lerko
f023e38fdc
Replace all monitor package-level mutable state with Engine struct. All state (liveState, logStore, histories, tokenIndex, HTTP clients) is now encapsulated in Engine, created via NewEngine(store). Key changes: - Engine struct holds all monitor state with proper mutex protection - Engine.Start(ctx) and monitorRoutine respect context cancellation for graceful shutdown — no more leaked goroutines - cluster.runFollowerLoop also respects context for clean exit - Token index (map[string]int) for O(1) push heartbeat lookup, replacing O(n) linear scan through LiveState - UpdateSiteConfig preserves 8 runtime fields instead of copying 17 config fields individually - triggerAlert goroutines get 30s timeout context - All consumers (TUI, server, cluster, main) receive *Engine via constructor/parameter — no package-level state access - main.go creates context.WithCancel, passes to engine and cluster First test suite: 12 tests across store and alert packages - Store: CRUD for sites/alerts/users, push token generation, import/export round-trip, check history persistence - Alert: Discord/Slack/Webhook payload format, HTTP 4xx error propagation, Ntfy headers, unknown provider returns nil
78 lines
1.8 KiB
Go
78 lines
1.8 KiB
Go
package cluster
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"go-upkeep/internal/monitor"
|
|
"net/http"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
type Config struct {
|
|
Mode string // "leader" or "follower"
|
|
PeerURL string // URL of the Leader (e.g., http://primary:8080)
|
|
SharedKey string // Security Key
|
|
}
|
|
|
|
func Start(ctx context.Context, cfg Config, eng *monitor.Engine) {
|
|
if cfg.Mode == "leader" {
|
|
fmt.Println("Cluster: Running as LEADER (Active)")
|
|
if cfg.SharedKey != "" {
|
|
fmt.Println("WARNING: Cluster mode enabled. Ensure the HTTP server is behind a TLS-terminating proxy.")
|
|
}
|
|
eng.SetActive(true)
|
|
return
|
|
}
|
|
|
|
if cfg.Mode == "follower" {
|
|
fmt.Println("Cluster: Running as FOLLOWER (Passive)")
|
|
if cfg.PeerURL != "" && !strings.HasPrefix(cfg.PeerURL, "https://") {
|
|
fmt.Println("WARNING: Cluster peer URL is not HTTPS. Cluster secret will be sent in cleartext.")
|
|
}
|
|
eng.SetActive(false)
|
|
go runFollowerLoop(ctx, cfg, eng)
|
|
}
|
|
}
|
|
|
|
func runFollowerLoop(ctx context.Context, cfg Config, eng *monitor.Engine) {
|
|
client := http.Client{Timeout: 2 * time.Second}
|
|
failures := 0
|
|
threshold := 3
|
|
|
|
for {
|
|
select {
|
|
case <-time.After(5 * time.Second):
|
|
case <-ctx.Done():
|
|
return
|
|
}
|
|
|
|
req, _ := http.NewRequest("GET", cfg.PeerURL+"/api/health", nil)
|
|
if cfg.SharedKey != "" {
|
|
req.Header.Set("X-Upkeep-Secret", cfg.SharedKey)
|
|
}
|
|
|
|
resp, err := client.Do(req)
|
|
isLeaderHealthy := false
|
|
|
|
if err == nil && resp.StatusCode == 200 {
|
|
isLeaderHealthy = true
|
|
resp.Body.Close()
|
|
}
|
|
|
|
if isLeaderHealthy {
|
|
failures = 0
|
|
if eng.IsActive() {
|
|
eng.SetActive(false)
|
|
eng.AddLog("Cluster: Leader detected. Switching to PASSIVE.")
|
|
}
|
|
} else {
|
|
failures++
|
|
if failures >= threshold && !eng.IsActive() {
|
|
eng.SetActive(true)
|
|
eng.AddLog("Cluster: Leader Unreachable. Switching to ACTIVE.")
|
|
}
|
|
}
|
|
}
|
|
}
|