zookeeper-notifications mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [zookeeper] symat commented on a change in pull request #1048: ZOOKEEPER-3188: Improve resilience to network
Date Fri, 23 Aug 2019 15:38:38 GMT
symat commented on a change in pull request #1048: ZOOKEEPER-3188: Improve resilience to network
URL: https://github.com/apache/zookeeper/pull/1048#discussion_r317189846
 
 

 ##########
 File path: zookeeper-server/src/main/java/org/apache/zookeeper/server/quorum/Leader.java
 ##########
 @@ -417,71 +427,111 @@ public boolean isQuorumSynced(QuorumVerifier qv) {
     protected final Proposal newLeaderProposal = new Proposal();
 
     class LearnerCnxAcceptor extends ZooKeeperCriticalThread {
-        private volatile boolean stop = false;
+        private final AtomicBoolean stop = new AtomicBoolean(false);
+        private final AtomicBoolean fail = new AtomicBoolean(false);
 
-        public LearnerCnxAcceptor() {
-            super("LearnerCnxAcceptor-" + ss.getLocalSocketAddress(), zk
-                    .getZooKeeperServerListener());
+        LearnerCnxAcceptor() {
+            super("LearnerCnxAcceptor-" + serverSockets.stream()
+                      .map(ServerSocket::getLocalSocketAddress)
+                      .map(Objects::toString)
+                      .collect(Collectors.joining(",")),
+                  zk.getZooKeeperServerListener());
         }
 
         @Override
         public void run() {
-            try {
-                while (!stop) {
-                    Socket s = null;
-                    boolean error = false;
-                    try {
-                        s = ss.accept();
-
-                        // start with the initLimit, once the ack is processed
-                        // in LearnerHandler switch to the syncLimit
-                        s.setSoTimeout(self.tickTime * self.initLimit);
-                        s.setTcpNoDelay(nodelay);
-
-                        BufferedInputStream is = new BufferedInputStream(
-                                s.getInputStream());
-                        LearnerHandler fh = new LearnerHandler(s, is,
-                                Leader.this);
-                        fh.start();
-                    } catch (SocketException e) {
-                        error = true;
-                        if (stop) {
-                            LOG.info("exception while shutting down acceptor: "
-                                    + e);
-
-                            // When Leader.shutdown() calls ss.close(),
-                            // the call to accept throws an exception.
-                            // We catch and set stop to true.
-                            stop = true;
-                        } else {
-                            throw e;
-                        }
-                    } catch (SaslException e){
-                        LOG.error("Exception while connecting to quorum learner", e);
-                        error = true;
-                    } catch (Exception e) {
-                        error = true;
+            if (!stop.get() && !serverSockets.isEmpty()) {
+                ExecutorService executor = Executors.newFixedThreadPool(serverSockets.size());
+                CountDownLatch latch = new CountDownLatch(serverSockets.size());
+
+                serverSockets.forEach(serverSocket ->
+                        executor.submit(new LearnerCnxAcceptorHandler(serverSocket, latch)));
+
+                try {
+                    latch.await();
 
 Review comment:
   The code basically now starting listener threads on all local addresses, then waiting until
all the listeners are dead, and then simply start over again (assuming no stop was requested
by Leader.shutdown() or no unexpected failure happened in the Listener threads). 
   
   I don't think we need a timeout here... ideally we want to wait forever :)

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

Mime
View raw message