001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.lang3.concurrent;
018
019import java.util.EnumMap;
020import java.util.Map;
021import java.util.concurrent.TimeUnit;
022import java.util.concurrent.atomic.AtomicReference;
023
024/**
025 * <p>
026 * A simple implementation of the <a
027 * href="http://martinfowler.com/bliki/CircuitBreaker.html">Circuit Breaker</a> pattern
028 * that counts specific events.
029 * </p>
030 * <p>
031 * A <em>circuit breaker</em> can be used to protect an application against unreliable
032 * services or unexpected load. A newly created {@code EventCountCircuitBreaker} object is
033 * initially in state <em>closed</em> meaning that no problem has been detected. When the
034 * application encounters specific events (like errors or service timeouts), it tells the
035 * circuit breaker to increment an internal counter. If the number of events reported in a
036 * specific time interval exceeds a configurable threshold, the circuit breaker changes
037 * into state <em>open</em>. This means that there is a problem with the associated sub
038 * system; the application should no longer call it, but give it some time to settle down.
039 * The circuit breaker can be configured to switch back to <em>closed</em> state after a
040 * certain time frame if the number of events received goes below a threshold.
041 * </p>
042 * <p>
043 * When a {@code EventCountCircuitBreaker} object is constructed the following parameters
044 * can be provided:
045 * </p>
046 * <ul>
047 * <li>A threshold for the number of events that causes a state transition to
048 * <em>open</em> state. If more events are received in the configured check interval, the
049 * circuit breaker switches to <em>open</em> state.</li>
050 * <li>The interval for checks whether the circuit breaker should open. So it is possible
051 * to specify something like "The circuit breaker should open if more than 10 errors are
052 * encountered in a minute."</li>
053 * <li>The same parameters can be specified for automatically closing the circuit breaker
054 * again, as in "If the number of requests goes down to 100 per minute, the circuit
055 * breaker should close itself again". Depending on the use case, it may make sense to use
056 * a slightly lower threshold for closing the circuit breaker than for opening it to avoid
057 * continuously flipping when the number of events received is close to the threshold.</li>
058 * </ul>
059 * <p>
060 * This class supports the following typical use cases:
061 * </p>
062 * <p>
063 * <strong>Protecting against load peaks</strong>
064 * </p>
065 * <p>
066 * Imagine you have a server which can handle a certain number of requests per minute.
067 * Suddenly, the number of requests increases significantly - maybe because a connected
068 * partner system is going mad or due to a denial of service attack. A
069 * {@code EventCountCircuitBreaker} can be configured to stop the application from
070 * processing requests when a sudden peak load is detected and to start request processing
071 * again when things calm down. The following code fragment shows a typical example of
072 * such a scenario. Here the {@code EventCountCircuitBreaker} allows up to 1000 requests
073 * per minute before it interferes. When the load goes down again to 800 requests per
074 * second it switches back to state <em>closed</em>:
075 * </p>
076 *
077 * <pre>
078 * EventCountCircuitBreaker breaker = new EventCountCircuitBreaker(1000, 1, TimeUnit.MINUTE, 800);
079 * ...
080 * public void handleRequest(Request request) {
081 *     if (breaker.incrementAndCheckState()) {
082 *         // actually handle this request
083 *     } else {
084 *         // do something else, e.g. send an error code
085 *     }
086 * }
087 * </pre>
088 * <p>
089 * <strong>Deal with an unreliable service</strong>
090 * </p>
091 * <p>
092 * In this scenario, an application uses an external service which may fail from time to
093 * time. If there are too many errors, the service is considered down and should not be
094 * called for a while. This can be achieved using the following pattern - in this concrete
095 * example we accept up to 5 errors in 2 minutes; if this limit is reached, the service is
096 * given a rest time of 10 minutes:
097 * </p>
098 *
099 * <pre>
100 * EventCountCircuitBreaker breaker = new EventCountCircuitBreaker(5, 2, TimeUnit.MINUTE, 5, 10, TimeUnit.MINUTE);
101 * ...
