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.
64 lines
1.7 KiB
Go
64 lines
1.7 KiB
Go
package main
|
|
|
|
import (
|
|
"bytes"
|
|
"reflect"
|
|
"testing"
|
|
)
|
|
|
|
func TestExtractAlertingAPIFlagDefault(t *testing.T) {
|
|
alertingURL, rest := extractAlertingAPIFlag([]string{"rule-1"}, func(string) string { return "" })
|
|
if alertingURL != defaultAlertingURL {
|
|
t.Fatalf("alertingURL = %q, want default %q", alertingURL, defaultAlertingURL)
|
|
}
|
|
if !reflect.DeepEqual(rest, []string{"rule-1"}) {
|
|
t.Fatalf("rest = %v", rest)
|
|
}
|
|
}
|
|
|
|
func TestExtractAlertingAPIFlagOverride(t *testing.T) {
|
|
alertingURL, rest := extractAlertingAPIFlag([]string{"--alerting-api", "http://custom:9091", "rule-1"}, func(string) string { return "" })
|
|
if alertingURL != "http://custom:9091" {
|
|
t.Fatalf("alertingURL = %q", alertingURL)
|
|
}
|
|
if !reflect.DeepEqual(rest, []string{"rule-1"}) {
|
|
t.Fatalf("rest = %v", rest)
|
|
}
|
|
}
|
|
|
|
func TestExtractAlertingAPIFlagFromEnv(t *testing.T) {
|
|
alertingURL, _ := extractAlertingAPIFlag(nil, func(k string) string {
|
|
if k == "SENTRYCTL_ALERTING_API_URL" {
|
|
return "http://env-alerting:8081"
|
|
}
|
|
return ""
|
|
})
|
|
if alertingURL != "http://env-alerting:8081" {
|
|
t.Fatalf("alertingURL = %q", alertingURL)
|
|
}
|
|
}
|
|
|
|
func TestCmdAlertsMissingSubcommand(t *testing.T) {
|
|
var stdout, stderr bytes.Buffer
|
|
code := cmdAlerts(nil, &stdout, &stderr)
|
|
if code != 1 {
|
|
t.Fatalf("code = %d, want 1", code)
|
|
}
|
|
}
|
|
|
|
func TestCmdAlertsApplyMissingFile(t *testing.T) {
|
|
var stdout, stderr bytes.Buffer
|
|
code := cmdAlerts([]string{"apply"}, &stdout, &stderr)
|
|
if code != 1 {
|
|
t.Fatalf("code = %d, want 1", code)
|
|
}
|
|
}
|
|
|
|
func TestCmdAlertsUnknownSubcommand(t *testing.T) {
|
|
var stdout, stderr bytes.Buffer
|
|
code := cmdAlerts([]string{"bogus"}, &stdout, &stderr)
|
|
if code != 1 {
|
|
t.Fatalf("code = %d, want 1", code)
|
|
}
|
|
}
|