Add documentation for alerts

README.md

@@ -1,6 +1,7 @@
-# gatus
+![Gatus](static/logo-with-name.png)
 
 ![build](https://github.com/TwinProduction/gatus/workflows/build/badge.svg?branch=master)
+[![Go Report Card](https://goreportcard.com/badge/github.com/TwinProduction/gatus)](https://goreportcard.com/report/github.com/TwinProduction/gatus)
 [![Docker pulls](https://img.shields.io/docker/pulls/twinproduction/gatus.svg)](https://cloud.docker.com/repository/docker/twinproduction/gatus)
 
 A service health dashboard in Go that is meant to be used as a docker 
@@ -40,33 +41,40 @@ Note that you can also add environment variables in the your configuration file
 
 ### Configuration
 
-| Parameter               | Description                                                     | Default        |
-| ----------------------- | --------------------------------------------------------------- | -------------- |
-| `metrics`               | Whether to expose metrics at /metrics                           | `false`        |
-| `services[].name`       | Name of the service. Can be anything.                           | Required `""`  |
-| `services[].url`        | URL to send the request to                                      | Required `""`  |
-| `services[].conditions` | Conditions used to determine the health of the service          | `[]`           |
-| `services[].interval`   | Duration to wait between every status check                     | `10s`          |
-| `services[].method`     | Request method                                                  | `GET`          |
-| `services[].graphql`    | Whether to wrap the body in a query param (`{"query":"$body"}`) | `false`        |
-| `services[].body`       | Request body                                                    | `""`           |
-| `services[].headers`    | Request headers                                                 | `{}`           |
+| Parameter                         | Description                                                     | Default        |
+| --------------------------------- | --------------------------------------------------------------- | -------------- |
+| `metrics`                         | Whether to expose metrics at /metrics                           | `false`        |
+| `alerting.slack`                  | Webhook to use for alerts of type `slack`                       | `""`           |
+| `services[].name`                 | Name of the service. Can be anything.                           | Required `""`  |
+| `services[].url`                  | URL to send the request to                                      | Required `""`  |
+| `services[].conditions`           | Conditions used to determine the health of the service          | `[]`           |
+| `services[].interval`             | Duration to wait between every status check                     | `10s`          |
+| `services[].method`               | Request method                                                  | `GET`          |
+| `services[].graphql`              | Whether to wrap the body in a query param (`{"query":"$body"}`) | `false`        |
+| `services[].body`                 | Request body                                                    | `""`           |
+| `services[].headers`              | Request headers                                                 | `{}`           |
+| `services[].alerts[].type`        | Type of alert. Currently, only `slack` is supported             | Required `""`  |
+| `services[].alerts[].enabled`     | Whether to enable the alert                                     | `false`        |
+| `services[].alerts[].threshold`   | Number of failures in a row needed before triggering the alert  | `3`            |
+| `services[].alerts[].description` | Description of the alert. Will be included in the alert sent    | `""`           |
 
 
 ### Conditions
 
 Here are some examples of conditions you can use:
 
-| Condition                             | Description                               | Passing values           | Failing values          |
-| ------------------------------------- | ----------------------------------------- | ------------------------ | ----------------------- |
-| `[STATUS] == 200`                     | Status must be equal to 200               | 200                      | 201, 404, 500           |
-| `[STATUS] < 300`                      | Status must lower than 300                | 200, 201, 299            | 301, 302, 400, 500      |
-| `[STATUS] <= 299`                     | Status must be less than or equal to 299  | 200, 201, 299            | 301, 302, 400, 500      |
-| `[STATUS] > 400`                      | Status must be greater than 400           | 401, 402, 403, 404       | 200, 201, 300, 400      |
-| `[RESPONSE_TIME] < 500`               | Response time must be below 500ms         | 100ms, 200ms, 300ms      | 500ms, 1500ms           |
-| `[BODY] == 1`                         | The body must be equal to 1               | 1                        | literally anything else |
-| `[BODY].data.id == 1`                 | The jsonpath `$.data.id` is equal to 1    | `{"data":{"id":1}}`      | literally anything else |
-| `[BODY].data[0].id == 1`              | The jsonpath `$.data[0].id` is equal to 1 | `{"data":[{"id":1}]}`    | literally anything else |
+| Condition                    | Description                                             | Passing values           | Failing values          |
+| -----------------------------| ------------------------------------------------------- | ------------------------ | ----------------------- |
+| `[STATUS] == 200`            | Status must be equal to 200                             | 200                      | 201, 404, 500           |
+| `[STATUS] < 300`             | Status must lower than 300                              | 200, 201, 299            | 301, 302, 400, 500      |
+| `[STATUS] <= 299`            | Status must be less than or equal to 299                | 200, 201, 299            | 301, 302, 400, 500      |
+| `[STATUS] > 400`             | Status must be greater than 400                         | 401, 402, 403, 404       | 200, 201, 300, 400      |
+| `[RESPONSE_TIME] < 500`      | Response time must be below 500ms                       | 100ms, 200ms, 300ms      | 500ms, 1500ms           |
+| `[BODY] == 1`                | The body must be equal to 1                             | 1                        | literally anything else |
+| `[BODY].data.id == 1`        | The jsonpath `$.data.id` is equal to 1                  | `{"data":{"id":1}}`      | literally anything else |
+| `[BODY].data[0].id == 1`     | The jsonpath `$.data[0].id` is equal to 1               | `{"data":[{"id":1}]}`    | literally anything else |
+| `len([BODY].data) > 0`       | Array at jsonpath `$.data` has less than 5 elements     | `{"data":[{"id":1}]}`    | `{"data":[{"id":1}]}`   |
+| `len([BODY].name) == 8`      | String at jsonpath `$.name` has a length of 8           | `{"name":"john.doe"}`    | `{"name":"bob"}`        |
 
