From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Sandeen Subject: [PATCH] ext3: retry failed direct IO allocations Date: Mon, 12 Oct 2009 21:34:27 -0500 Message-ID: <4AD3E733.4080903@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Jan Kara To: ext4 development Return-path: Received: from mx1.redhat.com ([209.132.183.28]:15374 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756757AbZJMCe7 (ORCPT ); Mon, 12 Oct 2009 22:34:59 -0400 Sender: linux-ext4-owner@vger.kernel.org List-ID: On a 256M 4k block filesystem, doing this in a loop: dd if=/dev/zero of=test oflag=direct bs=1M count=64 rm -f test eventually leads to spurious ENOSPC: dd: writing `test': No space left on device As with other block allocation callers, it looks like we need to potentially retry the allocations on the initial ENOSPC. A similar patch went into ext4 (commit fbbf69456619de5d251cb9f1df609069178c62d5) Signed-off-by: Eric Sandeen --- diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index acf1b14..069a163 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1735,6 +1735,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, ssize_t ret; int orphan = 0; size_t count = iov_length(iov, nr_segs); + int retries = 0; if (rw == WRITE) { loff_t final_size = offset + count; @@ -1757,9 +1758,12 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, } } +retry: ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, ext3_get_block, NULL); + if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries)) + goto retry; if (orphan) { int err;