VictoriaMetrics/app/vmalert/recording_test.go
Roman Khavronenko 0989649ad0
Vmalert compliance 2 (#2340)
* 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>
2022-03-29 15:09:07 +02:00

204 lines
5.8 KiB
Go

package main
import (
"context"
"errors"
"strings"
"testing"
"time"
"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompbmarshal"
)
func TestRecoridngRule_Exec(t *testing.T) {
timestamp := time.Now()
testCases := []struct {
rule *RecordingRule
metrics []datasource.Metric
expTS []prompbmarshal.TimeSeries
}{
{
&RecordingRule{Name: "foo"},
[]datasource.Metric{metricWithValueAndLabels(t, 10,
"__name__", "bar",
)},
[]prompbmarshal.TimeSeries{
newTimeSeries([]float64{10}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "foo",
}),
},
},
{
&RecordingRule{Name: "foobarbaz"},
[]datasource.Metric{
metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "foo"),
metricWithValueAndLabels(t, 2, "__name__", "bar", "job", "bar"),
metricWithValueAndLabels(t, 3, "__name__", "baz", "job", "baz"),
},
[]prompbmarshal.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "foobarbaz",
"job": "foo",
}),
newTimeSeries([]float64{2}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "foobarbaz",
"job": "bar",
}),
newTimeSeries([]float64{3}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "foobarbaz",
"job": "baz",
}),
},
},
{
&RecordingRule{Name: "job:foo", Labels: map[string]string{
"source": "test",
}},
[]datasource.Metric{
metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo"),
metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar")},
[]prompbmarshal.TimeSeries{
newTimeSeries([]float64{2}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "job:foo",
"job": "foo",
"source": "test",
}),
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "job:foo",
"job": "bar",
"source": "test",
}),
},
},
}
for _, tc := range testCases {
t.Run(tc.rule.Name, func(t *testing.T) {
fq := &fakeQuerier{}
fq.add(tc.metrics...)
tc.rule.q = fq
tss, err := tc.rule.Exec(context.TODO(), time.Now())
if err != nil {
t.Fatalf("unexpected Exec err: %s", err)
}
if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
t.Fatalf("timeseries missmatch: %s", err)
}
})
}
}
func TestRecoridngRule_ExecRange(t *testing.T) {
timestamp := time.Now()
testCases := []struct {
rule *RecordingRule
metrics []datasource.Metric
expTS []prompbmarshal.TimeSeries
}{
{
&RecordingRule{Name: "foo"},
[]datasource.Metric{metricWithValuesAndLabels(t, []float64{10, 20, 30},
"__name__", "bar",
)},
[]prompbmarshal.TimeSeries{
newTimeSeries([]float64{10, 20, 30},
[]int64{timestamp.UnixNano(), timestamp.UnixNano(), timestamp.UnixNano()},
map[string]string{
"__name__": "foo",
}),
},
},
{
&RecordingRule{Name: "foobarbaz"},
[]datasource.Metric{
metricWithValuesAndLabels(t, []float64{1}, "__name__", "foo", "job", "foo"),
metricWithValuesAndLabels(t, []float64{2, 3}, "__name__", "bar", "job", "bar"),
metricWithValuesAndLabels(t, []float64{4, 5, 6}, "__name__", "baz", "job", "baz"),
},
[]prompbmarshal.TimeSeries{
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "foobarbaz",
"job": "foo",
}),
newTimeSeries([]float64{2, 3}, []int64{timestamp.UnixNano(), timestamp.UnixNano()}, map[string]string{
"__name__": "foobarbaz",
"job": "bar",
}),
newTimeSeries([]float64{4, 5, 6},
[]int64{timestamp.UnixNano(), timestamp.UnixNano(), timestamp.UnixNano()},
map[string]string{
"__name__": "foobarbaz",
"job": "baz",
}),
},
},
{
&RecordingRule{Name: "job:foo", Labels: map[string]string{
"source": "test",
}},
[]datasource.Metric{
metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "foo"),
metricWithValueAndLabels(t, 1, "__name__", "bar", "job", "bar")},
[]prompbmarshal.TimeSeries{
newTimeSeries([]float64{2}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "job:foo",
"job": "foo",
"source": "test",
}),
newTimeSeries([]float64{1}, []int64{timestamp.UnixNano()}, map[string]string{
"__name__": "job:foo",
"job": "bar",
"source": "test",
}),
},
},
}
for _, tc := range testCases {
t.Run(tc.rule.Name, func(t *testing.T) {
fq := &fakeQuerier{}
fq.add(tc.metrics...)
tc.rule.q = fq
tss, err := tc.rule.ExecRange(context.TODO(), time.Now(), time.Now())
if err != nil {
t.Fatalf("unexpected Exec err: %s", err)
}
if err := compareTimeSeries(t, tc.expTS, tss); err != nil {
t.Fatalf("timeseries missmatch: %s", err)
}
})
}
}
func TestRecoridngRule_ExecNegative(t *testing.T) {
rr := &RecordingRule{Name: "job:foo", Labels: map[string]string{
"job": "test",
}}
fq := &fakeQuerier{}
expErr := "connection reset by peer"
fq.setErr(errors.New(expErr))
rr.q = fq
_, err := rr.Exec(context.TODO(), time.Now())
if err == nil {
t.Fatalf("expected to get err; got nil")
}
if !strings.Contains(err.Error(), expErr) {
t.Fatalf("expected to get err %q; got %q insterad", expErr, err)
}
fq.reset()
// add metrics which differs only by `job` label
// which will be overridden by rule
fq.add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "foo"))
fq.add(metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "bar"))
_, err = rr.Exec(context.TODO(), time.Now())
if err == nil {
t.Fatalf("expected to get err; got nil")
}
if !strings.Contains(err.Error(), errDuplicate.Error()) {
t.Fatalf("expected to get err %q; got %q insterad", errDuplicate, err)
}
}