maximum buffer size for splice(2) tcp->pipe?

[Volker Lendecke]

Hi!

While implementing splice support in Samba for better
performance I found it blocking when trying to pull data off
tcp into a pipe when the recvq was full. Attached find a
test program that shows this behaviour, on another host I
started

netcat 192.168.19.10 4711 < /dev/zero

vlendec@lenny:~$ uname -a
Linux lenny 2.6.28-06857-g5cbd04a #7 Wed Jan 7 10:10:42 CET 2009 x86_64 = GNU/Linux
vlendec@lenny:~$ gcc -o splicetest /host/home/vlendec/splicetest.c -O3 -Wall
vlendec@lenny:~$ ./splicetest out 65536 &
[1] 697
vlendec@lenny:~$ strace -p 697
Process 697 attached - interrupt to quit
splice(0x3, 0, 0x5, 0, 0x56a0, 0x1)     = 22176
splice(0x7, 0, 0x4, 0, 0x10000, 0x1^C <unfinished ...>
Process 697 detached
vlendec@lenny:~$ netstat -nt | grep 4711
tcp    69272      0 192.168.19.10:4711 192.168.19.1:33773 ESTABLISHED
vlendec@lenny:~$

Interestingly, whenever I start the strace, it gets another
chunk of data and then blocks in the next splice call.

If I start splicetest with a buffer size of 16384 instead of
65536, it does not block. I could not find a way to ask the
kernel for the tipping point below which it does not block.

What is a safe buffer size to use with splice?

BTW, this kernel is from Steve French's linux-cifs.git repo.

Thanks,

Volker Lendecke

Samba Team

P.S: I'm not subscribed to linux-kernel, so if possible
please CC me directly. If this is inappropriate behaviour,
please give me a quick hint :-)

-- 
SerNet GmbH, Bahnhofsallee 1b, 37081 Göttingen
phone: +49-551-370000-0, fax: +49-551-370000-9
AG Göttingen, HRB 2816, GF: Dr. Johannes Loxen
#define _GNU_SOURCE
#include <fcntl.h>

#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <string.h>
#include <errno.h>
#include <stdlib.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>

int main(int argc, const char *argv[])
{
	int pipefds[2];
	int file_fd;
	int sock;
	int listen_fd;
	struct sockaddr_in in_addr;
	int res;
	int to_read;

	if (argc != 3) {
		fprintf(stderr, "usage: %s <filename> to_read\n", argv[0]);
		exit(1);
	}

	to_read = atoi(argv[2]);

	if (pipe(pipefds) != 0) {
		fprintf(stderr, "pipe returned %s\n", strerror(errno));
		exit(1);
	}

	if ((file_fd = open(argv[1], O_CREAT|O_RDWR, 0644)) == -1) {
		fprintf(stderr, "open returned %s\n", strerror(errno));
		exit(1);
	}

	listen_fd = socket(PF_INET, SOCK_STREAM, 0);
	if (listen_fd == -1) {
		fprintf(stderr, "socket returned %s\n", strerror(errno));
		exit(1);
	}

	in_addr.sin_family = AF_INET;
	inet_aton("0.0.0.0", &in_addr.sin_addr);
	in_addr.sin_port = htons(4711);

	res = bind(listen_fd, (struct sockaddr *)&in_addr, sizeof(in_addr));
	if (res == -1) {
		fprintf(stderr, "bind returned %s\n", strerror(errno));
		exit(1);
	}

	res = listen(listen_fd, 5);
	if (res == -1) {
		fprintf(stderr, "listen returned %s\n", strerror(errno));
		exit(1);
	}

	sock = accept(listen_fd, NULL, NULL);
	if (sock == -1) {
		fprintf(stderr, "accept returned %s\n", strerror(errno));
		exit(1);
	}

	while (1) {
		ssize_t nread, nwritten;

		nread = splice(sock, NULL, pipefds[1], NULL, to_read,
			       SPLICE_F_MOVE);
		if (nread == -1) {
			fprintf(stderr, "splice failed: %s\n",
				strerror(errno));
			exit(1);
		}

		if (nread == 0) {
			printf("EOF\n");
			return 0;
		}

		nwritten = splice(pipefds[0], NULL, file_fd, NULL, nread,
				  SPLICE_F_MOVE);
		if (nwritten != nread) {
			fprintf(stderr, "splice failed: %d/%d %s\n",
				(int)nread, (int)nwritten,
				nwritten == -1 ? strerror(errno) : "");
			exit(1);
		}
	}

	return 0;
}

Attachment: pgp00000.pgp
Description: PGP signature