Compare commits

...

27 Commits

Author SHA1 Message Date
TwinProduction
230c8821ec Merge util.go into condition.go 2020-10-04 20:00:24 -04:00
TwinProduction
ecef3d9538 Add result.Connected in integration tests 2020-10-04 19:55:19 -04:00
TwinProduction
3ecfe4d322 Close #18: Support monitoring TCP services 2020-10-04 19:49:02 -04:00
TwinProduction
6a3f65db7f Close #14: Support skipping certificate verification (services[].insecure) 2020-10-04 17:01:10 -04:00
Chris C
ed490669b1 Merge pull request #15 from hurnhu/refresh-interval
Close #1: Add support for refresh interval
2020-10-02 12:20:09 -04:00
TwinProduction
187b38ee22 Fix format 2020-10-02 12:10:09 -04:00
TwinProduction
261fe27b2e Move refresh interval to bottom left corner instead
+ Use icon
+ Minor improvements
2020-10-02 12:08:52 -04:00
mike
a29f175cba default 30 seconds 2020-10-02 10:10:48 -04:00
mike
f26dacaf22 changed interval input to a select. select is autopopulated with options on load. default is 30 seconds 2020-10-02 09:48:23 -04:00
TwinProduction
b4d81a9661 Tables are cuter 2020-10-01 20:04:04 -04:00
TwinProduction
81c59f02d8 Close #16: Update documentation 2020-10-01 19:57:52 -04:00
TwinProduction
8101646ba5 Work on #16: Support patterns 2020-10-01 19:57:11 -04:00
Michael LaPan
93b7220d5f added code to set the refresh interval 2020-10-01 10:45:20 -04:00
TwinProduction
18d3236586 Make resolved/triggered alert logs more obvious 2020-09-29 20:06:47 -04:00
TwinProduction
bc16ae1794 Add tests for comparing two placeholders 2020-09-29 19:33:06 -04:00
Chris C
d019942278 Update README.md 2020-09-28 12:50:22 -04:00
TwinProduction
8c5551f93b Update build.yml 2020-09-27 20:39:42 -04:00
TwinProduction
3b15feaf7d Update README.md 2020-09-26 15:21:06 -04:00
TwinProduction
326ad2c80d Update README.md 2020-09-26 15:18:52 -04:00
TwinProduction
b4b9f5c1be Improve documentation 2020-09-26 15:15:50 -04:00
TwinProduction
ac5ad9d173 Work on common provider interface to make adding new providers easier 2020-09-26 14:23:43 -04:00
TwinProduction
7dcd462883 Clean up old code 2020-09-25 18:23:30 -04:00
TwinProduction
5655661778 Add missing provider.go file 2020-09-24 19:54:15 -04:00
TwinProduction
fac7b8551a Start working on implementing common provider interface 2020-09-24 19:52:59 -04:00
TwinProduction
59fed008e0 Rename service's EvaluateConditions() to EvaluateHealth() 2020-09-24 19:49:32 -04:00
TwinProduction
286e8f8590 Add config validation logs on application start 2020-09-22 17:46:40 -04:00
TwinProduction
4daf261d95 Minor update 2020-09-21 10:41:23 -04:00
24 changed files with 713 additions and 218 deletions

View File

@@ -14,13 +14,13 @@ jobs:
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- name: Set up Go 1.14
- name: Set up Go 1.15
uses: actions/setup-go@v1
with:
go-version: 1.14
go-version: 1.15
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v1
uses: actions/checkout@v2
- name: Build binary to make sure it works
run: go build -mod vendor
- name: Test

114
README.md
View File

@@ -1,13 +1,13 @@
![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)
[![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
image with a custom configuration file.
I personally deploy it in my Kubernetes cluster and have it monitor the status of my
I personally deploy it in my Kubernetes cluster and let it monitor the status of my
core applications: https://status.twinnation.org/
@@ -17,6 +17,8 @@ core applications: https://status.twinnation.org/
- [Usage](#usage)
- [Configuration](#configuration)
- [Conditions](#conditions)
- [Placeholders](#placeholders)
- [Functions](#functions)
- [Alerting](#alerting)
- [Configuring Slack alerts](#configuring-slack-alerts)
- [Configuring PagerDuty alerts](#configuring-pagerduty-alerts)
@@ -27,6 +29,9 @@ core applications: https://status.twinnation.org/
- [Using in Production](#using-in-production)
- [FAQ](#faq)
- [Sending a GraphQL request](#sending-a-graphql-request)
- [Recommended interval](#recommended-interval)
- [Default timeouts](#default-timeouts)
- [Monitoring a TCP service](#monitoring-a-tcp-service)
## Features
@@ -75,13 +80,14 @@ Note that you can also add environment variables in the configuration file (i.e.
### Configuration
| Parameter | Description | Default |
| ---------------------------------------- | ----------------------------------------------------------------------------- | -------------- |
|:---------------------------------------- |:----------------------------------------------------------------------------- |:-------------- |
| `debug` | Whether to enable debug logs | `false` |
| `metrics` | Whether to expose metrics at /metrics | `false` |
| `services` | List of services to monitor | Required `[]` |
| `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[].insecure` | Whether to skip verifying the server's certificate chain and host name | `false` |
| `services[].interval` | Duration to wait between every status check | `60s` |
| `services[].method` | Request method | `GET` |
| `services[].graphql` | Whether to wrap the body in a query param (`{"query":"$body"}`) | `false` |
@@ -114,23 +120,48 @@ Note that you can also add environment variables in the configuration file (i.e.
