feat(metrics): add gatus_results_endpoint_success (#970)

* feat(metrics): add gatus_endpoint_success

Signed-off-by: Devin Buhl <devin@buhl.casa>

* feat(metrics): add gatus_endpoint_success

Signed-off-by: Devin Buhl <devin@buhl.casa>

* chore: update readme

Signed-off-by: Devin Buhl <devin@buhl.casa>

* chore: update readme

Signed-off-by: Devin Buhl <devin@buhl.casa>

* chore: update readme

Signed-off-by: Devin Buhl <devin@buhl.casa>

* chore: update readme

Signed-off-by: Devin Buhl <devin@buhl.casa>

* chore: update readme

Signed-off-by: Devin Buhl <devin@buhl.casa>

---------

Signed-off-by: Devin Buhl <devin@buhl.casa>

README.md

@@ -120,6 +120,7 @@ Have any feedback or questions? [Create a discussion](https://github.com/TwiN/ga
       - [How to change the color thresholds of the response time badge](#how-to-change-the-color-thresholds-of-the-response-time-badge)
   - [API](#api)
     - [Raw Data](#raw-data)
+      - [Uptime](#uptime-1)
   - [Installing as binary](#installing-as-binary)
   - [High level design overview](#high-level-design-overview)
 
@@ -1745,11 +1746,12 @@ endpoint on the same port your application is configured to run on (`web.port`).
 
 | Metric name                                  | Type    | Description                                                                | Labels                          | Relevant endpoint types |
 |:---------------------------------------------|:--------|:---------------------------------------------------------------------------|:--------------------------------|:------------------------|
-| gatus_results_total                          | counter | Number of results per endpoint                                             | key, group, name, type, success | All                     |
+| gatus_results_total                          | counter | Number of results per endpoint per success state                           | key, group, name, type, success | All                     |
 | gatus_results_code_total                     | counter | Total number of results by code                                            | key, group, name, type, code    | DNS, HTTP               |
 | gatus_results_connected_total                | counter | Total number of results in which a connection was successfully established | key, group, name, type          | All                     |
 | gatus_results_duration_seconds               | gauge   | Duration of the request in seconds                                         | key, group, name, type          | All                     |
 | gatus_results_certificate_expiration_seconds | gauge   | Number of seconds until the certificate expires                            | key, group, name, type          | HTTP, STARTTLS          |
+| gatus_results_endpoint_success               | gauge   | Displays whether or not the endpoint was a success (0 failure, 1 success)  | key, group, name, type          | All                     |
 
 See [examples/docker-compose-grafana-prometheus](.examples/docker-compose-grafana-prometheus) for further documentation as well as an example.
 

metrics/metrics.go

@@ -18,6 +18,7 @@ var (
 	resultConnectedTotal               *prometheus.CounterVec
 	resultCodeTotal                    *prometheus.CounterVec
 	resultCertificateExpirationSeconds *prometheus.GaugeVec
+	resultEndpointSuccess              *prometheus.GaugeVec
 )
 
 func initializePrometheusMetrics() {
@@ -46,6 +47,11 @@ func initializePrometheusMetrics() {
 		Name:      "results_certificate_expiration_seconds",
 		Help:      "Number of seconds until the certificate expires",
 	}, []string{"key", "group", "name", "type"})
+	resultEndpointSuccess = promauto.NewGaugeVec(prometheus.GaugeOpts{
+		Namespace: namespace,
+		Name:      "results_endpoint_success",
+		Help:      "Displays whether or not the endpoint was a success",
+	}, []string{"key", "group", "name", "type"})
 }
 
 // PublishMetricsForEndpoint publishes metrics for the given endpoint and its result.
@@ -70,4 +76,9 @@ func PublishMetricsForEndpoint(ep *endpoint.Endpoint, result *endpoint.Result) {
 	if result.CertificateExpiration != 0 {
 		resultCertificateExpirationSeconds.WithLabelValues(ep.Key(), ep.Group, ep.Name, string(endpointType)).Set(result.CertificateExpiration.Seconds())
 	}
+	if result.Success {
+		resultEndpointSuccess.WithLabelValues(ep.Key(), ep.Group, ep.Name, string(endpointType)).Set(1)
+	} else {
+		resultEndpointSuccess.WithLabelValues(ep.Key(), ep.Group, ep.Name, string(endpointType)).Set(0)
+	}
 }

