Phase 3: dashboards and alerting
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.
This commit is contained in:
@@ -0,0 +1,24 @@
|
||||
// Package httpserver holds cross-handler HTTP concerns for /api. Phase 3
|
||||
// introduced a second handler package (internal/dashboards) alongside
|
||||
// internal/queryapi, so CORS moved out of individual handlers into one
|
||||
// wrap applied around the fully-assembled mux in cmd/api/main.go, rather
|
||||
// than each handler package wrapping itself.
|
||||
package httpserver
|
||||
|
||||
import "net/http"
|
||||
|
||||
// WithCORS is deliberately permissive by default (see CORSAllowedOrigin
|
||||
// in internal/config) since there's no auth yet and the SvelteKit dev
|
||||
// server runs on a different origin. Tighten alongside adding real auth.
|
||||
func WithCORS(next http.Handler, allowedOrigin string) http.Handler {
|
||||
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
w.Header().Set("Access-Control-Allow-Origin", allowedOrigin)
|
||||
w.Header().Set("Access-Control-Allow-Methods", "GET, POST, PUT, DELETE, OPTIONS")
|
||||
w.Header().Set("Access-Control-Allow-Headers", "Content-Type")
|
||||
if r.Method == http.MethodOptions {
|
||||
w.WriteHeader(http.StatusNoContent)
|
||||
return
|
||||
}
|
||||
next.ServeHTTP(w, r)
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,42 @@
|
||||
package httpserver
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestWithCORSPreflight(t *testing.T) {
|
||||
inner := http.NewServeMux()
|
||||
inner.HandleFunc("POST /query", func(w http.ResponseWriter, _ *http.Request) {
|
||||
w.WriteHeader(http.StatusOK)
|
||||
})
|
||||
h := WithCORS(inner, "*")
|
||||
|
||||
req := httptest.NewRequest(http.MethodOptions, "/query", nil)
|
||||
rec := httptest.NewRecorder()
|
||||
h.ServeHTTP(rec, req)
|
||||
|
||||
if rec.Code != http.StatusNoContent {
|
||||
t.Fatalf("status = %d, want 204", rec.Code)
|
||||
}
|
||||
if got := rec.Header().Get("Access-Control-Allow-Origin"); got != "*" {
|
||||
t.Fatalf("Access-Control-Allow-Origin = %q, want *", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestWithCORSPassesThroughNonPreflight(t *testing.T) {
|
||||
inner := http.NewServeMux()
|
||||
inner.HandleFunc("GET /healthz", func(w http.ResponseWriter, _ *http.Request) {
|
||||
w.WriteHeader(http.StatusOK)
|
||||
})
|
||||
h := WithCORS(inner, "*")
|
||||
|
||||
req := httptest.NewRequest(http.MethodGet, "/healthz", nil)
|
||||
rec := httptest.NewRecorder()
|
||||
h.ServeHTTP(rec, req)
|
||||
|
||||
if rec.Code != http.StatusOK {
|
||||
t.Fatalf("status = %d, want 200", rec.Code)
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user