102 * public void handleRequest(Request request) {
103 *     if (breaker.checkState()) {
104 *         try {
105 *             service.doSomething();
106 *         } catch (ServiceException ex) {
107 *             breaker.incrementAndCheckState();
108 *         }
109 *     } else {
110 *         // return an error code, use an alternative service, etc.
111 *     }
112 * }
113 * </pre>
114 * <p>
115 * In addition to automatic state transitions, the state of a circuit breaker can be
116 * changed manually using the methods {@link #open()} and {@link #close()}. It is also
117 * possible to register {@code PropertyChangeListener} objects that get notified whenever
118 * a state transition occurs. This is useful, for instance to directly react on a freshly
119 * detected error condition.
120 * </p>
121 * <p>
122 * <em>Implementation notes:</em>
123 * </p>
124 * <ul>
125 * <li>This implementation uses non-blocking algorithms to update the internal counter and
126 * state. This should be pretty efficient if there is not too much contention.</li>
127 * <li>This implementation is not intended to operate as a high-precision timer in very
128 * short check intervals. It is deliberately kept simple to avoid complex and
129 * time-consuming state checks. It should work well in time intervals from a few seconds
130 * up to minutes and longer. If the intervals become too short, there might be race
131 * conditions causing spurious state transitions.</li>
132 * <li>The handling of check intervals is a bit simplistic. Therefore, there is no
133 * guarantee that the circuit breaker is triggered at a specific point in time; there may
134 * be some delay (less than a check interval).</li>
135 * </ul>
136 * @since 3.5
137 */
138public class EventCountCircuitBreaker extends AbstractCircuitBreaker<Integer> {
139
140    /** A map for accessing the strategy objects for the different states. */
141    private static final Map<State, StateStrategy> STRATEGY_MAP = createStrategyMap();
142
143    /** Stores information about the current check interval. */
144    private final AtomicReference<CheckIntervalData> checkIntervalData;
145
146    /** The threshold for opening the circuit breaker. */
147    private final int openingThreshold;
148
149    /** The time interval for opening the circuit breaker. */
150    private final long openingInterval;
151
152    /** The threshold for closing the circuit breaker. */
153    private final int closingThreshold;
154
155    /** The time interval for closing the circuit breaker. */
156    private final long closingInterval;
157
158    /**
159     * Creates a new instance of {@code EventCountCircuitBreaker} and initializes all properties for
160     * opening and closing it based on threshold values for events occurring in specific
161     * intervals.
162     *
163     * @param openingThreshold the threshold for opening the circuit breaker; if this
164     * number of events is received in the time span determined by the opening interval,
165     * the circuit breaker is opened
166     * @param openingInterval the interval for opening the circuit breaker
167     * @param openingUnit the {@code TimeUnit} defining the opening interval
168     * @param closingThreshold the threshold for closing the circuit breaker; if the
169     * number of events received in the time span determined by the closing interval goes
170     * below this threshold, the circuit breaker is closed again
171     * @param closingInterval the interval for closing the circuit breaker
172     * @param closingUnit the {@code TimeUnit} defining the closing interval
173     */
174    public EventCountCircuitBreaker(final int openingThreshold, final long openingInterval,
175                                    final TimeUnit openingUnit, final int closingThreshold, final long closingInterval,
176                                    final TimeUnit closingUnit) {
177        super();
178        checkIntervalData = new AtomicReference<>(new CheckIntervalData(0, 0));
179        this.openingThreshold = openingThreshold;
180        this.openingInterval = openingUnit.toNanos(openingInterval);
181        this.closingThreshold = closingThreshold;
182        this.closingInterval = closingUnit.toNanos(closingInterval);
183    }
184
185    /**
186     * Creates a new instance of {@code EventCountCircuitBreaker} with the same interval for opening
187     * and closing checks.