metrics/metrics_test.go

@@ -25,9 +25,6 @@ func TestPublishMetricsForEndpoint(t *testing.T) {
 		CertificateExpiration: 49 * time.Hour,
 	})
 	err := testutil.GatherAndCompare(prometheus.Gatherers{prometheus.DefaultGatherer}, bytes.NewBufferString(`
-# HELP gatus_results_certificate_expiration_seconds Number of seconds until the certificate expires
-# TYPE gatus_results_certificate_expiration_seconds gauge
-gatus_results_certificate_expiration_seconds{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 176400
 # HELP gatus_results_code_total Total number of results by code
 # TYPE gatus_results_code_total counter
 gatus_results_code_total{code="200",group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 1
@@ -40,7 +37,13 @@ gatus_results_duration_seconds{group="http-ep-group",key="http-ep-group_http-ep-
 # HELP gatus_results_total Number of results per endpoint
 # TYPE gatus_results_total counter
 gatus_results_total{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",success="true",type="HTTP"} 1
-`), "gatus_results_code_total", "gatus_results_connected_total", "gatus_results_duration_seconds", "gatus_results_total", "gatus_results_certificate_expiration_seconds")
+# HELP gatus_results_certificate_expiration_seconds Number of seconds until the certificate expires
+# TYPE gatus_results_certificate_expiration_seconds gauge
+gatus_results_certificate_expiration_seconds{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 176400
+# HELP gatus_results_endpoint_success Displays whether or not the endpoint was a success
+# TYPE gatus_results_endpoint_success gauge
+gatus_results_endpoint_success{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 1
+`), "gatus_results_code_total", "gatus_results_connected_total", "gatus_results_duration_seconds", "gatus_results_total", "gatus_results_certificate_expiration_seconds", "gatus_results_endpoint_success")
 	if err != nil {
 		t.Errorf("Expected no errors but got: %v", err)
 	}
@@ -56,9 +59,6 @@ gatus_results_total{group="http-ep-group",key="http-ep-group_http-ep-name",name=
 		CertificateExpiration: 47 * time.Hour,
 	})
 	err = testutil.GatherAndCompare(prometheus.Gatherers{prometheus.DefaultGatherer}, bytes.NewBufferString(`
-# HELP gatus_results_certificate_expiration_seconds Number of seconds until the certificate expires
-# TYPE gatus_results_certificate_expiration_seconds gauge
-gatus_results_certificate_expiration_seconds{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 169200
 # HELP gatus_results_code_total Total number of results by code
 # TYPE gatus_results_code_total counter
 gatus_results_code_total{code="200",group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 2
@@ -72,7 +72,13 @@ gatus_results_duration_seconds{group="http-ep-group",key="http-ep-group_http-ep-
 # TYPE gatus_results_total counter
 gatus_results_total{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",success="false",type="HTTP"} 1
 gatus_results_total{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",success="true",type="HTTP"} 1
-`), "gatus_results_code_total", "gatus_results_connected_total", "gatus_results_duration_seconds", "gatus_results_total", "gatus_results_certificate_expiration_seconds")
+# HELP gatus_results_certificate_expiration_seconds Number of seconds until the certificate expires
+# TYPE gatus_results_certificate_expiration_seconds gauge
+gatus_results_certificate_expiration_seconds{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 169200
+# HELP gatus_results_endpoint_success Displays whether or not the endpoint was a success
+# TYPE gatus_results_endpoint_success gauge
+gatus_results_endpoint_success{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 0
+`), "gatus_results_code_total", "gatus_results_connected_total", "gatus_results_duration_seconds", "gatus_results_total", "gatus_results_certificate_expiration_seconds", "gatus_results_endpoint_success")
 	if err != nil {
 		t.Errorf("Expected no errors but got: %v", err)
 	}
@@ -90,9 +96,6 @@ gatus_results_total{group="http-ep-group",key="http-ep-group_http-ep-name",name=
 		Success: true,
 	})
 	err = testutil.GatherAndCompare(prometheus.Gatherers{prometheus.DefaultGatherer}, bytes.NewBufferString(`
-# HELP gatus_results_certificate_expiration_seconds Number of seconds until the certificate expires
-# TYPE gatus_results_certificate_expiration_seconds gauge
-gatus_results_certificate_expiration_seconds{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 169200
 # HELP gatus_results_code_total Total number of results by code
 # TYPE gatus_results_code_total counter
 gatus_results_code_total{code="200",group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 2
@@ -110,7 +113,14 @@ gatus_results_duration_seconds{group="http-ep-group",key="http-ep-group_http-ep-
 gatus_results_total{group="dns-ep-group",key="dns-ep-group_dns-ep-name",name="dns-ep-name",success="true",type="DNS"} 1
 gatus_results_total{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",success="false",type="HTTP"} 1
 gatus_results_total{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",success="true",type="HTTP"} 1
-`), "gatus_results_code_total", "gatus_results_connected_total", "gatus_results_duration_seconds", "gatus_results_total", "gatus_results_certificate_expiration_seconds")
+# HELP gatus_results_certificate_expiration_seconds Number of seconds until the certificate expires
+# TYPE gatus_results_certificate_expiration_seconds gauge
+gatus_results_certificate_expiration_seconds{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 169200
+# HELP gatus_results_endpoint_success Displays whether or not the endpoint was a success
+# TYPE gatus_results_endpoint_success gauge
+gatus_results_endpoint_success{group="dns-ep-group",key="dns-ep-group_dns-ep-name",name="dns-ep-name",type="DNS"} 1
+gatus_results_endpoint_success{group="http-ep-group",key="http-ep-group_http-ep-name",name="http-ep-name",type="HTTP"} 0
+`), "gatus_results_code_total", "gatus_results_connected_total", "gatus_results_duration_seconds", "gatus_results_total", "gatus_results_certificate_expiration_seconds", "gatus_results_endpoint_success")
 	if err != nil {
 		t.Errorf("Expected no errors but got: %v", err)
 	}