* calling thread wait for that time.
   *
   * The simplest way to maintain a rate of QPS is to keep the timestamp of the last granted
   * request, and ensure that (1/QPS) seconds have elapsed since then. For example, for a rate of
   * QPS=5 (5 tokens per second), if we ensure that a request isn't granted earlier than 200ms after

        for (double qps : qpsToTest) {
          // If warmupPermits = maxPermits - thresholdPermits then
          // warmupPeriod = (1 + coldFactor) * warmupPermits * stableInterval / 2
          long warmupMillis = (long) ((1 + coldFactor) * warmupPermits / (2.0 * qps) * 1000.0);
          RateLimiter rateLimiter =
              RateLimiter.create(qps, warmupMillis, MILLISECONDS, coldFactor, stopwatch);

        for (double qps : qpsToTest) {
          // If warmupPermits = maxPermits - thresholdPermits then
          // warmupPeriod = (1 + coldFactor) * warmupPermits * stableInterval / 2
          long warmupMillis = (long) ((1 + coldFactor) * warmupPermits / (2.0 * qps) * 1000.0);
          RateLimiter rateLimiter =
              RateLimiter.create(qps, warmupMillis, MILLISECONDS, coldFactor, stopwatch);

  // +optional
  optional string apiVersion = 3;
}

// ExternalMetricSource indicates how to scale on a metric not associated with
// any Kubernetes object (for example length of queue in cloud
// messaging service, or QPS from loadbalancer running outside of cluster).
message ExternalMetricSource {
  // metric identifies the target metric by name and selector
  optional MetricIdentifier metric = 1;

  // +optional
  optional string apiVersion = 3;
}

// ExternalMetricSource indicates how to scale on a metric not associated with
// any Kubernetes object (for example length of queue in cloud
// messaging service, or QPS from loadbalancer running outside of cluster).
message ExternalMetricSource {
  // metricName is the name of the metric in question.
  optional string metricName = 1;

@GwtIncompatible
@ElementTypesAreNonnullByDefault
public abstract class RateLimiter {
  /**
   * Creates a {@code RateLimiter} with the specified stable throughput, given as "permits per
   * second" (commonly referred to as <i>QPS</i>, queries per second).
   *
   * <p>The returned {@code RateLimiter} ensures that on average no more than {@code
   * permitsPerSecond} are issued during any given second, with sustained requests being smoothly

  // +optional
  optional string apiVersion = 3;
}

// ExternalMetricSource indicates how to scale on a metric not associated with
// any Kubernetes object (for example length of queue in cloud
// messaging service, or QPS from loadbalancer running outside of cluster).
message ExternalMetricSource {
  // metric identifies the target metric by name and selector
  optional MetricIdentifier metric = 1;

  // +optional
  optional string apiVersion = 3;
}

// ExternalMetricSource indicates how to scale on a metric not associated with
// any Kubernetes object (for example length of queue in cloud
// messaging service, or QPS from loadbalancer running outside of cluster).
// Exactly one "target" type should be set.
message ExternalMetricSource {
  // metricName is the name of the metric in question.
  optional string metricName = 1;

@GwtIncompatible
@ElementTypesAreNonnullByDefault
public abstract class RateLimiter {
  /**
   * Creates a {@code RateLimiter} with the specified stable throughput, given as "permits per
   * second" (commonly referred to as <i>QPS</i>, queries per second).
   *
   * <p>The returned {@code RateLimiter} ensures that on average no more than {@code
   * permitsPerSecond} are issued during any given second, with sustained requests being smoothly

            "defaults": {
               "custom": {
                  "fillOpacity": 10,
                  "gradientMode": "hue",
                  "showPoints": "never"
               },
               "unit": "qps"
            }
         },
         "gridPos": {
            "h": 8,
            "w": 8,
            "x": 16,
            "y": 10
         },
         "id": 8,
         "interval": "5s",