Files
pdbmux/main.go
T
unkin-agent 514377c7cb
ci/woodpecker/pr/build Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/pre-commit Pipeline was successful
Health-check backends and skip the ones that are down
A down backend costs a full timeout stall on every request, since fan-out
has no way to know before it asks, and the client is never told the answer
came from fewer backends than are configured.

- poll each backend's status endpoint in the background, one goroutine per
  backend, with failure/success thresholds so a blip cannot flap it
- skip backends the prober has down, and fall open to querying all of them
  when none is left healthy
- treat a not-yet-probed backend as healthy so a restart drops no traffic
- log only up/down transitions
- stamp merged responses with X-Backends: <contributed>/<configured>
- report per-backend probe state and the last round's partiality on /healthz
- add health_probe_enabled, health_probe_path, health_probe_interval,
  health_probe_timeout, health_probe_failures and health_probe_successes,
  with matching PDBMUX_* env vars and a --health-probe flag
2026-09-05 23:30:28 +10:00

205 lines
5.5 KiB
Go

// Command pdbmux is a small merging HTTP proxy over several PuppetDB backends.
package main
import (
"context"
"errors"
"fmt"
"log"
"net/http"
"os"
"os/signal"
"strings"
"syscall"
"time"
"github.com/spf13/cobra"
)
var version = "dev"
func main() {
var (
cfg Config
configPath string
listen string
merge string
healthProbe bool
)
// Loaded lazily: --config is only known once cobra has parsed flags.
loadConfig := func() error {
c, err := Load(configPath)
if err != nil {
return err
}
cfg = c
return nil
}
serve := func(cmd *cobra.Command) error {
if err := loadConfig(); err != nil {
return err
}
if cmd.Flags().Changed("listen") {
cfg.Listen = listen
}
if cmd.Flags().Changed("merge") {
cfg.Merge = merge
}
if cmd.Flags().Changed("health-probe") {
cfg.HealthProbe = healthProbe
}
if err := cfg.Validate(); err != nil {
return err
}
return runServer(cfg)
}
root := &cobra.Command{
Use: appName,
Short: "Merging HTTP proxy over several PuppetDB backends.",
Long: "pdbmux presents a single merged PuppetDB v4 query surface over several\n" +
"PuppetDB backends, so clients see one consistent view of nodes, facts and\n" +
"reports spanning all of them. Running pdbmux with no subcommand (or\n" +
"`pdbmux serve`) starts the proxy.",
SilenceUsage: true,
RunE: func(cmd *cobra.Command, args []string) error { return serve(cmd) },
}
pf := root.PersistentFlags()
pf.StringVar(&configPath, "config", "", "Config file path (overrides PDBMUX_CONFIG and the default search path)")
pf.StringVar(&listen, "listen", defaultListen, "HTTP listen address (overrides config and PDBMUX_LISTEN)")
pf.StringVar(&merge, "merge", mergeFreshness, "Facts merge strategy: freshness or static")
pf.BoolVar(&healthProbe, "health-probe", true, "Probe backend health and skip backends that are down")
serveCmd := &cobra.Command{
Use: "serve",
Short: "Start the proxy (default action)",
SilenceUsage: true,
RunE: func(cmd *cobra.Command, args []string) error { return serve(cmd) },
}
configCmd := &cobra.Command{Use: "config", Short: "Manage configuration"}
configCmd.AddCommand(
&cobra.Command{
Use: "init",
Short: "Write a default config file (--config path, else " + ConfigPath() + ")",
SilenceUsage: true,
RunE: func(cmd *cobra.Command, args []string) error {
path := explicitConfigPath(configPath)
if path == "" {
path = ConfigPath()
}
return writeDefaultConfig(path)
},
},
&cobra.Command{
Use: "show",
Short: "Print the active configuration",
SilenceUsage: true,
RunE: func(cmd *cobra.Command, args []string) error {
if err := loadConfig(); err != nil {
return err
}
printConfig(cfg)
return nil
},
},
)
versionCmd := &cobra.Command{
Use: "version",
Short: "Print the version",
Run: func(cmd *cobra.Command, args []string) { fmt.Println(version) },
SilenceUsage: true,
}
root.AddCommand(serveCmd, configCmd, versionCmd)
if err := root.Execute(); err != nil {
os.Exit(1)
}
}
func runServer(cfg Config) error {
logger := log.New(os.Stderr, "pdbmux: ", log.LstdFlags)
srv := NewServer(cfg, logger)
srv.StartProbes(context.Background())
defer srv.StopProbes()
httpSrv := &http.Server{
Addr: cfg.Listen,
Handler: srv.Handler(),
ReadHeaderTimeout: 10 * time.Second,
}
logger.Printf("listening on %s (merge=%s backends=%d)",
cfg.Listen, cfg.Merge, len(cfg.Backends))
errCh := make(chan error, 1)
go func() {
if err := httpSrv.ListenAndServe(); err != nil && !errors.Is(err, http.ErrServerClosed) {
errCh <- err
}
}()
stop := make(chan os.Signal, 1)
signal.Notify(stop, syscall.SIGINT, syscall.SIGTERM)
select {
case err := <-errCh:
return err
case <-stop:
logger.Println("shutting down")
ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
return httpSrv.Shutdown(ctx)
}
}
func factsTTLString(cfg Config) string {
s := durationString(cfg.FactsTTL)
switch {
case cfg.factsTTLClamped > 0:
return fmt.Sprintf("%s (clamped from %s, cap %s)",
s, durationString(cfg.factsTTLClamped), durationString(maxFactsTTL))
case !cfg.cacheEnabled():
return s + " (cache disabled)"
}
return s
}
func healthProbeString(cfg Config) string {
if !cfg.HealthProbe {
return "disabled"
}
return fmt.Sprintf("%s every %s (timeout %s, %d failures down / %d successes up)",
cfg.HealthProbePath, durationString(cfg.HealthProbeInterval),
durationString(cfg.HealthProbeTimeout), cfg.HealthProbeFailures, cfg.HealthProbeSuccesses)
}
func printConfig(cfg Config) {
if p := cfg.SourcePath(); p != "" {
fmt.Printf("config file : %s (loaded)\n", p)
} else {
fmt.Printf("config file : none loaded (searched %s)\n", strings.Join(configSearchPaths(), ", "))
}
fmt.Printf("listen : %s\n", cfg.Listen)
fmt.Printf("merge : %s\n", cfg.Merge)
fmt.Printf("timeout : %s\n", durationString(cfg.Timeout))
fmt.Printf("freshness_ttl: %s\n", durationString(cfg.FreshnessTTL))
if cfg.SourceFactEnabled {
fmt.Printf("source_fact : %s\n", cfg.SourceFact)
} else {
fmt.Printf("source_fact : disabled\n")
}
fmt.Printf("facts_ttl : %s\n", factsTTLString(cfg))
fmt.Printf("facts_cache : %d bytes\n", cfg.CacheBytes)
fmt.Printf("health_probe : %s\n", healthProbeString(cfg))
fmt.Println("backends:")
for _, b := range cfg.Backends {
fmt.Printf(" - %-8s %s\n", b.Name, b.URL)
}
}