feat(uptime): Ability to ingest and query in_incident

requirements.txt

@@ -28,7 +28,7 @@ python-dateutil==2.8.2
 python-rapidjson==1.8
 redis==4.5.4
 sentry-arroyo==2.19.12
-sentry-kafka-schemas==1.0.4
+sentry-kafka-schemas==1.0.8
 sentry-protos==0.1.59
 sentry-redis-tools==0.3.0
 sentry-relay==0.9.5

rust_snuba/Cargo.toml

@@ -32,7 +32,7 @@ procspawn = { version = "1.0.0", features = ["json"] }
 pyo3 = { version = "0.18.1", features = ["chrono"] }
 reqwest = { version = "0.11.11", features = ["stream"] }
 sentry = { version = "0.32.0", features = ["anyhow", "tracing"] }
-sentry-kafka-schemas = "1.0.4"
+sentry-kafka-schemas = "1.0.8"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = { version = "1.0" }
 thiserror = "1.0"

rust_snuba/src/processors/uptime_monitor_checks.rs

@@ -42,6 +42,7 @@ pub fn deserialize_message(payload: &[u8]) -> anyhow::Result<(Vec<UptimeMonitorC
             .http_status_code,
         trace_id: monitor_message.trace_id,
         retention_days: monitor_message.retention_days,
+        incident_status: monitor_message.incident_status,
     }];
     Ok((rows, monitor_message.actual_check_time_ms as f64))
 }
@@ -63,6 +64,7 @@ struct UptimeMonitorCheckMessage<'a> {
     status_reason: Option<CheckStatusReason<'a>>,
     trace_id: Uuid,
     request_info: Option<RequestInfo>,
+    incident_status: u16,
 }
 #[derive(Debug, Deserialize, Default)]
 pub struct RequestInfo {
@@ -95,6 +97,7 @@ pub struct UptimeMonitorCheckRow<'a> {
     http_status_code: Option<u16>,
     trace_id: Uuid,
     retention_days: u16,
+    incident_status: u16,
 }
 
 #[cfg(test)]
@@ -121,6 +124,7 @@ mod tests {
             },
             "http_status_code": 200,
             "trace_id": "550e8400-e29b-41d4-a716-446655440000",
+            "incident_status": 0,
             "request_info": {
                 "request_type": "GET",
                 "http_status_code": 200
@@ -145,6 +149,7 @@ mod tests {
         assert_eq!(monitor_row.retention_days, 30);
         assert_eq!(monitor_row.scheduled_check_time, 1702659277);
         assert_eq!(monitor_row.timestamp, 1702659277000);
+        assert_eq!(monitor_row.incident_status, 0);
         assert_eq!(timestamp, 1702659277000.0);
     }
 
@@ -165,6 +170,7 @@ mod tests {
             "status_reason": null,
             "http_status_code": 200,
             "trace_id": "550e8400-e29b-41d4-a716-446655440000",
+            "incident_status": 0,
             "request_info": {
                 "request_type": "GET",
                 "http_status_code": 200
@@ -188,6 +194,7 @@ mod tests {
         assert_eq!(monitor_row.check_status_reason, "");
         assert_eq!(monitor_row.http_status_code, Some(200));
         assert_eq!(monitor_row.retention_days, 30);
+        assert_eq!(monitor_row.incident_status, 0);
         assert_eq!(timestamp, 1702659277.0);
     }
 }

snuba/datasets/configuration/events_analytics_platform/entities/uptime_checks.yaml

@@ -18,6 +18,7 @@ schema:
     { name: http_status_code, type: UInt, args: { size: 16, schema_modifiers: [nullable] } },
     { name: trace_id, type: UUID },
     { name: retention_days, type: UInt, args: { size: 16 } },
+    { name: incident_status, type: UInt, args: { size: 16 } },
   ]
 
 storages:

snuba/datasets/configuration/events_analytics_platform/storages/uptime_monitor_checks.yaml

@@ -22,6 +22,7 @@ schema:
       { name: http_status_code, type: UInt, args: { size: 16, schema_modifiers: [nullable] } },
       { name: trace_id, type: UUID },
       { name: retention_days, type: UInt, args: { size: 16 } },
+      { name: incident_status, type: UInt, args: { size: 16 } },
     ]
   local_table_name: uptime_monitor_checks_v2_local
   dist_table_name: uptime_monitor_checks_v2_dist

snuba/web/rpc/v1/resolvers/R_uptime_checks/common/common.py

@@ -77,6 +77,7 @@ def transform(exp: Expression) -> Expression:
     "check_status_reason": AttributeKey.Type.TYPE_STRING,
     "http_status_code": AttributeKey.Type.TYPE_INT,
     "trace_id": AttributeKey.Type.TYPE_STRING,
+    "incident_status": AttributeKey.Type.TYPE_INT,
     "retention_days": AttributeKey.Type.TYPE_INT,
 }
 

tests/web/rpc/v1/test_endpoint_time_series/test_endpoint_time_series_uptime_checks.py

@@ -47,6 +47,7 @@ def gen_message(
         },
         "http_status_code": 200,
         "trace_id": _TRACE_ID,
+        "incident_status": 0,
         "request_info": {
             "request_type": "GET",
             "http_status_code": 200,
@@ -73,7 +74,8 @@ def store_timeseries(
         dt = start_datetime + timedelta(seconds=secs)
         messages.append(gen_message(dt))
     uptime_checks_storage = get_storage(StorageKey("uptime_monitor_checks"))
-    write_raw_unprocessed_events(uptime_checks_storage, messages)  # type: ignore
+    write_raw_unprocessed_events(
+        uptime_checks_storage, messages)  # type: ignore
 
 
 @pytest.mark.clickhouse_db
@@ -193,6 +195,7 @@ def test_with_group_by(self) -> None:
             ],
             group_by=[
                 AttributeKey(type=AttributeKey.TYPE_STRING, name="region"),
+                AttributeKey(type=AttributeKey.TYPE_STRING, name="incident_status"),
             ],
             granularity_secs=granularity_secs,
         )
@@ -206,7 +209,7 @@ def test_with_group_by(self) -> None:
             TimeSeries(
                 label="count",
                 buckets=expected_buckets,
-                group_by_attributes={"region": "global"},
+                group_by_attributes={"region": "global", "incident_status": 0},
                 data_points=[
                     DataPoint(data=300, data_present=True)
                     for _ in range(len(expected_buckets))

tests/web/rpc/v1/test_endpoint_trace_item_table/test_endpoint_trace_item_table_uptime_checks.py

@@ -52,6 +52,7 @@ def gen_message(
         },
         "http_status_code": 200,
         "trace_id": _TRACE_ID,
+        "incident_status": False,
         "request_info": {
             "request_type": "GET",
             "http_status_code": 200,