Linux NFS development
 help / color / mirror / Atom feed
From: Jeff Layton <jlayton@kernel.org>
To: trondmy@gmail.com, linux-nfs@vger.kernel.org
Subject: Re: [PATCH 00/11] LAYOUTRETURN on reboot
Date: Fri, 14 Jun 2024 07:47:40 -0400	[thread overview]
Message-ID: <c6caff32f8d9620e82a37d0fbd1a641da819c104.camel@kernel.org> (raw)
In-Reply-To: <20240613050055.854323-1-trond.myklebust@hammerspace.com>

On Thu, 2024-06-13 at 01:00 -0400, trondmy@gmail.com wrote:
> From: Trond Myklebust <trond.myklebust@hammerspace.com>
> 
> Now that https://datatracker.ietf.org/doc/draft-ietf-nfsv4-layrec/ is
> mostly done with the review process, I'd like to move the final patches
> for the client implementation upstream.
> 
> The following patch series therefore adds support to the flexfiles pNFS
> driver so that if a metadata server reboot occurs while a client has
> layouts outstanding, and is performing I/O, then the client will report
> layoutstats and layout errors through a LAYOUTRETURN during the grace
> period, after the metadata server comes back up.
> This has implications for mirrored workloads, since it allows the client
> to report exactly which mirror data instances may have been corrupted
> due to the presence of errors during WRITEs or COMMITs.
> 
> Trond Myklebust (11):
>   NFSv4/pnfs: Remove redundant list check
>   NFSv4.1: constify the stateid argument in nfs41_test_stateid()
>   NFSv4: Clean up encode_nfs4_stateid()
>   pNFS: Add a flag argument to pnfs_destroy_layouts_byclid()
>   NFSv4/pnfs: Add support for the PNFS_LAYOUT_FILE_BULK_RETURN flag
>   NFSv4/pNFS: Add a helper to defer failed layoutreturn calls
>   NFSv4/pNFS: Handle server reboots in pnfs_poc_release()
>   NFSv4/pNFS: Retry the layout return later in case of a timeout or
>     reboot
>   NFSv4/pnfs: Give nfs4_proc_layoutreturn() a flags argument
>   NFSv4/pNFS: Remove redundant call to unhash the layout
>   NFSv4/pNFS: Do layout state recovery upon reboot
> 
>  fs/nfs/callback_proc.c                 |   5 +-
>  fs/nfs/flexfilelayout/flexfilelayout.c |   2 +-
>  fs/nfs/nfs4_fs.h                       |   3 +-
>  fs/nfs/nfs4proc.c                      |  53 ++++--
>  fs/nfs/nfs4state.c                     |   4 +-
>  fs/nfs/nfs4xdr.c                       |   7 +-
>  fs/nfs/pnfs.c                          | 223 +++++++++++++++++++------
>  fs/nfs/pnfs.h                          |  30 +++-
>  include/linux/nfs_fs_sb.h              |   1 +
>  include/linux/nfs_xdr.h                |   2 +-
>  10 files changed, 249 insertions(+), 81 deletions(-)
> 

These have been used for a while inside of Meta vs. Hammerspace's
servers and have been behaving.

Reviewed-by: Jeff Layton <jlayton@kernel.org>

      parent reply	other threads:[~2024-06-14 11:47 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-13  5:00 [PATCH 00/11] LAYOUTRETURN on reboot trondmy
2024-06-13  5:00 ` [PATCH 01/11] NFSv4/pnfs: Remove redundant list check trondmy
2024-06-13  5:00   ` [PATCH 02/11] NFSv4.1: constify the stateid argument in nfs41_test_stateid() trondmy
2024-06-13  5:00     ` [PATCH 03/11] NFSv4: Clean up encode_nfs4_stateid() trondmy
2024-06-13  5:00       ` [PATCH 04/11] pNFS: Add a flag argument to pnfs_destroy_layouts_byclid() trondmy
2024-06-13  5:00         ` [PATCH 05/11] NFSv4/pnfs: Add support for the PNFS_LAYOUT_FILE_BULK_RETURN flag trondmy
2024-06-13  5:00           ` [PATCH 06/11] NFSv4/pNFS: Add a helper to defer failed layoutreturn calls trondmy
2024-06-13  5:00             ` [PATCH 07/11] NFSv4/pNFS: Handle server reboots in pnfs_poc_release() trondmy
2024-06-13  5:00               ` [PATCH 08/11] NFSv4/pNFS: Retry the layout return later in case of a timeout or reboot trondmy
2024-06-13  5:00                 ` [PATCH 09/11] NFSv4/pnfs: Give nfs4_proc_layoutreturn() a flags argument trondmy
2024-06-13  5:00                   ` [PATCH 10/11] NFSv4/pNFS: Remove redundant call to unhash the layout trondmy
2024-06-13  5:00                     ` [PATCH 11/11] NFSv4/pNFS: Do layout state recovery upon reboot trondmy
2024-06-14 11:47 ` Jeff Layton [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=c6caff32f8d9620e82a37d0fbd1a641da819c104.camel@kernel.org \
    --to=jlayton@kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=trondmy@gmail.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