前言
前几天和腾讯的大佬一起吃饭聊天，说起我对SOFAJRaft的理解，我自然以为我是很懂了的，但是大佬问起了我那SOFAJRaft集群之间的日志是怎么复制的？
我当时哑口无言，说不出是怎么实现的，所以这次来分析一下SOFAJRaft中日志复制是怎么做的。
Leader发送探针获取Follower的LastLogIndex
Leader 节点在通过 Replicator 和 Follower 建立连接之后，要发送一个 Probe 类型的探针请求，目的是知道 Follower 已经拥有的的日志位置，以便于向 Follower 发送后续的日志。
大致的流程如下：
NodeImpl#becomeLeader->replicatorGroup#addReplicator->Replicator#start->Replicator#sendEmptyEntries最后会通过调用Replicator的sendEmptyEntries方法来发送探针来获取Follower的LastLogIndex
Replicator#sendEmptyEntries
private void sendEmptyEntries(final boolean isHeartbeat,
final RpcResponseClosure heartBeatClosure) {
final AppendEntriesRequest.Builder rb = AppendEntriesRequest.newBuilder();
//将集群配置设置到rb中，例如Term，GroupId，ServerId等
if (!fillCommonFields(rb, this.nextIndex - 1, isHeartbeat)) {
// id is unlock in installSnapshot
installSnapshot();
if (isHeartbeat && heartBeatClosure != null) {
Utils.runClosureInThread(heartBeatClosure, new Status(RaftError.EAGAIN,
"Fail to send heartbeat to peer %s", this.options.getPeerId()));
}
return;
}
try {
final long monotonicSendTimeMs = Utils.monotonicMs();
final AppendEntriesRequest request = rb.build();
if (isHeartbeat) {
....//省略心跳代码
} else {
//statInfo这个类没看到哪里有用到，
// Sending a probe request.
//leader发送探针获取Follower的LastLogIndex
this.statInfo.runningState = RunningState.APPENDING_ENTRIES;
//将lastLogIndex设置为比firstLogIndex小1
this.statInfo.firstLogIndex = this.nextIndex;
this.statInfo.lastLogIndex = this.nextIndex - 1;
this.appendEntriesCounter++;
//设置当前Replicator为发送探针
this.state = State.Probe;
final int stateVersion = this.version;
//返回reqSeq，并将reqSeq加一
final int seq = getAndIncrementReqSeq();
final Future rpcFuture = this.rpcService.appendEntries(this.options.getPeerId().getEndpoint(),
request, -1, new RpcResponseClosureAdapter() {
@Override
public void run(final Status status) {
onRpcReturned(Replicator.this.id, RequestType.AppendEntries, status, request,
getResponse(), seq, stateVersion, monotonicSendTimeMs);
}
});
//Inflight 是对批量发送出去的 logEntry 的一种抽象，他表示哪些 logEntry 已经被封装成日志复制 request 发送出去了
//这里是将logEntry封装到Inflight中
addInflight(RequestType.AppendEntries, this.nextIndex, 0, 0, seq, rpcFuture);
}
LOG.debug("Node {} send HeartbeatRequest to {} term {} lastCommittedIndex {}", this.options.getNode()
.getNodeId(), this.options.getPeerId(), this.options.getTerm(), request.getCommittedIndex());
} finally {
this.id.unlock();
}
} 在调用sendEmptyEntries方法的时候，会传入isHeartbeat为false和heartBeatClosure为null，因为我们这个方法主要是发送探针获取Follower的位移。
首先调用fillCommonFields方法，将任期，groupId，ServerId，PeerIdLogIndex等设置到rb中，如：
private boolean fillCommonFields(final AppendEntriesRequest.Builder rb, long prevLogIndex, final boolean isHeartbeat) {
final long prevLogTerm = this.options.getLogManager().getTerm(prevLogIndex);
....
