From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jan Kara Subject: Re: [PATCH 6/7] ext4: endless truncate due to nonlocked dio readers V2 Date: Thu, 13 Sep 2012 14:07:36 +0200 Message-ID: <20120913120736.GA4328@quack.suse.cz> References: <1347211634-11509-1-git-send-email-dmonakhov@openvz.org> <1347211634-11509-7-git-send-email-dmonakhov@openvz.org> <20120913104136.GB11330@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Dmitry Monakhov , linux-ext4@vger.kernel.org, tytso@mit.edu, jack@suse.cz, wenqing.lz@taobao.com To: Zheng Liu Return-path: Received: from cantor2.suse.de ([195.135.220.15]:35817 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755179Ab2IMMHk (ORCPT ); Thu, 13 Sep 2012 08:07:40 -0400 Content-Disposition: inline In-Reply-To: <20120913104136.GB11330@gmail.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: Hello, On Thu 13-09-12 18:41:36, Zheng Liu wrote: > Could you please provide more detailed workload to convince me? I > am thinking about whether we really need to disable dioread_nolock > feature in here. In our benchmarks, we don't see this problem. I just did: # Create file dd if=/dev/zero of=/mnt/file bs=1M count=30 sync # Start 10 DIO dio readers in parallel reading the file in a loop for (( i = 0; i < 10; i++ )); do while true; do dd if=/mnt/file bs=4k iflag=direct of=/dev/null done & done sleep 1 # Try to truncate the file - never finishes. truncate -s 16 /mnt/file It is pretty easy to hit this. Besides being a DOS attack vector (but I won't be too concerned about this - there are plenty of ways how local process can screw you) I can easily imagine some application to get bitten by this. Honza > > Regards, > Zheng > > On Sun, Sep 09, 2012 at 09:27:13PM +0400, Dmitry Monakhov wrote: > > If we have enough aggressive DIO readers, truncate and other dio > > waiters will wait forever inside inode_dio_wait(). It is reasonable > > to disable nonlock DIO read optimization during truncate. > > > > Signed-off-by: Dmitry Monakhov > > --- > > fs/ext4/extents.c | 2 +- > > fs/ext4/fsync.c | 2 +- > > fs/ext4/inode.c | 2 +- > > 3 files changed, 3 insertions(+), 3 deletions(-) > > > > diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c > > index 8252651..b5b801f 100644 > > --- a/fs/ext4/extents.c > > +++ b/fs/ext4/extents.c > > @@ -4853,7 +4853,7 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) > > } > > > > /* finish any pending end_io work */ > > - inode_dio_wait(inode); > > + ext4_inode_dio_wait(inode, 1); > > ext4_flush_completed_IO(inode); > > > > credits = ext4_writepage_trans_blocks(inode); > > diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c > > index 290c5cf..bdf6bfd 100644 > > --- a/fs/ext4/fsync.c > > +++ b/fs/ext4/fsync.c > > @@ -204,7 +204,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) > > if (inode->i_sb->s_flags & MS_RDONLY) > > goto out; > > > > - inode_dio_wait(inode); > > + ext4_inode_dio_wait(inode, 1); > > ret = ext4_flush_completed_IO(inode); > > if (ret < 0) > > goto out; > > diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c > > index 93e6b09..a850026 100644 > > --- a/fs/ext4/inode.c > > +++ b/fs/ext4/inode.c > > @@ -4335,7 +4335,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) > > truncate_setsize(inode, attr->ia_size); > > /* Inode size will be reduced, wait for dio in flight */ > > if (orphan) > > - inode_dio_wait(inode); > > + ext4_inode_dio_wait(inode, 1); > > } > > ext4_truncate(inode); > > } > > -- > > 1.7.7.6 > > > > -- > > To unsubscribe from this list: send the line "unsubscribe linux-ext4" in > > the body of a message to majordomo@vger.kernel.org > > More majordomo info at http://vger.kernel.org/majordomo-info.html -- Jan Kara SUSE Labs, CR