mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2024-12-16 00:41:24 +01:00
ab10178c85
* vmalert: split alert's `Start` field into `ActiveAt` and `Start` The `ActiveAt` field identifies when alert becomes active for rules with `for > 0`. Previously, this value was stored in field `Start`. The field `Start` now identifies the moment alert became `FIRING`. The split is needed in order to distinguish these two moments in the API responses for alerts. Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: support specific moment of time for rules evaluation The Querier interface was extended to accept a new argument used as a timestamp at which evaluation should be made. It is needed to align rules execution time within the group. Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: mark disappeared series as stale Series generated by alerting rules, which were sent to remote write now will be marked as stale if they will disappear on the next evaluation. This would make ALERTS and ALERTS_FOR_TIME series more precise. Signed-off-by: hagen1778 <roman@victoriametrics.com> * wip Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: evaluate rules at fixed timestamp Before, time at which rules were evaluated was calculated right before rule execution. The change makes sure that timestamp is calculated only once per evalution round and all rules are using the same timestamp. It also updates the logic of resending of already resolved alert notification. Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: allow overridin `alertname` label value if it is present in response Previously, `alertname` was always equal to the Alerting Rule name. Now, its value can be overriden if series in response containt the different value for this label. The change is needed for improving compatibility with Prometheus. Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: align rules evaluation in time Now, evaluation timestamp for rules evaluates as if there was no delay in rules evaluation. It means, that rules will be evaluated at fixed timestamps+group_interval. This way provides more consistent evaluation results and improves compatibility with Prometheus, Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: add metric for missed iterations New metric `vmalert_iteration_missed_total` will show whether rules evaluation round was missed. Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: reduce delay before the initial rule evaluation in group Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: rollback alertname override According to the spec: ``` The alert name from the alerting rule (HighRequestLatency from the example above) MUST be added to the labels of the alert with the label name as alertname. It MUST override any existing alertname label. ``` https://github.com/prometheus/compliance/blob/main/alert_generator/specification.md#step-3 Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: throw err immediately on dedup detection ``` The execution of an alerting rule MUST error out immediately and MUST NOT send any alerts or add samples to samples receiver if there is more than one alert with the same labels ``` https://github.com/prometheus/compliance/blob/main/alert_generator/specification.md#step-4 Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: cleanup Signed-off-by: hagen1778 <roman@victoriametrics.com> * vmalert: use strings builder to reduce allocs Signed-off-by: hagen1778 <roman@victoriametrics.com>
150 lines
4.4 KiB
Go
150 lines
4.4 KiB
Go
package notifier
|
|
|
|
import (
|
|
"bytes"
|
|
"fmt"
|
|
"io"
|
|
"strings"
|
|
"text/template"
|
|
"time"
|
|
|
|
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/utils"
|
|
)
|
|
|
|
// Alert the triggered alert
|
|
// TODO: Looks like alert name isn't unique
|
|
type Alert struct {
|
|
// GroupID contains the ID of the parent rules group
|
|
GroupID uint64
|
|
// Name represents Alert name
|
|
Name string
|
|
// Labels is the list of label-value pairs attached to the Alert
|
|
Labels map[string]string
|
|
// Annotations is the list of annotations generated on Alert evaluation
|
|
Annotations map[string]string
|
|
// State represents the current state of the Alert
|
|
State AlertState
|
|
// Expr contains expression that was executed to generate the Alert
|
|
Expr string
|
|
// ActiveAt defines the moment of time when Alert has become active
|
|
ActiveAt time.Time
|
|
// Start defines the moment of time when Alert has become firing
|
|
Start time.Time
|
|
// End defines the moment of time when Alert supposed to expire
|
|
End time.Time
|
|
// ResolvedAt defines the moment when Alert was switched from Firing to Inactive
|
|
ResolvedAt time.Time
|
|
// LastSent defines the moment when Alert was sent last time
|
|
LastSent time.Time
|
|
// Value stores the value returned from evaluating expression from Expr field
|
|
Value float64
|
|
// ID is the unique identifer for the Alert
|
|
ID uint64
|
|
// Restored is true if Alert was restored after restart
|
|
Restored bool
|
|
}
|
|
|
|
// AlertState type indicates the Alert state
|
|
type AlertState int
|
|
|
|
const (
|
|
// StateInactive is the state of an alert that is neither firing nor pending.
