fix(pvc): Get disk name from k8s labels instead (#142)

When comparing the output data from opencost and cloudcost exporter, one bit that didn't quite make sense was a mismatch in PVC's between the two. The total costs between the two was small enough to be insignificant, which only made things more confusing.

After analyzing the metrics further, the biggest difference was the name of the disks. `cloudcost-exporter` was pulling the name directly from the disk metadata, which was prepending most pv's with `gke-$cluster`. The problem with this is that `kube-state-metrics` and other metrics only look at what k8s calls them.

This change updates how name is sourced.
1. Loads the `disk.Description` into a map
2. Check for the existence of two labels
3. If either keys are found, return the value
4. Otherwise, fall back to `disk.Name` as a final resource

pkg/google/gke/gke.go

@@ -175,12 +175,13 @@ func (c *Collector) Collect(ch chan<- prometheus.Metric) error {
 				region := getRegionFromDisk(disk)
 
 				namespace := getNamespaceFromDisk(disk)
+				name := getNameFromDisk(disk)
 				diskType := strings.Split(disk.Type, "/")
 				storageClass := diskType[len(diskType)-1]
 				labelValues := []string{
 					clusterName,
 					namespace,
-					disk.Name,
+					name,
 					region,
 					project,
 					storageClass,
@@ -247,22 +248,7 @@ func getNamespaceFromDisk(disk *compute.Disk) string {
 	if err != nil {
 		return ""
 	}
-	for _, key := range keys {
-		if val, ok := desc[key]; ok {
-			return val
-		}
-	}
-	return ""
-}
-
-func extractLabelsFromDesc(description string, labels map[string]string) error {
-	if description == "" {
-		return nil
-	}
-	if err := json.Unmarshal([]byte(description), &labels); err != nil {
-		return err
-	}
-	return nil
+	return coalesce(desc, keys...)
 }
 
 func getRegionFromDisk(disk *compute.Disk) string {
@@ -281,3 +267,42 @@ func getRegionFromDisk(disk *compute.Disk) string {
 	}
 	return zone[:strings.LastIndex(zone, "-")]
 }
+
+// getNameFromDisk will return the name of the disk. If the disk has a label "kubernetes.io/created-for/pv/name" it will return the value stored in that key.
+// otherwise it will return the disk name that is directly associated with the disk.
+func getNameFromDisk(disk *compute.Disk) string {
+	desc := make(map[string]string)
+	err := extractLabelsFromDesc(disk.Description, desc)
+	if err != nil {
+		return disk.Name
+	}
+	// first check that the key exists in the map, if it does return the value
+	name := coalesce(desc, "kubernetes.io/created-for/pv/name", "kubernetes.io-created-for/pv-name")
+	if name != "" {
+		return name
+	}
+	return disk.Name
+}
+
+// coalesce will take a map and a list of keys and return the first value that is found in the map. If no value is found it will return an empty string
+func coalesce(desc map[string]string, keys ...string) string {
+	for _, key := range keys {
+		if val, ok := desc[key]; ok {
+			return val
+		}
+	}
+	return ""
+}
+
+// extractLabelsFromDesc will take a description string and extract the labels from it. GKE disks store their description as
+// a json blob in the description field. This function will extract the labels from that json blob and return them as a map
+// Some useful information about the json blob are name, cluster, namespace, and pvc's that the disk is associated with
+func extractLabelsFromDesc(description string, labels map[string]string) error {
+	if description == "" {
+		return nil
+	}
+	if err := json.Unmarshal([]byte(description), &labels); err != nil {
+		return err
+	}
+	return nil
+}

pkg/google/gke/gke_test.go

@@ -559,3 +559,55 @@ func Test_getRegionFromDisk(t *testing.T) {
 		})
 	}
 }
+
+func Test_getNameFromDisk(t *testing.T) {
+	tests := map[string]struct {
+		disk *computev1.Disk
+		want string
+	}{
+		"Empty description should return an empty string": {
+			disk: &computev1.Disk{
+				Description: "",
+			},
+			want: "",
+		},
+		"Description not formatted as json should return an empty string": {
+			disk: &computev1.Disk{
+				Description: "test",
+			},
+			want: "",
+		},
+		"Description not formatted as json should return the disks name": {
+			disk: &computev1.Disk{
+				Description: "test",
+				Name:        "testing123",
+			},
+			want: "testing123",
+		},
+		"Description formatted as json with multiple keys should return the name": {
+			disk: &computev1.Disk{
+				Description: `{"kubernetes.io/created-for/pv/name":"pvc-32613356-4cee-481d-902f-daa7223d14ab","kubernetes.io/created-for/pvc/name":"prometheus","kubernetes.io/created-for/pvc/namespace":"prometheus"}`,
+			},
+			want: "pvc-32613356-4cee-481d-902f-daa7223d14ab",
+		},
+		"Description formatted as json with one key should return the name": {
+			disk: &computev1.Disk{
+				Description: `{"kubernetes.io-created-for/pv-name":"pvc-32613356-4cee-481d-902f-daa7223d14ab"}`,
+			},
+			want: "pvc-32613356-4cee-481d-902f-daa7223d14ab",
+		},
+		"Description formatted as json with multiple wrong keys should return empty string": {
+			disk: &computev1.Disk{
+				Description: `{"kubernetes.io/created-for/pvc/name":"prometheus","kubernetes.io/created-for/pvc/namespace":"prometheus"}`,
+			},
+			want: "",
+		},
+	}
+	for name, tt := range tests {
+		t.Run(name, func(t *testing.T) {
+			if got := getNameFromDisk(tt.disk); got != tt.want {
+				t.Errorf("getNameFromDisk() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}