zk解析(4)：Learner
前言
Learner类是Follower和Observer类的父类，要学习Follower和Observer首先要先学习Learner。
Learner
继承关系
1 | public class Learner {} |
成员变量
1 | QuorumPeer self; |
内部类PacketInFlight
PacketInFlight类，这个类是记录Leader发出提议，但是还没有通过过半验证时候记录的数据格式
类名代表”还在处理的包”
Follower读取PROPOSAL消息以及OBSERVER读取INFORM消息时，会生成相关记录1
2
3
4static class PacketInFlight {
TxnHeader hdr;
Record rec;
}
构造器
Learner类未显式声明构造器，即使用默认构造器。
方法
validateSession
向主服务器验证session1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20void validateSession(ServerCnxn cnxn, long clientId, int timeout)
throws IOException {
LOG.info("Revalidating client: 0x" + Long.toHexString(clientId));
ByteArrayOutputStream baos = new ByteArrayOutputStream();
DataOutputStream dos = new DataOutputStream(baos);
dos.writeLong(clientId);
dos.writeInt(timeout);
dos.close();
// 请求包
QuorumPacket qp = new QuorumPacket(Leader.REVALIDATE, -1, baos
.toByteArray(), null);
pendingRevalidations.put(clientId, cnxn);
if (LOG.isTraceEnabled()) {
ZooTrace.logTraceMessage(LOG,
ZooTrace.SESSION_TRACE_MASK,
"To validate session 0x"
+ Long.toHexString(clientId));
}
writePacket(qp, true);
}
revalidate 重新验证
1 | protected void revalidate(QuorumPacket qp) throws IOException { |
ping 发送ping请求
1 | protected void ping(QuorumPacket qp) throws IOException { |
writePacket 写入包
1 | void writePacket(QuorumPacket pp, boolean flush) throws IOException { |
readPacket 读取包
1 | void readPacket(QuorumPacket pp) throws IOException { |
request 发起请求
常见如Follower接受到客户端的写请求后将请求转给Leader1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19void request(Request request) throws IOException {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
DataOutputStream oa = new DataOutputStream(baos);
oa.writeLong(request.sessionId);
oa.writeInt(request.cxid);
oa.writeInt(request.type);
if (request.request != null) {
request.request.rewind();
int len = request.request.remaining();
byte b[] = new byte[len];
request.request.get(b);
request.request.rewind();
oa.write(b);
}
oa.close();
QuorumPacket qp = new QuorumPacket(Leader.REQUEST, -1, baos
.toByteArray(), request.authInfo);
writePacket(qp, true);
}
connectToLeader 连接到主节点
1 | protected void connectToLeader(InetSocketAddress addr, String hostname) |
registerWithLeader 注册到主节点
生成新的zxid需要过半的服务注册到主节点才能生成1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56protected long registerWithLeader(int pktType) throws IOException{
/*
* Send follower info, including last zxid and sid
*/
// 发送当前服务的zxid
long lastLoggedZxid = self.getLastLoggedZxid();
QuorumPacket qp = new QuorumPacket();
qp.setType(pktType);
qp.setZxid(ZxidUtils.makeZxid(self.getAcceptedEpoch(), 0));
/*
* Add sid to payload
*/
// sid服务器id，表示那个服务器
LearnerInfo li = new LearnerInfo(self.getId(), 0x10000);
ByteArrayOutputStream bsid = new ByteArrayOutputStream();
BinaryOutputArchive boa = BinaryOutputArchive.getArchive(bsid);
boa.writeRecord(li, "LearnerInfo");
qp.setData(bsid.toByteArray());
// 发送数据并读取数据
writePacket(qp, true);
readPacket(qp);
// 获取主节点服务器响应的新的zxid
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()) { // newEpoch和当前的一样，发送-1再次确认
// 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());
}
// 响应主节点
QuorumPacket ackNewEpoch = new QuorumPacket(Leader.ACKEPOCH, lastLoggedZxid, epochBytes, null);
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();
}
}
syncWithLeader 同步主节点记录
选主完毕后从节点同步主节点的记录。1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195protected void syncWithLeader(long newLeaderZxid) throws IOException, InterruptedException{