Here are some examples of conditions you can use:
| Condition | Description | Passing values | Failing values |
| -----------------------------| ------------------------------------------------------- | -------------------------- | -------------- |
|:-----------------------------|:------------------------------------------------------- |:-------------------------- | -------------- |
| `[STATUS] == 200` | Status must be equal to 200 | 200 | 201, 404, ... |
| `[STATUS] < 300` | Status must lower than 300 | 200, 201, 299 | 301, 302, ... |
| `[STATUS] <= 299` | Status must be less than or equal to 299 | 200, 201, 299 | 301, 302, ... |
| `[STATUS] > 400` | Status must be greater than 400 | 401, 402, 403, 404 | 400, 200, ... |
| `[CONNECTED] == true` | Connection to host must've been successful | true, false | |
| `[RESPONSE_TIME] < 500` | Response time must be below 500ms | 100ms, 200ms, 300ms | 500ms, 501ms |
| `[BODY] == 1` | The body must be equal to 1 | 1 | Anything else |
| `[IP] == 127.0.0.1` | Target IP must be 127.0.0.1 | 127.0.0.1 | 0.0.0.0 |
| `[BODY] == 1` | The body must be equal to 1 | 1 | `{}`, `2`, ... |
| `[BODY].user.name == john` | JSONPath value of `$.user.name` is equal to `john` | `{"user":{"name":"john"}}` | |
| `[BODY].data[0].id == 1` | JSONPath value of `$.data[0].id` is equal to 1 | `{"data":[{"id":1}]}` | |
| `[BODY].age == [BODY].id` | JSONPath value of `$.age` is equal JSONPath `$.id` | `{"age":1,"id":1}` | |
| `len([BODY].data) < 5` | Array at JSONPath `$.data` has less than 5 elements | `{"data":[{"id":1}]}` | |
| `len([BODY].name) == 8` | String at JSONPath `$.name` has a length of 8 | `{"name":"john.doe"}` | `{"name":"bob"}` |
| `[BODY].name == pat(john*)` | String at JSONPath `$.name` matches pattern `john*` | `{"name":"john.doe"}` | `{"name":"bob"}` |
#### Placeholders
| Placeholder | Description | Example of resolved value |
|:----------------------- |:------------------------------------------------------- |:------------------------- |
| `[STATUS]` | Resolves into the HTTP status of the request | 404
| `[RESPONSE_TIME]` | Resolves into the response time the request took, in ms | 10
| `[IP]` | Resolves into the IP of the target host | 192.168.0.232
| `[BODY]` | Resolves into the response body. Supports JSONPath. | `{"name":"john.doe"}`
| `[CONNECTED]` | Resolves into whether a connection could be established | `true`
#### Functions
| Function | Description | Example |
|:-----------|:---------------------------------------------------------------------------------------------------------------- |:-------------------------- |
| `len` | Returns the length of the object/slice. Works only with the `[BODY]` placeholder. | `len([BODY].username) > 8`
| `pat` | Specifies that the string passed as parameter should be evaluated as a pattern. Works only with `==` and `!=`. | `[IP] == pat(192.168.*)`
**NOTE**: Use `pat` only when you need to. `[STATUS] == pat(2*)` is a lot more expensive than `[STATUS] < 300`.
### Alerting
#### Configuring Slack alerts
```yaml
@@ -139,8 +170,8 @@ alerting:
webhook-url: "https://hooks.slack.com/services/**********/**********/**********"
services:
- name: twinnation
interval: 30s
url: "https://twinnation.org/health"
interval: 30s
alerts:
- type: slack
enabled: true
@@ -175,15 +206,15 @@ alerting:
integration-key: "********************************"
services:
- name: twinnation
interval: 30s
url: "https://twinnation.org/health"
interval: 30s
alerts:
- type: pagerduty
enabled: true
failure-threshold: 3
success-threshold: 5
description: "healthcheck failed 3 times in a row"
send-on-resolved: true
description: "healthcheck failed 3 times in a row"
conditions:
- "[STATUS] == 200"
- "[BODY].status == UP"
@@ -208,8 +239,8 @@ services:
- type: twilio
enabled: true
failure-threshold: 5
description: "healthcheck failed 5 times in a row"
send-on-resolved: true
description: "healthcheck failed 5 times in a row"
conditions:
- "[STATUS] == 200"
- "[BODY].status == UP"
@@ -245,8 +276,8 @@ alerting:
}
services:
- name: twinnation
interval: 30s
url: "https://twinnation.org/health"
interval: 30s
alerts:
- type: custom
enabled: true
@@ -267,12 +298,12 @@ Other than using one of the examples provided in the `examples` folder, you can
creating a configuration file - we'll call it `config.yaml` for this example - and running the following
command:
```
docker run -p 8080:8080 --mount type=bind,source="$(pwd)"/test.yaml,target=/config/config.yaml --name gatus twinproduction/gatus
docker run -p 8080:8080 --mount type=bind,source="$(pwd)"/config.yaml,target=/config/config.yaml --name gatus twinproduction/gatus
```
If you're on Windows, replace `"$(pwd)"` by the absolute path to your current directory, e.g.:
```
docker run -p 8080:8080 --mount type=bind,source=E:/Go/src/github.com/TwinProduction/gatus/test.yaml,target=/config/config.yaml --name gatus twinproduction/gatus
docker run -p 8080:8080 --mount type=bind,source=C:/Users/Chris/Desktop/config.yaml,target=/config/config.yaml --name gatus twinproduction/gatus
```
## Running the tests
@@ -320,3 +351,60 @@ will send a `POST` request to `http://localhost:8080/playground` with the follow
```json
{"query":" {\n user(gender: \"female\") {\n id\n name\n gender\n avatar\n }\n }"}
```
### Recommended interval
To ensure that Gatus provides reliable and accurate results (i.e. response time), Gatus only evaluates one service at a time.
In other words, even if you have multiple services with the exact same interval, they will not execute at the same time.
You can test this yourself by running Gatus with several services configured with a very short, unrealistic interval,
such as 1ms. You'll notice that the response time does not fluctuate - that is because while services are evaluated on
different goroutines, there's a global lock that prevents multiple services from running at the same time.
Unfortunately, there is a drawback. If you have a lot of services, including some that are very slow or prone to time out (the default
time out is 10s for HTTP and 5s for TCP), then it means that for the entire duration of the request, no other services can be evaluated.
**This does mean that Gatus will be unable to evaluate the health of other services**.
The interval does not include the duration of the request itself, which means that if a service has an interval of 30s
and the request takes 2s to complete, the timestamp between two evaluations will be 32s, not 30s.
While this does not prevent Gatus' from performing health checks on all other services, it may cause Gatus to be unable
to respect the configured interval, for instance:
- Service A has an interval of 5s, and times out after 10s to complete
- Service B has an interval of 5s, and takes 1ms to complete
- Service B will be unable to run every 5s, because service A's health evaluation takes longer than its interval
To sum it up, while Gatus can really handle any interval you throw at it, you're better off having slow requests with
higher interval.
As a rule of the thumb, I personally set interval for more complex health checks to `5m` (5 minutes) and
simple health checks used for alerting (PagerDuty/Twilio) to `30s`.
### Default timeouts
| Protocol | Timeout |
|:-------- |:------- |
| HTTP | 10s
| TCP | 5s
### Monitoring a TCP service
By prefixing `services[].url` with `tcp:\\`, you can monitor TCP services at a very basic level:
```yaml
- name: redis
url: "tcp://127.0.0.1:6379"
interval: 30s
conditions:
- "[CONNECTED] == true"
```
Placeholders `[STATUS]` and `[BODY]` as well as the fields `services[].body`, `services[].insecure`,
`services[].headers`, `services[].method` and `services[].graphql` are not supported for TCP services.
**NOTE**: `[CONNECTED] == true` does not guarantee that the service itself is healthy - it only guarantees that there's
something at the given address listening to the given port, and that a connection to that address was successfully
established.