rb.setTerm(this.options.getTerm());
rb.setGroupId(this.options.getGroupId());
rb.setServerId(this.options.getServerId().toString());
rb.setPeerId(this.options.getPeerId().toString());
rb.setPrevLogIndex(prevLogIndex);
rb.setPrevLogTerm(prevLogTerm);
rb.setCommittedIndex(this.options.getBallotBox().getLastCommittedIndex());
return true;
}注意prevLogIndex是nextIndex-1，表示当前的index
继续往下走，会设置statInfo实例里面的属性，但是statInfo这个对象我没看到哪里有用到过。
然后向该Follower发送一个AppendEntriesRequest请求，onRpcReturned负责响应请求。
发送完请求后调用addInflight初始化一个Inflight实例，加入到inflights集合中，如下：
private void addInflight(final RequestType reqType, final long startIndex, final int count, final int size,
final int seq, final Future rpcInfly) {
this.rpcInFly = new Inflight(reqType, startIndex, count, size, seq, rpcInfly);
this.inflights.add(this.rpcInFly);
this.nodeMetrics.recordSize("replicate-inflights-count", this.inflights.size());
} Inflight 是对批量发送出去的 logEntry 的一种抽象，他表示哪些 logEntry 已经被封装成日志复制 request 发送出去了，这里是将logEntry封装到Inflight中。
Leader批量的发送日志给Follower
Replicator#sendEntries
private boolean sendEntries(final long nextSendingIndex) {
final AppendEntriesRequest.Builder rb = AppendEntriesRequest.newBuilder();
//填写当前Replicator的配置信息到rb中
if (!fillCommonFields(rb, nextSendingIndex - 1, false)) {
// unlock id in installSnapshot
installSnapshot();
return false;
}
ByteBufferCollector dataBuf = null;
//获取最大的size为1024
final int maxEntriesSize = this.raftOptions.getMaxEntriesSize();
//这里使用了类似对象池的技术，避免重复创建对象
final RecyclableByteBufferList byteBufList = RecyclableByteBufferList.newInstance();
try {
//循环遍历出所有的logEntry封装到byteBufList和emb中
for (int i = 0; i < maxEntriesSize; i++) {
final RaftOutter.EntryMeta.Builder emb = RaftOutter.EntryMeta.newBuilder();
//nextSendingIndex代表下一个要发送的index，i代表偏移量
if (!prepareEntry(nextSendingIndex, i, emb, byteBufList)) {
break;
}
rb.addEntries(emb.build());
}
//如果EntriesCount为0的话，说明LogManager里暂时没有新数据
if (rb.getEntriesCount() == 0) {
if (nextSendingIndex < this.options.getLogManager().getFirstLogIndex()) {
installSnapshot();
return false;
}
// _id is unlock in _wait_more
waitMoreEntries(nextSendingIndex);
return false;
}
//将byteBufList里面的数据放入到rb中
if (byteBufList.getCapacity() > 0) {
dataBuf = ByteBufferCollector.allocateByRecyclers(byteBufList.getCapacity());
for (final ByteBuffer b : byteBufList) {
dataBuf.put(b);
}
final ByteBuffer buf = dataBuf.getBuffer();
buf.flip();
rb.setData(ZeroByteStringHelper.wrap(buf));
}
} finally {
//回收一下byteBufList
RecycleUtil.recycle(byteBufList);
}
final AppendEntriesRequest request = rb.build();
if (LOG.isDebugEnabled()) {
LOG.debug(
"Node {} send AppendEntriesRequest to {} term {} lastCommittedIndex {} prevLogIndex {} prevLogTerm {} logIndex {} count {}",
this.options.getNode().getNodeId(), this.options.getPeerId(), this.options.getTerm(),
request.getCommittedIndex(), request.getPrevLogIndex(), request.getPrevLogTerm(), nextSendingIndex,
request.getEntriesCount());
}
//statInfo没找到哪里有用到过
this.statInfo.runningState = RunningState.APPENDING_ENTRIES;
this.statInfo.firstLogIndex = rb.getPrevLogIndex() + 1;
this.statInfo.lastLogIndex = rb.getPrevLogIndex() + rb.getEntriesCount();
final Recyclable recyclable = dataBuf;
final int v = this.version;
final long monotonicSendTimeMs = Utils.monotonicMs();
final int seq = getAndIncrementReqSeq();
final Future rpcFuture = this.rpcService.appendEntries(this.options.getPeerId().getEndpoint(),
request, -1, new RpcResponseClosureAdapter() {
@Override
public void run(final Status status) {
//回收资源
RecycleUtil.recycle(recyclable);
onRpcReturned(Replicator.this.id, RequestType.AppendEntries, status, request, getResponse(), seq,
v, monotonicSendTimeMs);
}
});
//添加Inflight
addInflight(RequestType.AppendEntries, nextSendingIndex, request.getEntriesCount(), request.getData().size(),
seq, rpcFuture);
return true;
} - 首先会调用fillCommonFields方法，填写当前Replicator的配置信息到rb中；
