socket: add SO_KEEPALIVE option for upstream connections. (#3042)

Adds TCP Keepalive support for upstream connections. This can be configured on the cluster manager level, and overridden on the cluster level.

Risk Level: Medium

Testing:
Unit tests have been added. It appears to run and work.

Docs Changes:
envoyproxy/data-plane-api#614

Fixes envoyproxy/envoy#3028

API Changes:
envoyproxy/data-plane-api#614

Signed-off-by: Jonathan Oddy <jonathan.oddy@transferwise.com>

Mirrored from https://github.com/envoyproxy/envoy @ dd953f99945bb7c6b3251f71bffe252a5f6e9e62

envoy/api/v2/cds.proto

@@ -41,7 +41,7 @@ service ClusterDiscoveryService {
 // [#protodoc-title: Clusters]
 
 // Configuration for a single upstream cluster.
-// [#comment:next free field: 30]
+// [#comment:next free field: 31]
 message Cluster {
   // Supplies the name of the cluster which must be unique across all clusters.
   // The cluster name is used when emitting
@@ -428,6 +428,9 @@ message Cluster {
 
   // Determines how Envoy selects the protocol used to speak to upstream hosts.
   ClusterProtocolSelection protocol_selection = 26;
+
+  // Optional options for upstream connections.
+  envoy.api.v2.UpstreamConnectionOptions upstream_connection_options = 30;
 }
 
 // An extensible structure containing the address Envoy should bind to when
@@ -436,3 +439,8 @@ message UpstreamBindConfig {
   // The address Envoy should bind to when establishing upstream connections.
   core.Address source_address = 1;
 }
+
+message UpstreamConnectionOptions {
+  // If set then set SO_KEEPALIVE on the socket to enable TCP Keepalives.
+  core.TcpKeepalive tcp_keepalive = 1;
+}

envoy/api/v2/core/address.proto

@@ -58,6 +58,20 @@ message SocketAddress {
   bool ipv4_compat = 6;
 }
 
+message TcpKeepalive {
+  // Maximum number of keepalive probes to send without response before deciding
+  // the connection is dead. Default is to use the OS level configuration (unless
+  // overridden, Linux defaults to 9.)
+  google.protobuf.UInt32Value keepalive_probes = 1;
+  // The number of seconds a connection needs to be idle before keep-alive probes
+  // start being sent. Default is to use the OS level configuration (unless
+  // overridden, Linux defaults to 7200s (ie 2 hours.)
+  google.protobuf.UInt32Value keepalive_time = 2;
+  // The number of seconds between keep-alive probes. Default is to use the OS
+  // level configuration (unless overridden, Linux defaults to 75s.)
+  google.protobuf.UInt32Value keepalive_interval = 3;
+}
+
 message BindConfig {
   // The address to bind to when creating a socket.
   SocketAddress source_address = 1