View File

@@ -4,11 +4,14 @@ import (
"bytes"
"fmt"
"github.com/TwinProduction/gatus/client"
"github.com/TwinProduction/gatus/core"
"io/ioutil"
"net/http"
"strings"
)
// AlertProvider is the configuration necessary for sending an alert using a custom HTTP request
// Technically, all alert providers should be reachable using the custom alert provider
type AlertProvider struct {
Url string `yaml:"url"`
Method string `yaml:"method,omitempty"`
@@ -16,10 +19,16 @@ type AlertProvider struct {
Headers map[string]string `yaml:"headers,omitempty"`
}
// IsValid returns whether the provider's configuration is valid
func (provider *AlertProvider) IsValid() bool {
return len(provider.Url) > 0
}
// ToCustomAlertProvider converts the provider into a custom.AlertProvider
func (provider *AlertProvider) ToCustomAlertProvider(service *core.Service, alert *core.Alert, result *core.Result, resolved bool) *AlertProvider {
return provider
}
func (provider *AlertProvider) buildRequest(serviceName, alertDescription string, resolved bool) *http.Request {
body := provider.Body
providerUrl := provider.Url
@@ -64,7 +73,7 @@ func (provider *AlertProvider) buildRequest(serviceName, alertDescription string
// Send a request to the alert provider and return the body
func (provider *AlertProvider) Send(serviceName, alertDescription string, resolved bool) ([]byte, error) {
request := provider.buildRequest(serviceName, alertDescription, resolved)
response, err := client.GetHttpClient().Do(request)
response, err := client.GetHttpClient(false).Do(request)
if err != nil {
return nil, err
}

View File

@@ -6,16 +6,28 @@ import (
"github.com/TwinProduction/gatus/core"
)
// AlertProvider is the configuration necessary for sending an alert using PagerDuty
type AlertProvider struct {
IntegrationKey string `yaml:"integration-key"`
}
// IsValid returns whether the provider's configuration is valid
func (provider *AlertProvider) IsValid() bool {
return len(provider.IntegrationKey) == 32
}
// https://developer.pagerduty.com/docs/events-api-v2/trigger-events/
func (provider *AlertProvider) ToCustomAlertProvider(eventAction, resolveKey string, service *core.Service, message string) *custom.AlertProvider {
func (provider *AlertProvider) ToCustomAlertProvider(service *core.Service, alert *core.Alert, result *core.Result, resolved bool) *custom.AlertProvider {
var message, eventAction, resolveKey string
if resolved {
message = fmt.Sprintf("RESOLVED: %s - %s", service.Name, alert.Description)
eventAction = "resolve"
resolveKey = alert.ResolveKey
} else {
message = fmt.Sprintf("TRIGGERED: %s - %s", service.Name, alert.Description)
eventAction = "trigger"
resolveKey = ""
}
return &custom.AlertProvider{
Url: "https://events.pagerduty.com/v2/enqueue",
Method: "POST",

View File

@@ -0,0 +1,15 @@
package provider
import (
"github.com/TwinProduction/gatus/alerting/provider/custom"
"github.com/TwinProduction/gatus/core"
)
// AlertProvider is the interface that each providers should implement
type AlertProvider interface {
// IsValid returns whether the provider's configuration is valid
IsValid() bool
// ToCustomAlertProvider converts the provider into a custom.AlertProvider
ToCustomAlertProvider(service *core.Service, alert *core.Alert, result *core.Result, resolved bool) *custom.AlertProvider
}

View File

@@ -6,14 +6,17 @@ import (
"github.com/TwinProduction/gatus/core"
)
// AlertProvider is the configuration necessary for sending an alert using Slack
type AlertProvider struct {
WebhookUrl string `yaml:"webhook-url"`
}
// IsValid returns whether the provider's configuration is valid
func (provider *AlertProvider) IsValid() bool {
return len(provider.WebhookUrl) > 0
}
// ToCustomAlertProvider converts the provider into a custom.AlertProvider
func (provider *AlertProvider) ToCustomAlertProvider(service *core.Service, alert *core.Alert, result *core.Result, resolved bool) *custom.AlertProvider {
var message string
var color string

View File

@@ -4,9 +4,11 @@ import (
"encoding/base64"
"fmt"
"github.com/TwinProduction/gatus/alerting/provider/custom"
"github.com/TwinProduction/gatus/core"
"net/url"
)
// AlertProvider is the configuration necessary for sending an alert using Twilio
type AlertProvider struct {
SID string `yaml:"sid"`
Token string `yaml:"token"`
@@ -14,11 +16,19 @@ type AlertProvider struct {
To string `yaml:"to"`
}
// IsValid returns whether the provider's configuration is valid
func (provider *AlertProvider) IsValid() bool {
return len(provider.Token) > 0 && len(provider.SID) > 0 && len(provider.From) > 0 && len(provider.To) > 0
}
func (provider *AlertProvider) ToCustomAlertProvider(message string) *custom.AlertProvider {
// ToCustomAlertProvider converts the provider into a custom.AlertProvider
func (provider *AlertProvider) ToCustomAlertProvider(service *core.Service, alert *core.Alert, result *core.Result, resolved bool) *custom.AlertProvider {
var message string
if resolved {
message = fmt.Sprintf("RESOLVED: %s - %s", service.Name, alert.Description)
} else {
message = fmt.Sprintf("TRIGGERED: %s - %s", service.Name, alert.Description)
}
return &custom.AlertProvider{
Url: fmt.Sprintf("https://api.twilio.com/2010-04-01/Accounts/%s/Messages.json", provider.SID),
Method: "POST",

View File

@@ -1,19 +1,45 @@
package client
import (
"crypto/tls"
"net"
"net/http"
"time"
)
var (
client *http.Client
secureHttpClient *http.Client
insecureHttpClient *http.Client
)
func GetHttpClient() *http.Client {
if client == nil {
client = &http.Client{
Timeout: time.Second * 10,
func GetHttpClient(insecure bool) *http.Client {
if insecure {
if insecureHttpClient == nil {
insecureHttpClient = &http.Client{
Timeout: time.Second * 10,
Transport: &http.Transport{
TLSClientConfig: &tls.Config{
InsecureSkipVerify: true,
},
},
}
}
return insecureHttpClient
} else {
if secureHttpClient == nil {
secureHttpClient = &http.Client{
Timeout: time.Second * 10,
}
}
return secureHttpClient
}
return client
}
func CanCreateConnectionToTcpService(address string) bool {
conn, err := net.DialTimeout("tcp", address, 5*time.Second)
if err != nil {
return false
}
_ = conn.Close()
return true
}

28
client/client_test.go Normal file
View File

@@ -0,0 +1,28 @@
package client
import (
"testing"
)
func TestGetHttpClient(t *testing.T) {
if secureHttpClient != nil {
t.Error("secureHttpClient should've been nil since it hasn't been called a single time yet")
}
if insecureHttpClient != nil {