- 调用prepareEntry，根据当前的I和nextSendingIndex计算出当前的偏移量，然后去LogManager找到对应的LogEntry，再把LogEntry里面的属性设置到emb中，并把LogEntry里面的数据加入到RecyclableByteBufferList中；
- 如果LogEntry里面没有新的数据，那么EntriesCount会为0，那么就返回；
- 遍历byteBufList里面的数据，将数据添加到rb中，这样rb里面的数据就是前面是任期、类型、数据长度等信息，rb后面就是真正的数据；
- 新建AppendEntriesRequest实例发送请求；
- 添加 Inflight 到队列中。Leader 维护一个 queue，每发出一批 logEntry 就向 queue 中 添加一个代表这一批 logEntry 的 Inflight，这样当它知道某一批 logEntry 复制失败之后，就可以依赖 queue 中的 Inflight 把该批次 logEntry 以及后续的所有日志重新复制给 follower。既保证日志复制能够完成，又保证了复制日志的顺序不变
其中RecyclableByteBufferList采用对象池进行实例化，对象池的相关信息可以看我这篇：7. SOFAJRaft源码分析—如何实现一个轻量级的对象池？
下面我们详解一下sendEntries里面的具体方法。
prepareEntry填充emb属性
Replicator#prepareEntry
boolean prepareEntry(final long nextSendingIndex, final int offset, final RaftOutter.EntryMeta.Builder emb,
final RecyclableByteBufferList dateBuffer) {
if (dateBuffer.getCapacity() >= this.raftOptions.getMaxBodySize()) {
return false;
}
//设置当前要发送的index
final long logIndex = nextSendingIndex + offset;
//如果这个index已经在LogManager中找不到了，那么直接返回
final LogEntry entry = this.options.getLogManager().getEntry(logIndex);
if (entry == null) {
return false;
}
//下面就是把LogEntry里面的属性设置到emb中
emb.setTerm(entry.getId().getTerm());
if (entry.hasChecksum()) {
emb.setChecksum(entry.getChecksum()); //since 1.2.6
}
emb.setType(entry.getType());
if (entry.getPeers() != null) {
Requires.requireTrue(!entry.getPeers().isEmpty(), "Empty peers at logIndex=%d", logIndex);
for (final PeerId peer : entry.getPeers()) {
emb.addPeers(peer.toString());
}
if (entry.getOldPeers() != null) {
for (final PeerId peer : entry.getOldPeers()) {
emb.addOldPeers(peer.toString());
}
}
} else {
Requires.requireTrue(entry.getType() != EnumOutter.EntryType.ENTRY_TYPE_CONFIGURATION,
"Empty peers but is ENTRY_TYPE_CONFIGURATION type at logIndex=%d", logIndex);
}
final int remaining = entry.getData() != null ? entry.getData().remaining() : 0;
emb.setDataLen(remaining);
//把LogEntry里面的数据放入到dateBuffer中
if (entry.getData() != null) {
// should slice entry data
dateBuffer.add(entry.getData().slice());
}
return true;
}- 对比一下传入的dateBuffer的容量是否已经超过了系统设置的容量（512 * 1024），如果超过了则返回false
- 根据给定的起始的index和偏移量offset计算logIndex，然后去LogManager里面根据index获取LogEntry，如果返回的为则说明找不到了，那么就直接返回false，外层的if判断会执行break跳出循环
- 然后将LogEntry里面的属性设置到emb对象中，最后将LogEntry里面的数据添加到dateBuffer，这里要做到数据和属性分离
Follower处理Leader发送的日志复制请求
在leader发送完AppendEntriesRequest请求之后，请求的数据会在Follower中被AppendEntriesRequestProcessor所处理
具体的处理方法是processRequest0
public Message processRequest0(final RaftServerService service, final AppendEntriesRequest request,
final RpcRequestClosure done) {
final Node node = (Node) service;
//默认使用pipeline
if (node.getRaftOptions().isReplicatorPipeline()) {
final String groupId = request.getGroupId();
final String peerId = request.getPeerId();
//获取请求的次数，以groupId+peerId为一个维度
final int reqSequence = getAndIncrementSequence(groupId, peerId, done.getBizContext().getConnection());
//Follower处理leader发过来的日志请求
final Message response = service.handleAppendEntriesRequest(request, new SequenceRpcRequestClosure(done,
reqSequence, groupId, peerId));
//正常的数据只返回null，异常的数据会返回response
if (response != null) {
sendSequenceResponse(groupId, peerId, reqSequence, done.getAsyncContext(), done.getBizContext(),
response);
}
return null;
} else {
return service.handleAppendEntriesRequest(request, done);
}
}调用service的handleAppendEntriesRequest会调用到NodeIml的handleAppendEntriesRequest方法中，handleAppendEntriesRequest方法只是异常情况和leader没有发送数据时才会返回，正常情况是返回null
处理响应日志复制请求
NodeIml#handleAppendEntriesRequest
public Message handleAppendEntriesRequest(final AppendEntriesRequest request, final RpcRequestClosure done) {
boolean doUnlock = true;
final long startMs = Utils.monotonicMs();
this.writeLock.lock();
//获取entryLog个数
final int entriesCount = request.getEntriesCount();
try {
//校验当前节点是否活跃
if (!this.state.isActive()) {
LOG.warn("Node {} is not in active state, currTerm={}.", getNodeId(), this.currTerm);