|
|
StateInactive AlertState = iota
|
|
// StatePending is the state of an alert that has been active for less than
|
|
// the configured threshold duration.
|
|
StatePending
|
|
// StateFiring is the state of an alert that has been active for longer than
|
|
// the configured threshold duration.
|
|
StateFiring
|
|
)
|
|
|
|
// String stringer for AlertState
|
|
func (as AlertState) String() string {
|
|
switch as {
|
|
case StateFiring:
|
|
return "firing"
|
|
case StatePending:
|
|
return "pending"
|
|
}
|
|
return "inactive"
|
|
}
|
|
|
|
// AlertTplData is used to execute templating
|
|
type AlertTplData struct {
|
|
Labels map[string]string
|
|
Value float64
|
|
Expr string
|
|
}
|
|
|
|
var tplHeaders = []string{
|
|
"{{ $value := .Value }}",
|
|
"{{ $labels := .Labels }}",
|
|
"{{ $expr := .Expr }}",
|
|
"{{ $externalLabels := .ExternalLabels }}",
|
|
"{{ $externalURL := .ExternalURL }}",
|
|
}
|
|
|
|
// ExecTemplate executes the Alert template for given
|
|
// map of annotations.
|
|
// Every alert could have a different datasource, so function
|
|
// requires a queryFunction as an argument.
|
|
func (a *Alert) ExecTemplate(q QueryFn, annotations map[string]string) (map[string]string, error) {
|
|
tplData := AlertTplData{Value: a.Value, Labels: a.Labels, Expr: a.Expr}
|
|
return templateAnnotations(annotations, tplData, funcsWithQuery(q))
|
|
}
|
|
|
|
// ExecTemplate executes the given template for given annotations map.
|
|
func ExecTemplate(q QueryFn, annotations map[string]string, tpl AlertTplData) (map[string]string, error) {
|
|
return templateAnnotations(annotations, tpl, funcsWithQuery(q))
|
|
}
|
|
|
|
// ValidateTemplates validate annotations for possible template error, uses empty data for template population
|
|
func ValidateTemplates(annotations map[string]string) error {
|
|
_, err := templateAnnotations(annotations, AlertTplData{
|
|
Labels: map[string]string{},
|
|
Value: 0,
|
|
}, tmplFunc)
|
|
return err
|
|
}
|
|
|
|
func templateAnnotations(annotations map[string]string, data AlertTplData, funcs template.FuncMap) (map[string]string, error) {
|
|
var builder strings.Builder
|
|
var buf bytes.Buffer
|
|
eg := new(utils.ErrGroup)
|
|
r := make(map[string]string, len(annotations))
|
|
tData := tplData{data, externalLabels, externalURL}
|
|
header := strings.Join(tplHeaders, "")
|
|
for key, text := range annotations {
|
|
buf.Reset()
|
|
builder.Reset()
|
|
builder.Grow(len(header) + len(text))
|
|
builder.WriteString(header)
|
|
builder.WriteString(text)
|
|
if err := templateAnnotation(&buf, builder.String(), tData, funcs); err != nil {
|
|
r[key] = text
|
|
eg.Add(fmt.Errorf("key %q, template %q: %w", key, text, err))
|
|
continue
|
|
}
|
|
r[key] = buf.String()
|
|
}
|
|
return r, eg.Err()
|
|
}
|
|
|
|
type tplData struct {
|
|
AlertTplData
|
|
ExternalLabels map[string]string
|
|
ExternalURL string
|
|
}
|
|
|
|
func templateAnnotation(dst io.Writer, text string, data tplData, funcs template.FuncMap) error {
|
|
t := template.New("").Funcs(funcs).Option("missingkey=zero")
|
|
tpl, err := t.Parse(text)
|
|
if err != nil {
|
|
return fmt.Errorf("error parsing annotation: %w", err)
|
|
}
|
|
if err = tpl.Execute(dst, data); err != nil {
|
|
return fmt.Errorf("error evaluating annotation template: %w", err)
|
|
}
|
|
return nil
|
|
}
|