* underlying model is a continuous function mapping storedPermits (from 0.0 to maxStoredPermits)
   * onto the 1/rate (i.e. intervals) that is effective at the given storedPermits. "storedPermits"
   * essentially measure unused time; we spend unused time buying/storing permits. Rate is
   * "permits / time", thus "1 / rate = time / permits". Thus, "1/rate" (time / permits) times

   * we change the rate.
   */
  public void testWeNeverGetABurstMoreThanOneSec() {
    RateLimiter limiter = RateLimiter.create(1.0, stopwatch);
    int[] rates = {1000, 1, 10, 1000000, 10, 1};
    for (int rate : rates) {
      int oneSecWorthOfWork = rate;
      stopwatch.sleepMillis(rate * 1000);
      limiter.setRate(rate);

 * <p>Rate limiters are often used to restrict the rate at which some physical or logical resource
 * is accessed. This is in contrast to {@link java.util.concurrent.Semaphore} which restricts the
 * number of concurrent accesses instead of the rate (note though that concurrency and rate are
 * closely related, e.g. see <a href="http://en.wikipedia.org/wiki/Little%27s_law">Little's
 * Law</a>).
 *

error rate, and request latency at p50, p90, and p99 percentiles. The
query results are printed to the console, organized by workload name.

All metrics returned are from server-side reports. This means that latencies
and error rates are from the perspective of the service itself and not of an
individual client (or aggregate set of clients). Rates and latencies are
calculated over a time interval of 1 minute.

   * we change the rate.
   */
  public void testWeNeverGetABurstMoreThanOneSec() {
    RateLimiter limiter = RateLimiter.create(1.0, stopwatch);
    int[] rates = {1000, 1, 10, 1000000, 10, 1};
    for (int rate : rates) {
      int oneSecWorthOfWork = rate;
      stopwatch.sleepMillis(rate * 1000);
      limiter.setRate(rate);

  int maximumSize;

  @Param("5000")
  int distinctKeys;

  @Param("4")
  int segments;

  // 1 means uniform likelihood of keys; higher means some keys are more popular
  // tweak this to control hit rate
  @Param("2.5")
  double concentration;

  Random random = new Random();

  LoadingCache<Integer, Integer> cache;

  int max;

  static AtomicLong requests = new AtomicLong(0);

          "expr": "sum by (bucket) (rate(minio_bucket_traffic_sent_bytes{job=\"$scrape_jobs\"}[$__rate_interval]))",
          "interval": "1m",
          "intervalFactor": 2,
          "legendFormat": "Data Sent [{{bucket}}]",
          "refId": "A"
        }
      ],
      "thresholds": [],
      "timeRegions": [],
      "title": "Total Data Sent Rate",
      "tooltip": {
        "shared": true,

package bandwidth

//go:generate msgp -file=$GOFILE -unexported

import (
	"context"
	"sync"
	"time"

	"golang.org/x/time/rate"
)

//msgp:ignore bucketThrottle Monitor

type bucketThrottle struct {
	*rate.Limiter
	NodeBandwidthPerSec int64
}

// Monitor holds the state of the global bucket monitor
type Monitor struct {
	tlock sync.RWMutex // mutex for bucket throttling

                "name": "default.httpbin-rate-limiting",
                "typedConfig": {
                    "@type": "type.googleapis.com/envoy.extensions.filters.http.wasm.v3.Wasm",
                    "config": {
                        "name": "default.httpbin-rate-limiting",
                        "vmConfig": {
                            "runtime": "envoy.wasm.runtime.v8",

          },
          "exemplar": true,
          "expr": "sum by (bucket) (rate(minio_bucket_traffic_sent_bytes{job=\"$scrape_jobs\"}[$__rate_interval]))",
          "interval": "1m",
          "intervalFactor": 2,
          "legendFormat": "Data Sent [{{bucket}}]",
          "refId": "A"
        }
      ],
      "title": "Total Data Sent Rate",
      "type": "timeseries"
    },
    {
      "datasource": {