From: Jim Rees <rees@umich.edu>
To: Chuck Lever <chuck.lever@oracle.com>
Cc: Jeff Layton <jlayton@redhat.com>, Harshula <harshula@redhat.com>,
Steve Dickson <SteveD@redhat.com>, NeilBrown <neilb@suse.de>,
linux-nfs@vger.kernel.org
Subject: Re: "Using NFS over UDP on high-speed links such as Gigabit can cause silent data corruption."
Date: Tue, 28 Feb 2012 10:09:23 -0500 [thread overview]
Message-ID: <20120228150923.GA13432@umich.edu> (raw)
In-Reply-To: <BC3988C4-CC1A-4DFA-89AE-7046C674A873@oracle.com>
Chuck Lever wrote:
As above, most other uses of UDP do not involve large packets. But I
wonder if it is appropriate for us to suggest a change in the default
setting.
A minute is certainly too long. Just a guess, but 4 seconds seems
appropriate to me. That's good enough for gigabit ethernet. Anyone running
fragmented 10G networks gets what they deserve.
Yes, you can have more than four seconds of data in flight at moderate
speeds, but unless something is terribly wrong the fragments should come in
very close together.
next prev parent reply other threads:[~2012-02-28 15:09 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-02-28 5:22 "Using NFS over UDP on high-speed links such as Gigabit can cause silent data corruption." Harshula
2012-02-28 11:52 ` Jeff Layton
2012-02-28 12:32 ` Harshula
2012-02-28 12:41 ` Jeff Layton
2012-03-05 1:56 ` Harshula
2012-02-28 12:46 ` Jim Rees
2012-02-28 12:57 ` Jeff Layton
2012-02-28 14:35 ` Chuck Lever
2012-02-28 15:09 ` Jim Rees [this message]
2012-02-28 15:50 ` Chuck Lever
2012-03-05 2:17 ` Harshula
2012-03-05 15:08 ` Chuck Lever
2012-05-09 0:59 ` [PATCH] nfs-utils: Add a warning to the nfs manpage regarding using NFS over UDP on high-speed links Harshula Jayasuriya
2012-05-09 18:14 ` Steve Dickson
2012-05-09 18:38 ` Peter Staubach
2012-05-09 22:16 ` Harshula
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=20120228150923.GA13432@umich.edu \
--to=rees@umich.edu \
--cc=SteveD@redhat.com \
--cc=chuck.lever@oracle.com \
--cc=harshula@redhat.com \
--cc=jlayton@redhat.com \
--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).