From: Christoph Hellwig <hch@lst.de>
To: Peng Tao <bergwolf@primarydata.com>
Cc: Linux NFS Mailing List <linux-nfs@vger.kernel.org>
Subject: Re: [PATCH 3/9] pnfs: add return_range method
Date: Thu, 11 Sep 2014 17:36:31 +0200 [thread overview]
Message-ID: <20140911153631.GA8039@lst.de> (raw)
In-Reply-To: <CAKVebiXPaxN5hayCYAdd22vThFk=c+Vf0nHmWAnNssMQzyiLPw@mail.gmail.com>
On Thu, Sep 11, 2014 at 11:30:50PM +0800, Peng Tao wrote:
> It looks dangerous to have extents lurking around without matching
> layout segments. One example is NFS4ERR_EXPIRED and
> NFS4ERR_BAD_STATEID in nfs4_layoutget_done(), client needs to drop all
> layout segments but may keep the layout header, in which case blocks
> layout would still hold all extents at hand.
We never do I/O without a valid layout, but we keep the extents around
because we need to keep state like that it's been written to or has
a commit pending in a single place, and also need to keep it if a layout
goes away temporarily.
I hate the way it has been done in the old client, and tried moving the
extent tracking to a per-layout basis, and spent way too much time on it
but still couldn't get it to work, so I finally gave up. I think we're
between a rock (the idiocy on rfc5663 that it tracks data in extents and not
in layouts) and a hard place (the forgetful Linux client and it's lose layout
coherency) here.
next prev parent reply other threads:[~2014-09-11 15:36 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-10 15:23 pnfs block layout driver fixes V4 Christoph Hellwig
2014-09-10 15:23 ` [PATCH 1/9] pnfs: force a layout commit when encountering busy segments during recall Christoph Hellwig
2014-09-10 15:23 ` [PATCH 2/9] pnfs: add flag to force read-modify-write in ->write_begin Christoph Hellwig
2014-09-10 15:23 ` [PATCH 3/9] pnfs: add return_range method Christoph Hellwig
2014-09-11 13:54 ` Peng Tao
2014-09-11 15:20 ` Christoph Hellwig
2014-09-11 15:30 ` Peng Tao
2014-09-11 15:36 ` Christoph Hellwig [this message]
2014-09-12 2:22 ` Peng Tao
2014-09-13 19:38 ` Christoph Hellwig
2014-09-10 15:23 ` [PATCH 4/9] pnfs/blocklayout: remove read-modify-write handling in bl_write_pagelist Christoph Hellwig
2014-09-10 15:23 ` [PATCH 5/9] pnfs/blocklayout: don't set pages uptodate Christoph Hellwig
2014-09-10 15:23 ` [PATCH 6/9] pnfs/blocklayout: rewrite extent tracking Christoph Hellwig
2014-09-11 14:11 ` Peng Tao
2014-09-11 15:21 ` Christoph Hellwig
2014-09-10 15:23 ` [PATCH 7/9] pnfs/blocklayout: implement the return_range method Christoph Hellwig
2014-09-11 14:16 ` Peng Tao
2014-09-11 15:24 ` Christoph Hellwig
2014-09-10 15:23 ` [PATCH 8/9] pnfs/blocklayout: return layouts on setattr Christoph Hellwig
2014-09-11 14:24 ` Peng Tao
2014-09-11 14:42 ` Boaz Harrosh
2014-09-11 15:25 ` Christoph Hellwig
2014-09-11 15:38 ` Trond Myklebust
2014-09-11 15:48 ` Christoph Hellwig
2014-09-11 16:14 ` Trond Myklebust
2014-09-14 10:55 ` Boaz Harrosh
2014-09-14 13:24 ` Trond Myklebust
2014-09-14 13:51 ` Boaz Harrosh
2014-09-14 14:16 ` Trond Myklebust
2014-09-14 14:28 ` Boaz Harrosh
2014-09-10 15:23 ` [PATCH 9/9] pnfs/blocklayout: allocate separate pages for the layoutcommit payload Christoph Hellwig
-- strict thread matches above, loose matches on Subject: below --
2014-09-09 16:40 pnfs block layout driver fixes V3 Christoph Hellwig
2014-09-09 16:40 ` [PATCH 3/9] pnfs: add return_range method Christoph Hellwig
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=20140911153631.GA8039@lst.de \
--to=hch@lst.de \
--cc=bergwolf@primarydata.com \
--cc=linux-nfs@vger.kernel.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 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).