Linux-ext4 Archive on lore.kernel.org
 help / color / Atom feed
From: Andreas Gruenbacher <agruenba@redhat.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>,
	Goldwyn Rodrigues <rgoldwyn@suse.de>,
	Naohiro Aota <naohiro.aota@wdc.com>,
	linux-xfs@vger.kernel.org, Damien Le Moal <damien.lemoal@wdc.com>,
	linux-ext4 <linux-ext4@vger.kernel.org>,
	Matthew Wilcox <willy@infradead.org>,
	cluster-devel <cluster-devel@redhat.com>,
	Goldwyn Rodrigues <rgoldwyn@suse.com>,
	linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	Johannes Thumshirn <jth@kernel.org>,
	linux-btrfs@vger.kernel.org
Subject: Re: [Cluster-devel] [PATCH 3/3] iomap: fall back to buffered writes for invalidation failures
Date: Fri, 31 Jul 2020 16:03:13 +0200
Message-ID: <CAHc6FU4KpmW71xA1iX3rPp0evEPoYN3gjcSHt4de+K3R1ZKgEQ@mail.gmail.com> (raw)
In-Reply-To: <20200721183157.202276-4-hch@lst.de>

On Tue, Jul 21, 2020 at 8:55 PM Christoph Hellwig <hch@lst.de> 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.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Acked-by: Dave Chinner <dchinner@redhat.com>
> Reviewed-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/ext4/file.c       |  2 ++
>  fs/gfs2/file.c       |  3 ++-
>  fs/iomap/direct-io.c | 16 +++++++++++-----
>  fs/iomap/trace.h     |  1 +
>  fs/xfs/xfs_file.c    |  4 ++--
>  fs/zonefs/super.c    |  7 +++++--
>  6 files changed, 23 insertions(+), 10 deletions(-)
>
> diff --git a/fs/ext4/file.c b/fs/ext4/file.c
> index 2a01e31a032c4c..129cc1dd6b7952 100644
> --- a/fs/ext4/file.c
> +++ b/fs/ext4/file.c
> @@ -544,6 +544,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
>                 iomap_ops = &ext4_iomap_overwrite_ops;
>         ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
>                            is_sync_kiocb(iocb) || unaligned_io || extend);
> +       if (ret == -ENOTBLK)
> +               ret = 0;
>
>         if (extend)
>                 ret = ext4_handle_inode_extension(inode, offset, ret, count);
> diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
> index bebde537ac8cf2..b085a3bea4f0fd 100644
> --- a/fs/gfs2/file.c
> +++ b/fs/gfs2/file.c
> @@ -835,7 +835,8 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
>
>         ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL,
>                            is_sync_kiocb(iocb));
> -
> +       if (ret == -ENOTBLK)
> +               ret = 0;
>  out:
>         gfs2_glock_dq(&gh);
>  out_uninit:
> diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
> index 190967e87b69e4..c1aafb2ab99072 100644
> --- a/fs/iomap/direct-io.c
> +++ b/fs/iomap/direct-io.c
> @@ -10,6 +10,7 @@
>  #include <linux/backing-dev.h>
>  #include <linux/uio.h>
>  #include <linux/task_io_accounting_ops.h>
> +#include "trace.h"
>
>  #include "../internal.h"
>
> @@ -401,6 +402,9 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
>   * can be mapped into multiple disjoint IOs and only a subset of the IOs issued
>   * may be pure data writes. In that case, we still need to do a full data sync
>   * completion.
> + *
> + * Returns -ENOTBLK In case of a page invalidation invalidation failure for
> + * writes.  The callers needs to fall back to buffered I/O in this case.
>   */
>  ssize_t
>  iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
> @@ -478,13 +482,15 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
>         if (iov_iter_rw(iter) == WRITE) {
>                 /*
>                  * Try to invalidate cache pages for the range we are writing.
> -                * If this invalidation fails, tough, the write will still work,
> -                * but racing two incompatible write paths is a pretty crazy
> -                * thing to do, so we don't support it 100%.
> +                * If this invalidation fails, let the caller fall back to
> +                * buffered I/O.
>                  */
>                 if (invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
> -                               end >> PAGE_SHIFT))
> -                       dio_warn_stale_pagecache(iocb->ki_filp);
> +                               end >> PAGE_SHIFT)) {
> +                       trace_iomap_dio_invalidate_fail(inode, pos, count);
> +                       ret = -ENOTBLK;
> +                       goto out_free_dio;
> +               }
>
>                 if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) {
>                         ret = sb_init_dio_done_wq(inode->i_sb);
> diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
> index 5693a39d52fb63..fdc7ae388476f5 100644
> --- a/fs/iomap/trace.h
> +++ b/fs/iomap/trace.h
> @@ -74,6 +74,7 @@ DEFINE_EVENT(iomap_range_class, name, \
>  DEFINE_RANGE_EVENT(iomap_writepage);
>  DEFINE_RANGE_EVENT(iomap_releasepage);
>  DEFINE_RANGE_EVENT(iomap_invalidatepage);
> +DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail);
>
>  #define IOMAP_TYPE_STRINGS \
>         { IOMAP_HOLE,           "HOLE" }, \
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index a6ef90457abf97..1b4517fc55f1b9 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -553,8 +553,8 @@ xfs_file_dio_aio_write(
>         xfs_iunlock(ip, iolock);
>
>         /*
> -        * No fallback to buffered IO on errors for XFS, direct IO will either
> -        * complete fully or fail.
> +        * No fallback to buffered IO after short writes for XFS, direct I/O
> +        * will either complete fully or return an error.
>          */
>         ASSERT(ret < 0 || ret == count);
>         return ret;
> diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
> index 07bc42d62673ce..d0a04528a7e18e 100644
> --- a/fs/zonefs/super.c
> +++ b/fs/zonefs/super.c
> @@ -786,8 +786,11 @@ static ssize_t zonefs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
>         if (iocb->ki_pos >= ZONEFS_I(inode)->i_max_size)
>                 return -EFBIG;
>
> -       if (iocb->ki_flags & IOCB_DIRECT)
> -               return zonefs_file_dio_write(iocb, from);
> +       if (iocb->ki_flags & IOCB_DIRECT) {
> +               ssize_t ret = zonefs_file_dio_write(iocb, from);
> +               if (ret != -ENOTBLK)
> +                       return ret;
> +       }
>
>         return zonefs_file_buffered_write(iocb, from);
>  }
> --
> 2.27.0
>

Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com> # for gfs2

Thanks,
Andreas


      parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-21 18:31 iomap write invalidation v2 Christoph Hellwig
2020-07-21 18:31 ` [PATCH 1/3] xfs: use ENOTBLK for direct I/O to buffered I/O fallback Christoph Hellwig
2020-07-21 20:35   ` Darrick J. Wong
2020-07-21 18:31 ` [PATCH 2/3] iomap: Only invalidate page cache pages on direct IO writes Christoph Hellwig
2020-07-21 18:31 ` [PATCH 3/3] iomap: fall back to buffered writes for invalidation failures Christoph Hellwig
2020-07-21 20:37   ` Darrick J. Wong
2020-07-22  6:18     ` Christoph Hellwig
2020-07-22 16:15       ` Darrick J. Wong
2020-07-22 12:19     ` [Cluster-devel] " Bob Peterson
2020-07-21 23:01   ` Damien Le Moal
2020-07-22 23:13   ` Darrick J. Wong
2020-07-30  4:00     ` tytso
2020-07-31  7:01   ` Ritesh Harjani
2020-07-31 14:03   ` Andreas Gruenbacher [this message]

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=CAHc6FU4KpmW71xA1iX3rPp0evEPoYN3gjcSHt4de+K3R1ZKgEQ@mail.gmail.com \
    --to=agruenba@redhat.com \
    --cc=cluster-devel@redhat.com \
    --cc=damien.lemoal@wdc.com \
    --cc=david@fromorbit.com \
    --cc=hch@lst.de \
    --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.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

Linux-ext4 Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-ext4/0 linux-ext4/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-ext4 linux-ext4/ https://lore.kernel.org/linux-ext4 \
		linux-ext4@vger.kernel.org
	public-inbox-index linux-ext4

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-ext4


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git