 **NOTE**: `[BODY]` with JSON path (i.e. `[BODY].id == 1`) is currently in BETA. For the most part, the only thing that doesn't work is arrays.
 
@@ -105,9 +113,9 @@ See the [example](example) folder.
 By setting `services[].graphql` to true, the body will automatically be wrapped by the standard GraphQL `query` parameter.
 
 For instance, the following configuration:
-```
+```yaml
 services:
-  - name: properties
+  - name: filter users by gender
     url: http://localhost:8080/playground
     method: POST
     graphql: true
@@ -130,4 +138,28 @@ services:
 will send a `POST` request to `http://localhost:8080/playground` with the following body:
 ```json
 {"query":"      {\n        user(gender: \"female\") {\n          id\n          name\n          gender\n          avatar\n        }\n      }"}
+```
+
+
+### Configuring Slack alerts
+
+```yaml
+alerting:
+  slack: https://hooks.slack.com/services/**********/**********/**********
+services:
+  - name: twinnation
+    interval: 30s
+    url: https://twinnation.org/health
+    alerts:
+      - type: slack
+        enabled: true
+        description: "healthcheck failed 3 times in a row"
+      - type: slack
+        enabled: true
+        threshold: 5
+        description: "healthcheck failed 5 times in a row"
+    conditions:
+      - "[STATUS] == 200"
+      - "[BODY].status == UP"
+      - "[RESPONSE_TIME] < 300"
 ```

alerting/slack.go

@@ -0,0 +1,31 @@
+package alerting
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"github.com/TwinProduction/gatus/client"
+	"io/ioutil"
+)
+
+type requestBody struct {
+	Text string `json:"text"`
+}
+
+// SendSlackMessage sends a message to the given Slack webhook
+func SendSlackMessage(webhookUrl, service, description string) error {
+	body, _ := json.Marshal(requestBody{Text: fmt.Sprintf("*[Gatus]*\n*service:* %s\n*description:* %s", service, description)})
+	response, err := client.GetHttpClient().Post(webhookUrl, "application/json", bytes.NewBuffer(body))
+	if err != nil {
+		return err
+	}
+	defer response.Body.Close()
+	output, err := ioutil.ReadAll(response.Body)
+	if err != nil {
+		return fmt.Errorf("unable to read response body: %v", err.Error())
+	}
+	if string(output) != "ok" {
+		return fmt.Errorf("error: %s", string(output))
+	}
+	return nil
+}

config.yaml

@@ -1,21 +1,17 @@
 metrics: true
 services:
   - name: twinnation
-    interval: 10s
+    interval: 30s
     url: https://twinnation.org/health
     conditions:
       - "[STATUS] == 200"
       - "[BODY].status == UP"
       - "[RESPONSE_TIME] < 1000"
   - name: twinnation-articles-api
-    interval: 10s
+    interval: 30s
     url: https://twinnation.org/api/v1/articles/24
     conditions:
       - "[STATUS] == 200"
       - "[BODY].id == 24"
       - "[BODY].tags[0] == spring"
-  - name: example
-    url: https://example.org/
-    interval: 30s
-    conditions:
-      - "[STATUS] == 200"
+      - "len([BODY].tags) > 0"

config/config.go

@@ -22,6 +22,7 @@ var (
 
 type Config struct {
 	Metrics  bool            `yaml:"metrics"`
+	Alerting *core.Alerting  `yaml:"alerting"`
 	Services []*core.Service `yaml:"services"`
 }
 

