Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000

[Jeff Garzik <jgarzik@mandrakesoft.com>]

[-- Attachment #1: Type: text/plain, Size: 551 bytes --]

David S. Miller wrote:
>    From: Jeff Garzik <jgarzik@mandrakesoft.com>
>    Date: Mon, 16 Sep 2002 19:48:37 -0400
> 
>    I dunno when it happened, but 2.5.x now returns EINVAL for all 
>    file->file cases.
>    
>    In 2.4.x, if sendpage is NULL, file_send_actor in mm/filemap.c faked a 
>    call to fops->write().
>    In 2.5.x, if sendpage is NULL, EINVAL is unconditionally returned.
>    
> 
> What if source and destination file and offsets match?


The same data is written out.  No deadlock.
(unless the attached test is wrong)

	Jeff



[-- Attachment #2: sendfile-test-2.c --]
[-- Type: text/plain, Size: 635 bytes --]

#include <sys/sendfile.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <string.h>
#include <stdio.h>

int main (int argc, char *argv[])
{
	int in, out;
	struct stat st;
	off_t off = 0;
	ssize_t rc;

	in = open("test.data", O_RDONLY);
	if (in < 0) {
		perror("test.data read");
		return 1;
	}

	fstat(in, &st);

	out = open("test.data", O_WRONLY);
	if (out < 0) {
		perror("test.data write");
		return 1;
	}

	rc = sendfile(out, in, &off, st.st_size);
	if (rc < 0) {
		perror("sendfile");
		close(in);
		unlink("out");
		close(out);
		return 1;
	}

	close(in);
	close(out);
	return 0;
}