Re: TCP network cost

[Tom Lane <tgl@xxxxxxxxxxxxx>]

"Ross J. Reedstrom" <reedstrm@xxxxxxxx> writes:
> Summary: C client and large-object API python both send bits in
> reasonable time, but I suspect there's still room for improvement in
> libpq over TCP: I'm suspicious of the 6x difference. Detailed analysis
> will probably find it's all down to memory allocation and extra copying
> of bits around (client side)

I wonder if the backend isn't contributing to the problem too.  It chops
its sends up into 8K units, which doesn't seem to create huge overhead
in my environment but maybe it does in yours.  It'd be interesting to see
what results you get from the attached quick-and-dirty patch (against
HEAD, but it should apply back to at least 8.1).

			regards, tom lane

Index: src/backend/libpq/pqcomm.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/libpq/pqcomm.c,v
retrieving revision 1.199
diff -c -r1.199 pqcomm.c
*** src/backend/libpq/pqcomm.c	1 Jan 2009 17:23:42 -0000	1.199
--- src/backend/libpq/pqcomm.c	23 Feb 2009 21:09:45 -0000
***************
*** 124,129 ****
--- 124,130 ----
  static void pq_close(int code, Datum arg);
  static int	internal_putbytes(const char *s, size_t len);
  static int	internal_flush(void);
+ static int	internal_send(const char *bufptr, size_t len);
  
  #ifdef HAVE_UNIX_SOCKETS
  static int	Lock_AF_UNIX(unsigned short portNumber, char *unixSocketName);
***************
*** 1041,1046 ****
--- 1042,1056 ----
  		if (PqSendPointer >= PQ_BUFFER_SIZE)
  			if (internal_flush())
  				return EOF;
+ 
+ 		/*
+ 		 * If buffer is empty and we'd fill it, just push the data immediately
+ 		 * rather than copying it into PqSendBuffer.
+ 		 */
+ 		if (PqSendPointer == 0 && len >= PQ_BUFFER_SIZE)
+ 			return internal_send(s, len);
+ 
+ 		/* Else put (some of) the data into the buffer */
  		amount = PQ_BUFFER_SIZE - PqSendPointer;
  		if (amount > len)
  			amount = len;
***************
*** 1075,1090 ****
  static int
  internal_flush(void)
  {
  	static int	last_reported_send_errno = 0;
  
! 	char	   *bufptr = PqSendBuffer;
! 	char	   *bufend = PqSendBuffer + PqSendPointer;
  
  	while (bufptr < bufend)
  	{
  		int			r;
  
! 		r = secure_write(MyProcPort, bufptr, bufend - bufptr);
  
  		if (r <= 0)
  		{
--- 1085,1115 ----
  static int
  internal_flush(void)
  {
+ 	int			r;
+ 
+ 	r = internal_send(PqSendBuffer, PqSendPointer);
+ 
+ 	/*
+ 	 * On error, we drop the buffered data anyway so that processing can
+ 	 * continue, even though we'll probably quit soon.
+ 	 */
+ 	PqSendPointer = 0;
+ 
+ 	return r;
+ }
+ 
+ static int
+ internal_send(const char *bufptr, size_t len)
+ {
  	static int	last_reported_send_errno = 0;
  
! 	const char *bufend = bufptr + len;
  
  	while (bufptr < bufend)
  	{
  		int			r;
  
! 		r = secure_write(MyProcPort, (void *) bufptr, bufend - bufptr);
  
  		if (r <= 0)
  		{
***************
*** 1108,1118 ****
  						 errmsg("could not send data to client: %m")));
  			}
  
- 			/*
- 			 * We drop the buffered data anyway so that processing can
- 			 * continue, even though we'll probably quit soon.
- 			 */
- 			PqSendPointer = 0;
  			return EOF;
  		}
  
--- 1133,1138 ----
***************
*** 1120,1126 ****
  		bufptr += r;
  	}
  
- 	PqSendPointer = 0;
  	return 0;
  }
  
--- 1140,1145 ----

-- 
Sent via pgsql-performance mailing list (pgsql-performance@xxxxxxxxxxxxxx)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-performance