mirror of
https://github.com/TwiN/gatus.git
synced 2026-08-22 23:26:04 +00:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
394602bc47 | ||
|
|
15813d4297 | ||
|
|
d24c66cf96 | ||
|
|
70d7d0c54c |
@@ -366,7 +366,7 @@ or send an HTTP request:
|
||||
POST /api/v1/endpoints/{key}/external?success={success}&error={error}&duration={duration}
|
||||
```
|
||||
Where:
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
- Using the example configuration above, the key would be `core_ext-ep-test`.
|
||||
- `{success}` is a boolean (`true` or `false`) value indicating whether the health check was successful or not.
|
||||
- `{error}` (optional): a string describing the reason for a failed health check. If {success} is false, this should contain the error message; if the check is successful.
|
||||
@@ -2298,14 +2298,14 @@ endpoints:
|
||||
|
||||
> ⚠️ **WARNING**: This alerting provider has not been tested yet. If you've tested it and confirmed that it works, please remove this warning and create a pull request, or comment on [#1223](https://github.com/TwiN/gatus/discussions/1223) with whether the provider works as intended. Thank you for your cooperation.
|
||||
|
||||
| Parameter | Description | Default |
|
||||
|:-------------------------------|:-------------------------------------------------------------------------------------------|:--------------|
|
||||
| `alerting.webex` | Configuration for alerts of type `webex` | `{}` |
|
||||
| `alerting.webex.webhook-url` | Webex Teams webhook URL | Required `""` |
|
||||
| `alerting.webex.default-alert` | Default alert configuration. <br />See [Setting a default alert](#setting-a-default-alert) | N/A |
|
||||
| `alerting.webex.overrides` | List of overrides that may be prioritized over the default configuration | `[]` |
|
||||
| `alerting.webex.overrides[].group` | Endpoint group for which the configuration will be overridden by this configuration | `""` |
|
||||
| `alerting.webex.overrides[].*` | See `alerting.webex.*` parameters | `{}` |
|
||||
| Parameter | Description | Default |
|
||||
|:-----------------------------------|:-------------------------------------------------------------------------------------------|:--------------|
|
||||
| `alerting.webex` | Configuration for alerts of type `webex` | `{}` |
|
||||
| `alerting.webex.webhook-url` | Webex Teams webhook URL | Required `""` |
|
||||
| `alerting.webex.default-alert` | Default alert configuration. <br />See [Setting a default alert](#setting-a-default-alert) | N/A |
|
||||
| `alerting.webex.overrides` | List of overrides that may be prioritized over the default configuration | `[]` |
|
||||
| `alerting.webex.overrides[].group` | Endpoint group for which the configuration will be overridden by this configuration | `""` |
|
||||
| `alerting.webex.overrides[].*` | See `alerting.webex.*` parameters | `{}` |
|
||||
|
||||
```yaml
|
||||
alerting:
|
||||
@@ -2357,7 +2357,7 @@ endpoints:
|
||||
#### Configuring Zulip alerts
|
||||
| Parameter | Description | Default |
|
||||
|:-----------------------------------|:------------------------------------------------------------------------------------|:--------------|
|
||||
| `alerting.zulip` | Configuration for alerts of type `zulip` | `{}` |
|
||||
| `alerting.zulip` | Configuration for alerts of type `zulip` | `{}` |
|
||||
| `alerting.zulip.bot-email` | Bot Email | Required `""` |
|
||||
| `alerting.zulip.bot-api-key` | Bot API key | Required `""` |
|
||||
| `alerting.zulip.domain` | Full organization domain (e.g.: yourZulipDomain.zulipchat.com) | Required `""` |
|
||||
@@ -3297,7 +3297,7 @@ The path to generate a badge is the following:
|
||||
```
|
||||
Where:
|
||||
- `{duration}` is `30d`, `7d`, `24h` or `1h`
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
|
||||
For instance, if you want the uptime during the last 24 hours from the endpoint `frontend` in the group `core`,
|
||||
the URL would look like this:
|
||||
@@ -3323,7 +3323,7 @@ The path to generate a badge is the following:
|
||||
/api/v1/endpoints/{key}/health/badge.svg
|
||||
```
|
||||
Where:
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
|
||||
For instance, if you want the current status of the endpoint `frontend` in the group `core`,
|
||||
the URL would look like this:
|
||||
@@ -3340,7 +3340,7 @@ The path to generate a badge is the following:
|
||||
/api/v1/endpoints/{key}/health/badge.shields
|
||||
```
|
||||
Where:
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
|
||||
For instance, if you want the current status of the endpoint `frontend` in the group `core`,
|
||||
the URL would look like this:
|
||||
@@ -3363,7 +3363,7 @@ The endpoint to generate a badge is the following:
|
||||
```
|
||||
Where:
|
||||
- `{duration}` is `30d`, `7d`, `24h` or `1h`
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
|
||||
#### Response time (chart)
|
||||

|
||||
@@ -3376,7 +3376,7 @@ The endpoint to generate a response time chart is the following:
|
||||
```
|
||||
Where:
|
||||
- `{duration}` is `30d`, `7d`, or `24h`
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
|
||||
##### How to change the color thresholds of the response time badge
|
||||
To change the response time badges' threshold, a corresponding configuration can be added to an endpoint.
