Added supervised-init.sh to retry ctl init

alpine/rootfs-extra/etc/local.d/monok8s.start

@@ -38,4 +38,4 @@ if [ -n "$K8S_MINOR" ]; then
 	"$MIGRATION_STATE_DIR/k8s/$K8S_MINOR"
 fi
 
-/usr/local/bin/ctl init --env-file "$CONFIG_DIR/cluster.env" >>/var/log/monok8s/bootstrap.log 2>&1 &
+/usr/lib/monok8s/lib/supervised-init.sh &

alpine/rootfs-extra/usr/lib/monok8s/lib/supervised-init.sh

@@ -0,0 +1,57 @@
+#!/bin/sh
+set -eu
+
+CONFIG_DIR=/opt/monok8s/config
+LOG=/var/log/monok8s/bootstrap.log
+STATE_DIR=/run/monok8s
+FAIL_COUNT_FILE="$STATE_DIR/bootstrap-fail-count"
+LOCK_DIR="$STATE_DIR/supervised-init.lock"
+
+# For debugging
+HOLD_FILE="$CONFIG_DIR/bootstrap.hold"
+
+mkdir -p "$STATE_DIR" /var/log/monok8s
+
+if ! mkdir "$LOCK_DIR" 2>/dev/null; then
+	echo "[$(date -Is)] supervised-init already running" >> "$LOG"
+	exit 0
+fi
+
+trap 'rmdir "$LOCK_DIR"' EXIT INT TERM
+
+fail_count=0
+if [ -f "$FAIL_COUNT_FILE" ]; then
+	fail_count="$(cat "$FAIL_COUNT_FILE" 2>/dev/null || echo 0)"
+	case "$fail_count" in
+		''|*[!0-9]*) fail_count=0 ;;
+	esac
+fi
+
+while true; do
+	if [ -f "$HOLD_FILE" ]; then
+		echo "[$(date -Is)] bootstrap held by $HOLD_FILE" >> "$LOG"
+		sleep 300
+		continue
+	fi
+
+	echo "[$(date -Is)] starting ctl init" >> "$LOG"
+
+	if /usr/local/bin/ctl init --env-file "$CONFIG_DIR/cluster.env" >> "$LOG" 2>&1; then
+		echo "[$(date -Is)] ctl init succeeded" >> "$LOG"
+		rm -f "$FAIL_COUNT_FILE"
+		exit 0
+	fi
+
+	fail_count=$((fail_count + 1))
+	echo "$fail_count" > "$FAIL_COUNT_FILE"
+
+	echo "[$(date -Is)] ctl init failed, count=$fail_count" >> "$LOG"
+
+	case "$fail_count" in
+		1) sleep 10 ;;
+		2) sleep 30 ;;
+		3) sleep 60 ;;
+		4) sleep 120 ;;
+		*) sleep 300 ;;
+	esac
+done

clitools/pkg/bootstrap/runner.go

@@ -70,7 +70,7 @@ func NewRunner(cfg *monov1alpha1.MonoKSConfig) *Runner {
 			{
 				RegKey: "EngageControlGate",
 				Name:   "Engage the control gate",
-				Desc:   "Prevents agent polling resources prematurely",
+				Desc:   "Prevents agent watching resources prematurely",
 			},
 			{
 				RegKey: "StartCRIO",
@@ -165,7 +165,7 @@ func NewRunner(cfg *monov1alpha1.MonoKSConfig) *Runner {
 			{
 				RegKey: "ReleaseControlGate",
 				Name:   "Release the control gate",
-				Desc:   "Allow agent to start polling resources",
+				Desc:   "Allow agent to start watching resources",
 			},
 		},
 	}