t.Error("insecureHttpClient should've been nil since it hasn't been called a single time yet")
}
_ = GetHttpClient(false)
if secureHttpClient == nil {
t.Error("secureHttpClient shouldn't have been nil, since it has been called once")
}
if insecureHttpClient != nil {
t.Error("insecureHttpClient should've been nil since it hasn't been called a single time yet")
}
_ = GetHttpClient(true)
if secureHttpClient == nil {
t.Error("secureHttpClient shouldn't have been nil, since it has been called once")
}
if insecureHttpClient == nil {
t.Error("insecureHttpClient shouldn't have been nil, since it has been called once")
}
}

View File

@@ -1,15 +1,15 @@
metrics: true
services:
- name: twinnation
url: "https://twinnation.org/health"
interval: 30s
url: https://twinnation.org/health
conditions:
- "[STATUS] == 200"
- "[BODY].status == UP"
- "[RESPONSE_TIME] < 1000"
- name: cat-fact
interval: 1m
url: "https://cat-fact.herokuapp.com/facts/random"
interval: 1m
conditions:
- "[STATUS] == 200"
- "[BODY].deleted == false"

View File

@@ -3,6 +3,7 @@ package config
import (
"errors"
"github.com/TwinProduction/gatus/alerting"
"github.com/TwinProduction/gatus/alerting/provider"
"github.com/TwinProduction/gatus/core"
"gopkg.in/yaml.v2"
"io/ioutil"
@@ -11,6 +12,8 @@ import (
)
const (
// DefaultConfigurationFilePath is the default path that will be used to search for the configuration file
// if a custom path isn't configured through the GATUS_CONFIG_FILE environment variable
DefaultConfigurationFilePath = "config/config.yaml"
)
@@ -21,6 +24,7 @@ var (
config *Config
)
// Config is the main configuration structure
type Config struct {
Metrics bool `yaml:"metrics"`
Debug bool `yaml:"debug"`
@@ -36,7 +40,7 @@ func Get() *Config {
}
func Load(configFile string) error {
log.Printf("[config][Load] Attempting to load config from configFile=%s", configFile)
log.Printf("[config][Load] Reading configuration from configFile=%s", configFile)
cfg, err := readConfigurationFile(configFile)
if err != nil {
if os.IsNotExist(err) {
@@ -75,13 +79,79 @@ func parseAndValidateConfigBytes(yamlBytes []byte) (config *Config, err error) {
// Parse configuration file
err = yaml.Unmarshal(yamlBytes, &config)
// Check if the configuration file at least has services.
if config == nil || len(config.Services) == 0 {
if config == nil || config.Services == nil || len(config.Services) == 0 {
err = ErrNoServiceInConfig
} else {
// Set the default values if they aren't set
for _, service := range config.Services {
service.Validate()
}
validateAlertingConfig(config)
validateServicesConfig(config)
}
return
}
func validateServicesConfig(config *Config) {
for _, service := range config.Services {
if config.Debug {
log.Printf("[config][validateServicesConfig] Validating service '%s'", service.Name)
}
service.ValidateAndSetDefaults()
}
log.Printf("[config][validateServicesConfig] Validated %d services", len(config.Services))
}
func validateAlertingConfig(config *Config) {
if config.Alerting == nil {
log.Printf("[config][validateAlertingConfig] Alerting is not configured")
return
}
alertTypes := []core.AlertType{
core.SlackAlert,
core.TwilioAlert,
core.PagerDutyAlert,
core.CustomAlert,
}
var validProviders, invalidProviders []core.AlertType
for _, alertType := range alertTypes {
alertProvider := GetAlertingProviderByAlertType(config, alertType)
if alertProvider != nil {
if alertProvider.IsValid() {
validProviders = append(validProviders, alertType)
} else {
log.Printf("[config][validateAlertingConfig] Ignoring provider=%s because configuration is invalid", alertType)
invalidProviders = append(invalidProviders, alertType)
}
} else {
invalidProviders = append(invalidProviders, alertType)
}
}
log.Printf("[config][validateAlertingConfig] configuredProviders=%s; ignoredProviders=%s", validProviders, invalidProviders)
}
func GetAlertingProviderByAlertType(config *Config, alertType core.AlertType) provider.AlertProvider {
switch alertType {
case core.SlackAlert:
if config.Alerting.Slack == nil {
// Since we're returning an interface, we need to explicitly return nil, even if the provider itself is nil
return nil
}
return config.Alerting.Slack
case core.TwilioAlert:
if config.Alerting.Twilio == nil {
// Since we're returning an interface, we need to explicitly return nil, even if the provider itself is nil
return nil
}
return config.Alerting.Twilio
case core.PagerDutyAlert:
if config.Alerting.PagerDuty == nil {
// Since we're returning an interface, we need to explicitly return nil, even if the provider itself is nil
return nil
}
return config.Alerting.PagerDuty
case core.CustomAlert:
if config.Alerting.Custom == nil {
// Since we're returning an interface, we need to explicitly return nil, even if the provider itself is nil
return nil
}
return config.Alerting.Custom
}
return nil
}

View File

@@ -1,7 +1,6 @@
package config
import (
"fmt"
"github.com/TwinProduction/gatus/core"
"testing"
"time"
@@ -36,7 +35,6 @@ services:
if config.Services[1].Url != "https://api.github.com/healthz" {
t.Errorf("URL should have been %s", "https://api.github.com/healthz")
}
fmt.Println(config.Services[0].Interval)
if config.Services[0].Interval != 15*time.Second {
t.Errorf("Interval should have been %s", 15*time.Second)
}
@@ -123,6 +121,8 @@ func TestParseAndValidateConfigBytesWithAlerting(t *testing.T) {
alerting:
slack:
webhook-url: "http://example.com"
pagerduty:
integration-key: "00000000000000000000000000000000"
services:
- name: twinnation
url: https://twinnation.org/actuator/health
@@ -144,10 +144,19 @@ services:
t.Error("Metrics should've been false by default")
}
if config.Alerting == nil {
t.Fatal("config.AlertingConfig shouldn't have been nil")
t.Fatal("config.Alerting shouldn't have been nil")
}
if config.Alerting.Slack == nil || !config.Alerting.Slack.IsValid() {
t.Fatal("Slack alerting config should've been valid")
}
if config.Alerting.Slack.WebhookUrl != "http://example.com" {
t.Errorf("Slack webhook should've been %s, but was %s", "http://example.com", config.Alerting.Slack)
t.Errorf("Slack webhook should've been %s, but was %s", "http://example.com", config.Alerting.Slack.WebhookUrl)
}
if config.Alerting.PagerDuty == nil || !config.Alerting.PagerDuty.IsValid() {
t.Fatal("PagerDuty alerting config should've been valid")
}
if config.Alerting.PagerDuty.IntegrationKey != "00000000000000000000000000000000" {
