentry.Monitor")
+    monitor_environment = FlexibleForeignKey("sentry.MonitorEnvironment")
+    starting_checkin = FlexibleForeignKey(
+        "sentry.MonitorCheckIn", null=True, related_name="created_incidents"
+    )
+    starting_timestamp = models.DateTimeField(null=True)
+    resolving_checkin = FlexibleForeignKey(
+        "sentry.MonitorCheckIn", null=True, related_name="resolved_incidents"
+    )
+    resolving_timestamp = models.DateTimeField(null=True)
+    grouphash = models.CharField(max_length=32)
+    date_added = models.DateTimeField(default=timezone.now)
+
+    class Meta:
+        app_label = "sentry"
+        db_table = "sentry_monitorincident"