config/config_test.go

@@ -2,6 +2,7 @@ package config
 
 import (
 	"fmt"
+	"github.com/TwinProduction/gatus/core"
 	"testing"
 	"time"
 )
@@ -23,6 +24,9 @@ services:
 	if err != nil {
 		t.Error("No error should've been returned")
 	}
+	if config == nil {
+		t.Fatal("Config shouldn't have been nil")
+	}
 	if len(config.Services) != 2 {
 		t.Error("Should have returned two services")
 	}
@@ -58,6 +62,9 @@ services:
 	if err != nil {
 		t.Error("No error should've been returned")
 	}
+	if config == nil {
+		t.Fatal("Config shouldn't have been nil")
+	}
 	if config.Metrics {
 		t.Error("Metrics should've been false by default")
 	}
@@ -81,6 +88,9 @@ services:
 	if err != nil {
 		t.Error("No error should've been returned")
 	}
+	if config == nil {
+		t.Fatal("Config shouldn't have been nil")
+	}
 	if !config.Metrics {
 		t.Error("Metrics should have been true")
 	}
@@ -107,3 +117,62 @@ badconfig:
 		t.Error("The error returned should have been of type ErrNoServiceInConfig")
 	}
 }
+
+func TestParseAndValidateConfigBytesWithAlerting(t *testing.T) {
+	config, err := parseAndValidateConfigBytes([]byte(`
+alerting:
+  slack: "http://example.com"
+services:
+  - name: twinnation
+    url: https://twinnation.org/actuator/health
+    alerts:
+      - type: slack
+        enabled: true
+        threshold: 7
+        description: "Healthcheck failed 7 times in a row"
+    conditions:
+      - "[STATUS] == 200"
+`))
+	if err != nil {
+		t.Error("No error should've been returned")
+	}
+	if config == nil {
+		t.Fatal("Config shouldn't have been nil")
+	}
+	if config.Metrics {
+		t.Error("Metrics should've been false by default")
+	}
+	if config.Alerting == nil {
+		t.Fatal("config.Alerting shouldn't have been nil")
+	}
+	if config.Alerting.Slack != "http://example.com" {
+		t.Errorf("Slack webhook should've been %s, but was %s", "http://example.com", config.Alerting.Slack)
+	}
+	if len(config.Services) != 1 {
+		t.Error("There should've been 1 service")
+	}
+	if config.Services[0].Url != "https://twinnation.org/actuator/health" {
+		t.Errorf("URL should have been %s", "https://twinnation.org/actuator/health")
+	}
+	if config.Services[0].Interval != 10*time.Second {
+		t.Errorf("Interval should have been %s, because it is the default value", 10*time.Second)
+	}
+	if config.Services[0].Alerts == nil {
+		t.Fatal("The service alerts shouldn't have been nil")
+	}
+	if len(config.Services[0].Alerts) != 1 {
+		t.Fatal("There should've been 1 alert configured")
+	}
+	if !config.Services[0].Alerts[0].Enabled {
+		t.Error("The alert should've been enabled")
+	}
+	if config.Services[0].Alerts[0].Threshold != 7 {
+		t.Errorf("The threshold of the alert should've been %d, but it was %d", 7, config.Services[0].Alerts[0].Threshold)
+	}
+	if config.Services[0].Alerts[0].Type != core.SlackAlert {
+		t.Errorf("The type of the alert should've been %s, but it was %s", core.SlackAlert, config.Services[0].Alerts[0].Type)
+	}
+	if config.Services[0].Alerts[0].Description != "Healthcheck failed 7 times in a row" {
+		t.Errorf("The type of the alert should've been %s, but it was %s", "Healthcheck failed 7 times in a row", config.Services[0].Alerts[0].Description)
+	}
+}

core/alert.go

@@ -0,0 +1,22 @@
+package core
+
+// Alert is the service's alert configuration
+type Alert struct {
+	// Type of alert
+	Type AlertType `yaml:"type"`
+
+	// Enabled defines whether or not the alert is enabled
+	Enabled bool `yaml:"enabled"`
+
+	// Threshold is the number of failures in a row needed before triggering the alert
+	Threshold int `yaml:"threshold"`
+
+	// Description of the alert. Will be included in the alert sent.
+	Description string `yaml:"description"`
+}
+
+type AlertType string
+
+const (
+	SlackAlert AlertType = "slack"
+)

core/alerting.go

@@ -0,0 +1,5 @@
+package core
+
+type Alerting struct {
+	Slack string `yaml:"slack"`
+}

core/condition.go

@@ -41,10 +41,10 @@ func (c *Condition) evaluate(result *Result) bool {
 		return false
 	}
 	conditionToDisplay := condition
-	// If the condition isn't a success, return the resolved condition
+	// If the condition isn't a success, return what the resolved condition was too
 	if !success {
 		log.Printf("[Condition][evaluate] Condition '%s' did not succeed because '%s' is false", condition, resolvedCondition)
-		conditionToDisplay = resolvedCondition
+		conditionToDisplay = fmt.Sprintf("%s (%s)", condition, resolvedCondition)
 	}
 	result.ConditionResults = append(result.ConditionResults, &ConditionResult{Condition: conditionToDisplay, Success: success})
 	return success