t.Errorf("PagerDuty integration key should've been %s, but was %s", "00000000000000000000000000000000", config.Alerting.PagerDuty.IntegrationKey)
}
if len(config.Services) != 1 {
t.Error("There should've been 1 service")
@@ -180,3 +189,31 @@ services:
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)
}
}
func TestParseAndValidateConfigBytesWithInvalidPagerDutyAlertingConfig(t *testing.T) {
config, err := parseAndValidateConfigBytes([]byte(`
alerting:
pagerduty:
integration-key: "INVALID_KEY"
services:
- name: twinnation
url: https://twinnation.org/actuator/health
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.Alerting == nil {
t.Fatal("config.Alerting shouldn't have been nil")
}
if config.Alerting.PagerDuty == nil {
t.Fatal("PagerDuty alerting config shouldn't have been nil")
}
if config.Alerting.PagerDuty.IsValid() {
t.Fatal("PagerDuty alerting config should've been invalid")
}
}

View File

@@ -2,23 +2,41 @@ package core
import (
"fmt"
"github.com/TwinProduction/gatus/jsonpath"
"github.com/TwinProduction/gatus/pattern"
"log"
"strconv"
"strings"
)
const (
StatusPlaceholder = "[STATUS]"
IPPlaceHolder = "[IP]"
ResponseTimePlaceHolder = "[RESPONSE_TIME]"
BodyPlaceHolder = "[BODY]"
ConnectedPlaceHolder = "[CONNECTED]"
LengthFunctionPrefix = "len("
PatternFunctionPrefix = "pat("
FunctionSuffix = ")"
InvalidConditionElementSuffix = "(INVALID)"
)
type Condition string
// evaluate the Condition with the Result of the health check
func (c *Condition) evaluate(result *Result) bool {
condition := string(*c)
success := false
var resolvedCondition string
if strings.Contains(condition, "==") {
parts := sanitizeAndResolve(strings.Split(condition, "=="), result)
success = parts[0] == parts[1]
success = isEqual(parts[0], parts[1])
resolvedCondition = fmt.Sprintf("%v == %v", parts[0], parts[1])
} else if strings.Contains(condition, "!=") {
parts := sanitizeAndResolve(strings.Split(condition, "!="), result)
success = parts[0] != parts[1]
success = !isEqual(parts[0], parts[1])
resolvedCondition = fmt.Sprintf("%v != %v", parts[0], parts[1])
} else if strings.Contains(condition, "<=") {
parts := sanitizeAndResolveNumerical(strings.Split(condition, "<="), result)
@@ -49,3 +67,83 @@ func (c *Condition) evaluate(result *Result) bool {
result.ConditionResults = append(result.ConditionResults, &ConditionResult{Condition: conditionToDisplay, Success: success})
return success
}
// isEqual compares two strings.
//
// It also supports the pattern function. That is to say, if one of the strings starts with PatternFunctionPrefix
// and ends with FunctionSuffix, it will be treated like a pattern.
func isEqual(first, second string) bool {
var isFirstPattern, isSecondPattern bool
if strings.HasPrefix(first, PatternFunctionPrefix) && strings.HasSuffix(first, FunctionSuffix) {
isFirstPattern = true
first = strings.TrimSuffix(strings.TrimPrefix(first, PatternFunctionPrefix), FunctionSuffix)
}
if strings.HasPrefix(second, PatternFunctionPrefix) && strings.HasSuffix(second, FunctionSuffix) {
isSecondPattern = true
second = strings.TrimSuffix(strings.TrimPrefix(second, PatternFunctionPrefix), FunctionSuffix)
}
if isFirstPattern && !isSecondPattern {
return pattern.Match(first, second)
} else if !isFirstPattern && isSecondPattern {
return pattern.Match(second, first)
} else {
return first == second
}
}
// sanitizeAndResolve sanitizes and resolves a list of element and returns the list of resolved elements
func sanitizeAndResolve(list []string, result *Result) []string {
var sanitizedList []string
body := strings.TrimSpace(string(result.Body))
for _, element := range list {
element = strings.TrimSpace(element)
switch strings.ToUpper(element) {
case StatusPlaceholder:
element = strconv.Itoa(result.HttpStatus)
case IPPlaceHolder:
element = result.Ip
case ResponseTimePlaceHolder:
element = strconv.Itoa(int(result.Duration.Milliseconds()))
case BodyPlaceHolder:
element = body
case ConnectedPlaceHolder:
element = strconv.FormatBool(result.Connected)
default:
// if contains the BodyPlaceHolder, then evaluate json path
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 {
if wantLength {
element = fmt.Sprintf("%d", resolvedElementLength)
} else {
element = resolvedElement
}
}
}
}
sanitizedList = append(sanitizedList, element)
}
return sanitizedList
}
func sanitizeAndResolveNumerical(list []string, result *Result) []int {
var sanitizedNumbers []int
sanitizedList := sanitizeAndResolve(list, result)
for _, element := range sanitizedList {
if number, err := strconv.Atoi(element); err != nil {
// Default to 0 if the string couldn't be converted to an integer
sanitizedNumbers = append(sanitizedNumbers, 0)
} else {
sanitizedNumbers = append(sanitizedNumbers, number)
}
}
return sanitizedNumbers
}

View File

@@ -113,6 +113,24 @@ func TestCondition_evaluateWithBodyJsonPathComplex(t *testing.T) {
}
}
func TestCondition_evaluateWithBodyJsonPathDoublePlaceholders(t *testing.T) {
condition := Condition("[BODY].user.firstName != [BODY].user.lastName")
result := &Result{Body: []byte("{\"user\": {\"firstName\": \"john\", \"lastName\": \"doe\"}}")}
condition.evaluate(result)
if !result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a success", condition)
}
}
func TestCondition_evaluateWithBodyJsonPathDoublePlaceholdersFailure(t *testing.T) {
condition := Condition("[BODY].user.firstName == [BODY].user.lastName")
result := &Result{Body: []byte("{\"user\": {\"firstName\": \"john\", \"lastName\": \"doe\"}}")}
condition.evaluate(result)
if result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a failure", condition)
}
}
func TestCondition_evaluateWithBodyJsonPathLongInt(t *testing.T) {
condition := Condition("[BODY].data.id == 1")
result := &Result{Body: []byte("{\"data\": {\"id\": 1}}")}
@@ -184,3 +202,84 @@ func TestCondition_evaluateWithBodyStringLength(t *testing.T) {
t.Errorf("Condition '%s' should have been a success", condition)
}
}
func TestCondition_evaluateWithBodyStringPattern(t *testing.T) {
condition := Condition("[BODY].name == pat(*ohn*)")
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)
}
}
func TestCondition_evaluateWithBodyStringPatternFailure(t *testing.T) {
condition := Condition("[BODY].name == pat(bob*)")
result := &Result{Body: []byte("{\"name\": \"john.doe\"}")}
condition.evaluate(result)
if result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a failure", condition)
}
}
func TestCondition_evaluateWithBodyPatternFailure(t *testing.T) {
condition := Condition("[BODY] == pat(*john*)")