return RpcResponseFactory.newResponse(RaftError.EINVAL, "Node %s is not in active state, state %s.",
getNodeId(), this.state.name());
}
//校验传入的serverId是否能被正常解析
final PeerId serverId = new PeerId();
if (!serverId.parse(request.getServerId())) {
LOG.warn("Node {} received AppendEntriesRequest from {} serverId bad format.", getNodeId(),
request.getServerId());
return RpcResponseFactory.newResponse(RaftError.EINVAL, "Parse serverId failed: %s.",
request.getServerId());
}
//校验任期
// Check stale term
if (request.getTerm() < this.currTerm) {
LOG.warn("Node {} ignore stale AppendEntriesRequest from {}, term={}, currTerm={}.", getNodeId(),
request.getServerId(), request.getTerm(), this.currTerm);
return AppendEntriesResponse.newBuilder() //
.setSuccess(false) //
.setTerm(this.currTerm) //
.build();
}
// Check term and state to step down
//当前节点如果不是Follower节点的话要执行StepDown操作
checkStepDown(request.getTerm(), serverId);
//这说明请求的节点不是当前节点的leader
if (!serverId.equals(this.leaderId)) {
LOG.error("Another peer {} declares that it is the leader at term {} which was occupied by leader {}.",
serverId, this.currTerm, this.leaderId);
// Increase the term by 1 and make both leaders step down to minimize the
// loss of split brain
stepDown(request.getTerm() + 1, false, new Status(RaftError.ELEADERCONFLICT,
"More than one leader in the same term."));
return AppendEntriesResponse.newBuilder() //
.setSuccess(false) //
.setTerm(request.getTerm() + 1) //
.build();
}
updateLastLeaderTimestamp(Utils.monotonicMs());
//校验是否正在生成快照
if (entriesCount > 0 && this.snapshotExecutor != null && this.snapshotExecutor.isInstallingSnapshot()) {
LOG.warn("Node {} received AppendEntriesRequest while installing snapshot.", getNodeId());
return RpcResponseFactory.newResponse(RaftError.EBUSY, "Node %s:%s is installing snapshot.",
this.groupId, this.serverId);
}
//传入的是发起请求节点的nextIndex-1
final long prevLogIndex = request.getPrevLogIndex();
final long prevLogTerm = request.getPrevLogTerm();
final long localPrevLogTerm = this.logManager.getTerm(prevLogIndex);
//发起请求的节点prevLogIndex对应的任期和当前节点的index所对应的任期不匹配
if (localPrevLogTerm != prevLogTerm) {
final long lastLogIndex = this.logManager.getLastLogIndex();
LOG.warn(
"Node {} reject term_unmatched AppendEntriesRequest from {}, term={}, prevLogIndex={}, prevLogTerm={}, localPrevLogTerm={}, lastLogIndex={}, entriesSize={}.",
getNodeId(), request.getServerId(), request.getTerm(), prevLogIndex, prevLogTerm, localPrevLogTerm,
lastLogIndex, entriesCount);
return AppendEntriesResponse.newBuilder() //
.setSuccess(false) //
.setTerm(this.currTerm) //
.setLastLogIndex(lastLogIndex) //
.build();
}
//响应心跳或者发送的是sendEmptyEntry
if (entriesCount == 0) {
// heartbeat
final AppendEntriesResponse.Builder respBuilder = AppendEntriesResponse.newBuilder() //
.setSuccess(true) //
.setTerm(this.currTerm)
// 返回当前节点的最新的index
.setLastLogIndex(this.logManager.getLastLogIndex());
doUnlock = false;
this.writeLock.unlock();
// see the comments at FollowerStableClosure#run()
this.ballotBox.setLastCommittedIndex(Math.min(request.getCommittedIndex(), prevLogIndex));
return respBuilder.build();
}
// Parse request
long index = prevLogIndex;
final List entries = new ArrayList<>(entriesCount);
ByteBuffer allData = null;
if (request.hasData()) {
allData = request.getData().asReadOnlyByteBuffer();
}
//获取所有数据
final List entriesList = request.getEntriesList();
for (int i = 0; i < entriesCount; i++) {
final RaftOutter.EntryMeta entry = entriesList.get(i);
index++;
if (entry.getType() != EnumOutter.EntryType.ENTRY_TYPE_UNKNOWN) {
//给logEntry属性设值
final LogEntry logEntry = new LogEntry();
logEntry.setId(new LogId(index, entry.getTerm()));
logEntry.setType(entry.getType());
if (entry.hasChecksum()) {
logEntry.setChecksum(entry.getChecksum()); // since 1.2.6
}
//将数据填充到logEntry
final long dataLen = entry.getDataLen();
if (dataLen > 0) {
final byte[] bs = new byte[(int) dataLen];