QuorumPacket ack = new QuorumPacket(Leader.ACK, 0, null, null);
QuorumPacket qp = new QuorumPacket();
long newEpoch = ZxidUtils.getEpochFromZxid(newLeaderZxid);
// In the DIFF case we don't need to do a snapshot because the transactions will sync on top of any existing snapshot
// For SNAP and TRUNC the snapshot is needed to save that history
boolean snapshotNeeded = true;
readPacket(qp);
LinkedList<Long> packetsCommitted = new LinkedList<Long>();
LinkedList<PacketInFlight> packetsNotCommitted = new LinkedList<PacketInFlight>();
synchronized (zk) {
if (qp.getType() == Leader.DIFF) { // 单个提案同步
LOG.info("Getting a diff from the leader 0x{}", Long.toHexString(qp.getZxid()));
snapshotNeeded = false;
}
else if (qp.getType() == Leader.SNAP) { // 同步快照
LOG.info("Getting a snapshot from leader 0x" + Long.toHexString(qp.getZxid()));
// The leader is going to dump the database
// clear our own database and read
zk.getZKDatabase().clear();
zk.getZKDatabase().deserializeSnapshot(leaderIs);
String signature = leaderIs.readString("signature");
if (!signature.equals("BenWasHere")) {
LOG.error("Missing signature. Got " + signature);
throw new IOException("Missing signature");
}
zk.getZKDatabase().setlastProcessedZxid(qp.getZxid());
} else if (qp.getType() == Leader.TRUNC) { // 回退到主节点的数据版本
//we need to truncate the log to the lastzxid of the leader
LOG.warn("Truncating log to get in sync with the leader 0x"
+ Long.toHexString(qp.getZxid()));
boolean truncated=zk.getZKDatabase().truncateLog(qp.getZxid());
if (!truncated) {
// not able to truncate the log
LOG.error("Not able to truncate the log "
+ Long.toHexString(qp.getZxid()));
System.exit(13);
}
zk.getZKDatabase().setlastProcessedZxid(qp.getZxid());
}
else {
LOG.error("Got unexpected packet from leader "
+ qp.getType() + " exiting ... " );
System.exit(13);
}
zk.createSessionTracker();
long lastQueued = 0;
// in Zab V1.0 (ZK 3.4+) we might take a snapshot when we get the NEWLEADER message, but in pre V1.0
// we take the snapshot on the UPDATE message, since Zab V1.0 also gets the UPDATE (after the NEWLEADER)
// we need to make sure that we don't take the snapshot twice.
boolean isPreZAB1_0 = true;
//If we are not going to take the snapshot be sure the transactions are not applied in memory
// but written out to the transaction log
boolean writeToTxnLog = !snapshotNeeded;
// we are now going to start getting transactions to apply followed by an UPTODATE
outerLoop:
while (self.isRunning()) {
readPacket(qp);
switch(qp.getType()) {
case Leader.PROPOSAL: // 提案
PacketInFlight pif = new PacketInFlight();
pif.hdr = new TxnHeader();
pif.rec = SerializeUtils.deserializeTxn(qp.getData(), pif.hdr);
if (pif.hdr.getZxid() != lastQueued + 1) {
LOG.warn("Got zxid 0x"
+ Long.toHexString(pif.hdr.getZxid())
+ " expected 0x"
+ Long.toHexString(lastQueued + 1));
}
lastQueued = pif.hdr.getZxid();
packetsNotCommitted.add(pif);
break;
case Leader.COMMIT: // 提交
if (!writeToTxnLog) {
pif = packetsNotCommitted.peekFirst();
if (pif.hdr.getZxid() != qp.getZxid()) {
LOG.warn("Committing " + qp.getZxid() + ", but next proposal is " + pif.hdr.getZxid());
} else {
zk.processTxn(pif.hdr, pif.rec);
packetsNotCommitted.remove();
}
} else {
packetsCommitted.add(qp.getZxid());
}
break;
case Leader.INFORM: //观察者才有这个类型
/*
* Only observer get this type of packet. We treat this
* as receiving PROPOSAL and COMMMIT.