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)
}
}
func TestCondition_evaluateWithIPPattern(t *testing.T) {
condition := Condition("[IP] == pat(10.*)")
result := &Result{Ip: "10.0.0.0"}
condition.evaluate(result)
if !result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a success", condition)
}
}
func TestCondition_evaluateWithIPPatternFailure(t *testing.T) {
condition := Condition("[IP] == pat(10.*)")
result := &Result{Ip: "255.255.255.255"}
condition.evaluate(result)
if result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a failure", condition)
}
}
func TestCondition_evaluateWithStatusPattern(t *testing.T) {
condition := Condition("[STATUS] == pat(4*)")
result := &Result{HttpStatus: 404}
condition.evaluate(result)
if !result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a success", condition)
}
}
func TestCondition_evaluateWithStatusPatternFailure(t *testing.T) {
condition := Condition("[STATUS] != pat(4*)")
result := &Result{HttpStatus: 404}
condition.evaluate(result)
if result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a failure", condition)
}
}
func TestCondition_evaluateWithConnected(t *testing.T) {
condition := Condition("[CONNECTED] == true")
result := &Result{Connected: true}
condition.evaluate(result)
if !result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a success", condition)
}
}
func TestCondition_evaluateWithConnectedFailure(t *testing.T) {
condition := Condition("[CONNECTED] == true")
result := &Result{Connected: false}
condition.evaluate(result)
if result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a failure", condition)
}
}

View File

@@ -9,6 +9,7 @@ import (
"net"
"net/http"
"net/url"
"strings"
"time"
)
@@ -46,11 +47,15 @@ type Service struct {
// Alerts is the alerting configuration for the service in case of failure
Alerts []*Alert `yaml:"alerts"`
// Insecure is whether to skip verifying the server's certificate chain and host name
Insecure bool `yaml:"insecure,omitempty"`
NumberOfFailuresInARow int
NumberOfSuccessesInARow int
}
func (service *Service) Validate() {
// ValidateAndSetDefaults validates the service's configuration and sets the default value of fields that have one
func (service *Service) ValidateAndSetDefaults() {
// Set default values
if service.Interval == 0 {
service.Interval = 1 * time.Minute
@@ -83,7 +88,8 @@ func (service *Service) Validate() {
}
}
func (service *Service) EvaluateConditions() *Result {
// EvaluateHealth sends a request to the service's URL and evaluates the conditions of the service.
func (service *Service) EvaluateHealth() *Result {
result := &Result{Success: true, Errors: []string{}}
service.getIp(result)
if len(result.Errors) == 0 {
@@ -131,19 +137,30 @@ func (service *Service) getIp(result *Result) {
}
func (service *Service) call(result *Result) {
request := service.buildRequest()
startTime := time.Now()
response, err := client.GetHttpClient().Do(request)
if err != nil {
result.Duration = time.Since(startTime)
result.Errors = append(result.Errors, err.Error())
return
isServiceTcp := strings.HasPrefix(service.Url, "tcp://")
var request *http.Request
var response *http.Response
var err error
if !isServiceTcp {
request = service.buildRequest()
}
result.Duration = time.Since(startTime)
result.HttpStatus = response.StatusCode
result.Body, err = ioutil.ReadAll(response.Body)
if err != nil {
result.Errors = append(result.Errors, err.Error())
startTime := time.Now()
if isServiceTcp {
result.Connected = client.CanCreateConnectionToTcpService(strings.TrimPrefix(service.Url, "tcp://"))
result.Duration = time.Since(startTime)
} else {
response, err = client.GetHttpClient(service.Insecure).Do(request)
result.Duration = time.Since(startTime)
if err != nil {
result.Errors = append(result.Errors, err.Error())
return
}
result.HttpStatus = response.StatusCode
result.Connected = response.StatusCode > 0
result.Body, err = ioutil.ReadAll(response.Body)
if err != nil {
result.Errors = append(result.Errors, err.Error())
}
}
}

View File

@@ -4,33 +4,39 @@ import (
"testing"
)
func TestIntegrationEvaluateConditions(t *testing.T) {
func TestIntegrationEvaluateHealth(t *testing.T) {
condition := Condition("[STATUS] == 200")
service := Service{
Name: "TwiNNatioN",
Url: "https://twinnation.org/health",
Conditions: []*Condition{&condition},
}
result := service.EvaluateConditions()
result := service.EvaluateHealth()
if !result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a success", condition)
}
if !result.Connected {
t.Error("Because the connection has been established, result.Connected should've been true")
}
if !result.Success {
t.Error("Because all conditions passed, this should have been a success")
}
}
func TestIntegrationEvaluateConditionsWithFailure(t *testing.T) {
func TestIntegrationEvaluateHealthWithFailure(t *testing.T) {
condition := Condition("[STATUS] == 500")
service := Service{
Name: "TwiNNatioN",
Url: "https://twinnation.org/health",
Conditions: []*Condition{&condition},
}
result := service.EvaluateConditions()
result := service.EvaluateHealth()
if result.ConditionResults[0].Success {
t.Errorf("Condition '%s' should have been a failure", condition)
}
if !result.Connected {
t.Error("Because the connection has been established, result.Connected should've been true")
}
if result.Success {
t.Error("Because one of the conditions failed, success should have been false")
}

View File

@@ -9,16 +9,37 @@ type HealthStatus struct {
Message string `json:"message,omitempty"`
}
// Result of the evaluation of a Service
type Result struct {
HttpStatus int `json:"status"`
Body []byte `json:"-"`
Hostname string `json:"hostname"`
Ip string `json:"-"`
Duration time.Duration `json:"duration"`
Errors []string `json:"errors"`
// HttpStatus is the HTTP response status code
HttpStatus int `json:"status"`
// Body is the response body
Body []byte `json:"-"`
// Hostname extracted from the Service Url
Hostname string `json:"hostname"`
// Ip resolved from the Service Url
Ip string `json:"-"`
// Connected whether a connection to the host was established successfully
Connected bool `json:"-"`
// Duration time that the request took
Duration time.Duration `json:"duration"`
// Errors encountered during the evaluation of the service's health
Errors []string `json:"errors"`
// ConditionResults results of the service's conditions
ConditionResults []*ConditionResult `json:"condition-results"`