assert allData != null;
allData.get(bs, 0, bs.length);
logEntry.setData(ByteBuffer.wrap(bs));
}
if (entry.getPeersCount() > 0) {
//只有配置类型的entry才有多个Peer
if (entry.getType() != EnumOutter.EntryType.ENTRY_TYPE_CONFIGURATION) {
throw new IllegalStateException(
"Invalid log entry that contains peers but is not ENTRY_TYPE_CONFIGURATION type: "
+ entry.getType());
}
final List peers = new ArrayList<>(entry.getPeersCount());
for (final String peerStr : entry.getPeersList()) {
final PeerId peer = new PeerId();
peer.parse(peerStr);
peers.add(peer);
}
logEntry.setPeers(peers);
if (entry.getOldPeersCount() > 0) {
final List oldPeers = new ArrayList<>(entry.getOldPeersCount());
for (final String peerStr : entry.getOldPeersList()) {
final PeerId peer = new PeerId();
peer.parse(peerStr);
oldPeers.add(peer);
}
logEntry.setOldPeers(oldPeers);
}
} else if (entry.getType() == EnumOutter.EntryType.ENTRY_TYPE_CONFIGURATION) {
throw new IllegalStateException(
"Invalid log entry that contains zero peers but is ENTRY_TYPE_CONFIGURATION type");
}
// Validate checksum
if (this.raftOptions.isEnableLogEntryChecksum() && logEntry.isCorrupted()) {
long realChecksum = logEntry.checksum();
LOG.error(
"Corrupted log entry received from leader, index={}, term={}, expectedChecksum={}, " +
"realChecksum={}",
logEntry.getId().getIndex(), logEntry.getId().getTerm(), logEntry.getChecksum(),
realChecksum);
return RpcResponseFactory.newResponse(RaftError.EINVAL,
"The log entry is corrupted, index=%d, term=%d, expectedChecksum=%d, realChecksum=%d",
logEntry.getId().getIndex(), logEntry.getId().getTerm(), logEntry.getChecksum(),
realChecksum);
}
entries.add(logEntry);
}
}
//存储日志，并回调返回response
final FollowerStableClosure closure = new FollowerStableClosure(request, AppendEntriesResponse.newBuilder()
.setTerm(this.currTerm), this, done, this.currTerm);
this.logManager.appendEntries(entries, closure);
// update configuration after _log_manager updated its memory status
this.conf = this.logManager.checkAndSetConfiguration(this.conf);
return null;
} finally {
if (doUnlock) {
this.writeLock.unlock();
}
this.metrics.recordLatency("handle-append-entries", Utils.monotonicMs() - startMs);
this.metrics.recordSize("handle-append-entries-count", entriesCount);
}
} handleAppendEntriesRequest方法写的很长，但是实际上做了很多校验的事情，具体的处理逻辑不多
- 校验当前的Node节点是否还处于活跃状态，如果不是的话，那么直接返回一个error的response
- 校验请求的serverId的格式是否正确，不正确则返回一个error的response
- 校验请求的任期是否小于当前的任期，如果是那么返回一个AppendEntriesResponse类型的response
- 调用checkStepDown方法检测当前节点的任期，以及状态，是否有leader等
- 如果请求的serverId和当前节点的leaderId是不是同一个，用来校验是不是leader发起的请求，如果不是返回一个AppendEntriesResponse
- 校验是否正在生成快照
- 获取请求的Index在当前节点中对应的LogEntry的任期是不是和请求传入的任期相同，不同的话则返回AppendEntriesResponse
- 如果传入的entriesCount为零，那么leader发送的可能是心跳或者发送的是sendEmptyEntry，返回AppendEntriesResponse，并将当前任期和最新index封装返回
- 请求的数据不为空，那么遍历所有的数据
- 实例化一个logEntry，并且将数据和属性设置到logEntry实例中，最后将logEntry放入到entries集合中
- 调用logManager将数据批量提交日志写入 RocksDB
发送响应给leader
最终发送给leader的响应是通过AppendEntriesRequestProcessor的sendSequenceResponse来发送的
void sendSequenceResponse(final String groupId, final String peerId, final int seq,
final AsyncContext asyncContext, final BizContext bizContext, final Message msg) {
final Connection connection = bizContext.getConnection();
//获取context，维度是groupId和peerId
final PeerRequestContext ctx = getPeerRequestContext(groupId, peerId, connection);
final PriorityQueue respQueue = ctx.responseQueue;
assert (respQueue != null);
synchronized (Utils.withLockObject(respQueue)) {
//将要响应的数据放入到优先队列中
respQueue.add(new SequenceMessage(asyncContext, msg, seq));
//校验队列里面的数据是否超过了256
if (!ctx.hasTooManyPendingResponses()) {
while (!respQueue.isEmpty()) {
final SequenceMessage queuedPipelinedResponse = respQueue.peek();
//如果序列对应不上，那么就不发送响应
if (queuedPipelinedResponse.sequence != getNextRequiredSequence(groupId, peerId, connection)) {
// sequence mismatch, waiting for next response.