188     *
189     * @param openingThreshold the threshold for opening the circuit breaker; if this
190     * number of events is received in the time span determined by the check interval, the
191     * circuit breaker is opened
192     * @param checkInterval the check interval for opening or closing the circuit breaker
193     * @param checkUnit the {@code TimeUnit} defining the check interval
194     * @param closingThreshold the threshold for closing the circuit breaker; if the
195     * number of events received in the time span determined by the check interval goes
196     * below this threshold, the circuit breaker is closed again
197     */
198    public EventCountCircuitBreaker(final int openingThreshold, final long checkInterval, final TimeUnit checkUnit,
199                                    final int closingThreshold) {
200        this(openingThreshold, checkInterval, checkUnit, closingThreshold, checkInterval,
201                checkUnit);
202    }
203
204    /**
205     * Creates a new instance of {@code EventCountCircuitBreaker} which uses the same parameters for
206     * opening and closing checks.
207     *
208     * @param threshold the threshold for changing the status of the circuit breaker; if
209     * the number of events received in a check interval is greater than this value, the
210     * circuit breaker is opened; if it is lower than this value, it is closed again
211     * @param checkInterval the check interval for opening or closing the circuit breaker
212     * @param checkUnit the {@code TimeUnit} defining the check interval
213     */
214    public EventCountCircuitBreaker(final int threshold, final long checkInterval, final TimeUnit checkUnit) {
215        this(threshold, checkInterval, checkUnit, threshold);
216    }
217
218    /**
219     * Returns the threshold value for opening the circuit breaker. If this number of
220     * events is received in the time span determined by the opening interval, the circuit
221     * breaker is opened.
222     *
223     * @return the opening threshold
224     */
225    public int getOpeningThreshold() {
226        return openingThreshold;
227    }
228
229    /**
230     * Returns the interval (in nanoseconds) for checking for the opening threshold.
231     *
232     * @return the opening check interval
233     */
234    public long getOpeningInterval() {
235        return openingInterval;
236    }
237
238    /**
239     * Returns the threshold value for closing the circuit breaker. If the number of
240     * events received in the time span determined by the closing interval goes below this
241     * threshold, the circuit breaker is closed again.
242     *
243     * @return the closing threshold
244     */
245    public int getClosingThreshold() {
246        return closingThreshold;
247    }
248
249    /**
250     * Returns the interval (in nanoseconds) for checking for the closing threshold.
251     *
252     * @return the opening check interval
253     */
254    public long getClosingInterval() {
255        return closingInterval;
256    }
257
258    /**
259     * {@inheritDoc} This implementation checks the internal event counter against the
260     * threshold values and the check intervals. This may cause a state change of this
261     * circuit breaker.
262     */
263    @Override
264    public boolean checkState() {
265        return performStateCheck(0);
266    }
267
268    /**
269     * {@inheritDoc}
270     */
271    @Override
272    public boolean incrementAndCheckState(final Integer increment) {
273        return performStateCheck(increment);
274    }
275
276    /**
277     * Increments the monitored value by <strong>1</strong> and performs a check of the current state of this
278     * circuit breaker. This method works like {@link #checkState()}, but the monitored
279     * value is incremented before the state check is performed.
280     *
281     * @return <strong>true</strong> if the circuit breaker is now closed;
282     * <strong>false</strong> otherwise
283     */
284    public boolean incrementAndCheckState() {
285        return incrementAndCheckState(1);
286    }
287
288    /**
289     * {@inheritDoc} This circuit breaker may close itself again if the number of events
290     * received during a check interval goes below the closing threshold. If this circuit
291     * breaker is already open, this method has no effect, except that a new check
292     * interval is started.
293     */
294    @Override
295    public void open() {
296        super.open();
297        checkIntervalData.set(new CheckIntervalData(0, now()));
298    }
299
300    /**
301     * {@inheritDoc} A new check interval is started. If too many events are received in
302     * this interval, the circuit breaker changes again to state open. If this circuit
303     * breaker is already closed, this method has no effect, except that a new check
304     * interval is started.
305     */
306    @Override
307    public void close() {
308        super.close();
309        checkIntervalData.set(new CheckIntervalData(0, now()));
310    }
311
312    /**
313     * Actually checks the state of this circuit breaker and executes a state transition
314     * if necessary.
