PATCH: add support for TCP_NODELAY on network streams

PATCH: add support for TCP_NODELAY on network streams

[Eric Marsden]

[-- Attachment #1: Type: text/plain, Size: 782 bytes --]

Hi,

The attached patch adds support for the socket option TCP_NODELAY,
to disable Nagle's algorithm. This means that network segments are
sent as soon as possible, even when they contain little data. This
reduces network latency on the network connection, but can lead to
many small packets being sent.

I have only tested on Linux/AMD64, but support for this socket option
is very widespread.

My motivation for adding this support is that Emacs is very slow
when connecting to the PostgreSQL database over the network, using
my pg-el library, and is unable to saturate CPU when sending a
stream of messages. It is much faster when using a local Unix
connection and saturates CPU.

With this patch, a test case that takes 911 seconds goes down to
76 seconds (x 12 speedup).

Eric

[-- Attachment #2: add-tcp-nodelay.diff --]
[-- Type: text/x-patch, Size: 2260 bytes --]

diff --git a/doc/lispref/processes.texi b/doc/lispref/processes.texi
index 79ef959ae65..93ac5a6aa7d 100644
--- a/doc/lispref/processes.texi
+++ b/doc/lispref/processes.texi
@@ -3090,6 +3090,13 @@ Network Options
 may be a period of time after the last use of that port (by any
 process on the host) where it is not possible to make a new server on
 that port.
+
+@item :nodelay @var{nodelay-flag}
+If @var{nodelay-flag} is non-@code{nil}, the @code{TCP_NODELAY} option
+is enabled on the socket. This disables the Nagle algorithm, meaning
+that network segments are sent as soon as possible, even when they
+contain little data. This reduces network latency on the network
+connection, but can lead to many small packets being sent.
 @end table
 
 @defun set-network-process-option process option value &optional no-error
diff --git a/lisp/emacs-lisp/bytecomp.el b/lisp/emacs-lisp/bytecomp.el
index f058fc48cc7..07eb4690fce 100644
--- a/lisp/emacs-lisp/bytecomp.el
+++ b/lisp/emacs-lisp/bytecomp.el
@@ -6049,8 +6049,8 @@ bytecomp--check-keyword-args
             :buffer :host :service :type :family :local :remote :coding
             :nowait :noquery :stop :filter :filter-multibyte :sentinel
             :log :plist :tls-parameters :server :broadcast :dontroute
-            :keepalive :linger :oobinline :priority :reuseaddr :bindtodevice
-            :use-external-socket)
+            :keepalive :linger :oobinline :priority :reuseaddr :nodelay
+            :bindtodevice :use-external-socket)
           '(:name :service))))
 
 (provide 'byte-compile)
diff --git a/src/process.c b/src/process.c
index b71ba3daf2d..0b994d6c5b7 100644
--- a/src/process.c
+++ b/src/process.c
@@ -38,6 +38,7 @@ Copyright (C) 1985-1988, 1993-1996, 1998-1999, 2001-2024 Free Software
 #include <sys/socket.h>
 #include <netdb.h>
 #include <netinet/in.h>
+#include <netinet/tcp.h>
 #include <arpa/inet.h>
 
 #else
@@ -2860,6 +2861,9 @@ DEFUN ("set-process-datagram-address", Fset_process_datagram_address, Sset_proce
 #endif
 #ifdef SO_REUSEADDR
     { ":reuseaddr", SOL_SOCKET, SO_REUSEADDR, SOPT_BOOL, OPIX_REUSEADDR },
+#endif
+#ifdef TCP_NODELAY
+    { ":nodelay", IPPROTO_TCP, TCP_NODELAY, SOPT_BOOL, OPIX_MISC },
 #endif
     { 0, 0, 0, SOPT_UNKNOWN, OPIX_NONE }
   };

Re: PATCH: add support for TCP_NODELAY on network streams

[Robert Pluim]

>>>>> On Wed, 11 Dec 2024 11:51:27 +0100, Eric Marsden <eric.marsden@risk-engineering.org> said:

    Eric> Hi,
    Eric> The attached patch adds support for the socket option TCP_NODELAY,
    Eric> to disable Nagle's algorithm. This means that network segments are
    Eric> sent as soon as possible, even when they contain little data. This
    Eric> reduces network latency on the network connection, but can lead to
    Eric> many small packets being sent.

    Eric> I have only tested on Linux/AMD64, but support for this socket option
    Eric> is very widespread.

If setting it fails you can get an error, so thatʼs not a big deal. I
should be able to verify it on macOS later this week.

    Eric> My motivation for adding this support is that Emacs is very slow
    Eric> when connecting to the PostgreSQL database over the network, using
    Eric> my pg-el library, and is unable to saturate CPU when sending a
    Eric> stream of messages. It is much faster when using a local Unix
    Eric> connection and saturates CPU.