break;
}
respQueue.remove();
try {
//发送响应
queuedPipelinedResponse.sendResponse();
} finally {
//序列加一
getAndIncrementNextRequiredSequence(groupId, peerId, connection);
}
}
} else {
LOG.warn("Closed connection to peer {}/{}, because of too many pending responses, queued={}, max={}",
ctx.groupId, peerId, respQueue.size(), ctx.maxPendingResponses);
connection.close();
// Close the connection if there are too many pending responses in queue.
removePeerRequestContext(groupId, peerId);
}
}
} 这个方法会将要发送的数据依次压入到PriorityQueue优先队列中进行排序，然后获取序列号最小的元素和nextRequiredSequence比较，如果不相等，那么则是出现了乱序的情况，那么就不发送请求
Leader处理日志复制的Response
Leader收到Follower发过来的Response响应之后会调用Replicator的onRpcReturned方法
static void onRpcReturned(final ThreadId id, final RequestType reqType, final Status status, final Message request,
final Message response, final int seq, final int stateVersion, final long rpcSendTime) {
if (id == null) {
return;
}
final long startTimeMs = Utils.nowMs();
Replicator r;
if ((r = (Replicator) id.lock()) == null) {
return;
}
//检查版本号，因为每次resetInflights都会让version加一，所以检查一下
if (stateVersion != r.version) {
LOG.debug(
"Replicator {} ignored old version response {}, current version is {}, request is {}\n, and response is {}\n, status is {}.",
r, stateVersion, r.version, request, response, status);
id.unlock();
return;
}
//使用优先队列按seq排序,最小的会在第一个
final PriorityQueue holdingQueue = r.pendingResponses;
//这里用一个优先队列是因为响应是异步的，seq小的可能响应比seq大慢
holdingQueue.add(new RpcResponse(reqType, seq, status, request, response, rpcSendTime));
//默认holdingQueue队列里面的数量不能超过256
if (holdingQueue.size() > r.raftOptions.getMaxReplicatorInflightMsgs()) {
LOG.warn("Too many pending responses {} for replicator {}, maxReplicatorInflightMsgs={}",
holdingQueue.size(), r.options.getPeerId(), r.raftOptions.getMaxReplicatorInflightMsgs());
//重新发送探针
//清空数据
r.resetInflights();
r.state = State.Probe;
r.sendEmptyEntries(false);
return;
}
boolean continueSendEntries = false;
final boolean isLogDebugEnabled = LOG.isDebugEnabled();
StringBuilder sb = null;
if (isLogDebugEnabled) {
sb = new StringBuilder("Replicator ").append(r).append(" is processing RPC responses,");
}
try {
int processed = 0;
while (!holdingQueue.isEmpty()) {
//取出holdingQueue里seq最小的数据
final RpcResponse queuedPipelinedResponse = holdingQueue.peek();
//如果Follower没有响应的话就会出现次序对不上的情况，那么就不往下走了
//sequence mismatch, waiting for next response.
if (queuedPipelinedResponse.seq != r.requiredNextSeq) {
// 如果之前存在处理，则到此直接break循环
if (processed > 0) {
if (isLogDebugEnabled) {
sb.append("has processed ").append(processed).append(" responses,");
}
break;
} else {
//Do not processed any responses, UNLOCK id and return.
continueSendEntries = false;
id.unlock();
return;
}
}
//走到这里说明seq对的上，那么就移除优先队列里面seq最小的数据
holdingQueue.remove();
processed++;
//获取inflights队列里的第一个元素
final Inflight inflight = r.pollInflight();
//发起一个请求的时候会将inflight放入到队列中
//如果为空，那么就忽略
if (inflight == null) {
// The previous in-flight requests were cleared.