Success bool `json:"success"`
Timestamp time.Time `json:"timestamp"`
// Success whether the result signifies a success or not
Success bool `json:"success"`
// Timestamp when the request was sent
Timestamp time.Time `json:"timestamp"`
}
type ConditionResult struct {

View File

@@ -1,74 +0,0 @@
package core
import (
"fmt"
"github.com/TwinProduction/gatus/jsonpath"
"strconv"
"strings"
)
const (
StatusPlaceholder = "[STATUS]"
IPPlaceHolder = "[IP]"
ResponseTimePlaceHolder = "[RESPONSE_TIME]"
BodyPlaceHolder = "[BODY]"
LengthFunctionPrefix = "len("
FunctionSuffix = ")"
InvalidConditionElementSuffix = "(INVALID)"
)
func sanitizeAndResolve(list []string, result *Result) []string {
var sanitizedList []string
body := strings.TrimSpace(string(result.Body))
for _, element := range list {
element = strings.TrimSpace(element)
switch strings.ToUpper(element) {
case StatusPlaceholder:
element = strconv.Itoa(result.HttpStatus)
case IPPlaceHolder:
element = result.Ip
case ResponseTimePlaceHolder:
element = strconv.Itoa(int(result.Duration.Milliseconds()))
case BodyPlaceHolder:
element = body
default:
// if starts with BodyPlaceHolder, then evaluate json path
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 {
if wantLength {
element = fmt.Sprintf("%d", resolvedElementLength)
} else {
element = resolvedElement
}
}
}
}
sanitizedList = append(sanitizedList, element)
}
return sanitizedList
}
func sanitizeAndResolveNumerical(list []string, result *Result) []int {
var sanitizedNumbers []int
sanitizedList := sanitizeAndResolve(list, result)
for _, element := range sanitizedList {
if number, err := strconv.Atoi(element); err != nil {
// Default to 0 if the string couldn't be converted to an integer
sanitizedNumbers = append(sanitizedNumbers, 0)
} else {
sanitizedNumbers = append(sanitizedNumbers, number)
}
}
return sanitizedNumbers
}

View File

@@ -49,10 +49,10 @@ spec:
protocol: TCP
resources:
limits:
cpu: 50m
cpu: 200m
memory: 50M
requests:
cpu: 20m
cpu: 50m
memory: 20M
volumeMounts:
- mountPath: /config

12
pattern/pattern.go Normal file
View File

@@ -0,0 +1,12 @@
package pattern
import "path/filepath"
// Match checks whether a string matches a pattern
func Match(pattern, s string) bool {
if pattern == "*" {
return true
}
matched, _ := filepath.Match(pattern, s)
return matched
}

37
pattern/pattern_test.go Normal file
View File

@@ -0,0 +1,37 @@
package pattern
import "testing"
func TestMatch(t *testing.T) {
testMatch(t, "*", "livingroom_123", true)
testMatch(t, "**", "livingroom_123", true)
testMatch(t, "living*", "livingroom_123", true)
testMatch(t, "*living*", "livingroom_123", true)
testMatch(t, "*123", "livingroom_123", true)
testMatch(t, "*_*", "livingroom_123", true)
testMatch(t, "living*_*3", "livingroom_123", true)
testMatch(t, "living*room_*3", "livingroom_123", true)
testMatch(t, "living*room_*3", "livingroom_123", true)
testMatch(t, "*vin*om*2*", "livingroom_123", true)
testMatch(t, "livingroom_123", "livingroom_123", true)
testMatch(t, "*livingroom_123*", "livingroom_123", true)
testMatch(t, "livingroom", "livingroom_123", false)
testMatch(t, "livingroom123", "livingroom_123", false)
testMatch(t, "what", "livingroom_123", false)
testMatch(t, "*what*", "livingroom_123", false)
testMatch(t, "*.*", "livingroom_123", false)
testMatch(t, "room*123", "livingroom_123", false)
}
func testMatch(t *testing.T, pattern, key string, expectedToMatch bool) {
matched := Match(pattern, key)
if expectedToMatch {
if !matched {
t.Errorf("%s should've matched pattern '%s'", key, pattern)
}
} else {
if matched {
t.Errorf("%s shouldn't have matched pattern '%s'", key, pattern)
}
}
}

View File

@@ -90,6 +90,15 @@
#social img:hover {
opacity: 1;
}
#settings {
position: fixed;
left: 5px;
bottom: 5px;
padding: 5px;
}
#settings select:focus {
box-shadow: none;
}
</style>
</head>
<body>
@@ -128,9 +137,26 @@
</a>
</div>
<div id="settings">
<div class="input-group input-group-sm">
<div class="input-group-prepend">
<div class="input-group-text">&#x21bb;</div>
</div>
<select class="form-control form-control-sm" id="refresh-rate">
<option value="10">10s</option>
<option value="30" selected>30s</option>
<option value="60">1m</option>
<option value="120">2m</option>
<option value="300">5m</option>
<option value="600">10m</option>
</select>
</div>
</div>
<script>
let serviceStatuses = {};
let timerHandler = 0;
let refreshIntervalHandler = 0;
let userClickedStatus = false;
function showTooltip(serviceName, index, element) {
@@ -291,10 +317,19 @@
.replace(/'/g, '&apos;');
}
refreshResults();
setInterval(function() {
function setRefreshInterval(seconds) {
refreshResults();
}, 30000);
refreshIntervalHandler = setInterval(function() {
refreshResults();
}, seconds * 1000)
}
$("#refresh-rate").change(function() {
clearInterval(refreshIntervalHandler);
setRefreshInterval($(this).val())
});
setRefreshInterval(30);
$("#refresh-rate").val(30);
</script>
</body>
</html>

View File

@@ -2,8 +2,6 @@ package watchdog
import (
"encoding/json"
"fmt"
"github.com/TwinProduction/gatus/alerting/provider/custom"
"github.com/TwinProduction/gatus/config"
"github.com/TwinProduction/gatus/core"
"log"
@@ -32,46 +30,20 @@ func handleAlertsToTrigger(service *core.Service, result *core.Result, cfg *conf
}
if alert.Triggered {
if cfg.Debug {
log.Printf("[watchdog][handleAlertsToTrigger] Alert with description='%s' has already been triggered, skipping", alert.Description)
log.Printf("[watchdog][handleAlertsToTrigger] Alert with description='%s' has already been TRIGGERED, skipping", alert.Description)
}
continue
}
var alertProvider *custom.AlertProvider
if alert.Type == core.SlackAlert {
if cfg.Alerting.Slack != nil && cfg.Alerting.Slack.IsValid() {
log.Printf("[watchdog][handleAlertsToTrigger] Sending Slack alert because alert with description='%s' has been triggered", alert.Description)
alertProvider = cfg.Alerting.Slack.ToCustomAlertProvider(service, alert, result, false)
} else {
log.Printf("[watchdog][handleAlertsToTrigger] Not sending Slack alert despite being triggered, because there is no Slack webhook configured")
}
} else if alert.Type == core.PagerDutyAlert {
if cfg.Alerting.PagerDuty != nil && cfg.Alerting.PagerDuty.IsValid() {
log.Printf("[watchdog][handleAlertsToTrigger] Sending PagerDuty alert because alert with description='%s' has been triggered", alert.Description)
alertProvider = cfg.Alerting.PagerDuty.ToCustomAlertProvider("trigger", "", service, fmt.Sprintf("TRIGGERED: %s - %s", service.Name, alert.Description))