    Eric> With this patch, a test case that takes 911 seconds goes down to
    Eric> 76 seconds (x 12 speedup).

    Eric> Eric

ENOCOMMITMESSAGE

    Eric> diff --git a/doc/lispref/processes.texi b/doc/lispref/processes.texi
    Eric> index 79ef959ae65..93ac5a6aa7d 100644
    Eric> --- a/doc/lispref/processes.texi
    Eric> +++ b/doc/lispref/processes.texi
    Eric> @@ -3090,6 +3090,13 @@ Network Options
    Eric>  may be a period of time after the last use of that port (by any
    Eric>  process on the host) where it is not possible to make a new server on
    Eric>  that port.
    Eric> +
    Eric> +@item :nodelay @var{nodelay-flag}
    Eric> +If @var{nodelay-flag} is non-@code{nil}, the @code{TCP_NODELAY} option
    Eric> +is enabled on the socket. This disables the Nagle algorithm, meaning
    Eric> +that network segments are sent as soon as possible, even when they
    Eric> +contain little data. This reduces network latency on the network
    Eric> +connection, but can lead to many small packets being sent.
    Eric>  @end table
 
    Eric>  @defun set-network-process-option process option value &optional no-error
    Eric> diff --git a/lisp/emacs-lisp/bytecomp.el b/lisp/emacs-lisp/bytecomp.el
    Eric> index f058fc48cc7..07eb4690fce 100644
    Eric> --- a/lisp/emacs-lisp/bytecomp.el
    Eric> +++ b/lisp/emacs-lisp/bytecomp.el
    Eric> @@ -6049,8 +6049,8 @@ bytecomp--check-keyword-args
    Eric>              :buffer :host :service :type :family :local :remote :coding
    Eric>              :nowait :noquery :stop :filter :filter-multibyte :sentinel
    Eric>              :log :plist :tls-parameters :server :broadcast :dontroute
    Eric> -            :keepalive :linger :oobinline :priority :reuseaddr :bindtodevice
    Eric> -            :use-external-socket)
    Eric> +            :keepalive :linger :oobinline :priority :reuseaddr :nodelay
    Eric> +            :bindtodevice :use-external-socket)
    Eric>            '(:name :service))))

I think you need to update the docstring of `make-network-process' as
well, as itʼs possible to set options on process creation.

    Eric>  (provide 'byte-compile)
    Eric> diff --git a/src/process.c b/src/process.c
    Eric> index b71ba3daf2d..0b994d6c5b7 100644
    Eric> --- a/src/process.c
    Eric> +++ b/src/process.c
    Eric> @@ -38,6 +38,7 @@ Copyright (C) 1985-1988, 1993-1996, 1998-1999, 2001-2024 Free Software
    Eric>  #include <sys/socket.h>
    Eric>  #include <netdb.h>
    Eric>  #include <netinet/in.h>
    Eric> +#include <netinet/tcp.h>
    Eric>  #include <arpa/inet.h>
 
    Eric>  #else
    Eric> @@ -2860,6 +2861,9 @@ DEFUN ("set-process-datagram-address", Fset_process_datagram_address, Sset_proce
    Eric>  #endif
    Eric>  #ifdef SO_REUSEADDR
    Eric>      { ":reuseaddr", SOL_SOCKET, SO_REUSEADDR, SOPT_BOOL, OPIX_REUSEADDR },
    Eric> +#endif
    Eric> +#ifdef TCP_NODELAY
    Eric> +    { ":nodelay", IPPROTO_TCP, TCP_NODELAY, SOPT_BOOL, OPIX_MISC },
    Eric>  #endif
    Eric>      { 0, 0, 0, SOPT_UNKNOWN, OPIX_NONE }
    Eric>    };

Iʼm not sure why we have a separate field for the option type, when the
only socket option that gets special treatment is :reuseaddr. Oh well,
hysterical raisins :-)

Robert
-- 

Re: PATCH: add support for TCP_NODELAY on network streams

[Eli Zaretskii]

> Date: Wed, 11 Dec 2024 11:51:27 +0100
> From: Eric Marsden <eric.marsden@risk-engineering.org>
> 
> The attached patch adds support for the socket option TCP_NODELAY,
> to disable Nagle's algorithm. This means that network segments are
> sent as soon as possible, even when they contain little data. This
> reduces network latency on the network connection, but can lead to
> many small packets being sent.

Thanks, but please in the future send patches to the bug tracker (we
have a submit-emacs-patch command for that).

> +@item :nodelay @var{nodelay-flag}
> +If @var{nodelay-flag} is non-@code{nil}, the @code{TCP_NODELAY} option
> +is enabled on the socket. This disables the Nagle algorithm, meaning
> +that network segments are sent as soon as possible, even when they
> +contain little data. This reduces network latency on the network
> +connection, but can lead to many small packets being sent.

Our conventions are to leave two spaces between sentences.