jcoffey-dev
9435115ab7
Saved, shareable multi-panel dashboards (table/line/bar/single-stat panels via gridstack + uPlot, global + per-panel time range, JSON export/import) and threshold/absence alert rules with an ok/pending/firing evaluator and webhook/Slack/PagerDuty delivery. - New /metadata component: Postgres control-plane store for dashboards, panels, notification targets, alert rules/state, and delivery log -- see docs/phase-3-dashboard-design.md for why ClickHouse's MergeTree family isn't a fit for this access pattern (needs real row-level locking and read-your-writes consistency). - api/internal/dashboards: dashboard/panel CRUD, pure -- panel query execution stays client-side, reusing the existing /query endpoint. - New /alerting service: rule/target CRUD, a ticker-driven evaluator (claim-then-evaluate concurrency control, transactional-outbox delivery, query errors and threshold zero-rows never coerced into a false transition) and webhook/Slack/PagerDuty delivery with retry/backoff. See docs/phase-3-alerting-design.md for the full state-machine design and the four correctness properties it implements. - web: /dashboards and /alerts UIs; cli: sentryctl dashboards/alerts list/get/apply, seeding a future Terraform provider's JSON contract. - hack/alert-load-test: 500 rules against real ClickHouse data, real measured results in docs/phase-3-runbook.md. Five real bugs found by actually running this against a live stack (documented in the runbook, not just fixed silently): a latent Phase 2 bug where ClickHouse rejected the timestamp format used for earliest=/latest= queries; a "now" literal token injected into query text; a GridStack/uPlot layout-timing race; JS's Date.parse being too lenient to use as a timestamp-detection heuristic; a rule's "enabled" field silently defaulting to false when omitted; and the evaluator's claim-batch-size and worker-pool-concurrency defaulting to the same value, causing 500 concurrently-due rules to take 125s to cycle through instead of the configured 60s.
119 lines
3.7 KiB
Go
119 lines
3.7 KiB
Go
package evaluator
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/sentry/sentry/alerting/internal/queryclient"
|
|
"github.com/sentry/sentry/alerting/internal/rulestore"
|
|
)
|
|
|
|
func thresholdRule(comparator rulestore.Comparator, threshold float64) rulestore.Rule {
|
|
return rulestore.Rule{
|
|
ConditionType: rulestore.ConditionThreshold,
|
|
Comparator: &comparator,
|
|
ThresholdValue: &threshold,
|
|
}
|
|
}
|
|
|
|
func TestEvaluateConditionThresholdTrue(t *testing.T) {
|
|
rule := thresholdRule(rulestore.Gt, 100)
|
|
result := &queryclient.Result{Columns: []string{"count"}, Rows: [][]any{{150.0}}}
|
|
|
|
got, value, err := evaluateCondition(rule, result)
|
|
if err != nil {
|
|
t.Fatalf("unexpected error: %v", err)
|
|
}
|
|
if !got {
|
|
t.Fatalf("expected condition true for 150 > 100")
|
|
}
|
|
if value == nil || *value != 150.0 {
|
|
t.Fatalf("expected value=150, got %v", value)
|
|
}
|
|
}
|
|
|
|
func TestEvaluateConditionThresholdFalse(t *testing.T) {
|
|
rule := thresholdRule(rulestore.Gt, 100)
|
|
result := &queryclient.Result{Columns: []string{"count"}, Rows: [][]any{{50.0}}}
|
|
|
|
got, _, err := evaluateCondition(rule, result)
|
|
if err != nil {
|
|
t.Fatalf("unexpected error: %v", err)
|
|
}
|
|
if got {
|
|
t.Fatalf("expected condition false for 50 > 100")
|
|
}
|
|
}
|
|
|
|
// TestEvaluateConditionThresholdZeroRowsIsError pins down fix 4: zero
|
|
// rows on a threshold rule must be an error, not silently coerced to 0
|
|
// (which would make `count > 100` falsely report "fine" when actually
|
|
// nothing ran).
|
|
func TestEvaluateConditionThresholdZeroRowsIsError(t *testing.T) {
|
|
rule := thresholdRule(rulestore.Gt, 100)
|
|
result := &queryclient.Result{Columns: []string{"count"}, Rows: [][]any{}}
|
|
|
|
_, value, err := evaluateCondition(rule, result)
|
|
if err == nil {
|
|
t.Fatalf("expected an error for zero rows on a threshold rule, got condition evaluated with value=%v", value)
|
|
}
|
|
}
|
|
|
|
func TestEvaluateConditionThresholdMultipleRowsIsError(t *testing.T) {
|
|
rule := thresholdRule(rulestore.Gt, 100)
|
|
result := &queryclient.Result{Columns: []string{"host", "count"}, Rows: [][]any{{"h1", 50.0}, {"h2", 200.0}}}
|
|
|
|
_, _, err := evaluateCondition(rule, result)
|
|
if err == nil {
|
|
t.Fatalf("expected an error for multiple rows on a threshold rule (no per-group alerting, a named non-goal)")
|
|
}
|
|
}
|
|
|
|
func TestEvaluateConditionThresholdNonNumericIsError(t *testing.T) {
|
|
rule := thresholdRule(rulestore.Gt, 100)
|
|
result := &queryclient.Result{Columns: []string{"host"}, Rows: [][]any{{"host-01"}}}
|
|
|
|
_, _, err := evaluateCondition(rule, result)
|
|
if err == nil {
|
|
t.Fatalf("expected an error for a non-numeric first column")
|
|
}
|
|
}
|
|
|
|
func TestEvaluateConditionAbsenceTrueWhenZeroRows(t *testing.T) {
|
|
rule := rulestore.Rule{ConditionType: rulestore.ConditionAbsence}
|
|
result := &queryclient.Result{Columns: []string{"message"}, Rows: [][]any{}}
|
|
|
|
got, value, err := evaluateCondition(rule, result)
|
|
if err != nil {
|
|
t.Fatalf("unexpected error: %v", err)
|
|
}
|
|
if !got {
|
|
t.Fatalf("expected absence condition true for zero rows")
|
|
}
|
|
if value != nil {
|
|
t.Fatalf("expected nil value for an absence rule, got %v", value)
|
|
}
|
|
}
|
|
|
|
func TestEvaluateConditionAbsenceFalseWhenRowsPresent(t *testing.T) {
|
|
rule := rulestore.Rule{ConditionType: rulestore.ConditionAbsence}
|
|
result := &queryclient.Result{Columns: []string{"message"}, Rows: [][]any{{"something happened"}}}
|
|
|
|
got, _, err := evaluateCondition(rule, result)
|
|
if err != nil {
|
|
t.Fatalf("unexpected error: %v", err)
|
|
}
|
|
if got {
|
|
t.Fatalf("expected absence condition false when rows are present")
|
|
}
|
|
}
|
|
|
|
func TestEvaluateConditionUnknownTypeIsError(t *testing.T) {
|
|
rule := rulestore.Rule{ConditionType: "bogus"}
|
|
result := &queryclient.Result{Columns: []string{"count"}, Rows: [][]any{{1.0}}}
|
|
|
|
_, _, err := evaluateCondition(rule, result)
|
|
if err == nil {
|
|
t.Fatalf("expected an error for an unknown condition_type")
|
|
}
|
|
}
|