315     *
316     * @param increment the increment for the internal counter
317     * @return a flag whether the circuit breaker is now closed
318     */
319    private boolean performStateCheck(final int increment) {
320        CheckIntervalData currentData;
321        CheckIntervalData nextData;
322        State currentState;
323
324        do {
325            final long time = now();
326            currentState = state.get();
327            currentData = checkIntervalData.get();
328            nextData = nextCheckIntervalData(increment, currentData, currentState, time);
329        } while (!updateCheckIntervalData(currentData, nextData));
330
331        // This might cause a race condition if other changes happen in between!
332        // Refer to the header comment!
333        if (stateStrategy(currentState).isStateTransition(this, currentData, nextData)) {
334            currentState = currentState.oppositeState();
335            changeStateAndStartNewCheckInterval(currentState);
336        }
337        return !isOpen(currentState);
338    }
339
340    /**
341     * Updates the {@code CheckIntervalData} object. The current data object is replaced
342     * by the one modified by the last check. The return value indicates whether this was
343     * successful. If it is <strong>false</strong>, another thread interfered, and the
344     * whole operation has to be redone.
345     *
346     * @param currentData the current check data object
347     * @param nextData the replacing check data object
348     * @return a flag whether the update was successful
349     */
350    private boolean updateCheckIntervalData(final CheckIntervalData currentData,
351            final CheckIntervalData nextData) {
352        return currentData == nextData
353                || checkIntervalData.compareAndSet(currentData, nextData);
354    }
355
356    /**
357     * Changes the state of this circuit breaker and also initializes a new
358     * {@code CheckIntervalData} object.
359     *
360     * @param newState the new state to be set
361     */
362    private void changeStateAndStartNewCheckInterval(final State newState) {
363        changeState(newState);
364        checkIntervalData.set(new CheckIntervalData(0, now()));
365    }
366
367    /**
368     * Calculates the next {@code CheckIntervalData} object based on the current data and
369     * the current state. The next data object takes the counter increment and the current
370     * time into account.
371     *
372     * @param increment the increment for the internal counter
373     * @param currentData the current check data object
374     * @param currentState the current state of the circuit breaker
375     * @param time the current time
376     * @return the updated {@code CheckIntervalData} object
377     */
378    private CheckIntervalData nextCheckIntervalData(final int increment,
379            final CheckIntervalData currentData, final State currentState, final long time) {
380        CheckIntervalData nextData;
381        if (stateStrategy(currentState).isCheckIntervalFinished(this, currentData, time)) {
382            nextData = new CheckIntervalData(increment, time);
383        } else {
384            nextData = currentData.increment(increment);
385        }
386        return nextData;
387    }
388
389    /**
390     * Returns the current time in nanoseconds. This method is used to obtain the current
391     * time. This is needed to calculate the check intervals correctly.
392     *
393     * @return the current time in nanoseconds
394     */
395    long now() {
396        return System.nanoTime();
397    }
398
399    /**
400     * Returns the {@code StateStrategy} object responsible for the given state.
401     *
402     * @param state the state
403     * @return the corresponding {@code StateStrategy}
404     * @throws CircuitBreakingException if the strategy cannot be resolved
405     */
406    private static StateStrategy stateStrategy(final State state) {
407        return STRATEGY_MAP.get(state);
408    }
409
410    /**
411     * Creates the map with strategy objects. It allows access for a strategy for a given
412     * state.
413     *
414     * @return the strategy map
415     */
416    private static Map<State, StateStrategy> createStrategyMap() {
417        final Map<State, StateStrategy> map = new EnumMap<>(State.class);
418        map.put(State.CLOSED, new StateStrategyClosed());
419        map.put(State.OPEN, new StateStrategyOpen());
420        return map;
421    }
422
423    /**
424     * An internally used data class holding information about the checks performed by
425     * this class. Basically, the number of received events and the start time of the
426     * current check interval are stored.
427     */
428    private static class CheckIntervalData {
429        /** The counter for events. */
430        private final int eventCount;
431
432        /** The start time of the current check interval. */
433        private final long checkIntervalStart;
434
435        /**
436         * Creates a new instance of {@code CheckIntervalData}.
