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.
73 lines
2.1 KiB
Go
73 lines
2.1 KiB
Go
package main
|
|
|
|
import (
|
|
"bytes"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"os"
|
|
"time"
|
|
)
|
|
|
|
var httpClient = &http.Client{Timeout: 30 * time.Second}
|
|
|
|
// httpGetJSON GETs path and prints the pretty-printed JSON response to
|
|
// stdout, or the error body/status to stderr. Shared by dashboards/alerts
|
|
// list and get, which otherwise differ only in path and resource name.
|
|
func httpGetJSON(baseURL, path string, stdout, stderr io.Writer) int {
|
|
resp, err := httpClient.Get(baseURL + path)
|
|
if err != nil {
|
|
fmt.Fprintf(stderr, "request failed: %v\n", err)
|
|
return 1
|
|
}
|
|
defer resp.Body.Close()
|
|
return printJSONResponse(resp, stdout, stderr)
|
|
}
|
|
|
|
// httpPostFileJSON reads file (a JSON document, e.g. an exported
|
|
// dashboard or a rule definition) and POSTs it to path as-is -- no
|
|
// reshaping, since the file's shape already matches what the endpoint
|
|
// expects (the same JSON the web UI's export button and POST /rules
|
|
// produce/accept respectively). This is what makes "apply" the seed of a
|
|
// future Terraform provider: one JSON contract, multiple callers.
|
|
func httpPostFileJSON(baseURL, path, file string, stdout, stderr io.Writer) int {
|
|
body, err := os.ReadFile(file)
|
|
if err != nil {
|
|
fmt.Fprintf(stderr, "reading %s: %v\n", file, err)
|
|
return 1
|
|
}
|
|
resp, err := httpClient.Post(baseURL+path, "application/json", bytes.NewReader(body))
|
|
if err != nil {
|
|
fmt.Fprintf(stderr, "request failed: %v\n", err)
|
|
return 1
|
|
}
|
|
defer resp.Body.Close()
|
|
return printJSONResponse(resp, stdout, stderr)
|
|
}
|
|
|
|
func printJSONResponse(resp *http.Response, stdout, stderr io.Writer) int {
|
|
body, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
fmt.Fprintf(stderr, "reading response: %v\n", err)
|
|
return 1
|
|
}
|
|
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
|
|
var errResp errorResponseBody
|
|
if json.Unmarshal(body, &errResp) == nil && errResp.Error != "" {
|
|
fmt.Fprintf(stderr, "request failed: %s\n", errResp.Error)
|
|
} else {
|
|
fmt.Fprintf(stderr, "request failed: status %d\n", resp.StatusCode)
|
|
}
|
|
return 1
|
|
}
|
|
var pretty bytes.Buffer
|
|
if json.Indent(&pretty, body, "", " ") == nil {
|
|
stdout.Write(pretty.Bytes())
|
|
} else {
|
|
stdout.Write(body)
|
|
}
|
|
fmt.Fprintln(stdout)
|
|
return 0
|
|
}
|