core/condition_test.go

@@ -166,3 +166,21 @@ func TestCondition_evaluateWithBodyJsonPathComplexIntFailureUsingLessThan(t *tes
 		t.Errorf("Condition '%s' should have been a failure", condition)
 	}
 }
+
+func TestCondition_evaluateWithBodySliceLength(t *testing.T) {
+	condition := Condition("len([BODY].data) == 3")
+	result := &Result{Body: []byte("{\"data\": [{\"id\": 1}, {\"id\": 2}, {\"id\": 3}]}")}
+	condition.evaluate(result)
+	if !result.ConditionResults[0].Success {
+		t.Errorf("Condition '%s' should have been a success", condition)
+	}
+}
+
+func TestCondition_evaluateWithBodyStringLength(t *testing.T) {
+	condition := Condition("len([BODY].name) == 8")
+	result := &Result{Body: []byte("{\"name\": \"john.doe\"}")}
+	condition.evaluate(result)
+	if !result.ConditionResults[0].Success {
+		t.Errorf("Condition '%s' should have been a success", condition)
+	}
+}

core/service.go

@@ -26,6 +26,9 @@ type Service struct {
 	Headers    map[string]string `yaml:"headers,omitempty"`
 	Interval   time.Duration     `yaml:"interval,omitempty"`
 	Conditions []*Condition      `yaml:"conditions"`
+	Alerts     []*Alert          `yaml:"alerts"`
+
+	numberOfFailuresInARow int
 }
 
 func (service *Service) Validate() {
@@ -39,6 +42,11 @@ func (service *Service) Validate() {
 	if len(service.Headers) == 0 {
 		service.Headers = make(map[string]string)
 	}
+	for _, alert := range service.Alerts {
+		if alert.Threshold <= 0 {
+			alert.Threshold = 3
+		}
+	}
 	if len(service.Url) == 0 {
 		panic(ErrNoUrl)
 	}
@@ -68,9 +76,29 @@ func (service *Service) EvaluateConditions() *Result {
 		}
 	}
 	result.Timestamp = time.Now()
+	if result.Success {
+		service.numberOfFailuresInARow = 0
+		// TODO: Send notification that alert has been resolved?
+	} else {
+		service.numberOfFailuresInARow++
+	}
 	return result
 }
 
+func (service *Service) GetAlertsTriggered() []Alert {
+	var alerts []Alert
+	if service.numberOfFailuresInARow == 0 {
+		return alerts
+	}
+	for _, alert := range service.Alerts {
+		if alert.Enabled && alert.Threshold == service.numberOfFailuresInARow {
+			alerts = append(alerts, *alert)
+			continue
+		}
+	}
+	return alerts
+}
+
 func (service *Service) getIp(result *Result) {
 	urlObject, err := url.Parse(service.Url)
 	if err != nil {

core/util.go

@@ -13,6 +13,9 @@ const (
 	ResponseTimePlaceHolder = "[RESPONSE_TIME]"
 	BodyPlaceHolder         = "[BODY]"
 
+	LengthFunctionPrefix = "len("
+	FunctionSuffix       = ")"
+
 	InvalidConditionElementSuffix = "(INVALID)"
 )
 
@@ -32,13 +35,22 @@ func sanitizeAndResolve(list []string, result *Result) []string {
 			element = body
 		default:
 			// if starts with BodyPlaceHolder, then evaluate json path
-			if strings.HasPrefix(element, BodyPlaceHolder) {
-				resolvedElement, err := jsonpath.Eval(strings.Replace(element, fmt.Sprintf("%s.", BodyPlaceHolder), "", 1), result.Body)
+			if strings.Contains(element, BodyPlaceHolder) {
+				wantLength := false
+				if strings.HasPrefix(element, LengthFunctionPrefix) && strings.HasSuffix(element, FunctionSuffix) {
+					wantLength = true
+					element = strings.TrimSuffix(strings.TrimPrefix(element, LengthFunctionPrefix), FunctionSuffix)
+				}
+				resolvedElement, resolvedElementLength, err := jsonpath.Eval(strings.Replace(element, fmt.Sprintf("%s.", BodyPlaceHolder), "", 1), result.Body)
 				if err != nil {
 					result.Errors = append(result.Errors, err.Error())
 					element = fmt.Sprintf("%s %s", element, InvalidConditionElementSuffix)
 				} else {
-					element = resolvedElement
+					if wantLength {
+						element = fmt.Sprintf("%d", resolvedElementLength)
+					} else {
+						element = resolvedElement
+					}
 				}
 			}
 		}

