Add configurable tcp keepalive support enabled by default

conf/minion

@@ -362,3 +362,32 @@
 #
 # The list of services to restart after a successful update. Empty by default.
 #update_restart_services: []
+
+
+######      Keepalive settings        ######
+############################################
+# ZeroMQ now includes support for configuring SO_KEEPALIVE if supported by
+# the OS. If connections between the minion and the master pass through
+# a state tracking device such as a firewall or VPN gateway, there is
+# the risk that it could tear down the connection the master and minion
+# without informing either party that their connection has been taken away.
+# Enabling TCP Keepalives prevents this from happening.
+#
+# Overall state of TCP Keepalives, enable (1 or True), disable (0 or False) 
+# or leave to the OS defaults (-1), on linux, typically disabled. Default True, enabled.
+#tcp_keepalive: True
+#
+# How long before the first keepalive should be sent in seconds. Default -1 
+# to use OS defaults, typically 7200 seconds on Linux see 
+# /proc/sys/net/ipv4/tcp_keepalive_time.
+#tcp_keepalive_idle: -1
+#
+# How many lost probes are needed to consider the connection lost. Default -1
+# to use OS defaults, typically 9 on Linux, see /proc/sys/net/ipv4/tcp_keepalive_probes.
+#tcp_keepalive_cnt: -1
+#
+# How often, in seconds, to send keepalives after the first one. Default -1 to 
+# use OS defaults, typically 75 seconds on Linux, see 
+# /proc/sys/net/ipv4/tcp_keepalive_intvl.
+#tcp_keepalive_intvl: -1
+

salt/config.py

@@ -239,6 +239,10 @@ def minion_config(path, check_dns=True):
             'recon_max': 5000,
             'win_repo_cachefile': 'salt://win/repo/winrepo.p',
             'pidfile': '/var/run/salt-minion.pid',
+            'tcp_keepalive': True,
+            'tcp_keepalive_idle': 300,
+            'tcp_keepalive_cnt': -1,
+            'tcp_keepalive_intvl': -1,
             }
 
     if len(opts['sock_dir']) > len(opts['cachedir']) + 10:

salt/minion.py

@@ -657,6 +657,11 @@ def tune_in(self):
             self.socket.setsockopt(
                 zmq.RECONNECT_IVL_MAX, self.opts['recon_max']
             )
+        if hasattr(zmq, 'TCP_KEEPALIVE'):
+            self.socket.setsockopt(zmq.TCP_KEEPALIVE, self.opts['tcp_keepalive'])
+            self.socket.setsockopt(zmq.TCP_KEEPALIVE_IDLE, self.opts['tcp_keepalive_idle'])
+            self.socket.setsockopt(zmq.TCP_KEEPALIVE_CNT, self.opts['tcp_keepalive_cnt'])
+            self.socket.setsockopt(zmq.TCP_KEEPALIVE_INTVL, self.opts['tcp_keepalive_intvl'])
         self.socket.connect(self.master_pub)
         self.poller.register(self.socket, zmq.POLLIN)
         self.epoller.register(self.epull_sock, zmq.POLLIN)