} else {
log.Printf("[watchdog][handleAlertsToTrigger] Not sending PagerDuty alert despite being triggered, because PagerDuty isn't configured properly")
}
} else if alert.Type == core.TwilioAlert {
if cfg.Alerting.Twilio != nil && cfg.Alerting.Twilio.IsValid() {
log.Printf("[watchdog][handleAlertsToTrigger] Sending Twilio alert because alert with description='%s' has been triggered", alert.Description)
alertProvider = cfg.Alerting.Twilio.ToCustomAlertProvider(fmt.Sprintf("TRIGGERED: %s - %s", service.Name, alert.Description))
} else {
log.Printf("[watchdog][handleAlertsToTrigger] Not sending Twilio alert despite being triggered, because Twilio config settings missing")
}
} else if alert.Type == core.CustomAlert {
if cfg.Alerting.Custom != nil && cfg.Alerting.Custom.IsValid() {
log.Printf("[watchdog][handleAlertsToTrigger] Sending custom alert because alert with description='%s' has been triggered", alert.Description)
alertProvider = cfg.Alerting.Custom
} else {
log.Printf("[watchdog][handleAlertsToTrigger] Not sending custom alert despite being triggered, because there is no custom url configured")
}
}
if alertProvider != nil {
alertProvider := config.GetAlertingProviderByAlertType(cfg, alert.Type)
if alertProvider != nil && alertProvider.IsValid() {
log.Printf("[watchdog][handleAlertsToTrigger] Sending %s alert because alert with description='%s' has been TRIGGERED", alert.Type, alert.Description)
customAlertProvider := alertProvider.ToCustomAlertProvider(service, alert, result, false)
// TODO: retry on error
var err error
// We need to extract the DedupKey from PagerDuty's response
if alert.Type == core.PagerDutyAlert {
var body []byte
body, err = alertProvider.Send(service.Name, alert.Description, true)
body, err = customAlertProvider.Send(service.Name, alert.Description, false)
if err == nil {
var response pagerDutyResponse
err = json.Unmarshal(body, &response)
@@ -82,13 +54,17 @@ func handleAlertsToTrigger(service *core.Service, result *core.Result, cfg *conf
}
}
} else {
_, err = alertProvider.Send(service.Name, alert.Description, false)
// All other alert types don't need to extract anything from the body, so we can just send the request right away
_, err = customAlertProvider.Send(service.Name, alert.Description, false)
}
if err != nil {
log.Printf("[watchdog][handleAlertsToTrigger] Ran into error sending an alert: %s", err.Error())
} else {
alert.Triggered = true
}
} else {
log.Printf("[watchdog][handleAlertsToResolve] Not sending alert of type=%s despite being TRIGGERED, because the provider wasn't configured properly", alert.Type)
}
}
}
@@ -103,44 +79,12 @@ func handleAlertsToResolve(service *core.Service, result *core.Result, cfg *conf
if !alert.SendOnResolved {
continue
}
var alertProvider *custom.AlertProvider
if alert.Type == core.SlackAlert {
if cfg.Alerting.Slack != nil && cfg.Alerting.Slack.IsValid() {
log.Printf("[watchdog][handleAlertsToResolve] Sending Slack alert because alert with description='%s' has been resolved", alert.Description)
alertProvider = cfg.Alerting.Slack.ToCustomAlertProvider(service, alert, result, true)
} else {
log.Printf("[watchdog][handleAlertsToResolve] Not sending Slack alert despite being resolved, because there is no Slack webhook configured")
}
} else if alert.Type == core.PagerDutyAlert {
if cfg.Alerting.PagerDuty != nil && cfg.Alerting.PagerDuty.IsValid() {
log.Printf("[watchdog][handleAlertsToResolve] Sending PagerDuty alert because alert with description='%s' has been resolved", alert.Description)
alertProvider = cfg.Alerting.PagerDuty.ToCustomAlertProvider("resolve", alert.ResolveKey, service, fmt.Sprintf("RESOLVED: %s - %s", service.Name, alert.Description))
} else {
log.Printf("[watchdog][handleAlertsToResolve] Not sending PagerDuty alert despite being resolved, because PagerDuty isn't configured properly")
}
} else if alert.Type == core.TwilioAlert {
if cfg.Alerting.Twilio != nil && cfg.Alerting.Twilio.IsValid() {
log.Printf("[watchdog][handleAlertsToResolve] Sending Twilio alert because alert with description='%s' has been resolved", alert.Description)
alertProvider = cfg.Alerting.Twilio.ToCustomAlertProvider(fmt.Sprintf("RESOLVED: %s - %s", service.Name, alert.Description))
} else {
log.Printf("[watchdog][handleAlertsToResolve] Not sending Twilio alert despite being resolved, because Twilio isn't configured properly")
}
} else if alert.Type == core.CustomAlert {
if cfg.Alerting.Custom != nil && cfg.Alerting.Custom.IsValid() {
log.Printf("[watchdog][handleAlertsToResolve] Sending custom alert because alert with description='%s' has been resolved", alert.Description)
alertProvider = &custom.AlertProvider{
Url: cfg.Alerting.Custom.Url,
Method: cfg.Alerting.Custom.Method,
Body: cfg.Alerting.Custom.Body,
Headers: cfg.Alerting.Custom.Headers,
}
} else {
log.Printf("[watchdog][handleAlertsToResolve] Not sending custom alert despite being resolved, because the custom provider isn't configured properly")
}
}
if alertProvider != nil {
alertProvider := config.GetAlertingProviderByAlertType(cfg, alert.Type)
if alertProvider != nil && alertProvider.IsValid() {
log.Printf("[watchdog][handleAlertsToResolve] Sending %s alert because alert with description='%s' has been RESOLVED", alert.Type, alert.Description)
customAlertProvider := alertProvider.ToCustomAlertProvider(service, alert, result, true)
// TODO: retry on error
_, err := alertProvider.Send(service.Name, alert.Description, true)
_, err := customAlertProvider.Send(service.Name, alert.Description, true)
if err != nil {
log.Printf("[watchdog][handleAlertsToResolve] Ran into error sending an alert: %s", err.Error())
} else {
@@ -148,6 +92,8 @@ func handleAlertsToResolve(service *core.Service, result *core.Result, cfg *conf
alert.ResolveKey = ""
}
}
} else {
log.Printf("[watchdog][handleAlertsToResolve] Not sending alert of type=%s despite being RESOLVED, because the provider wasn't configured properly", alert.Type)
}
}
service.NumberOfFailuresInARow = 0

View File

@@ -50,7 +50,7 @@ func monitor(service *core.Service) {
if cfg.Debug {
log.Printf("[watchdog][monitor] Monitoring serviceName=%s", service.Name)
}
result := service.EvaluateConditions()
result := service.EvaluateHealth()
metric.PublishMetricsForService(service, result)
serviceResultsMutex.Lock()
serviceResults[service.Name] = append(serviceResults[service.Name], result)