Add support for busy port message queue

4 files changed, 77 insertions, 4 deletions

diff --git a/lib/kernel/doc/src/inet.xml b/lib/kernel/doc/src/inet.xml
index bf6c4cfb1a..bfdb163e17 100644
--- a/lib/kernel/doc/src/inet.xml
+++ b/lib/kernel/doc/src/inet.xml
@@ -487,6 +487,36 @@ fe80::204:acff:fe17:bf38
               example <c>Size == 2</c>, the data received will match
               <c>[Byte1,Byte2|Binary]</c>.</p>
           </item>
+          <tag><c>{high_msgq_watermark, Size}</c> (TCP/IP sockets)</tag>
+          <item>
+	    <p>The socket message queue will be set into a busy
+	    state when the amount of data queued on the message
+	    queue reaches this limit. Note that this limit only
+	    concerns data that have not yet reached the ERTS internal
+	    socket implementation. Default value used is 8 kB.</p>
+	    <p>Senders of data to the socket will be suspended if
+	    either the socket message queue is busy, or the socket
+	    itself is busy.</p>
+	    <p>For more information see the <c>low_msgq_watermark</c>,
+	    <c>high_watermark</c>, and <c>low_watermark</c> options.</p>
+	    <p>Note that distribution sockets will disable the use of
+	    <c>high_msgq_watermark</c> and <c>low_msgq_watermark</c>,
+	    and will instead use the
+	    <seealso marker="erts:erlang#system_info_dist_buf_busy_limit">distribution
+	    buffer busy limit</seealso> which is a similar feature.</p>
+          </item>
+          <tag><c>{high_watermark, Size}</c> (TCP/IP sockets)</tag>
+          <item>
+	    <p>The socket will be set into a busy state when the amount
+	    of data queued internally by the ERTS socket implementation
+	    reaches this limit. Default value used is 8 kB.</p>
+	    <p>Senders of data to the socket will be suspended if
+	    either the socket message queue is busy, or the socket
+	    itself is busy.</p>
+	    <p>For more information see the <c>low_watermark</c>,
+	    <c>high_msgq_watermark</c>, and <c>low_msqg_watermark</c>
+	    options.</p>
+          </item>
           <tag><c>{keepalive, Boolean}</c>(TCP/IP sockets)</tag>
           <item>
             <p>Enables/disables periodic transmission on a connected
@@ -495,6 +525,40 @@ fe80::204:acff:fe17:bf38
               considered broken and an error message will be sent to
               the controlling process. Default disabled.</p>
           </item>
+          <tag><c>{low_msgq_watermark, Size}</c> (TCP/IP sockets)</tag>
+          <item>
+	    <p>If the socket message queue is in a busy state, the
+	    socket message queue will be set in a not busy state when
+	    the amount of data queued in the message queue falls
+	    below this limit. Note that this limit only concerns data
+	    that have not yet reached the ERTS internal socket
+	    implementation. Default value used is 4 kB.</p>
+	    <p>Senders that have been suspended due to either a
+	    busy message queue or a busy socket, will be resumed
+	    when neither the socket message queue, nor the socket
+	    are busy.</p>
+	    <p>For more information see the <c>high_msgq_watermark</c>,
+	    <c>high_watermark</c>, and <c>low_watermark</c> options.</p>
+	    <p>Note that distribution sockets will disable the use of
+	    <c>high_msgq_watermark</c> and <c>low_msgq_watermark</c>,
+	    and will instead use the
+	    <seealso marker="erts:erlang#system_info_dist_buf_busy_limit">distribution
+	    buffer busy limit</seealso> which is a similar feature.</p>
+          </item>
+          <tag><c>{low_watermark, Size}</c> (TCP/IP sockets)</tag>
+          <item>
+	    <p>If the socket is in a busy state, the socket will
+	    be set in a not busy state when the amount of data
+	    queued internally by the ERTS socket implementation
+	    falls below this limit. Default value used is 4 kB.</p>
+	    <p>Senders that have been suspended due to either a
+	    busy message queue or a busy socket, will be resumed
+	    when neither the socket message queue, nor the socket
+	    are busy.</p>
+	    <p>For more information see the <c>high_watermark</c>,
+	    <c>high_msgq_watermark</c>, and <c>low_msgq_watermark</c>
+	    options.</p>
+          </item>
           <tag><c>{nodelay, Boolean}</c>(TCP/IP sockets)</tag>
           <item>
             <p>If <c>Boolean == true</c>, the <c>TCP_NODELAY</c> option
diff --git a/lib/kernel/src/gen_tcp.erl b/lib/kernel/src/gen_tcp.erl
index ef6bfdf7f4..519c1bb8b4 100644
--- a/lib/kernel/src/gen_tcp.erl
+++ b/lib/kernel/src/gen_tcp.erl
@@ -38,9 +38,11 @@
         {dontroute,       boolean()} |
         {exit_on_close,   boolean()} |
         {header,          non_neg_integer()} |
+        {high_msgq_watermark, pos_integer()} |
         {high_watermark,  non_neg_integer()} |
         {keepalive,       boolean()} |
         {linger,          {boolean(), non_neg_integer()}} |
+        {low_msgq_watermark, pos_integer()} |
         {low_watermark,   non_neg_integer()} |
         {mode,            list | binary} | list | binary |
         {nodelay,         boolean()} |
@@ -68,9 +70,11 @@
         dontroute |
         exit_on_close |
         header |
+        high_msgq_watermark |
         high_watermark |
         keepalive |
         linger |
+        low_msgq_watermark |
         low_watermark |
         mode |
         nodelay |
diff --git a/lib/kernel/src/inet.erl b/lib/kernel/src/inet.erl
index abaf4486dc..e791bb135f 100644
--- a/lib/kernel/src/inet.erl
+++ b/lib/kernel/src/inet.erl
@@ -535,6 +535,7 @@ options() ->
      buffer, header, active, packet, deliver, mode,
      multicast_if, multicast_ttl, multicast_loop,
      exit_on_close, high_watermark, low_watermark,
+     high_msgq_watermark, low_msgq_watermark,
      bit8, send_timeout, send_timeout_close
     ].
 
