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.
56 lines
1.6 KiB
Go
56 lines
1.6 KiB
Go
package main
|
|
|
|
import (
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
)
|
|
|
|
func cmdDashboards(args []string, stdout, stderr io.Writer) int {
|
|
if len(args) == 0 {
|
|
fmt.Fprintln(stderr, "sentryctl dashboards: expected a subcommand (list, get, apply)")
|
|
return 1
|
|
}
|
|
apiURL, rest := extractAPIFlag(args[1:], os.Getenv)
|
|
|
|
switch args[0] {
|
|
case "list":
|
|
return httpGetJSON(apiURL, "/dashboards", stdout, stderr)
|
|
case "get":
|
|
if len(rest) == 0 {
|
|
fmt.Fprintln(stderr, "sentryctl dashboards get: missing dashboard id")
|
|
return 1
|
|
}
|
|
return httpGetJSON(apiURL, "/dashboards/"+rest[0], stdout, stderr)
|
|
case "apply":
|
|
if len(rest) == 0 {
|
|
fmt.Fprintln(stderr, "sentryctl dashboards apply: missing file path")
|
|
return 1
|
|
}
|
|
// The import endpoint consumes exactly the shape GET
|
|
// /dashboards/{id}/export produces and the web UI's Export JSON
|
|
// button downloads -- one JSON contract, three call sites.
|
|
return httpPostFileJSON(apiURL, "/dashboards/import", rest[0], stdout, stderr)
|
|
default:
|
|
fmt.Fprintf(stderr, "sentryctl dashboards: unknown subcommand %q (want list, get, apply)\n", args[0])
|
|
return 1
|
|
}
|
|
}
|
|
|
|
// extractAPIFlag pulls an optional --api <url> out of args, resolving
|
|
// the default the same way parsePingArgs/parseQueryArgs do, and returns
|
|
// the remaining positional args. Shared by dashboards and alerts since
|
|
// both take an optional --api/--alerting-api override the same way.
|
|
func extractAPIFlag(args []string, env func(string) string) (apiURL string, rest []string) {
|
|
apiURL = resolveAPIURL(env)
|
|
for i := 0; i < len(args); i++ {
|
|
if args[i] == "--api" && i+1 < len(args) {
|
|
apiURL = args[i+1]
|
|
i++
|
|
continue
|
|
}
|
|
rest = append(rest, args[i])
|
|
}
|
|
return apiURL, rest
|
|
}
|