if (isLogDebugEnabled) {
sb.append("ignore response because request not found:").append(queuedPipelinedResponse)
.append(",\n");
}
continue;
}
//seq没有对上，说明顺序乱了，重置状态
if (inflight.seq != queuedPipelinedResponse.seq) {
// reset state
LOG.warn(
"Replicator {} response sequence out of order, expect {}, but it is {}, reset state to try again.",
r, inflight.seq, queuedPipelinedResponse.seq);
r.resetInflights();
r.state = State.Probe;
continueSendEntries = false;
// 锁住节点，根据错误类别等待一段时间
r.block(Utils.nowMs(), RaftError.EREQUEST.getNumber());
return;
}
try {
switch (queuedPipelinedResponse.requestType) {
case AppendEntries:
//处理日志复制的response
continueSendEntries = onAppendEntriesReturned(id, inflight, queuedPipelinedResponse.status,
(AppendEntriesRequest) queuedPipelinedResponse.request,
(AppendEntriesResponse) queuedPipelinedResponse.response, rpcSendTime, startTimeMs, r);
break;
case Snapshot:
//处理快照的response
continueSendEntries = onInstallSnapshotReturned(id, r, queuedPipelinedResponse.status,
(InstallSnapshotRequest) queuedPipelinedResponse.request,
(InstallSnapshotResponse) queuedPipelinedResponse.response);
break;
}
} finally {
if (continueSendEntries) {
// Success, increase the response sequence.
r.getAndIncrementRequiredNextSeq();
} else {
// The id is already unlocked in onAppendEntriesReturned/onInstallSnapshotReturned, we SHOULD break out.
break;
}
}
}
} finally {
if (isLogDebugEnabled) {
sb.append(", after processed, continue to send entries: ").append(continueSendEntries);
LOG.debug(sb.toString());
}
if (continueSendEntries) {
// unlock in sendEntries.
r.sendEntries();
}
}
} - 检查版本号，因为每次resetInflights都会让version加一，所以检查一下是不是同一批的数据
- 获取Replicator的pendingResponses队列，然后将当前响应的数据封装成RpcResponse实例加入到队列中
- 校验队列里面的元素是否大于256，大于256则清空数据重新同步
- 校验holdingQueue队列里面的seq最小的序列数据序列和当前的requiredNextSeq是否相同，不同的话如果是刚进入循环那么直接break退出循环
- 获取inflights队列中第一个元素，如果seq没有对上，说明顺序乱了，重置状态
- 调用onAppendEntriesReturned方法处理日志复制的response
- 如果处理成功，那么则调用sendEntries继续发送复制日志到Follower
Replicator#onAppendEntriesReturned
private static boolean onAppendEntriesReturned(final ThreadId id, final Inflight inflight, final Status status,
final AppendEntriesRequest request,
final AppendEntriesResponse response, final long rpcSendTime,
final long startTimeMs, final Replicator r) {
//校验数据序列有没有错
if (inflight.startIndex != request.getPrevLogIndex() + 1) {
LOG.warn(
"Replicator {} received invalid AppendEntriesResponse, in-flight startIndex={}, request prevLogIndex={}, reset the replicator state and probe again.",
r, inflight.startIndex, request.getPrevLogIndex());
r.resetInflights();
r.state = State.Probe;
// unlock id in sendEmptyEntries
r.sendEmptyEntries(false);
return false;
}
//度量
// record metrics
if (request.getEntriesCount() > 0) {
r.nodeMetrics.recordLatency("replicate-entries", Utils.monotonicMs() - rpcSendTime);
r.nodeMetrics.recordSize("replicate-entries-count", request.getEntriesCount());
r.nodeMetrics.recordSize("replicate-entries-bytes", request.getData() != null ? request.getData().size()
: 0);
}
final boolean isLogDebugEnabled = LOG.isDebugEnabled();
StringBuilder sb = null;
if (isLogDebugEnabled) {
sb = new StringBuilder("Node "). //
append(r.options.getGroupId()).append(":").append(r.options.getServerId()). //
append(" received AppendEntriesResponse from "). //
append(r.options.getPeerId()). //
append(" prevLogIndex=").append(request.getPrevLogIndex()). //
append(" prevLogTerm=").append(request.getPrevLogTerm()). //
append(" count=").append(request.getEntriesCount());
}
//如果follower因为崩溃，RPC调用失败等原因没有收到成功响应
//那么需要阻塞一段时间再进行调用
if (!status.isOk()) {
// If the follower crashes, any RPC to the follower fails immediately,
// so we need to block the follower for a while instead of looping until
// it comes back or be removed
