From: Christoph Hellwig <hch@lst.de>
To: Matthew Wilcox <willy@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>,
Dave Chinner <david@fromorbit.com>,
Goldwyn Rodrigues <rgoldwyn@suse.de>,
Damien Le Moal <damien.lemoal@wdc.com>,
Naohiro Aota <naohiro.aota@wdc.com>,
Johannes Thumshirn <jth@kernel.org>,
linux-btrfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
cluster-devel@redhat.com, linux-ext4@vger.kernel.org,
linux-xfs@vger.kernel.org
Subject: Re: [PATCH 2/2] iomap: fall back to buffered writes for invalidation failures
Date: Tue, 14 Jul 2020 13:00:11 +0200 [thread overview]
Message-ID: <20200714110011.GB16178@lst.de> (raw)
In-Reply-To: <20200713115509.GW12769@casper.infradead.org>
On Mon, Jul 13, 2020 at 12:55:09PM +0100, Matthew Wilcox wrote:
> On Mon, Jul 13, 2020 at 09:46:33AM +0200, Christoph Hellwig wrote:
> > Failing to invalid the page cache means data in incoherent, which is
> > a very bad state for the system. Always fall back to buffered I/O
> > through the page cache if we can't invalidate mappings.
>
> Is that the right approach though? I don't have a full picture in my head,
> but wouldn't we be better off marking these pages as !Uptodate and doing
> the direct I/O?
Isn't that a problem if e.g. pages are mapped into userspace and mlocked?
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: cluster-devel.redhat.com
Subject: [Cluster-devel] [PATCH 2/2] iomap: fall back to buffered writes for invalidation failures
Date: Tue, 14 Jul 2020 13:00:11 +0200 [thread overview]
Message-ID: <20200714110011.GB16178@lst.de> (raw)
In-Reply-To: <20200713115509.GW12769@casper.infradead.org>
On Mon, Jul 13, 2020 at 12:55:09PM +0100, Matthew Wilcox wrote:
> On Mon, Jul 13, 2020 at 09:46:33AM +0200, Christoph Hellwig wrote:
> > Failing to invalid the page cache means data in incoherent, which is
> > a very bad state for the system. Always fall back to buffered I/O
> > through the page cache if we can't invalidate mappings.
>
> Is that the right approach though? I don't have a full picture in my head,
> but wouldn't we be better off marking these pages as !Uptodate and doing
> the direct I/O?
Isn't that a problem if e.g. pages are mapped into userspace and mlocked?
next prev parent reply other threads:[~2020-07-14 11:00 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-13 7:46 RFC: iomap write invalidation Christoph Hellwig
2020-07-13 7:46 ` [Cluster-devel] " Christoph Hellwig
2020-07-13 7:46 ` [PATCH 1/2] iomap: Only invalidate page cache pages on direct IO writes Christoph Hellwig
2020-07-13 7:46 ` [Cluster-devel] " Christoph Hellwig
2020-07-13 7:46 ` [PATCH 2/2] iomap: fall back to buffered writes for invalidation failures Christoph Hellwig
2020-07-13 7:46 ` [Cluster-devel] " Christoph Hellwig
2020-07-13 11:55 ` Matthew Wilcox
2020-07-13 11:55 ` [Cluster-devel] " Matthew Wilcox
2020-07-14 11:00 ` Christoph Hellwig [this message]
2020-07-14 11:00 ` Christoph Hellwig
2020-07-13 12:20 ` Goldwyn Rodrigues
2020-07-13 12:20 ` [Cluster-devel] " Goldwyn Rodrigues
2020-07-13 16:09 ` David Sterba
2020-07-13 16:09 ` [Cluster-devel] " David Sterba
2020-07-13 15:39 ` Darrick J. Wong
2020-07-13 15:39 ` [Cluster-devel] " Darrick J. Wong
2020-07-14 11:00 ` Christoph Hellwig
2020-07-14 11:00 ` [Cluster-devel] " Christoph Hellwig
2020-07-14 1:41 ` Damien Le Moal
2020-07-14 1:41 ` [Cluster-devel] " Damien Le Moal
2020-07-15 1:47 ` RFC: iomap write invalidation Dave Chinner
2020-07-15 1:47 ` [Cluster-devel] " Dave Chinner
2020-07-20 21:51 ` Goldwyn Rodrigues
2020-07-20 21:51 ` [Cluster-devel] " Goldwyn Rodrigues
2020-07-21 14:53 ` Christoph Hellwig
2020-07-21 14:53 ` [Cluster-devel] " Christoph Hellwig
2020-07-21 14:59 ` Darrick J. Wong
2020-07-21 14:59 ` [Cluster-devel] " Darrick J. Wong
2020-07-21 15:04 ` Matthew Wilcox
2020-07-21 15:04 ` [Cluster-devel] " Matthew Wilcox
2020-07-21 15:06 ` Christoph Hellwig
2020-07-21 15:06 ` [Cluster-devel] " Christoph Hellwig
2020-07-21 15:14 ` Matthew Wilcox
2020-07-21 15:14 ` [Cluster-devel] " Matthew Wilcox
2020-07-21 15:16 ` Christoph Hellwig
2020-07-21 15:16 ` [Cluster-devel] " Christoph Hellwig
2020-07-21 15:27 ` Darrick J. Wong
2020-07-21 15:27 ` [Cluster-devel] " Darrick J. Wong
2020-07-21 15:41 ` Christoph Hellwig
2020-07-21 15:41 ` [Cluster-devel] " Christoph Hellwig
2020-07-21 15:59 ` Darrick J. Wong
2020-07-21 15:59 ` [Cluster-devel] " Darrick J. Wong
2020-07-21 16:01 ` Christoph Hellwig
2020-07-21 16:01 ` [Cluster-devel] " Christoph Hellwig
2020-07-21 16:05 ` Darrick J. Wong
2020-07-21 16:05 ` [Cluster-devel] " Darrick J. Wong
2020-07-21 15:31 ` Matthew Wilcox
2020-07-21 15:31 ` [Cluster-devel] " Matthew Wilcox
2020-07-21 15:42 ` Christoph Hellwig
2020-07-21 15:42 ` [Cluster-devel] " Christoph Hellwig
2020-07-21 15:52 ` Matthew Wilcox
2020-07-21 15:52 ` [Cluster-devel] " Matthew Wilcox
2020-07-21 16:03 ` Darrick J. Wong
2020-07-21 16:03 ` [Cluster-devel] " Darrick J. Wong
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=20200714110011.GB16178@lst.de \
--to=hch@lst.de \
--cc=cluster-devel@redhat.com \
--cc=damien.lemoal@wdc.com \
--cc=david@fromorbit.com \
--cc=jth@kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=naohiro.aota@wdc.com \
--cc=rgoldwyn@suse.de \
--cc=willy@infradead.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.