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.
78 lines
2.2 KiB
Go
78 lines
2.2 KiB
Go
// Package config loads api's configuration from environment variables,
|
|
// same convention as /ingest: no config file format for Phase 0.
|
|
package config
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"strconv"
|
|
"time"
|
|
)
|
|
|
|
type Config struct {
|
|
HTTPListenAddr string
|
|
ClickHouse ClickHouseConfig
|
|
Postgres PostgresConfig
|
|
SearchGRPCAddr string
|
|
QueryTimeout time.Duration
|
|
CORSAllowedOrigin string
|
|
}
|
|
|
|
type ClickHouseConfig struct {
|
|
Addr string
|
|
Database string
|
|
Username string
|
|
Password string
|
|
}
|
|
|
|
// PostgresConfig is the control-plane metadata store (dashboards, panels
|
|
// -- see /docs/phase-3-dashboard-design.md), distinct from ClickHouse
|
|
// which remains log-data-only.
|
|
type PostgresConfig struct {
|
|
Addr string
|
|
Database string
|
|
Username string
|
|
Password string
|
|
}
|
|
|
|
func Load() (Config, error) {
|
|
cfg := Config{
|
|
HTTPListenAddr: getenv("HTTP_LISTEN_ADDR", ":8080"),
|
|
ClickHouse: ClickHouseConfig{
|
|
Addr: getenv("CLICKHOUSE_ADDR", "localhost:9000"),
|
|
Database: getenv("CLICKHOUSE_DATABASE", "sentry"),
|
|
Username: getenv("CLICKHOUSE_USERNAME", "default"),
|
|
Password: getenv("CLICKHOUSE_PASSWORD", ""),
|
|
},
|
|
Postgres: PostgresConfig{
|
|
Addr: getenv("POSTGRES_ADDR", "localhost:5432"),
|
|
Database: getenv("POSTGRES_DATABASE", "sentry_metadata"),
|
|
Username: getenv("POSTGRES_USERNAME", "sentry"),
|
|
Password: getenv("POSTGRES_PASSWORD", ""),
|
|
},
|
|
// Search service's gRPC address (see /search) -- default matches
|
|
// /search's own default GRPC_LISTEN_ADDR.
|
|
SearchGRPCAddr: getenv("SEARCH_GRPC_ADDR", "localhost:50052"),
|
|
// Phase 0 has no auth, so this is wide open by default to keep
|
|
// the local SvelteKit dev server (a different origin/port)
|
|
// working out of the box. Tighten before this is ever reachable
|
|
// from outside a trusted dev/homelab network.
|
|
CORSAllowedOrigin: getenv("CORS_ALLOWED_ORIGIN", "*"),
|
|
}
|
|
|
|
timeoutSec, err := strconv.Atoi(getenv("QUERY_TIMEOUT_SECONDS", "30"))
|
|
if err != nil {
|
|
return Config{}, fmt.Errorf("QUERY_TIMEOUT_SECONDS: %w", err)
|
|
}
|
|
cfg.QueryTimeout = time.Duration(timeoutSec) * time.Second
|
|
|
|
return cfg, nil
|
|
}
|
|
|
|
func getenv(key, fallback string) string {
|
|
if v := os.Getenv(key); v != "" {
|
|
return v
|
|
}
|
|
return fallback
|
|
}
|