example/docker-compose-grafana-prometheus/config.yaml

@@ -2,11 +2,12 @@ metrics: true
 services:
   - name: TwiNNatioN
     url: https://twinnation.org/health
-    interval: 10s
+    interval: 30s
     conditions:
       - "[STATUS] == 200"
   - name: GitHub
     url: https://api.github.com/healthz
+    interval: 5m
     conditions:
       - "[STATUS] == 200"
   - name: Example

example/kubernetes/gatus.yaml

@@ -10,6 +10,7 @@ data:
           - "[STATUS] == 200"
       - name: GitHub
         url: https://api.github.com/healthz
+        interval: 5m
         conditions:
           - "[STATUS] == 200"
       - name: Example

go.mod

@@ -1,6 +1,6 @@
 module github.com/TwinProduction/gatus
 
-go 1.14
+go 1.15
 
 require (
 	github.com/prometheus/client_golang v1.2.1

jsonpath/jsonpath.go

@@ -8,26 +8,30 @@ import (
 )
 
 // Eval is a half-baked json path implementation that needs some love
-func Eval(path string, b []byte) (string, error) {
+func Eval(path string, b []byte) (string, int, error) {
 	var object interface{}
 	err := json.Unmarshal(b, &object)
 	if err != nil {
 		// Try to unmarshal it into an array instead
-		return "", err
+		return "", 0, err
 	}
 	return walk(path, object)
 }
 
-func walk(path string, object interface{}) (string, error) {
+func walk(path string, object interface{}) (string, int, error) {
 	keys := strings.Split(path, ".")
 	currentKey := keys[0]
 	switch value := extractValue(currentKey, object).(type) {
 	case map[string]interface{}:
 		return walk(strings.Replace(path, fmt.Sprintf("%s.", currentKey), "", 1), value)
+	case string:
+		return value, len(value), nil
+	case []interface{}:
+		return fmt.Sprintf("%v", value), len(value), nil
 	case interface{}:
-		return fmt.Sprintf("%v", value), nil
+		return fmt.Sprintf("%v", value), 1, nil
 	default:
-		return "", fmt.Errorf("couldn't walk through '%s' because type was '%T', but expected 'map[string]interface{}'", currentKey, value)
+		return "", 0, fmt.Errorf("couldn't walk through '%s' because type was '%T', but expected 'map[string]interface{}'", currentKey, value)
 	}
 }
 

jsonpath/jsonpath_test.go

@@ -8,10 +8,13 @@ func TestEval(t *testing.T) {
 
 	expectedOutput := "value"
 
-	output, err := Eval(path, []byte(data))
+	output, outputLength, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
+	if outputLength != len(expectedOutput) {
+		t.Errorf("Expected output length to be %v, but was %v", len(expectedOutput), outputLength)
+	}
 	if output != expectedOutput {
 		t.Errorf("Expected output to be %v, but was %v", expectedOutput, output)
 	}
@@ -23,7 +26,7 @@ func TestEvalWithLongSimpleWalk(t *testing.T) {
 
 	expectedOutput := "value"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
@@ -38,10 +41,11 @@ func TestEvalWithArrayOfMaps(t *testing.T) {
 
 	expectedOutput := "2"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
+
 	if output != expectedOutput {
 		t.Errorf("Expected output to be %v, but was %v", expectedOutput, output)
 	}
@@ -53,7 +57,7 @@ func TestEvalWithArrayOfValues(t *testing.T) {
 
 	expectedOutput := "1"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
@@ -68,7 +72,7 @@ func TestEvalWithRootArrayOfValues(t *testing.T) {
 
 	expectedOutput := "2"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
@@ -83,7 +87,7 @@ func TestEvalWithRootArrayOfMaps(t *testing.T) {
 
 	expectedOutput := "1"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
@@ -96,7 +100,7 @@ func TestEvalWithRootArrayOfMapsUsingInvalidArrayIndex(t *testing.T) {
 	path := "[5].id"
 	data := `[{"id": 1}, {"id": 2}]`
 
-	_, err := Eval(path, []byte(data))
+	_, _, err := Eval(path, []byte(data))
 	if err == nil {
 		t.Error("Should've returned an error, but didn't")
 	}
@@ -108,7 +112,7 @@ func TestEvalWithLongWalkAndArray(t *testing.T) {
 
 	expectedOutput := "1"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
@@ -123,7 +127,7 @@ func TestEvalWithNestedArray(t *testing.T) {
 
 	expectedOutput := "7"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}
@@ -138,7 +142,7 @@ func TestEvalWithMapOfNestedArray(t *testing.T) {
 
 	expectedOutput := "e"
 
