/** * 开始ping * * @param qp * @throws IOException */ protected void ping(QuorumPacket qp) throws IOException { // Send back the ping with our session data ByteArrayOutputStream bos = new ByteArrayOutputStream(); DataOutputStream dos = new DataOutputStream(bos); HashMap<Long, Integer> touchTable = zk.getTouchSnapshot(); for (Entry<Long, Integer> entry : touchTable.entrySet()) { dos.writeLong(entry.getKey()); dos.writeInt(entry.getValue()); } qp.setData(bos.toByteArray()); writePacket(qp, true); }
/** * Once connected to the leader, perform the handshake protocol to establish a following / * observing connection. * * @param pktType * @return the zxid the Leader sends for synchronization purposes. * @throws IOException */ protected long registerWithLeader(int pktType) throws IOException { /* * Send follower info, including last zxid and sid */ long lastLoggedZxid = self.getLastLoggedZxid(); QuorumPacket qp = new QuorumPacket(); qp.setType(pktType); qp.setZxid(ZxidUtils.makeZxid(self.getAcceptedEpoch(), 0)); /* * Add sid to payload */ LearnerInfo li = new LearnerInfo(self.getId(), 0x10000); ByteArrayOutputStream bsid = new ByteArrayOutputStream(); BinaryOutputArchive boa = BinaryOutputArchive.getArchive(bsid); boa.writeRecord(li, "LearnerInfo"); qp.setData(bsid.toByteArray()); writePacket(qp, true); readPacket(qp); final long newEpoch = ZxidUtils.getEpochFromZxid(qp.getZxid()); if (qp.getType() == Leader.LEADERINFO) { // we are connected to a 1.0 server so accept the new epoch and read // the next packet leaderProtocolVersion = ByteBuffer.wrap(qp.getData()).getInt(); byte epochBytes[] = new byte[4]; final ByteBuffer wrappedEpochBytes = ByteBuffer.wrap(epochBytes); if (newEpoch > self.getAcceptedEpoch()) { wrappedEpochBytes.putInt((int) self.getCurrentEpoch()); self.setAcceptedEpoch(newEpoch); } else if (newEpoch == self.getAcceptedEpoch()) { // since we have already acked an epoch equal to the leaders, we // cannot ack // again, but we still need to send our lastZxid to the leader // so that we can // sync with it if it does assume leadership of the epoch. // the -1 indicates that this reply should not count as an ack // for the new epoch wrappedEpochBytes.putInt(-1); } else { throw new IOException( "Leaders epoch, " + newEpoch + " is less than accepted epoch, " + self.getAcceptedEpoch()); } QuorumPacket ackNewEpoch = new QuorumPacket(Leader.ACKEPOCH, lastLoggedZxid, epochBytes); // 发送ack writePacket(ackNewEpoch, true); return ZxidUtils.makeZxid(newEpoch, 0); } else { if (newEpoch > self.getAcceptedEpoch()) { self.setAcceptedEpoch(newEpoch); } if (qp.getType() != Leader.NEWLEADER) { LOG.error("First packet should have been NEWLEADER"); throw new IOException("First packet should have been NEWLEADER"); } return qp.getZxid(); } }
/** * This thread will receive packets from the peer and process them and also listen to new * connections from new peers. */ @Override public void run() { try { ia = BinaryInputArchive.getArchive(new BufferedInputStream(sock.getInputStream())); bufferedOutput = new BufferedOutputStream(sock.getOutputStream()); oa = BinaryOutputArchive.getArchive(bufferedOutput); QuorumPacket qp = new QuorumPacket(); ia.readRecord(qp, "packet"); if (qp.getType() != Leader.FOLLOWERINFO && qp.getType() != Leader.OBSERVERINFO) { LOG.error("First packet " + qp.toString() + " is not FOLLOWERINFO or OBSERVERINFO!"); return; } if (qp.getData() != null) { ByteBuffer bbsid = ByteBuffer.wrap(qp.getData()); this.sid = bbsid.getLong(); } else { this.sid = leader.followerCounter.getAndDecrement(); } LOG.info("Follower sid: " + this.sid + " : info : " + leader.self.quorumPeers.get(this.sid)); if (qp.getType() == Leader.OBSERVERINFO) { learnerType = LearnerType.OBSERVER; } long peerLastZxid = qp.getZxid(); /* the default to send to the follower */ int packetToSend = Leader.SNAP; long zxidToSend = 0; long leaderLastZxid = 0; /** the packets that the follower needs to get updates from * */ long updates = peerLastZxid; /* we are sending the diff check if we have proposals in memory to be able to * send a diff to the */ ReentrantReadWriteLock lock = leader.zk.getZKDatabase().getLogLock(); ReadLock rl = lock.readLock(); try { rl.lock(); final long maxCommittedLog = leader.zk.getZKDatabase().getmaxCommittedLog(); final long minCommittedLog = leader.zk.getZKDatabase().getminCommittedLog(); LOG.info( "Synchronizing with Follower sid: " + this.sid + " maxCommittedLog =" + Long.toHexString(maxCommittedLog) + " minCommittedLog = " + Long.toHexString(minCommittedLog) + " peerLastZxid = " + Long.toHexString(peerLastZxid)); LinkedList<Proposal> proposals = leader.zk.getZKDatabase().getCommittedLog(); if (proposals.size() != 0) { if ((maxCommittedLog >= peerLastZxid) && (minCommittedLog <= peerLastZxid)) { // as we look through proposals, this variable keeps track of previous // proposal Id. long prevProposalZxid = minCommittedLog; // Keep track of whether we are about to send the first packet. // Before sending the first packet, we have to tell the learner // whether to expect a trunc or a diff boolean firstPacket = true; for (Proposal propose : proposals) { // skip the proposals the peer already has if (propose.packet.getZxid() <= peerLastZxid) { prevProposalZxid = propose.packet.getZxid(); continue; } else { // If we are sending the first packet, figure out whether to trunc // in case the follower has some proposals that the leader doesn't if (firstPacket) { firstPacket = false; // Does the peer have some proposals that the leader hasn't seen yet if (prevProposalZxid < peerLastZxid) { // send a trunc message before sending the diff packetToSend = Leader.TRUNC; LOG.info("Sending TRUNC"); zxidToSend = prevProposalZxid; updates = zxidToSend; } else { // Just send the diff packetToSend = Leader.DIFF; LOG.info("Sending diff"); zxidToSend = maxCommittedLog; } } queuePacket(propose.packet); QuorumPacket qcommit = new QuorumPacket(Leader.COMMIT, propose.packet.getZxid(), null, null); queuePacket(qcommit); } } } else if (peerLastZxid > maxCommittedLog) { packetToSend = Leader.TRUNC; zxidToSend = maxCommittedLog; updates = zxidToSend; } } else { // just let the state transfer happen } leaderLastZxid = leader.startForwarding(this, updates); if (peerLastZxid == leaderLastZxid) { // We are in sync so we'll do an empty diff packetToSend = Leader.DIFF; zxidToSend = leaderLastZxid; } } finally { rl.unlock(); } QuorumPacket newLeaderQP = new QuorumPacket(Leader.NEWLEADER, leaderLastZxid, null, null); oa.writeRecord(newLeaderQP, "packet"); bufferedOutput.flush(); // Need to set the zxidToSend to the latest zxid if (packetToSend == Leader.SNAP) { zxidToSend = leader.zk.getZKDatabase().getDataTreeLastProcessedZxid(); } oa.writeRecord(new QuorumPacket(packetToSend, zxidToSend, null, null), "packet"); bufferedOutput.flush(); /* if we are not truncating or sending a diff just send a snapshot */ if (packetToSend == Leader.SNAP) { LOG.info( "Sending snapshot last zxid of peer is 0x" + Long.toHexString(peerLastZxid) + " " + " zxid of leader is 0x" + Long.toHexString(leaderLastZxid) + "sent zxid of db as 0x" + Long.toHexString(zxidToSend)); // Dump data to peer leader.zk.getZKDatabase().serializeSnapshot(oa); oa.writeString("BenWasHere", "signature"); } bufferedOutput.flush(); // Mutation packets will be queued during the