437         *
438         * @param count the current count value
439         * @param intervalStart the start time of the check interval
440         */
441        CheckIntervalData(final int count, final long intervalStart) {
442            eventCount = count;
443            checkIntervalStart = intervalStart;
444        }
445
446        /**
447         * Returns the event counter.
448         *
449         * @return the number of received events
450         */
451        public int getEventCount() {
452            return eventCount;
453        }
454
455        /**
456         * Returns the start time of the current check interval.
457         *
458         * @return the check interval start time
459         */
460        public long getCheckIntervalStart() {
461            return checkIntervalStart;
462        }
463
464        /**
465         * Returns a new instance of {@code CheckIntervalData} with the event counter
466         * incremented by the given delta. If the delta is 0, this object is returned.
467         *
468         * @param delta the delta
469         * @return the updated instance
470         */
471        public CheckIntervalData increment(final int delta) {
472            return (delta == 0) ? this : new CheckIntervalData(getEventCount() + delta,
473                    getCheckIntervalStart());
474        }
475    }
476
477    /**
478     * Internally used class for executing check logic based on the current state of the
479     * circuit breaker. Having this logic extracted into special classes avoids complex
480     * if-then-else cascades.
481     */
482    private abstract static class StateStrategy {
483        /**
484         * Returns a flag whether the end of the current check interval is reached.
485         *
486         * @param breaker the {@code CircuitBreaker}
487         * @param currentData the current state object
488         * @param now the current time
489         * @return a flag whether the end of the current check interval is reached
490         */
491        public boolean isCheckIntervalFinished(final EventCountCircuitBreaker breaker,
492                final CheckIntervalData currentData, final long now) {
493            return now - currentData.getCheckIntervalStart() > fetchCheckInterval(breaker);
494        }
495
496        /**
497         * Checks whether the specified {@code CheckIntervalData} objects indicate that a
498         * state transition should occur. Here the logic which checks for thresholds
499         * depending on the current state is implemented.
500         *
501         * @param breaker the {@code CircuitBreaker}
502         * @param currentData the current {@code CheckIntervalData} object
503         * @param nextData the updated {@code CheckIntervalData} object
504         * @return a flag whether a state transition should be performed
505         */
506        public abstract boolean isStateTransition(EventCountCircuitBreaker breaker,
507                CheckIntervalData currentData, CheckIntervalData nextData);
508
509        /**
510         * Obtains the check interval to applied for the represented state from the given
511         * {@code CircuitBreaker}.
512         *
513         * @param breaker the {@code CircuitBreaker}
514         * @return the check interval to be applied
515         */
516        protected abstract long fetchCheckInterval(EventCountCircuitBreaker breaker);
517    }
518
519    /**
520     * A specialized {@code StateStrategy} implementation for the state closed.
521     */
522    private static class StateStrategyClosed extends StateStrategy {
523
524        /**
525         * {@inheritDoc}
526         */
527        @Override
528        public boolean isStateTransition(final EventCountCircuitBreaker breaker,
529                final CheckIntervalData currentData, final CheckIntervalData nextData) {
530            return nextData.getEventCount() > breaker.getOpeningThreshold();
531        }
532
533        /**
534         * {@inheritDoc}
535         */
536        @Override
537        protected long fetchCheckInterval(final EventCountCircuitBreaker breaker) {
538            return breaker.getOpeningInterval();
539        }
540    }
541
542    /**
543     * A specialized {@code StateStrategy} implementation for the state open.
544     */
545    private static class StateStrategyOpen extends StateStrategy {
546        /**
547         * {@inheritDoc}
548         */
549        @Override
550        public boolean isStateTransition(final EventCountCircuitBreaker breaker,
551                final CheckIntervalData currentData, final CheckIntervalData nextData) {
552            return nextData.getCheckIntervalStart() != currentData
553                    .getCheckIntervalStart()
554                    && currentData.getEventCount() < breaker.getClosingThreshold();
555        }
556
557        /**
558         * {@inheritDoc}
559         */
560        @Override
561        protected long fetchCheckInterval(final EventCountCircuitBreaker breaker) {
562            return breaker.getClosingInterval();
563        }
564    }
565
566}