|
||||
@@ -3434,7 +3434,7 @@ The path to get raw uptime data for an endpoint is:
|
||||
```
|
||||
Where:
|
||||
- `{duration}` is `30d`, `7d`, `24h` or `1h`
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
|
||||
For instance, if you want the raw uptime data for the last 24 hours from the endpoint `frontend` in the group `core`, the URL would look like this:
|
||||
```
|
||||
@@ -3448,7 +3448,7 @@ The path to get raw response time data for an endpoint is:
|
||||
```
|
||||
Where:
|
||||
- `{duration}` is `30d`, `7d`, `24h` or `1h`
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `(`, `)`, `+` and `&` replaced by `-`.
|
||||
- `{key}` has the pattern `<GROUP_NAME>_<ENDPOINT_NAME>` in which both variables have ` `, `/`, `_`, `,`, `.`, `#`, `+` and `&` replaced by `-`.
|
||||
|
||||
For instance, if you want the raw response time data for the last 24 hours from the endpoint `frontend` in the group `core`, the URL would look like this:
|
||||
```
|
||||
|
||||
@@ -498,7 +498,7 @@ func (e *Endpoint) call(result *Result) {
|
||||
result.Duration = time.Since(startTime)
|
||||
} else if endpointType == TypeSSH {
|
||||
// If there's no username/password specified, attempt to validate just the SSH banner
|
||||
if len(e.SSHConfig.Username) == 0 && len(e.SSHConfig.Password) == 0 {
|
||||
if e.SSHConfig == nil || (len(e.SSHConfig.Username) == 0 && len(e.SSHConfig.Password) == 0) {
|
||||
result.Connected, result.HTTPStatus, err = client.CheckSSHBanner(strings.TrimPrefix(e.URL, "ssh://"), e.ClientConfig)
|
||||
if err != nil {
|
||||
result.AddError(err.Error())
|
||||
|
||||
@@ -15,8 +15,6 @@ func sanitize(s string) string {
|
||||
s = strings.ReplaceAll(s, ",", "-")
|
||||
s = strings.ReplaceAll(s, " ", "-")
|
||||
s = strings.ReplaceAll(s, "#", "-")
|
||||
s = strings.ReplaceAll(s, "(", "-")
|
||||
s = strings.ReplaceAll(s, ")", "-")
|
||||
s = strings.ReplaceAll(s, "+", "-")
|
||||
s = strings.ReplaceAll(s, "&", "-")
|
||||
return s
|
||||
|
||||
@@ -32,12 +32,12 @@ func TestConvertGroupAndNameToKey(t *testing.T) {
|
||||
{
|
||||
GroupName: "API (v1)",
|
||||
Name: "endpoint",
|
||||
ExpectedOutput: "api--v1-_endpoint",
|
||||
ExpectedOutput: "api-(v1)_endpoint",
|
||||
},
|
||||
{
|
||||
GroupName: "website (admin)",
|
||||
Name: "test",
|
||||
ExpectedOutput: "website--admin-_test",
|
||||
ExpectedOutput: "website-(admin)_test",
|
||||
},
|
||||
{
|
||||
GroupName: "search",
|
||||
|
||||
@@ -183,6 +183,33 @@ func initializeStorage(cfg *config.Config) {
|
||||
}
|
||||
}
|
||||
}
|
||||
// Load persisted triggered alerts for suite endpoints
|
||||
for _, suite := range cfg.Suites {
|
||||
for _, ep := range suite.Endpoints {
|
||||
var checksums []string
|
||||
for _, alert := range ep.Alerts {
|
||||
if alert.IsEnabled() {
|
||||
checksums = append(checksums, alert.Checksum())
|
||||
}
|
||||
}
|
||||
numberOfTriggeredAlertsDeleted := store.Get().DeleteAllTriggeredAlertsNotInChecksumsByEndpoint(ep, checksums)
|
||||
if numberOfTriggeredAlertsDeleted > 0 {
|
||||