*/
PacketInFlight packet = new PacketInFlight();
packet.hdr = new TxnHeader();
packet.rec = SerializeUtils.deserializeTxn(qp.getData(), packet.hdr);
// Log warning message if txn comes out-of-order
if (packet.hdr.getZxid() != lastQueued + 1) {
LOG.warn("Got zxid 0x"
+ Long.toHexString(packet.hdr.getZxid())
+ " expected 0x"
+ Long.toHexString(lastQueued + 1));
}
lastQueued = packet.hdr.getZxid();
if (!writeToTxnLog) {
// Apply to db directly if we haven't taken the snapshot
zk.processTxn(packet.hdr, packet.rec);
} else {
packetsNotCommitted.add(packet);
packetsCommitted.add(qp.getZxid());
}
break;
case Leader.UPTODATE: // 过半机器完成了leader验证，自己也完成了数据同步,可以跳出循环
if (isPreZAB1_0) {
zk.takeSnapshot();
self.setCurrentEpoch(newEpoch);
}
self.cnxnFactory.setZooKeeperServer(zk);
break outerLoop;
case Leader.NEWLEADER: // Getting NEWLEADER here instead of in discovery
// means this is Zab 1.0
// Create updatingEpoch file and remove it after current
// epoch is set. QuorumPeer.loadDataBase() uses this file to
// detect the case where the server was terminated after
// taking a snapshot but before setting the current epoch.
File updating = new File(self.getTxnFactory().getSnapDir(),
QuorumPeer.UPDATING_EPOCH_FILENAME);
if (!updating.exists() && !updating.createNewFile()) {
throw new IOException("Failed to create " +
updating.toString());
}
if (snapshotNeeded) {
zk.takeSnapshot();
}
self.setCurrentEpoch(newEpoch);
if (!updating.delete()) {
throw new IOException("Failed to delete " +
updating.toString());
}
writeToTxnLog = true; //Anything after this needs to go to the transaction log, not applied directly in memory
isPreZAB1_0 = false;
writePacket(new QuorumPacket(Leader.ACK, newLeaderZxid, null, null), true);
break;
}
}
}
ack.setZxid(ZxidUtils.makeZxid(newEpoch, 0));
// 响应
writePacket(ack, true);
sock.setSoTimeout(self.tickTime * self.syncLimit);
zk.startup();
/*
* Update the election vote here to ensure that all members of the
* ensemble report the same vote to new servers that start up and
* send leader election notifications to the ensemble.
*
* @see https://issues.apache.org/jira/browse/ZOOKEEPER-1732
*/
self.updateElectionVote(newEpoch);
// We need to log the stuff that came in between the snapshot and the uptodate
if (zk instanceof FollowerZooKeeperServer) {
FollowerZooKeeperServer fzk = (FollowerZooKeeperServer)zk;
for(PacketInFlight p: packetsNotCommitted) {
fzk.logRequest(p.hdr, p.rec);
}
for(Long zxid: packetsCommitted) {
fzk.commit(zxid); // commit
}
} else if (zk instanceof ObserverZooKeeperServer) {
// Similar to follower, we need to log requests between the snapshot
// and UPTODATE
ObserverZooKeeperServer ozk = (ObserverZooKeeperServer) zk;
for (PacketInFlight p : packetsNotCommitted) {
Long zxid = packetsCommitted.peekFirst();
if (p.hdr.getZxid() != zxid) {
// log warning message if there is no matching commit
// old leader send outstanding proposal to observer
LOG.warn("Committing " + Long.toHexString(zxid)
+ ", but next proposal is "
+ Long.toHexString(p.hdr.getZxid()));
continue;
}
packetsCommitted.remove();
Request request = new Request(null, p.hdr.getClientId(),
p.hdr.getCxid(), p.hdr.getType(), null, null);
request.txn = p.rec;
request.hdr = p.hdr;
ozk.commitRequest(request);
}
} else {
// New server type need to handle in-flight packets
throw new UnsupportedOperationException("Unknown server type");
}
}