"Count of offline nodes in the cluster")
	healthNodesOnlineCountMD = NewGaugeMD(healthNodesOnlineCount,
		"Count of online nodes in the cluster")
)

// loadClusterHealthNodeMetrics - `MetricsLoaderFn` for cluster health node
// metrics.
func loadClusterHealthNodeMetrics(ctx context.Context, m MetricValues,
	c *metricsCache,
) error {
	nodesUpDown, _ := c.nodesUpDown.Get()

	m.Set(healthNodesOfflineCount, float64(nodesUpDown.Offline))

		return ctx, done, ctx.Err()
	}

	atomic.StoreInt64(&p.health.lastStarted, time.Now().UnixNano())
	p.health.waiting.Add(1)

	ctx = context.WithValue(ctx, healthDiskCtxKey{}, &healthDiskCtxValue{lastSuccess: &p.health.lastSuccess})
	si := p.updateStorageMetrics(s, paths...)
	var once sync.Once
	return ctx, func(errp *error) {
		p.health.waiting.Add(-1)
		once.Do(func() {
			if errp != nil {
				err := *errp

		opts := HealthOptions{}
		result := objLayer.Health(ctx, opts)

		metrics = make([]MetricV2, 0, 2+4*len(result.ESHealth))

		metrics = append(metrics, MetricV2{
			Description: getClusterWriteQuorumMD(),
			Value:       float64(result.WriteQuorum),
		})

		health := 1
		if !result.Healthy {
			health = 0
		}

		metrics = append(metrics, MetricV2{

		Online:   true,
	}
	sys.hMutex.Unlock()
}

// newHCClient initializes an anonymous client for performing health check on the remote endpoints
func newHCClient() *madmin.AnonymousClient {
	clnt, e := madmin.NewAnonymousClientNoEndpoint()
	if e != nil {
		bugLogIf(GlobalContext, errors.New("Unable to initialize health check client"))
		return nil
	}
	clnt.SetCustomTransport(globalRemoteTargetTransport)
	return clnt
}

## Liveness probe

This probe always responds with '200 OK'. Only fails if 'etcd' is configured and unreachable. When liveness probe fails, Kubernetes like platforms restart the container.

```
livenessProbe:
  httpGet:
    path: /minio/health/live
    port: 9000
    scheme: HTTP
  initialDelaySeconds: 120

| `minio_cluster_health_drives_online_count`         | `gauge` | Count of online drives in the cluster          |        |
| `minio_cluster_health_drives_count`                | `gauge` | Count of all drives in the cluster             |        |
| `minio_cluster_health_nodes_offline_count`         | `gauge` | Count of offline nodes in the cluster          |        |

	op = strings.Replace(op, "(*peerS3Server)", "s3", 1)
	op = strings.Replace(op, "ClusterCheckHandler", "health.Cluster", 1)
	op = strings.Replace(op, "ClusterReadCheckHandler", "health.ClusterRead", 1)
	op = strings.Replace(op, "LivenessCheckHandler", "health.Liveness", 1)
	op = strings.Replace(op, "ReadinessCheckHandler", "health.Readiness", 1)
	op = strings.Replace(op, "-fm", "", 1)
	return op
}

          "expr": "minio_cluster_health_status{job=~\"$scrape_jobs\"}",
          "fullMetaSearch": false,
          "includeNullMetadata": true,
          "interval": "",
          "legendFormat": "Pool: {{pool}} Set: {{set}}",
          "range": true,
          "refId": "A",
          "useBackend": false
        }
      ],
      "title": "Cluster Health Status",
      "type": "stat"
    },
    {

	ReadQuorum    int
	UsingDefaults bool
}

// Health - returns current status of the object layer health,
// provides if write access exists across sets, additionally
// can be used to query scenarios if health may be lost
// if this node is taken down by an external orchestrator.
func (z *erasureServerPools) Health(ctx context.Context, opts HealthOptions) HealthResult {

| `minio_cluster_health_status`                     | Get current cluster health status              |
| `minio_cluster_health_erasure_set_healing_drives` | Count of healing drives in the erasure set     |
| `minio_cluster_health_erasure_set_online_drives`  | Count of online drives in the erasure set      |
| `minio_cluster_health_erasure_set_read_quorum`    | Get read quorum of the erasure set             |