serialize, // so we need to mark when the peer can actually start // using the data // queuedPackets.add(new QuorumPacket(Leader.UPTODATE, -1, null, null)); // Start sending packets new Thread() { public void run() { Thread.currentThread().setName("Sender-" + sock.getRemoteSocketAddress()); try { sendPackets(); } catch (InterruptedException e) { LOG.warn("Unexpected interruption", e); } } }.start(); /* * Have to wait for the first ACK, wait until * the leader is ready, and only then we can * start processing messages. */ qp = new QuorumPacket(); ia.readRecord(qp, "packet"); if (qp.getType() != Leader.ACK) { LOG.error("Next packet was supposed to be an ACK"); return; } leader.processAck(this.sid, qp.getZxid(), sock.getLocalSocketAddress()); /* * Wait until leader starts up */ synchronized (leader.zk) { while (!leader.zk.isRunning()) { leader.zk.wait(500); } } while (true) { qp = new QuorumPacket(); ia.readRecord(qp, "packet"); long traceMask = ZooTrace.SERVER_PACKET_TRACE_MASK; if (qp.getType() == Leader.PING) { traceMask = ZooTrace.SERVER_PING_TRACE_MASK; } if (LOG.isTraceEnabled()) { ZooTrace.logQuorumPacket(LOG, traceMask, 'i', qp); } tickOfLastAck = leader.self.tick; ByteBuffer bb; long sessionId; int cxid; int type; switch (qp.getType()) { case Leader.ACK: if (this.learnerType == LearnerType.OBSERVER) { if (LOG.isDebugEnabled()) { LOG.debug("Received ACK from Observer " + this.sid); } } leader.processAck(this.sid, qp.getZxid(), sock.getLocalSocketAddress()); break; case Leader.PING: // Process the touches ByteArrayInputStream bis = new ByteArrayInputStream(qp.getData()); DataInputStream dis = new DataInputStream(bis); while (dis.available() > 0) { long sess = dis.readLong(); int to = dis.readInt(); leader.zk.touch(sess, to); } break; case Leader.REVALIDATE: bis = new ByteArrayInputStream(qp.getData()); dis = new DataInputStream(bis); long id = dis.readLong(); int to = dis.readInt(); ByteArrayOutputStream bos = new ByteArrayOutputStream(); DataOutputStream dos = new DataOutputStream(bos); dos.writeLong(id); boolean valid = leader.zk.touch(id, to); if (valid) { try { // set the session owner // as the follower that // owns the session leader.zk.setOwner(id, this); } catch (SessionExpiredException e) { LOG.error( "Somehow session " + Long.toHexString(id) + " expired right after being renewed! (impossible)", e); } } if (LOG.isTraceEnabled()) { ZooTrace.logTraceMessage( LOG, ZooTrace.SESSION_TRACE_MASK, "Session 0x" + Long.toHexString(id) + " is valid: " + valid); } dos.writeBoolean(valid); qp.setData(bos.toByteArray()); queuedPackets.add(qp); break; case Leader.REQUEST: bb = ByteBuffer.wrap(qp.getData()); sessionId = bb.getLong(); cxid = bb.getInt(); type = bb.getInt(); bb = bb.slice(); Request si; if (type == OpCode.sync) { si = new LearnerSyncRequest(this, sessionId, cxid, type, bb, qp.getAuthinfo()); } else { si = new Request(null, sessionId, cxid, type, bb, qp.getAuthinfo()); } si.setOwner(this); leader.zk.submitRequest(si); break; default: } } } catch (IOException e) { if (sock != null && !sock.isClosed()) { LOG.error("Unexpected exception causing shutdown while sock " + "still open", e); // close the socket to make sure the // other side can see it being close try { sock.close(); } catch (IOException ie) { // do nothing } } } catch (InterruptedException e) { LOG.error("Unexpected exception causing shutdown", e); } finally { LOG.warn( "******* GOODBYE " + (sock != null ? sock.getRemoteSocketAddress() : "<null>") + " ********"); // Send the packet of death try { queuedPackets.put(proposalOfDeath); } catch (InterruptedException e) { LOG.warn("Ignoring unexpected exception", e); } shutdown(); } }