linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Chuck Lever <chuck.lever@oracle.com>
To: Trond Myklebust <trond.myklebust@primarydata.com>
Cc: Andrew Martin <amartin@xes-inc.com>, Jim Rees <rees@umich.edu>,
	Neil Brown <neilb@suse.de>,
	Linux NFS Mailing List <linux-nfs@vger.kernel.org>
Subject: Re: Optimal NFS mount options to safely allow interrupts and timeouts on newer kernels
Date: Thu, 6 Mar 2014 10:59:35 -0500	[thread overview]
Message-ID: <17607EE5-614A-4B13-B5E7-0D1344A30C7F@oracle.com> (raw)
In-Reply-To: <5B1102FE-8521-4BEF-8A2B-CE17EC32777F@primarydata.com>


On Mar 6, 2014, at 10:33 AM, Trond Myklebust <trond.myklebust@primarydata.com> wrote:

> 
> On Mar 6, 2014, at 10:26, Chuck Lever <chuck.lever@oracle.com> wrote:
> 
>> 
>> On Mar 6, 2014, at 7:34 AM, Jim Rees <rees@umich.edu> wrote:
>> 
>>> Given this is apache, I think if I were doing this I'd use ro,soft,intr,tcp
>>> and not try to write anything to nfs.
>> 
>> I agree. A static web page workload should be read-mostly or read-only. The (small) corruption risk with “ro,soft" is that an interrupted read would cause the client to cache incomplete data.
> 
> What? How? If that were the case, we would have a blatant read bug. As I read the current code, _any_ error will cause the page to not be marked as up to date.

Agree, the design is sound. But we don’t test this use case very much, so I don’t have 100% confidence that there are no bugs.

--
Chuck Lever
chuck[dot]lever[at]oracle[dot]com




  reply	other threads:[~2014-03-06 15:59 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <1696396609.119284.1394040541217.JavaMail.zimbra@xes-inc.com>
2014-03-05 17:45 ` Optimal NFS mount options to safely allow interrupts and timeouts on newer kernels Andrew Martin
2014-03-05 20:11   ` Jim Rees
2014-03-05 20:41     ` Andrew Martin
2014-03-05 21:11       ` Jim Rees
2014-03-06  3:34         ` NeilBrown
2014-03-06  3:47           ` Jim Rees
2014-03-06  4:37             ` NeilBrown
2014-03-05 20:15   ` Brian Hawley
2014-03-05 20:54     ` Chuck Lever
2014-03-06  9:37     ` Ric Wheeler
2014-03-06  3:50   ` NeilBrown
2014-03-06  5:03     ` Andrew Martin
2014-03-06  5:37       ` NeilBrown
2014-03-06  5:47         ` Brian Hawley
2014-03-06 15:30           ` Andrew Martin
2014-03-06 16:22             ` Jim Rees
2014-03-06 16:43               ` Andrew Martin
2014-03-06 17:36                 ` Jim Rees
2014-03-06 18:26                   ` Trond Myklebust
2014-03-06 18:35                   ` Andrew Martin
2014-03-06 18:48                     ` Jim Rees
2014-03-06 19:02                       ` Trond Myklebust
2014-03-06 18:50                     ` Trond Myklebust
2014-03-06 19:46                       ` Andrew Martin
2014-03-06 19:52                         ` Trond Myklebust
2014-03-06 20:45                           ` Andrew Martin
2014-03-06 21:01                             ` Trond Myklebust
2014-03-18 21:50                               ` Andrew Martin
2014-03-18 22:27                                 ` Trond Myklebust
2014-03-28 22:00                                   ` Dr Fields James Bruce
2014-04-04 18:15                                     ` Andrew Martin
2014-03-06 19:00                 ` Brian Hawley
2014-03-06 19:06                   ` Trond Myklebust
2014-03-06 19:14                     ` Brian Hawley
2014-03-06 19:26                       ` Trond Myklebust
2014-03-06 19:33                         ` Brian Hawley
2014-03-06 19:47                           ` Trond Myklebust
2014-03-06 19:56                             ` Brian Hawley
2014-03-06 20:31                               ` Trond Myklebust
2014-03-06 20:34                                 ` Brian Hawley
2014-03-06 20:41                                   ` Trond Myklebust
2014-03-06 19:29                       ` Ric Wheeler
2014-03-06 19:38                         ` Brian Hawley
2014-04-04 18:15                           ` Andrew Martin
2014-03-06 18:56             ` Brian Hawley
2014-03-06 12:34       ` Jim Rees
2014-03-06 15:26         ` Chuck Lever
2014-03-06 15:33           ` Trond Myklebust
2014-03-06 15:59             ` Chuck Lever [this message]
2014-03-06 16:02               ` Trond Myklebust
2014-03-06 16:13                 ` Chuck Lever
2014-03-06 16:16                   ` Trond Myklebust
2014-03-06 16:45                     ` Chuck Lever
2014-03-06 17:47                       ` Trond Myklebust
2014-03-06 20:38                         ` Chuck Lever

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=17607EE5-614A-4B13-B5E7-0D1344A30C7F@oracle.com \
    --to=chuck.lever@oracle.com \
    --cc=amartin@xes-inc.com \
    --cc=linux-nfs@vger.kernel.org \
    --cc=neilb@suse.de \
    --cc=rees@umich.edu \
    --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).