// dummy_id is unlock in block
if (isLogDebugEnabled) {
sb.append(" fail, sleep.");
LOG.debug(sb.toString());
}
//如果注册了Replicator状态监听器，那么通知所有监听器
notifyReplicatorStatusListener(r, ReplicatorEvent.ERROR, status);
if (++r.consecutiveErrorTimes % 10 == 0) {
LOG.warn("Fail to issue RPC to {}, consecutiveErrorTimes={}, error={}", r.options.getPeerId(),
r.consecutiveErrorTimes, status);
}
r.resetInflights();
r.state = State.Probe;
// unlock in in block
r.block(startTimeMs, status.getCode());
return false;
}
r.consecutiveErrorTimes = 0;
//响应失败
if (!response.getSuccess()) {
// Leader 的切换，表明可能出现过一次网络分区，从新跟随新的 Leader
if (response.getTerm() > r.options.getTerm()) {
if (isLogDebugEnabled) {
sb.append(" fail, greater term ").append(response.getTerm()).append(" expect term ")
.append(r.options.getTerm());
LOG.debug(sb.toString());
}
// 获取当前本节点的表示对象——NodeImpl
final NodeImpl node = r.options.getNode();
r.notifyOnCaughtUp(RaftError.EPERM.getNumber(), true);
r.destroy();
// 调整自己的 term 任期值
node.increaseTermTo(response.getTerm(), new Status(RaftError.EHIGHERTERMRESPONSE,
"Leader receives higher term heartbeat_response from peer:%s", r.options.getPeerId()));
return false;
}
if (isLogDebugEnabled) {
sb.append(" fail, find nextIndex remote lastLogIndex ").append(response.getLastLogIndex())
.append(" local nextIndex ").append(r.nextIndex);
LOG.debug(sb.toString());
}
if (rpcSendTime > r.lastRpcSendTimestamp) {
r.lastRpcSendTimestamp = rpcSendTime;
}
// Fail, reset the state to try again from nextIndex.
r.resetInflights();
//如果Follower最新的index小于下次要发送的index，那么设置为Follower响应的index
// prev_log_index and prev_log_term doesn't match
if (response.getLastLogIndex() + 1 < r.nextIndex) {
LOG.debug("LastLogIndex at peer={} is {}", r.options.getPeerId(), response.getLastLogIndex());
// The peer contains less logs than leader
r.nextIndex = response.getLastLogIndex() + 1;
} else {
// The peer contains logs from old term which should be truncated,
// decrease _last_log_at_peer by one to test the right index to keep
if (r.nextIndex > 1) {
LOG.debug("logIndex={} dismatch", r.nextIndex);
r.nextIndex--;
} else {
LOG.error("Peer={} declares that log at index=0 doesn't match, which is not supposed to happen",
r.options.getPeerId());
}
}
//响应失败需要重新获取Follower的日志信息，用来重新同步
// dummy_id is unlock in _send_heartbeat
r.sendEmptyEntries(false);
return false;
}
if (isLogDebugEnabled) {
sb.append(", success");
LOG.debug(sb.toString());
}
// success
//响应成功检查任期
if (response.getTerm() != r.options.getTerm()) {
r.resetInflights();
r.state = State.Probe;
LOG.error("Fail, response term {} dismatch, expect term {}", response.getTerm(), r.options.getTerm());
id.unlock();
return false;
}
if (rpcSendTime > r.lastRpcSendTimestamp) {
r.lastRpcSendTimestamp = rpcSendTime;
}
// 本次提交的日志数量
final int entriesSize = request.getEntriesCount();
if (entriesSize > 0) {
// 节点确认提交
r.options.getBallotBox().commitAt(r.nextIndex, r.nextIndex + entriesSize - 1, r.options.getPeerId());
if (LOG.isDebugEnabled()) {
LOG.debug("Replicated logs in [{}, {}] to peer {}", r.nextIndex, r.nextIndex + entriesSize - 1,
r.options.getPeerId());
}
} else {
// The request is probe request, change the state into Replicate.
r.state = State.Replicate;
}
r.nextIndex += entriesSize;
r.hasSucceeded = true;
r.notifyOnCaughtUp(RaftError.SUCCESS.getNumber(), false);
// dummy_id is unlock in _send_entries
if (r.timeoutNowIndex > 0 && r.timeoutNowIndex < r.nextIndex) {
r.sendTimeoutNow(false, false);
}
return true;
}onAppendEntriesReturned方法也非常的长，但是我们要有点耐心往下看
- 校验数据序列有没有错
- 进行度量和拼接日志操作
- 判断一下返回的状态如果不是正常的，那么就通知监听器，进行重置操作并阻塞一定时间后再发送
- 如果返回Success状态为false，那么校验一下任期，因为Leader 的切换，表明可能出现过一次网络分区，需要重新跟随新的 Leader；如果任期没有问题那么就进行重置操作,并根据Follower返回的最新的index来重新设值nextIndex
- 如果各种校验都没有问题的话，那么进行日志提交确认，更新最新的日志提交位置索引