logr.Debugf("[main.initializeStorage] Deleted %d triggered alerts for suite endpoint with key=%s because their configurations have been changed or deleted", numberOfTriggeredAlertsDeleted, ep.Key())
|
||||
}
|
||||
for _, alert := range ep.Alerts {
|
||||
exists, resolveKey, numberOfSuccessesInARow, err := store.Get().GetTriggeredEndpointAlert(ep, alert)
|
||||
if err != nil {
|
||||
logr.Errorf("[main.initializeStorage] Failed to get triggered alert for suite endpoint with key=%s: %s", ep.Key(), err.Error())
|
||||
continue
|
||||
}
|
||||
if exists {
|
||||
alert.Triggered, alert.ResolveKey = true, resolveKey
|
||||
ep.NumberOfSuccessesInARow, ep.NumberOfFailuresInARow = numberOfSuccessesInARow, alert.FailureThreshold
|
||||
numberOfPersistedTriggeredAlertsLoaded++
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if numberOfPersistedTriggeredAlertsLoaded > 0 {
|
||||
logr.Infof("[main.initializeStorage] Loaded %d persisted triggered alerts", numberOfPersistedTriggeredAlertsLoaded)
|
||||
}
|
||||
|
||||
@@ -64,7 +64,6 @@ func executeEndpoint(ep *endpoint.Endpoint, cfg *config.Config, extraLabels []st
|
||||
}
|
||||
}
|
||||
if !cfg.Maintenance.IsUnderMaintenance() && !inEndpointMaintenanceWindow {
|
||||
// TODO: Consider moving this after the monitoring lock is unlocked? I mean, how much noise can a single alerting provider cause...
|
||||
HandleAlerting(ep, result, cfg.Alerting)
|
||||
} else {
|
||||
logr.Debug("[watchdog.executeEndpoint] Not handling alerting because currently in the maintenance window")
|
||||
|
||||
+2
-2
@@ -50,6 +50,8 @@ func executeSuite(s *suite.Suite, cfg *config.Config, extraLabels []string) {
|
||||
if cfg.Metrics {
|
||||
metrics.PublishMetricsForSuite(s, result, extraLabels)
|
||||
}
|
||||
// Store result
|
||||
UpdateSuiteStatus(s, result)
|
||||
// Handle alerting for suite endpoints
|
||||
for i, ep := range s.Endpoints {
|
||||
if i < len(result.EndpointResults) {
|
||||
@@ -72,8 +74,6 @@ func executeSuite(s *suite.Suite, cfg *config.Config, extraLabels []string) {
|
||||
}
|
||||
}
|
||||
logr.Infof("[watchdog.executeSuite] Completed suite=%s; success=%v; errors=%d; duration=%v; endpoints_executed=%d/%d", s.Name, result.Success, len(result.Errors), result.Duration, len(result.EndpointResults), len(s.Endpoints))
|
||||
// Store result in database
|
||||
UpdateSuiteStatus(s, result)
|
||||
}
|
||||
|
||||
// UpdateSuiteStatus persists the suite result in the database
|
||||
|
||||
+1
-2
@@ -197,13 +197,12 @@ const buttons = computed(() => {
|
||||
const fetchConfig = async () => {
|
||||
try {
|
||||
const response = await fetch(`${SERVER_URL}/api/v1/config`, { credentials: 'include' })
|
||||
retrievedConfig.value = true
|
||||
|
||||
if (response.status === 200) {
|
||||
const data = await response.json()
|
||||
config.value = data
|
||||
announcements.value = data.announcements || []
|
||||
}
|
||||
retrievedConfig.value = true
|
||||
} catch (error) {
|
||||
console.error('Failed to fetch config:', error)
|
||||
retrievedConfig.value = true
|
||||
|
||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user