From f20b26fd712c9247133ca0e5b8da052363f49ffa Mon Sep 17 00:00:00 2001
From: Ben Vincent <ben@unkin.net>
Date: Sat, 8 Aug 2026 22:38:20 +1000
Subject: [PATCH] Wait for HA peer DNS before starting kea-dhcp4

## Why
kea-dhcp4 crash-loops on a cold container start: the HA hook resolves the StatefulSet peer URL hostnames once at config load, but the peer DNS records are not resolvable in the first moment of a fresh container, and kea exits hard instead of retrying (HA_CONFIGURATION_FAILED / "Failed to convert string to address"). Once DNS is warm the exact config validates, so the failure is purely a startup race.

## How
- gate the dhcp4 entrypoint on `kea-dhcp4 -t` and retry until the config validates before exec'ing the server
---
 internal/kea/agent.go       |  9 +++++++++
 internal/kea/config_test.go | 11 +++++++++++
 2 files changed, 20 insertions(+)

diff --git a/internal/kea/agent.go b/internal/kea/agent.go
index 273f1c3..e5b848c 100644
--- a/internal/kea/agent.go
+++ b/internal/kea/agent.go
@@ -37,6 +37,15 @@ ORD="${HOSTNAME##*-}"
 mkdir -p %[1]s
 chmod 0750 %[1]s
 sed "s/%[2]s/server${ORD}/g" %[3]s/kea-dhcp4.conf > %[4]s
+# The HA hook resolves peer URL hostnames once at load; on a cold container
+# start the StatefulSet peer DNS records may not resolve yet, and kea exits
+# hard instead of retrying. Wait for the config to validate before starting.
+i=0
+until %[5]s -t %[4]s >/dev/null 2>&1; do
+  i=$((i+1))
+  if [ "$i" -ge 60 ]; then break; fi
+  sleep 2
+done
 exec %[5]s -c %[4]s
 `, RunDir, ThisServerPlaceholder, ConfigDir, DHCP4ConfPath, DHCP4Bin)
 }
diff --git a/internal/kea/config_test.go b/internal/kea/config_test.go
index 47bc01a..396296d 100644
--- a/internal/kea/config_test.go
+++ b/internal/kea/config_test.go
@@ -249,6 +249,17 @@ func TestEntrypointsHardenSocketDir(t *testing.T) {
 	}
 }
 
+func TestEntrypointWaitsForConfigToValidate(t *testing.T) {
+	// The dhcp4 entrypoint must gate startup on `kea-dhcp4 -t` so a cold-start
+	// HA peer DNS resolution failure retries instead of crash-looping.
+	ep := EntrypointDHCP4()
+	for _, want := range []string{"until " + DHCP4Bin + " -t " + DHCP4ConfPath, "exec " + DHCP4Bin + " -c " + DHCP4ConfPath} {
+		if !strings.Contains(ep, want) {
+			t.Errorf("dhcp4 entrypoint must contain %q, got:\n%s", want, ep)
+		}
+	}
+}
+
 func TestControlSocketPathAllowedByKea(t *testing.T) {
 	if !strings.HasPrefix(CtrlSocketPath, "/var/run/kea/") {
 		t.Errorf("CtrlSocketPath %q must live under /var/run/kea (kea 2.6+ restriction)", CtrlSocketPath)
-- 
2.47.3