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 +1,112 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"os"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
type queryArgs struct {
|
||||
apiURL string
|
||||
jsonOut bool
|
||||
language string
|
||||
query string
|
||||
}
|
||||
|
||||
// parseQueryArgs is pure (env passed in, no I/O), same testability
|
||||
// reasoning as parsePingArgs. Non-flag arguments are joined with spaces
|
||||
// to form the query, so `sentryctl query service=api status=500` (no
|
||||
// quotes, no shell-special characters) works without requiring users to
|
||||
// quote every query -- though anything using "|" still needs shell
|
||||
// quoting regardless, since that's a real shell pipe character otherwise.
|
||||
func parseQueryArgs(args []string, env func(string) string) queryArgs {
|
||||
qa := queryArgs{apiURL: resolveAPIURL(env)}
|
||||
var rest []string
|
||||
for i := 0; i < len(args); i++ {
|
||||
switch args[i] {
|
||||
case "--api":
|
||||
if i+1 < len(args) {
|
||||
qa.apiURL = args[i+1]
|
||||
i++
|
||||
}
|
||||
case "--json":
|
||||
qa.jsonOut = true
|
||||
case "--language":
|
||||
if i+1 < len(args) {
|
||||
qa.language = args[i+1]
|
||||
i++
|
||||
}
|
||||
default:
|
||||
rest = append(rest, args[i])
|
||||
}
|
||||
}
|
||||
qa.query = strings.Join(rest, " ")
|
||||
return qa
|
||||
}
|
||||
|
||||
type queryRequestBody struct {
|
||||
Query string `json:"query"`
|
||||
Language string `json:"language"`
|
||||
}
|
||||
|
||||
type queryResponseBody struct {
|
||||
Columns []string `json:"columns"`
|
||||
Rows [][]any `json:"rows"`
|
||||
}
|
||||
|
||||
func cmdQuery(args []string, stdout, stderr io.Writer) int {
|
||||
qa := parseQueryArgs(args, os.Getenv)
|
||||
if strings.TrimSpace(qa.query) == "" {
|
||||
fmt.Fprintln(stderr, "sentryctl query: missing query string")
|
||||
return 1
|
||||
}
|
||||
|
||||
reqBody, err := json.Marshal(queryRequestBody{Query: qa.query, Language: qa.language})
|
||||
if err != nil {
|
||||
fmt.Fprintf(stderr, "encoding request: %v\n", err)
|
||||
return 1
|
||||
}
|
||||
|
||||
client := &http.Client{Timeout: 30 * time.Second}
|
||||
resp, err := client.Post(qa.apiURL+"/query", "application/json", bytes.NewReader(reqBody))
|
||||
if err != nil {
|
||||
fmt.Fprintf(stderr, "query failed: %v\n", err)
|
||||
return 1
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
respBody, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
fmt.Fprintf(stderr, "reading response: %v\n", err)
|
||||
return 1
|
||||
}
|
||||
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
var errResp errorResponseBody
|
||||
if json.Unmarshal(respBody, &errResp) == nil && errResp.Error != "" {
|
||||
fmt.Fprintf(stderr, "query failed: %s\n", errResp.Error)
|
||||
} else {
|
||||
fmt.Fprintf(stderr, "query failed: api returned status %d\n", resp.StatusCode)
|
||||
}
|
||||
return 1
|
||||
}
|
||||
|
||||
if qa.jsonOut {
|
||||
_, _ = stdout.Write(respBody)
|
||||
fmt.Fprintln(stdout)
|
||||
return 0
|
||||
}
|
||||
|
||||
var result queryResponseBody
|
||||
if err := json.Unmarshal(respBody, &result); err != nil {
|
||||
fmt.Fprintf(stderr, "decoding response: %v\n", err)
|
||||
return 1
|
||||
}
|
||||
printTable(stdout, result.Columns, result.Rows)
|
||||
return 0
|
||||
}
|
||||
Reference in New Issue
Block a user