@@ -552,8 +553,9 @@ stats() ->
 connect_options() ->
     [tos, priority, reuseaddr, keepalive, linger, sndbuf, recbuf, nodelay,
      header, active, packet, packet_size, buffer, mode, deliver,
-     exit_on_close, high_watermark, low_watermark, bit8, send_timeout,
-     send_timeout_close, delay_send,raw].
+     exit_on_close, high_watermark, low_watermark, high_msgq_watermark,
+     low_msgq_watermark, bit8, send_timeout, send_timeout_close,
+     delay_send,raw].
     
 connect_options(Opts, Family) ->
     BaseOpts = 
@@ -608,8 +610,9 @@ con_add(Name, Val, R, Opts, AllOpts) ->
 listen_options() ->
     [tos, priority, reuseaddr, keepalive, linger, sndbuf, recbuf, nodelay,
      header, active, packet, buffer, mode, deliver, backlog,
-     exit_on_close, high_watermark, low_watermark, bit8, send_timeout,
-     send_timeout_close, delay_send, packet_size,raw].
+     exit_on_close, high_watermark, low_watermark, high_msgq_watermark,
+     low_msgq_watermark, bit8, send_timeout, send_timeout_close,
+     delay_send, packet_size,raw].
 
 listen_options(Opts, Family) ->
     BaseOpts = 
diff --git a/lib/kernel/src/inet_int.hrl b/lib/kernel/src/inet_int.hrl
index cf893c73eb..2dfbf75d25 100644
--- a/lib/kernel/src/inet_int.hrl
+++ b/lib/kernel/src/inet_int.hrl
@@ -141,6 +141,8 @@
 -define(INET_LOPT_READ_PACKETS,  33).
 -define(INET_OPT_RAW,            34).
 -define(INET_LOPT_TCP_SEND_TIMEOUT_CLOSE, 35).
+-define(INET_LOPT_TCP_MSGQ_HIWTRMRK,  36).
+-define(INET_LOPT_TCP_MSGQ_LOWTRMRK,  37).
 % Specific SCTP options: separate range:
 -define(SCTP_OPT_RTOINFO,	 	100).
 -define(SCTP_OPT_ASSOCINFO,	 	101).