-	output, err := Eval(path, []byte(data))
+	output, _, err := Eval(path, []byte(data))
 	if err != nil {
 		t.Error("Didn't expect any error, but got", err)
 	}

main.go

@@ -1,6 +1,8 @@
 package main
 
 import (
+	"bytes"
+	"compress/gzip"
 	"encoding/json"
 	"github.com/TwinProduction/gatus/config"
 	"github.com/TwinProduction/gatus/watchdog"
@@ -8,6 +10,16 @@ import (
 	"log"
 	"net/http"
 	"os"
+	"strings"
+	"time"
+)
+
+const CacheTTL = 10 * time.Second
+
+var (
+	cachedServiceResults          []byte
+	cachedServiceResultsGzipped   []byte
+	cachedServiceResultsTimestamp time.Time
 )
 
 func main() {
@@ -37,14 +49,30 @@ func loadConfiguration() *config.Config {
 	return config.Get()
 }
 
-func serviceResultsHandler(writer http.ResponseWriter, _ *http.Request) {
-	serviceResults := watchdog.GetServiceResults()
-	data, err := json.Marshal(serviceResults)
-	if err != nil {
-		log.Printf("[main][serviceResultsHandler] Unable to marshall object to JSON: %s", err.Error())
-		writer.WriteHeader(http.StatusInternalServerError)
-		_, _ = writer.Write([]byte("Unable to marshall object to JSON"))
-		return
+func serviceResultsHandler(writer http.ResponseWriter, r *http.Request) {
+	if isExpired := cachedServiceResultsTimestamp.IsZero() || time.Now().Sub(cachedServiceResultsTimestamp) > CacheTTL; isExpired {
+		buffer := &bytes.Buffer{}
+		gzipWriter := gzip.NewWriter(buffer)
+		serviceResults := watchdog.GetServiceResults()
+		data, err := json.Marshal(serviceResults)
+		if err != nil {
+			log.Printf("[main][serviceResultsHandler] Unable to marshall object to JSON: %s", err.Error())
+			writer.WriteHeader(http.StatusInternalServerError)
+			_, _ = writer.Write([]byte("Unable to marshall object to JSON"))
+			return
+		}
+		gzipWriter.Write(data)
+		gzipWriter.Close()
+		cachedServiceResults = data
+		cachedServiceResultsGzipped = buffer.Bytes()
+		cachedServiceResultsTimestamp = time.Now()
+	}
+	var data []byte
+	if strings.Contains(r.Header.Get("Accept-Encoding"), "gzip") {
+		writer.Header().Set("Content-Encoding", "gzip")
+		data = cachedServiceResultsGzipped
+	} else {
+		data = cachedServiceResults
 	}
 	writer.Header().Add("Content-type", "application/json")
 	writer.WriteHeader(http.StatusOK)

static/index.html

@@ -31,11 +31,18 @@
 		}
 		.status {
 			cursor: pointer;
-			transition: opacity 500ms ease-in-out;
+			transition: all 500ms ease-in-out;
+			overflow-x: hidden;
+			padding: .25em 0;
+			color: white;
+		}
+		.title {
+			font-size: 2.5rem;
 		}
 		.status:hover {
 			opacity: 0.7;
 			transition: opacity 100ms ease-in-out;
+			color: black;
 		}
 		.status-over-time {
 			overflow: auto;
@@ -48,6 +55,9 @@
 			opacity: 0.5;
 			margin-top: 5px;
 		}
+		.status-min-max-ms {
+			overflow-x: hidden;
+		}
 		#tooltip {
 			position: fixed;
 			top: 0;
@@ -76,9 +86,16 @@
 	</style>
 </head>
 <body>
-	<div class="container my-3 rounded p-4 border shadow">
-		<div class="mb-3">
-			<div class="display-4">Health Status</div>
+	<div class="container my-3 rounded p-3 border shadow">
+		<div class="mb-2">
+			<div class="row">
+				<div class="col-8 text-left my-auto">
+					<div class="title display-4">Health Status</div>
+				</div>
+				<div class="col-4 text-right">
+					<img src="logo.png" alt="GaTuS" style="position: relative; min-width: 50px; max-width: 200px; width: 20%;"/>
+				</div>
+			</div>
 		</div>
 		<div id="results"></div>
 	</div>
@@ -136,6 +153,9 @@
 			let tooltipBoundingClientRect = document.querySelector('#tooltip').getBoundingClientRect();
 			if (targetLeftPosition + window.scrollX + tooltipBoundingClientRect.width + 50 > document.body.getBoundingClientRect().width) {
 				targetLeftPosition = element.getBoundingClientRect().x - tooltipBoundingClientRect.width + element.getBoundingClientRect().width;
+				if (targetLeftPosition < 0) {
+					targetLeftPosition += -targetLeftPosition;
+				}
 			}
 			if (targetTopPosition + window.scrollY + tooltipBoundingClientRect.height + 50 > document.body.getBoundingClientRect().height) {
 				targetTopPosition = element.getBoundingClientRect().y - (tooltipBoundingClientRect.height + 10)
@@ -160,62 +180,69 @@
 
