From: Trond Myklebust <trond.myklebust@fys.uio.no>
To: Aaron Straus <aaron@merfinllc.com>
Cc: Hans-Peter Jansen <hpj@urpla.net>,
linux-kernel@vger.kernel.org,
Chuck Lever <chuck.lever@oracle.com>, Neil Brown <neilb@suse.de>,
Linux NFS Mailing List <linux-nfs@vger.kernel.org>
Subject: Re: [NFS] blocks of zeros (NULLs) in NFS files in kernels >= 2.6.20
Date: Mon, 22 Sep 2008 13:29:01 -0400 [thread overview]
Message-ID: <1222104541.7615.23.camel@localhost> (raw)
In-Reply-To: <20080922170414.GC12483@merfinllc.com>
[-- Attachment #1: Type: text/plain, Size: 1122 bytes --]
On Mon, 2008-09-22 at 10:04 -0700, Aaron Straus wrote:
> Here is the crux. It was possible previously but unlikely e.g. our app
> never saw this behavior. The new writeout semantics causes visible
> holes in files often.
>
> Anyway, I agree the new writeout semantics are allowed and possibly
> saner than the previous writeout path. The problem is that it is
> __annoying__ for this use case (log files).
There is always the option of using syslog.
> I'm not sure if there is an easy solution. We want the VM to writeout
> the address space in order. Maybe we can start the scan for dirty
> pages at the last page we wrote out i.e. page 0 in the example above?
You can never guarantee that in a multi-threaded environment.
Two threads may, for instance, force 2 competing fsync() calls: that
again may cause out-of-order writes.
...and even if the client doesn't reorder the writes, the _server_ may
do it, since multiple nfsd threads may race when processing writes to
the same file.
Anyway, the patch to force a single threaded nfs client to write out the
data in order is trivial. See attachment...
Trond
[-- Attachment #2: linux-2.6.27-ordered_writes.dif --]
[-- Type: message/rfc822, Size: 749 bytes --]
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Subject: No Subject
Date:
Message-ID: <1222104509.7615.22.camel@localhost>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
fs/nfs/write.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 3229e21..eb6b211 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1428,7 +1428,8 @@ static int nfs_write_mapping(struct address_space *mapping, int how)
.sync_mode = WB_SYNC_NONE,
.nr_to_write = LONG_MAX,
.for_writepages = 1,
- .range_cyclic = 1,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
};
int ret;
next prev parent reply other threads:[~2008-09-22 17:29 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-09-05 19:19 blocks of zeros (NULLs) in NFS files in kernels >= 2.6.20 Aaron Straus
2008-09-05 19:56 ` [NFS] " Chuck Lever
2008-09-05 20:04 ` Aaron Straus
2008-09-05 20:36 ` Bernd Eckenfels
2008-09-05 20:36 ` Chuck Lever
2008-09-05 22:14 ` Aaron Straus
2008-09-06 0:03 ` Aaron Straus
2008-09-08 19:02 ` Aaron Straus
2008-09-08 21:15 ` Chuck Lever
2008-09-08 22:02 ` Aaron Straus
2008-09-09 19:46 ` Aaron Straus
2008-09-11 16:55 ` Chuck Lever
2008-09-11 17:19 ` Aaron Straus
2008-09-11 17:48 ` Chuck Lever
2008-09-11 18:49 ` Aaron Straus
2008-09-22 16:05 ` Hans-Peter Jansen
2008-09-22 16:35 ` Trond Myklebust
2008-09-22 17:04 ` Aaron Straus
2008-09-22 17:26 ` Chuck Lever
2008-09-22 17:37 ` Aaron Straus
2008-09-22 17:29 ` Trond Myklebust [this message]
2008-09-22 17:45 ` Aaron Straus
2008-09-22 18:43 ` Aaron Straus
2008-09-22 18:45 ` Hans-Peter Jansen
2008-09-22 18:45 ` Hans-Peter Jansen
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=1222104541.7615.23.camel@localhost \
--to=trond.myklebust@fys.uio.no \
--cc=aaron@merfinllc.com \
--cc=chuck.lever@oracle.com \
--cc=hpj@urpla.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neilb@suse.de \
/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).