From mboxrd@z Thu Jan  1 00:00:00 1970
From: erik quanstrom <quanstro@quanstro.net>
Date: Sat, 21 Sep 2013 22:55:06 -0400
To: 9fans@9fans.net
Message-ID: <64cc61c082febe489ac3244473bb4ca4@brasstown.quanstro.net>
MIME-Version: 1.0
Content-Type: multipart/mixed;
	boundary="upas-zsqqltwbdhadqpzlvypphibita"
Subject: [9fans] userspace semlocks
Topicbox-Message-UUID: 80d6cc78-ead8-11e9-9d60-3106f5b1d025

This is a multi-part message in MIME format.
--upas-zsqqltwbdhadqpzlvypphibita
Content-Disposition: inline
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

when i measure chan send performance with the attached program with
the semaphore locks that have been made the default for sources and
with the old locks, the old locks surprisingly outperform the new ones
by a large margin.

the test is let O be the number of buffers in the channel, and M be
the number of sending procs, then cycles is the number of machine
cycles required to send 1<<21 messages per proc, and receive them
on a single listener.

on my machine, i get the following raw numbers (averaged over a few tries):

	new	1.84e9 cycles	O=10	M=1
	old	1.10e9

	new	4.61e9		O=0	M=1
	old	4.38e9

	new	1.55e10		O=10	M=8
	old	2.74e10

	new	3.64e10		O=0	M=8
	old	5.14e10

am i doing something fundamental wrong, or are the new locks substantially
slower than the old ones?

- erik
--upas-zsqqltwbdhadqpzlvypphibita
Content-Disposition: attachment; filename=chantest.c
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

#include <u.h>
#include <libc.h>
#include <thread.h>

enum {
	Ndflt	= 1<<21,
	Mdflt	= 1,
	Odflt	= 10,
};

N	= Ndflt;
M	= Mdflt;
O	= Odflt;

Channel *c, *endc;

void
sendthread(void*)
{
	ulong i;

	for(i = 0; i < N; i++)
		sendul(c, i);
	threadexits("");
}

void
receivethread(void*)
{
	int i;

	for(i = 0; i <N*M; i++)
		recvul(c);
	sendul(endc, 1);
	threadexits("");
}

void
usage(void)
{
	fprint(2, "usage: chantest [-O nbuf] [-M nproc]\n");
	exits("usage");
}

void
threadmain(int argc, char **argv)
{
	int i;
	uvlong t;

	ARGBEGIN{
	default:
		usage();
	case 'M':
		M = atoi(EARGF(usage()));
		break;
	case 'O':
		O = atoi(EARGF(usage()));
		break;
	}ARGEND
	if(argc > 0)
		usage();

	t = -nsec();
	c = chancreate(sizeof(ulong), O);
	endc = chancreate(sizeof(ulong), 0);

	proccreate(receivethread, nil, 4*1024);
	for(i = 0; i < M; i++)
		proccreate(sendthread, (void*)(uintptr)i, 4*1024);

	recvul(endc);
	t += nsec();

	print("%lld\n", t);

	threadexits("");
}
--upas-zsqqltwbdhadqpzlvypphibita--