 		function refreshResults() {
 			$.getJSON("/api/v1/results", function (data) {
-				serviceStatuses = data;
-				let output = "";
-				for (let serviceName in data) {
-					let serviceStatusOverTime = "";
-					let hostname = data[serviceName][data[serviceName].length-1].hostname
-					let minResponseTime = null;
-					let maxResponseTime = null;
-					let newestTimestamp = null;
-					let oldestTimestamp = null;
-					for (let key in data[serviceName]) {
-						let serviceResult = data[serviceName][key];
-						serviceStatusOverTime = createStatusBadge(serviceName, key, serviceResult.success) + serviceStatusOverTime;
-						const responseTime = parseInt(serviceResult.duration/1000000);
-						if (minResponseTime == null || minResponseTime > responseTime) {
-							minResponseTime = responseTime;
-						}
-						if (maxResponseTime == null || maxResponseTime < responseTime) {
-							maxResponseTime = responseTime;
-						}
-						const timestamp = new Date(serviceResult.timestamp);
-						if (newestTimestamp == null || newestTimestamp > timestamp) {
-							newestTimestamp = timestamp;
-						}
-						if (oldestTimestamp == null || oldestTimestamp < timestamp) {
-							oldestTimestamp = timestamp;
-						}
-					}
-					output += ""
-						+ "<div class='container py-3 border-left border-right border-top border-black'>"
-						+ "  <div class='row mb-2'>"
-						+ "    <div class='col-8'>"
-						+ "      <span class='font-weight-bold'>" + serviceName + "</span> <span class='text-secondary font-weight-lighter'>- " + hostname + "</span>"
-						+ "    </div>"
-						+ "    <div class='col-4 text-right'>"
-						+ "      <span class='font-weight-lighter'>" + (minResponseTime === maxResponseTime ? minResponseTime : (minResponseTime + "-" + maxResponseTime)) + "ms</span>"
-						+ "    </div>"
-						+ "  </div>"
-						+ "  <div class='row'>"
-						+ "    <div class='col-12 d-flex flex-row-reverse status-over-time'>"
-						+ "      " + serviceStatusOverTime
-						+ "    </div>"
-						+ "  </div>"
-						+ "  <div class='row status-time-ago'>"
-						+ "    <div class='col-6'>"
-						+ "      " + generatePrettyTimeAgo(newestTimestamp)
-						+ "    </div>"
-						+ "    <div class='col-6 text-right'>"
-						+ "      " + generatePrettyTimeAgo(oldestTimestamp)
-						+ "    </div>"
-						+ "  </div>"
-						+ "</div>";
+				// Update the table only if there's a change
+				if (JSON.stringify(serviceStatuses) !== JSON.stringify(data)) {
+					serviceStatuses = data;
+					buildTable();
 				}
-				$("#results").html(output);
 			});
 		}
 
