Optimize TCP keepalive detection time

src/util.cc

@@ -77,10 +77,42 @@ Status SockSetTcpNoDelay(int fd, int val) {
   return Status::OK();
 }
 
-Status SockSetTcpKeepalive(int fd, int val) {
+Status SockSetTcpKeepalive(int fd, int interval) {
+  int val = 1;
   if (setsockopt(fd, SOL_SOCKET, SO_KEEPALIVE, &val, sizeof(val)) == -1) {
     return Status(Status::NotOK, strerror(errno));
   }
+
+#ifdef __linux__
+  // Default settings are more or less garbage, with the keepalive time
+  // set to 7200 by default on Linux. Modify settings to make the feature
+  // actually useful.
+
+  // Send first probe after interval.
+  val = interval;
+  if (setsockopt(fd, IPPROTO_TCP, TCP_KEEPIDLE, &val, sizeof(val)) < 0) {
+    return Status(Status::NotOK, std::string("setsockopt TCP_KEEPIDLE: ")+strerror(errno));
+  }
+
+  // Send next probes after the specified interval. Note that we set the
+  // delay as interval / 3, as we send three probes before detecting
+  // an error (see the next setsockopt call).
+  val = interval / 3;
+  if (val == 0) val = 1;
+  if (setsockopt(fd, IPPROTO_TCP, TCP_KEEPINTVL, &val, sizeof(val)) < 0) {
+    return Status(Status::NotOK, std::string("setsockopt TCP_KEEPINTVL: ")+strerror(errno));
+  }
+
+  // Consider the socket in error state after three we send three ACK
+  // probes without getting a reply.
+  val = 3;
+  if (setsockopt(fd, IPPROTO_TCP, TCP_KEEPCNT, &val, sizeof(val)) < 0) {
+    return Status(Status::NotOK, std::string("setsockopt TCP_KEEPCNT: ")+strerror(errno));
+  }
+#else
+  ((void) interval);  // Avoid unused var warning for non Linux systems.
+#endif
+
   return Status::OK();
 }
 

src/util.h

@@ -41,7 +41,7 @@ sockaddr_in NewSockaddrInet(const std::string &host, uint32_t port);
 Status SockConnect(std::string host, uint32_t port, int *fd);
 Status SockConnect(std::string host, uint32_t port, int *fd, uint64_t conn_timeout, uint64_t timeout = 0);
 Status SockSetTcpNoDelay(int fd, int val);
-Status SockSetTcpKeepalive(int fd, int val);
+Status SockSetTcpKeepalive(int fd, int interval);
 Status SockSend(int fd, const std::string &data);
 Status SockReadLine(int fd, std::string *data);
 int GetPeerAddr(int fd, std::string *addr, uint32_t *port);

src/worker.cc

@@ -70,7 +70,7 @@ void Worker::newConnection(evconnlistener *listener, evutil_socket_t fd,
                << " from port: " << worker->svr_->GetConfig()->port << " thread #"
                << worker->tid_;
   }
-  auto s = Util::SockSetTcpKeepalive(fd, 1);
+  auto s = Util::SockSetTcpKeepalive(fd, 120);
   if (!s.IsOK()) {
     LOG(ERROR) << "[worker] Failed to set tcp-keepalive, err:" << s.Msg();
     evutil_closesocket(fd);