From: Christoph Hellwig <hch@lst.de>
To: Peng Tao <bergwolf@gmail.com>
Cc: Trond Myklebust <trond.myklebust@primarydata.com>,
linuxnfs <linux-nfs@vger.kernel.org>,
"faibish, sorin" <faibish_sorin@emc.com>
Subject: Re: [PATCH 08/17] pnfs/blocklayout: reject pnfs blocksize larger than page size
Date: Thu, 7 Aug 2014 18:20:59 +0200 [thread overview]
Message-ID: <20140807162059.GA23188@lst.de> (raw)
In-Reply-To: <CA+a=Yy4YmBzYFUTHb72hyZ1--N_w6YDZhmbFEAU11YTt+1qxOg@mail.gmail.com>
On Thu, Aug 07, 2014 at 09:43:09PM +0800, Peng Tao wrote:
> we can't assume all pages written back have their pari pages (for 8K
> block size e.g.) read in read_pagelists(). A page can also be read in
> via MDS read. So what we need is a hook into nfs_readpage to read or
> zero additional pages. But we might not even have a layout there.
We can't assume the page is there for writeback either, what all this
mess exists for. That's why we really shouldn't even attempt to support
a a block size large than the page size, and that's also why the local
Linux filesystems strictly refuse to support it. If you want to hack
around it you will run into problems in either case.
I also don't really see why a server would insist on this large block
size, there really isn't any major benefit in doing that today (aka the last 20
years) now that we have extent based filesystems.
next prev parent reply other threads:[~2014-08-07 16:21 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-07 7:23 pnfs block layout driver fixes Christoph Hellwig
2014-08-07 7:23 ` [PATCH 01/17] nfs: cap request size to fit a kmalloced page array Christoph Hellwig
2014-08-07 7:23 ` [PATCH 02/17] pnfs: do not pass uninitialized lsegs to ->free_lseg Christoph Hellwig
2014-08-07 7:23 ` [PATCH 03/17] pnfs: force a layout commit when encountering busy segments during recall Christoph Hellwig
2014-08-07 7:23 ` [PATCH 04/17] pnfs: don't check sequence on new stateids in layoutget Christoph Hellwig
2014-08-07 7:23 ` [PATCH 05/17] pnfs: add flag to force read-modify-write in ->write_begin Christoph Hellwig
2014-08-07 7:23 ` [PATCH 06/17] pnfs: add return_range method Christoph Hellwig
2014-08-07 7:23 ` [PATCH 07/17] pnfs: allow splicing pre-encoded pages into the layoutcommit args Christoph Hellwig
2014-08-07 7:23 ` [PATCH 08/17] pnfs/blocklayout: reject pnfs blocksize larger than page size Christoph Hellwig
2014-08-07 10:43 ` Peng Tao
2014-08-07 11:25 ` Christoph Hellwig
2014-08-07 11:51 ` Peng Tao
2014-08-07 12:10 ` Christoph Hellwig
2014-08-07 13:43 ` Peng Tao
2014-08-07 16:20 ` Christoph Hellwig [this message]
2014-08-08 10:28 ` Peng Tao
2014-08-07 12:56 ` faibish, sorin
2014-08-07 13:45 ` Peng Tao
2014-08-07 16:10 ` Christoph Hellwig
2014-08-07 16:18 ` faibish, sorin
2014-08-07 13:13 ` Steve Dickson
2014-08-07 13:17 ` Steve Dickson
2014-08-07 7:23 ` [PATCH 09/17] pnfs/blocklayout: improve GETDEVICEINFO error reporting Christoph Hellwig
2014-08-07 7:23 ` [PATCH 10/17] pnfs/blocklayout: plug block queues Christoph Hellwig
2014-08-07 7:23 ` [PATCH 11/17] pnfs/blocklayout: correctly decrement extent length Christoph Hellwig
2014-08-07 7:23 ` [PATCH 12/17] pnfs/blocklayout: remove read-modify-write handling in bl_write_pagelist Christoph Hellwig
2014-08-07 7:23 ` [PATCH 13/17] pnfs/blocklayout: don't set pages uptodate Christoph Hellwig
2014-08-07 7:23 ` [PATCH 14/17] pnfs/blocklayout: rewrite extent tracking Christoph Hellwig
2014-08-07 7:23 ` [PATCH 15/17] pnfs/blocklayout: implement the return_range method Christoph Hellwig
2014-08-07 7:23 ` [PATCH 16/17] pnfs/blocklayout: return layouts on setattr Christoph Hellwig
2014-08-07 7:23 ` [PATCH 17/17] pnfs/blocklayout: allocate separate pages for the layoutcommit payload Christoph Hellwig
2014-08-07 11:05 ` Peng Tao
2014-08-07 11:27 ` Christoph Hellwig
2014-08-07 11:57 ` Peng Tao
2014-08-20 18:43 ` pnfs block layout driver fixes Jeff Layton
2014-08-20 22:14 ` Christoph Hellwig
2014-09-07 15:39 ` Christoph Hellwig
2014-09-07 16:44 ` 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=20140807162059.GA23188@lst.de \
--to=hch@lst.de \
--cc=bergwolf@gmail.com \
--cc=faibish_sorin@emc.com \
--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).