backend: Add metrics endpoints

Pull request #656 adds the necessary instance_stats database table as well as functions for querying instance counts (by channel, version, and architecture) from the groups, instance, and instance_application tables and storing the results in the new table.

To make this data accessible outside Nebraska, we create the following:

- Prometheus metrics endpoint: A new HTTP endpoint (instance-metrics/prometheus) that serves only the latest snapshot from the instance_stats table. As Prometheus is a time-series database, this serves instance counts with the latest timestamp only.
- JSON metrics data endpoint: A new HTTP endpoint that emits all instance_stats data in JSON format. The difference here is that we query for all data, and we emit one JSON document per row.

Author: skoeva

backend/api/spec.yaml

@@ -1177,6 +1177,41 @@ paths:
           description: Activity not found response
         "500":
           description: List activity error response
+  /instance-metrics/prometheus:
+    get:
+      description: Get latest instance stats
+      operationId: getLatestInstanceStats
+      security:
+        - oidcBearerAuth: []
+        - oidcCookieAuth: []
+        - githubCookieAuth: []
+      responses:
+        "200":
+          description: Get latest instance stats success response
+          content:
+            text/plain:
+              schema:
+                type: string
+        "500":
+          description: Get latest instance stats error response
+  /instance-metrics/json:
+    get:
+      description: Get instance stats
+      operationId: getInstanceStats
+      security:
+        - oidcBearerAuth: []
+        - oidcCookieAuth: []
+        - githubCookieAuth: []
+      responses:
+        "200":
+          description: Get instance stats success response
+          content:
+            application/x-ndjson:
+              schema:
+                $ref: "#/components/schemas/instanceStats"
+        "500":
+          description: Get instance stats error response
+      
 components:
   schemas:
     ## request Body
@@ -1339,6 +1374,30 @@ components:
         package_id:
           type: string
 
+    instanceStats:
+      type: object
+      required:
+        - type
+        - channel
+        - version
+        - arch
+        - timestamp
+        - instances
+      properties:
+        type:
+          type: string
+          enum: ["instance_count"]
+        channel:
+          type: string
+        version:
+          type: string
+        arch:
+          type: string
+        timestamp:
+          type: string
+        count:
+          type: integer
+
 
     ## response     
     config:

backend/pkg/api/instances.go

@@ -49,7 +49,7 @@ const (
 
 const (
 	validityInterval postgresDuration = "1 days"
-	defaultInterval  time.Duration    = time.Hour
+	defaultInterval  time.Duration    = 2 * time.Hour
 )
 
 // Instance represents an instance running one or more applications for which
@@ -651,7 +651,7 @@ func (api *API) GetDefaultInterval() time.Duration {
 // that have been checked in during a given duration from a given time.
 func (api *API) instanceStatsQuery(t *time.Time, duration *time.Duration) *goqu.SelectDataset {
 	if t == nil {
-		now := time.Now()
+		now := time.Now().UTC()
 		t = &now
 	}
 

backend/pkg/api/metrics.go

@@ -21,6 +21,12 @@ WHERE a.id = e.application_id AND e.event_type_id = et.id AND et.result = 0 AND
 GROUP BY app_name
 ORDER BY app_name
 `, ignoreFakeInstanceCondition("e.instance_id"))
+
+	latestInstanceStatsSQL string = `
+SELECT channel_name, version, arch, timestamp, instances AS instances_count
+FROM instance_stats
+WHERE timestamp = (SELECT MAX(timestamp) FROM instance_stats)
+`
 )
 
 type AppInstancesPerChannelMetric struct {
@@ -77,6 +83,35 @@ func (api *API) GetFailedUpdatesMetrics() ([]FailedUpdatesMetric, error) {
 	return metrics, nil
 }
 
+type LatestInstanceStatsMetric struct {
+	ChannelName    string `db:"channel_name" json:"channel_name"`
+	Version        string `db:"version" json:"version"`
+	Arch           string `db:"arch" json:"arch"`
+	Timestamp      string `db:"timestamp" json:"timestamp"`
+	InstancesCount int    `db:"instances_count" json:"instances_count"`
+}
+
+func (api *API) GetLatestInstanceStatsMetrics() ([]LatestInstanceStatsMetric, error) {
+	var metrics []LatestInstanceStatsMetric
+	rows, err := api.db.Queryx(latestInstanceStatsSQL)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	for rows.Next() {
+		var metric LatestInstanceStatsMetric
+		err := rows.StructScan(&metric)
+		if err != nil {
+			return nil, err
+		}
+		metrics = append(metrics, metric)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return metrics, nil
+}
+
 func (api *API) DbStats() sql.DBStats {
 	return api.db.Stats()
 }