+		function buildTable() {
+			let output = "";
+			for (let serviceName in serviceStatuses) {
+				let serviceStatusOverTime = "";
+				let hostname = serviceStatuses[serviceName][serviceStatuses[serviceName].length-1].hostname
+				let minResponseTime = null;
+				let maxResponseTime = null;
+				let newestTimestamp = null;
+				let oldestTimestamp = null;
+				for (let key in serviceStatuses[serviceName]) {
+					let serviceResult = serviceStatuses[serviceName][key];
+					serviceStatusOverTime = createStatusBadge(serviceName, key, serviceResult.success) + serviceStatusOverTime;
+					const responseTime = parseInt(serviceResult.duration/1000000);
+					if (minResponseTime == null || minResponseTime > responseTime) {
+						minResponseTime = responseTime;
+					}
+					if (maxResponseTime == null || maxResponseTime < responseTime) {
+						maxResponseTime = responseTime;
+					}
+					const timestamp = new Date(serviceResult.timestamp);
+					if (newestTimestamp == null || newestTimestamp < timestamp) {
+						newestTimestamp = timestamp;
+					}
+					if (oldestTimestamp == null || oldestTimestamp > timestamp) {
+						oldestTimestamp = timestamp;
+					}
+				}
+				output += ""
+					+ "<div class='container py-3 border-left border-right border-top border-black'>"
+					+ "  <div class='row mb-2'>"
+					+ "    <div class='col-md-10'>"
+					+ "      <span class='font-weight-bold'>" + serviceName + "</span> <span class='text-secondary font-weight-lighter'>- " + hostname + "</span>"
+					+ "    </div>"
+					+ "    <div class='col-md-2 text-right'>"
+					+ "      <span class='font-weight-lighter status-min-max-ms'>" + (minResponseTime === maxResponseTime ? minResponseTime : (minResponseTime + "-" + maxResponseTime)) + "ms</span>"
+					+ "    </div>"
+					+ "  </div>"
+					+ "  <div class='row'>"
+					+ "    <div class='col-12 d-flex flex-row-reverse status-over-time'>"
+					+ "      " + serviceStatusOverTime
+					+ "    </div>"
+					+ "  </div>"
+					+ "  <div class='row status-time-ago'>"
+					+ "    <div class='col-6'>"
+					+ "      " + generatePrettyTimeAgo(oldestTimestamp)
+					+ "    </div>"
+					+ "    <div class='col-6 text-right'>"
+					+ "      " + generatePrettyTimeAgo(newestTimestamp)
+					+ "    </div>"
+					+ "  </div>"
+					+ "</div>";
+			}
+			$("#results").html(output);
+		}
+
 		function prettifyTimestamp(timestamp) {
 			let date = new Date(timestamp);
 			let YYYY = date.getFullYear();
@@ -224,7 +251,7 @@
 			let hh = ((date.getHours())<10?"0":"")+""+(date.getHours());
 			let mm = ((date.getMinutes())<10?"0":"")+""+(date.getMinutes());
 			let ss = ((date.getSeconds())<10?"0":"")+""+(date.getSeconds());
-			return YYYY+"-"+MM+"-"+DD+" "+hh+":"+mm+":"+ss;
+			return YYYY + "-" + MM + "-" + DD + " " + hh + ":" + mm + ":" + ss;
 		}
 
 		function generatePrettyTimeAgo(t) {

watchdog/watchdog.go

@@ -2,6 +2,7 @@ package watchdog
 
 import (
 	"fmt"
+	"github.com/TwinProduction/gatus/alerting"
 	"github.com/TwinProduction/gatus/config"
 	"github.com/TwinProduction/gatus/core"
 	"github.com/TwinProduction/gatus/metric"
@@ -15,10 +16,12 @@ var (
 	rwLock         sync.RWMutex
 )
 
+// GetServiceResults returns a list of the last 20 results for each services
 func GetServiceResults() *map[string][]*core.Result {
 	return &serviceResults
 }
 
+// Monitor loops over each services and starts a goroutine to monitor each services separately
 func Monitor(cfg *config.Config) {
 	for _, service := range cfg.Services {
 		go monitor(service)
@@ -27,12 +30,13 @@ func Monitor(cfg *config.Config) {
 	}
 }
 
+// monitor monitors a single service in a loop
 func monitor(service *core.Service) {
 	for {
 		// By placing the lock here, we prevent multiple services from being monitored at the exact same time, which
 		// could cause performance issues and return inaccurate results
 		rwLock.Lock()
-		log.Printf("[watchdog][Monitor] Monitoring serviceName=%s", service.Name)
+		log.Printf("[watchdog][monitor] Monitoring serviceName=%s", service.Name)
 		result := service.EvaluateConditions()
 		metric.PublishMetricsForService(service, result)
 		serviceResults[service.Name] = append(serviceResults[service.Name], result)
@@ -45,13 +49,28 @@ func monitor(service *core.Service) {
 			extra = fmt.Sprintf("responseBody=%s", result.Body)
 		}
 		log.Printf(
-			"[watchdog][Monitor] Finished monitoring serviceName=%s; errors=%d; requestDuration=%s; %s",
+			"[watchdog][monitor] Finished monitoring serviceName=%s; errors=%d; requestDuration=%s; %s",
 			service.Name,
 			len(result.Errors),
 			result.Duration.Round(time.Millisecond),
 			extra,
 		)
-		log.Printf("[watchdog][Monitor] Waiting interval=%s before monitoring serviceName=%s", service.Interval, service.Name)
+
+		cfg := config.Get()
+		if cfg.Alerting != nil {
+			for _, alertTriggered := range service.GetAlertsTriggered() {
+				if alertTriggered.Type == core.SlackAlert {
+					if len(cfg.Alerting.Slack) > 0 {
+						log.Printf("[watchdog][monitor] Sending Slack alert because alert with description=%s has been triggered", alertTriggered.Description)
+						alerting.SendSlackMessage(cfg.Alerting.Slack, service.Name, alertTriggered.Description)
+					} else {
+						log.Printf("[watchdog][monitor] Not sending Slack alert despite being triggered, because there is no Slack webhook configured")
+					}
+				}
+			}
+		}
+
+		log.Printf("[watchdog][monitor] Waiting for interval=%s before monitoring serviceName=%s", service.Interval, service.Name)
 		time.Sleep(service.Interval)
 	}
 }