linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@infradead.org>
To: Trond Myklebust <trond.myklebust@primarydata.com>
Cc: linux-nfs@vger.kernel.org
Subject: Re: [PATCH 10/12] NFS: Do not serialise O_DIRECT reads and writes
Date: Wed, 15 Jun 2016 00:13:43 -0700	[thread overview]
Message-ID: <20160615071343.GC4318@infradead.org> (raw)
In-Reply-To: <1465931115-30784-10-git-send-email-trond.myklebust@primarydata.com>

> +void
> +nfs_lock_bio(struct nfs_inode *nfsi)

bio stands for buffered I/O?  This could really use a more descriptive
name and/or a comment..

> +{
> +	/* Be an optimist! */
> +	down_read(&nfsi->io_lock);
> +	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0)
> +		return;
> +	up_read(&nfsi->io_lock);

So if no direct I/O is going on this locks shared?

> +	/* Slow path.... */
> +	down_write(&nfsi->io_lock);
> +	clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
> +	downgrade_write(&nfsi->io_lock);

The whole locking here seems rather confusing.  Why not use the XFS
locking model:

buffered write:		exclusive
buffered read:		shared
direct write:		shared (exclusive for pagecache invalidate)
direct read:		shared (exclusive for pagecache invalidate)

The nice thing is than in 4.7-rc i_mutex has been replaced with a
rw_mutex so you can just use that in shared mode for direct I/O
as-is without needing any new lock.

  parent reply	other threads:[~2016-06-15  7:13 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-14 19:05 [PATCH 01/12] NFS: Don't flush caches for a getattr that races with writeback Trond Myklebust
2016-06-14 19:05 ` [PATCH 02/12] NFS: Cache access checks more aggressively Trond Myklebust
2016-06-14 19:05   ` [PATCH 03/12] NFS: Cache aggressively when file is open for writing Trond Myklebust
2016-06-14 19:05     ` [PATCH 04/12] NFS: Kill NFS_INO_NFS_INO_FLUSHING: it is a performance killer Trond Myklebust
2016-06-14 19:05       ` [PATCH 05/12] NFS: writepage of a single page should not be synchronous Trond Myklebust
2016-06-14 19:05         ` [PATCH 06/12] NFS: Don't hold the inode lock across fsync() Trond Myklebust
2016-06-14 19:05           ` [PATCH 07/12] NFS: Don't enable deep stack recursion when doing memory reclaim Trond Myklebust
2016-06-14 19:05             ` [PATCH 08/12] NFS: Fix O_DIRECT verifier problems Trond Myklebust
2016-06-14 19:05               ` [PATCH 09/12] NFS: Ensure we reset the write verifier 'committed' value on resend Trond Myklebust
2016-06-14 19:05                 ` [PATCH 10/12] NFS: Do not serialise O_DIRECT reads and writes Trond Myklebust
2016-06-14 19:05                   ` [PATCH 11/12] NFS: Don't count O_DIRECT reads in the inode->i_dio_count Trond Myklebust
2016-06-14 19:05                     ` [PATCH 12/12] NFS: Clean up nfs_direct_complete() Trond Myklebust
2016-06-15  7:16                     ` [PATCH 11/12] NFS: Don't count O_DIRECT reads in the inode->i_dio_count Christoph Hellwig
2016-06-15 14:36                       ` Trond Myklebust
2016-06-15 14:41                         ` Christoph Hellwig
2016-06-15 14:50                           ` Trond Myklebust
2016-06-15 14:53                             ` Christoph Hellwig
2016-06-15  7:13                   ` Christoph Hellwig [this message]
2016-06-15 14:29                     ` [PATCH 10/12] NFS: Do not serialise O_DIRECT reads and writes Trond Myklebust
2016-06-15 14:48                       ` Christoph Hellwig
2016-06-15 14:52                         ` Trond Myklebust
2016-06-15 14:56                           ` Christoph Hellwig
2016-06-15 15:09                             ` Trond Myklebust
2016-06-15 15:14                               ` Christoph Hellwig
2016-06-15 15:45                                 ` Trond Myklebust
2016-06-16  9:12                                   ` Christoph Hellwig
2016-06-15  7:09             ` [PATCH 07/12] NFS: Don't enable deep stack recursion when doing memory reclaim Christoph Hellwig
2016-06-15  7:08           ` [PATCH 06/12] NFS: Don't hold the inode lock across fsync() Christoph Hellwig
2016-06-15 14:47             ` Trond Myklebust
2016-06-15 14:54               ` Christoph Hellwig
2016-06-17  1:11     ` [PATCH 03/12] NFS: Cache aggressively when file is open for writing Oleg Drokin
2016-06-17 14:01       ` Trond Myklebust

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=20160615071343.GC4318@infradead.org \
    --to=hch@infradead.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=trond.myklebust@primarydata.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).