public Vote lookForLeader()

in zookeeper-server/src/main/java/org/apache/zookeeper/server/quorum/FastLeaderElection.java [907:1138]


    public Vote lookForLeader() throws InterruptedException {
        try {
            self.jmxLeaderElectionBean = new LeaderElectionBean();
            MBeanRegistry.getInstance().register(self.jmxLeaderElectionBean, self.jmxLocalPeerBean);
        } catch (Exception e) {
            LOG.warn("Failed to register with JMX", e);
            self.jmxLeaderElectionBean = null;
        }

        self.start_fle = Time.currentElapsedTime();
        try {
            /*
             * The votes from the current leader election are stored in recvset. In other words, a vote v is in recvset
             * if v.electionEpoch == logicalclock. The current participant uses recvset to deduce on whether a majority
             * of participants has voted for it.
             */
            Map<Long, Vote> recvset = new HashMap<>();

            /*
             * The votes from previous leader elections, as well as the votes from the current leader election are
             * stored in outofelection. Note that notifications in a LOOKING state are not stored in outofelection.
             * Only FOLLOWING or LEADING notifications are stored in outofelection. The current participant could use
             * outofelection to learn which participant is the leader if it arrives late (i.e., higher logicalclock than
             * the electionEpoch of the received notifications) in a leader election.
             */
            Map<Long, Vote> outofelection = new HashMap<>();

            int notTimeout = minNotificationInterval;

            synchronized (this) {
                logicalclock.incrementAndGet();
                updateProposal(getInitId(), getInitLastLoggedZxid(), getPeerEpoch());
            }

            LOG.info(
                "New election. My id = {}, proposed zxid=0x{}",
                self.getMyId(),
                Long.toHexString(proposedZxid));
            sendNotifications();

            SyncedLearnerTracker voteSet = null;

            /*
             * Loop in which we exchange notifications until we find a leader
             */

            while ((self.getPeerState() == ServerState.LOOKING) && (!stop)) {
                /*
                 * Remove next notification from queue, times out after 2 times
                 * the termination time
                 */
                Notification n = recvqueue.poll(notTimeout, TimeUnit.MILLISECONDS);

                /*
                 * Sends more notifications if haven't received enough.
                 * Otherwise processes new notification.
                 */
                if (n == null) {
                    if (manager.haveDelivered()) {
                        sendNotifications();
                    } else {
                        manager.connectAll();
                    }

                    /*
                     * Exponential backoff
                     */
                    notTimeout = Math.min(notTimeout << 1, maxNotificationInterval);

                    /*
                     * When a leader failure happens on a master, the backup will be supposed to receive the honour from
                     * Oracle and become a leader, but the honour is likely to be delay. We do a re-check once timeout happens
                     *
                     * The leader election algorithm does not provide the ability of electing a leader from a single instance
                     * which is in a configuration of 2 instances.
                     * */
                    if (self.getQuorumVerifier() instanceof QuorumOracleMaj
                            && self.getQuorumVerifier().revalidateVoteset(voteSet, notTimeout != minNotificationInterval)) {
                        setPeerState(proposedLeader, voteSet);
                        Vote endVote = new Vote(proposedLeader, proposedZxid, logicalclock.get(), proposedEpoch);
                        leaveInstance(endVote);
                        return endVote;
                    }

                    LOG.info("Notification time out: {} ms", notTimeout);

                } else if (validVoter(n.sid) && validVoter(n.leader)) {
                    /*
                     * Only proceed if the vote comes from a replica in the current or next
                     * voting view for a replica in the current or next voting view.
                     */
                    switch (n.state) {
                    case LOOKING:
                        if (getInitLastLoggedZxid() == -1) {
                            LOG.debug("Ignoring notification as our zxid is -1");
                            break;
                        }
                        if (n.zxid == -1) {
                            LOG.debug("Ignoring notification from member with -1 zxid {}", n.sid);
                            break;
                        }
                        // If notification > current, replace and send messages out
                        if (n.electionEpoch > logicalclock.get()) {
                            logicalclock.set(n.electionEpoch);
                            recvset.clear();
                            if (totalOrderPredicate(n.leader, n.zxid, n.peerEpoch, getInitId(), getInitLastLoggedZxid(), getPeerEpoch())) {
                                updateProposal(n.leader, n.zxid, n.peerEpoch);
                            } else {
                                updateProposal(getInitId(), getInitLastLoggedZxid(), getPeerEpoch());
                            }
                            sendNotifications();
                        } else if (n.electionEpoch < logicalclock.get()) {
                                LOG.debug(
                                    "Notification election epoch is smaller than logicalclock. n.electionEpoch = 0x{}, logicalclock=0x{}",
                                    Long.toHexString(n.electionEpoch),
                                    Long.toHexString(logicalclock.get()));
                            break;
                        } else if (totalOrderPredicate(n.leader, n.zxid, n.peerEpoch, proposedLeader, proposedZxid, proposedEpoch)) {
                            updateProposal(n.leader, n.zxid, n.peerEpoch);
                            sendNotifications();
                        }

