feat(cert): dial the TLS terminator directly so cert-expiry works from the container
checkCertExpiry now accepts a `dial` address and sets ServerName to the hostname — it connects to the terminator's IP while SNI/cert-read use the hostname. The scheduler container has no mesh interface and the host resolver doesn't know the split-horizon zone, so *.hubris.network can't be dialed by name from there; dialing Caddy's lab IP (reachable on the LAN) makes the probe work. The builder passes through a cert entity's `dial` attribute. Re-seed the 20 *.hubris.network certificate entities with dial=192.168.8.175 (Caddy) and uses-certificate edges; cert-expiry monitoring now has real data.
This commit is contained in:
@@ -536,6 +536,12 @@ func checkDisk(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkRes
|
||||
func checkCertExpiry(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
|
||||
cfg := struct {
|
||||
Host string `json:"host"`
|
||||
// Dial is an optional explicit dial address (the TLS terminator's IP)
|
||||
// for when the hostname doesn't resolve/reach from the scheduler — the
|
||||
// container has no mesh interface and the host resolver doesn't know
|
||||
// the split-horizon zone, so *.hubris.network dials Caddy's lab IP
|
||||
// directly while SNI/cert-read still uses Host.
|
||||
Dial string `json:"dial"`
|
||||
Port int `json:"port"`
|
||||
WarnDays int `json:"warn_days"`
|
||||
CritDays int `json:"crit_days"`
|
||||
@@ -556,9 +562,13 @@ func checkCertExpiry(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) ch
|
||||
timeout = 30 * time.Second
|
||||
}
|
||||
|
||||
addr := net.JoinHostPort(cfg.Host, fmt.Sprintf("%d", cfg.Port))
|
||||
dialHost := cfg.Host
|
||||
if cfg.Dial != "" {
|
||||
dialHost = cfg.Dial
|
||||
}
|
||||
addr := net.JoinHostPort(dialHost, fmt.Sprintf("%d", cfg.Port))
|
||||
|
||||
d := tls.Dialer{Config: &tls.Config{InsecureSkipVerify: true}}
|
||||
d := tls.Dialer{Config: &tls.Config{InsecureSkipVerify: true, ServerName: cfg.Host}}
|
||||
conn, err := d.DialContext(ctx, "tcp", addr)
|
||||
if err != nil {
|
||||
return checkResult{
|
||||
|
||||
Reference in New Issue
Block a user