docs(ops): record 188 node exporter recovery [skip ci]

scripts/ops/188-node-exporter-restore.sh

@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+IMAGE="${NODE_EXPORTER_IMAGE:-quay.io/prometheus/node-exporter:v1.8.2}"
+CONTAINER_NAME="${NODE_EXPORTER_CONTAINER_NAME:-node-exporter}"
+TEXTFILE_DIR="${NODE_EXPORTER_TEXTFILE_DIR:-/home/ollama/node_exporter_textfiles}"
+PORT="${NODE_EXPORTER_PORT:-9100}"
+
+if [ ! -d "$TEXTFILE_DIR" ]; then
+  echo "TEXTFILE_DIR_MISSING $TEXTFILE_DIR" >&2
+  exit 1
+fi
+
+if docker ps -a --format '{{.Names}}' | grep -qx "$CONTAINER_NAME"; then
+  docker rm -f "$CONTAINER_NAME" >/dev/null
+fi
+
+docker run -d \
+  --name "$CONTAINER_NAME" \
+  --restart unless-stopped \
+  -p "${PORT}:9100" \
+  -v /:/host:ro,rslave \
+  -v "${TEXTFILE_DIR}:/textfile:ro" \
+  "$IMAGE" \
+  --path.rootfs=/host \
+  --collector.textfile.directory=/textfile \
+  '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc|run/credentials|var/lib/docker|run/docker)($|/)' \
+  '--collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs|tmpfs|shm)$' \
+  --no-collector.infiniband \
+  --no-collector.ipvs \
+  --no-collector.mdadm \
+  --no-collector.nfs \
+  --no-collector.nfsd \
+  --no-collector.xfs \
+  --no-collector.zfs \
+  --no-collector.processes \
+  --no-collector.arp \
+  --no-collector.netclass \
+  --no-collector.netdev >/dev/null
+
+for _ in $(seq 1 20); do
+  if curl -fsS --max-time 3 "http://127.0.0.1:${PORT}/metrics" \
+    | grep -q '^awoooi_backup_health_monitor_up{host="188"} 1$'; then
+    echo "NODE_EXPORTER_188_OK port=${PORT} textfile_dir=${TEXTFILE_DIR}"
+    exit 0
+  fi
+  sleep 1
+done
+
+echo "NODE_EXPORTER_188_BACKUP_HEALTH_METRIC_MISSING port=${PORT}" >&2
+docker logs --tail=80 "$CONTAINER_NAME" >&2 || true
+exit 1