                        LOG.debug(
                            "Adding vote: from={}, proposed leader={}, proposed zxid=0x{}, proposed election epoch=0x{}",
                            n.sid,
                            n.leader,
                            Long.toHexString(n.zxid),
                            Long.toHexString(n.electionEpoch));

                        // don't care about the version if it's in LOOKING state
                        recvset.put(n.sid, new Vote(n.leader, n.zxid, n.electionEpoch, n.peerEpoch));

                        voteSet = getVoteTracker(recvset, new Vote(proposedLeader, proposedZxid, logicalclock.get(), proposedEpoch));

                        if (voteSet.hasAllQuorums()) {

                            // Verify if there is any change in the proposed leader
                            while ((n = recvqueue.poll(finalizeWait, TimeUnit.MILLISECONDS)) != null) {
                                if (totalOrderPredicate(n.leader, n.zxid, n.peerEpoch, proposedLeader, proposedZxid, proposedEpoch)) {
                                    recvqueue.put(n);
                                    break;
                                }
                            }

                            /*
                             * This predicate is true once we don't read any new
                             * relevant message from the reception queue
                             */
                            if (n == null) {
                                setPeerState(proposedLeader, voteSet);
                                Vote endVote = new Vote(proposedLeader, proposedZxid, logicalclock.get(), proposedEpoch);
                                leaveInstance(endVote);
                                return endVote;
                            }
                        }
                        break;
                    case OBSERVING:
                        LOG.debug("Notification from observer: {}", n.sid);
                        break;

                        /*
                        * In ZOOKEEPER-3922, we separate the behaviors of FOLLOWING and LEADING.
                        * To avoid the duplication of codes, we create a method called followingBehavior which was used to
                        * shared by FOLLOWING and LEADING. This method returns a Vote. When the returned Vote is null, it follows
                        * the original idea to break switch statement; otherwise, a valid returned Vote indicates, a leader
                        * is generated.
                        *
                        * The reason why we need to separate these behaviors is to make the algorithm runnable for 2-node
                        * setting. An extra condition for generating leader is needed. Due to the majority rule, only when
                        * there is a majority in the voteset, a leader will be generated. However, in a configuration of 2 nodes,
                        * the number to achieve the majority remains 2, which means a recovered node cannot generate a leader which is
                        * the existed leader. Therefore, we need the Oracle to kick in this situation. In a two-node configuration, the Oracle
                        * only grants the permission to maintain the progress to one node. The oracle either grants the permission to the
                        * remained node and makes it a new leader when there is a faulty machine, which is the case to maintain the progress.
                        * Otherwise, the oracle does not grant the permission to the remained node, which further causes a service down.
                        *
                        * In the former case, when a failed server recovers and participate in the leader election, it would not locate a
                        * new leader because there does not exist a majority in the voteset. It fails on the containAllQuorum() infinitely due to
                        * two facts. First one is the fact that it does do not have a majority in the voteset. The other fact is the fact that
                        * the oracle would not give the permission since the oracle already gave the permission to the existed leader, the healthy machine.
                        * Logically, when the oracle replies with negative, it implies the existed leader which is LEADING notification comes from is a valid leader.
                        * To threat this negative replies as a permission to generate the leader is the purpose to separate these two behaviors.
                        *
                        *
                        * */
                    case FOLLOWING:
                        /*
                        * To avoid duplicate codes
                        * */
                        Vote resultFN = receivedFollowingNotification(recvset, outofelection, voteSet, n);
                        if (resultFN == null) {
                            break;
                        } else {
                            return resultFN;
                        }
                    case LEADING:
                        /*
                        * In leadingBehavior(), it performs followingBehvior() first. When followingBehavior() returns
                        * a null pointer, ask Oracle whether to follow this leader.
                        * */
                        Vote resultLN = receivedLeadingNotification(recvset, outofelection, voteSet, n);
                        if (resultLN == null) {
                            break;
                        } else {
                            return resultLN;
                        }
                    default:
                        LOG.warn("Notification state unrecognized: {} (n.state), {}(n.sid)", n.state, n.sid);
                        break;
                    }
                } else {
                    if (!validVoter(n.leader)) {
                        LOG.warn("Ignoring notification for non-cluster member sid {} from sid {}", n.leader, n.sid);
                    }
                    if (!validVoter(n.sid)) {
                        LOG.warn("Ignoring notification for sid {} from non-quorum member sid {}", n.leader, n.sid);
                    }
                }
            }
            return null;
        } finally {
            try {
                if (self.jmxLeaderElectionBean != null) {
                    MBeanRegistry.getInstance().unregister(self.jmxLeaderElectionBean);
                }
            } catch (Exception e) {
                LOG.warn("Failed to unregister with JMX", e);
            }
            self.jmxLeaderElectionBean = null;
            LOG.debug("Number of connection processing threads: {}", manager.getConnectionThreadCount());
        }
    }