}

  private void assertBad(String spec) {
    try {
      HostSpecifier.fromValid(spec);
      fail("Should have thrown IllegalArgumentException: " + spec);
    } catch (IllegalArgumentException expected) {
    }

    try {
      HostSpecifier.from(spec);
      fail("Should have thrown ParseException: " + spec);
    } catch (ParseException expected) {

  // value represents the integer value of this priority class. This is the actual priority that pods
  // receive when they have the name of this class in their pod spec.
  optional int32 value = 2;

  // globalDefault specifies whether this PriorityClass should be considered as
  // the default priority for pods that do not have any priority class.
  // Only one PriorityClass can be marked as `globalDefault`. However, if more than

   * 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

// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program.  If not, see <http://www.gnu.org/licenses/>.

package cmd

import (
	"net/http"

	"github.com/minio/minio/internal/grid"

 * permits being adjusted to ensure that the configured rate is maintained.
 *
 * <p>It is possible to configure a {@code RateLimiter} to have a warmup period during which time
 * the permits issued each second steadily increases until it hits the stable rate.
 *
 * <p>As an example, imagine that we have a list of tasks to execute, but we don't want to submit
 * more than 2 per second:
 *
 * <pre>{@code

    taskRunner.lock.withLock {
      check(currentTask == TestThreadSerialTask)
      nanoTime = newTime
      yieldUntil(ResumePriority.AfterOtherTasks)
    }
  }

  /** Confirm all tasks have completed. Used by the test thread only. */
  fun assertNoMoreTasks() {
    taskRunner.assertThreadDoesntHoldLock()

    taskRunner.lock.withLock {
      assertThat(activeThreads).isEqualTo(0)
    }
  }

            (workerRunningState == IDLE || workerRunningState == QUEUING)
                && queue.removeLastOccurrence(submittedTask);
        // If the delegate is directExecutor(), the submitted runnable could have thrown a REE. But
        // that's handled by the log check that catches RuntimeExceptions in the queue worker.
        if (!(t instanceof RejectedExecutionException) || removed) {
          throw t;
        }
      }

 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 * 
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

            (workerRunningState == IDLE || workerRunningState == QUEUING)
                && queue.removeLastOccurrence(submittedTask);
        // If the delegate is directExecutor(), the submitted runnable could have thrown a REE. But
        // that's handled by the log check that catches RuntimeExceptions in the queue worker.
        if (!(t instanceof RejectedExecutionException) || removed) {
          throw t;
        }
      }

## Use Case

Let's start with an example **use case** and then see how to solve it with this.

Let's imagine that you have some **machine learning models** that you want to use to handle requests. 🤖

The same models are shared among requests, so, it's not one model per request, or one per user or something similar.