linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zheng Liu <gnehzuil.liu@gmail.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	xfs@oss.sgi.com
Subject: Re: [BUG] ext2/3/4: dio reads stale data when we do some append dio writes
Date: Tue, 19 Nov 2013 19:51:22 +0800	[thread overview]
Message-ID: <20131119115122.GC4782@gmail.com> (raw)
In-Reply-To: <20131119111826.GA20485@infradead.org>

On Tue, Nov 19, 2013 at 03:18:26AM -0800, Christoph Hellwig wrote:
> On Tue, Nov 19, 2013 at 07:19:47PM +0800, Zheng Liu wrote:
> > Yes, I know that XFS has a shared/exclusive lock.  I guess that is why
> > it can pass the test.  But another question is why xfs fails when we do
> > some append dio writes with doing buffered read.
> 
> Can you provide a test case for that issue?

Simple.  Reader just need to open this file without O_DIRECT flag.  I
paste the full code snippet below.  Please take care of this line:
	readfd = open(argv[1], /*O_DIRECT|*/O_RDONLY, S_IRWXU);

The result of this program on my own sand box looks like below:
        encounter an error: offset 0

                                                - Zheng

#define _GNU_SOURCE

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <memory.h>

#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <errno.h>

#include <pthread.h>

#define BUF_ALIGN	1024

struct writer_data {
	int fd;
	size_t blksize;
	char *buf;
};

static void *writer(void *arg)
{
	struct writer_data *data = (struct writer_data *)arg;
	int ret;

	ret = write(data->fd, data->buf, data->blksize);
	if (ret < 0)
		fprintf(stderr, "write file failed: %s\n", strerror(errno));

	return NULL;
}

int main(int argc, char *argv[])
{
	pthread_t tid;
	struct writer_data wdata;
	size_t max_blocks = 10 * 1024;
	size_t blksize = 1 * 1024 * 1024;
	char *rbuf, *wbuf;
	int readfd, writefd;
	int i, j;

	if (argc < 2) {
		fprintf(stderr, "usage: %s [filename]\n", argv[0]);
		exit(1);
	}

	writefd = open(argv[1], O_CREAT|O_DIRECT|O_WRONLY|O_APPEND|O_TRUNC, S_IRWXU);
	if (writefd < 0) {
		fprintf(stderr, "failed to open wfile: %s\n", strerror(errno));
		exit(1);
	}
	readfd = open(argv[1], /*O_DIRECT|*/O_RDONLY, S_IRWXU);
	if (readfd < 0) {
		fprintf(stderr, "failed to open rfile: %s\n", strerror(errno));
		exit(1);
	}

	if (posix_memalign((void **)&wbuf, BUF_ALIGN, blksize)) {
		fprintf(stderr, "failed to alloc memory: %s\n", strerror(errno));
		exit(1);
	}

	if (posix_memalign((void **)&rbuf, 4096, blksize)) {
		fprintf(stderr, "failed to alloc memory: %s\n", strerror(errno));
		exit(1);
	}

	memset(wbuf, 'a', blksize);

	wdata.fd = writefd;
	wdata.blksize = blksize;
	wdata.buf = wbuf;

	for (i = 0; i < max_blocks; i++) {
		void *retval;
		int ret;

		ret = pthread_create(&tid, NULL, writer, &wdata);
		if (ret) {
			fprintf(stderr, "create thread failed: %s\n", strerror(errno));
			exit(1);
		}

		memset(rbuf, 'b', blksize);
		do {
			ret = pread(readfd, rbuf, blksize, i * blksize);
		} while (ret <= 0);

		if (ret < 0) {
			fprintf(stderr, "read file failed: %s\n", strerror(errno));
			exit(1);
		}

		if (pthread_join(tid, &retval)) {
			fprintf(stderr, "pthread join failed: %s\n", strerror(errno));
			exit(1);
		}

		if (ret >= 0) {
			for (j = 0; j < ret; j++) {
				if (rbuf[i] != 'a') {
					fprintf(stderr, "encounter an error: offset %ld\n",
						i);
					goto err;
				}
			}
		}
	}

err:
	free(wbuf);
	free(rbuf);

	return 0;
}

  reply	other threads:[~2013-11-19 11:51 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-19  9:53 [BUG] ext2/3/4: dio reads stale data when we do some append dio writes Zheng Liu
2013-11-19 10:22 ` Christoph Hellwig
2013-11-19 10:45   ` Zheng Liu
2013-11-19 11:01     ` Christoph Hellwig
2013-11-19 11:19       ` Zheng Liu
2013-11-19 11:18         ` Christoph Hellwig
2013-11-19 11:51           ` Zheng Liu [this message]
2013-11-19 12:09             ` Dave Chinner
2013-11-19 12:18               ` Zheng Liu
2013-11-19 12:01           ` Dave Chinner
2013-11-19 12:20             ` Zheng Liu
2013-11-19 10:54 ` Dmitry Monakhov
2013-11-19 11:45   ` Zheng Liu
2013-11-27 23:01 ` Jan Kara

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20131119115122.GC4782@gmail.com \
    --to=gnehzuil.liu@gmail.com \
    --cc=hch@infradead.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=xfs@oss.sgi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).