linux-ext4 - Re: Odd locking pattern introduced as part of "nowait aio support"

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 11 Sep 2019 02:39:26 -0700
From:   Andres Freund <andres@...razel.de>
To:     Dave Chinner <david@...morbit.com>, David Sterba <dsterba@...e.com>
Cc:     Goldwyn Rodrigues <rgoldwyn@...e.de>,
        linux-fsdevel@...r.kernel.org, jack@...e.com, hch@...radead.org,
        linux-ext4@...r.kernel.org, linux-btrfs@...r.kernel.org
Subject: Re: Odd locking pattern introduced as part of "nowait aio support"

Hi,

On 2019-09-11 14:04:20 +1000, Dave Chinner wrote:
> On Tue, Sep 10, 2019 at 03:33:27PM -0700, Andres Freund wrote:
> > Hi,
> > 
> > Especially with buffered io it's fairly easy to hit contention on the
> > inode lock, during writes. With something like io_uring, it's even
> > easier, because it currently (but see [1]) farms out buffered writes to
> > workers, which then can easily contend on the inode lock, even if only
> > one process submits writes.  But I've seen it in plenty other cases too.
> > 
> > Looking at the code I noticed that several parts of the "nowait aio
> > support" (cf 728fbc0e10b7f3) series introduced code like:
> > 
> > static ssize_t
> > ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
> > {
> > ...
> > 	if (!inode_trylock(inode)) {
> > 		if (iocb->ki_flags & IOCB_NOWAIT)
> > 			return -EAGAIN;
> > 		inode_lock(inode);
> > 	}
> 
> The ext4 code is just buggy here - we don't support RWF_NOWAIT on
> buffered writes.

But both buffered and non-buffered writes go through
ext4_file_write_iter(). And there's a preceding check, at least these
days, preventing IOCB_NOWAIT to apply to buffered writes:

	if (!o_direct && (iocb->ki_flags & IOCB_NOWAIT))
		return -EOPNOTSUPP;


I do really wish buffered NOWAIT was supported... The overhead of having
to do async buffered writes through the workqueue in io_uring, even if
an already existing page is targeted, is quite noticable. Even if it
failed with EAGAIN as soon as the buffered write's target isn't in the
page cache, it'd be worthwhile.


> > isn't trylocking and then locking in a blocking fashion an inefficient
> > pattern? I.e. I think this should be
> > 
> > 	if (iocb->ki_flags & IOCB_NOWAIT) {
> > 		if (!inode_trylock(inode))
> > 			return -EAGAIN;
> > 	}
> >         else
> >         	inode_lock(inode);
> 
> Yes, you are right.
> 
> History: commit 91f9943e1c7b ("fs: support RWF_NOWAIT
> for buffered reads") which introduced the first locking pattern
> you describe in XFS.

Seems, as part of the nowait work, the pattern was introduced in ext4,
xfs and btrfs. And fixed in xfs.


> That was followed soon after by:
> 
> commit 942491c9e6d631c012f3c4ea8e7777b0b02edeab
> Author: Christoph Hellwig <hch@....de>
> Date:   Mon Oct 23 18:31:50 2017 -0700
> 
>     xfs: fix AIM7 regression
>     
>     Apparently our current rwsem code doesn't like doing the trylock, then
>     lock for real scheme.  So change our read/write methods to just do the
>     trylock for the RWF_NOWAIT case.  This fixes a ~25% regression in
>     AIM7.
>     
>     Fixes: 91f9943e ("fs: support RWF_NOWAIT for buffered reads")
>     Reported-by: kernel test robot <xiaolong.ye@...el.com>
>     Signed-off-by: Christoph Hellwig <hch@....de>
>     Reviewed-by: Darrick J. Wong <darrick.wong@...cle.com>
>     Signed-off-by: Darrick J. Wong <darrick.wong@...cle.com>
> 
> Which changed all the trylock/eagain/lock patterns to the second
> form you quote. None of the other filesystems had AIM7 regressions
> reported against them, so nobody changed them....

:(


> > Obviously this isn't going to improve scalability to a very significant
> > degree. But not unnecessarily doing two atomic ops on a contended lock
> > can't hurt scalability either. Also, the current code just seems
> > confusing.
> > 
> > Am I missing something?
> 
> Just that the sort of performance regression testing that uncovers
> this sort of thing isn't widely done, and most filesystems are
> concurrency limited in some way before they hit inode lock
> scalability issues. Hence filesystem concurrency foccussed
> benchmarks that could uncover it (like aim7) won't because the inode
> locks don't end up stressed enough to make a difference to
> benchmark performance.

Ok.  Goldwyn, do you want to write a patch, or do you want me to write
one up?


Greetings,

Andres Freund