From: Tom Talpey <tmtalpey@gmail.com>
To: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Steve Dickson <SteveD@redhat.com>,
Linux NFS Mailing List <linux-nfs@vger.kernel.org>
Subject: Re: Link performance over NFS degraded in RHEL5. -- was : Read/Write NFS I/O performance degraded by FLUSH_STABLE page flushing
Date: Fri, 05 Jun 2009 09:58:17 -0400 [thread overview]
Message-ID: <4A292479.4060008@gmail.com> (raw)
In-Reply-To: <1244210096.5410.35.camel@heimdal.trondhjem.org>
On 6/5/2009 9:54 AM, Trond Myklebust wrote:
> On Fri, 2009-06-05 at 09:50 -0400, Tom Talpey wrote:
>> I'm not 100% clear on what you mean by removing it. Since it's
>> a "no_" option, removing it means that "wdelay" becomes the
>> default? That would certainly cause a regression for many.
>
> You've misunderstood. The current default is to _set_ 'wdelay' on all
> exports that do not explicitly turn it off.
Ok, then turning it off will help some and hurt some. There's no
right setting for all. I do agree that fixing the server is the
best solution, not grabbing wildly at its crockful controls.
Tom.
next prev parent reply other threads:[~2009-06-05 13:58 UTC|newest]
Thread overview: 94+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-30 20:12 Read/Write NFS I/O performance degraded by FLUSH_STABLE page flushing Brian R Cowan
2009-04-30 20:25 ` Christoph Hellwig
2009-04-30 20:28 ` Chuck Lever
2009-04-30 20:41 ` Peter Staubach
2009-04-30 21:13 ` Chuck Lever
2009-04-30 21:23 ` Trond Myklebust
2009-05-01 16:39 ` Brian R Cowan
[not found] ` <1241126587.15476.62.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 15:55 ` Brian R Cowan
2009-05-29 16:46 ` Trond Myklebust
[not found] ` <1243615595.7155.48.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 17:25 ` Brian R Cowan
2009-05-29 17:35 ` Trond Myklebust
[not found] ` <1243618500.7155.56.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-30 0:22 ` Greg Banks
[not found] ` <ac442c870905291722x1ec811b2sda997d464898fcda-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-05-30 7:57 ` Christoph Hellwig
2009-06-01 22:30 ` J. Bruce Fields
2009-06-05 14:54 ` Christoph Hellwig
2009-06-05 16:01 ` J. Bruce Fields
2009-06-05 16:12 ` Trond Myklebust
[not found] ` <1244218328.5410.38.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-06-05 19:54 ` J. Bruce Fields
2009-06-05 21:21 ` Trond Myklebust
2009-05-30 12:26 ` Trond Myklebust
[not found] ` <1243686363.5209.16.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-30 12:43 ` Trond Myklebust
2009-05-30 13:02 ` Greg Banks
[not found] ` <ac442c870905300602v6950ec42y5195d2d6ea7dd4c-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2009-06-01 22:30 ` J. Bruce Fields
2009-06-02 15:00 ` Chuck Lever
2009-06-02 17:27 ` Trond Myklebust
[not found] ` <1243963631.4868.124.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-06-02 18:15 ` Chuck Lever
2009-06-03 16:22 ` Carlos Carvalho
2009-06-03 17:10 ` Trond Myklebust
[not found] ` <OFB53BFCCB.0CEC7A7E-ON852575C <1244138698.5203.59.camel@heimdal.trondhjem.org>
2009-06-03 21:28 ` Dean Hildebrand
2009-06-04 2:16 ` Carlos Carvalho
2009-06-04 17:42 ` Brian R Cowan
2009-06-04 18:04 ` Trond Myklebust
2009-06-04 20:43 ` Link performance over NFS degraded in RHEL5. -- was : " Brian R Cowan
2009-06-04 20:57 ` Trond Myklebust
2009-06-04 21:30 ` Brian R Cowan
2009-06-04 21:48 ` Trond Myklebust
2009-06-04 21:07 ` Peter Staubach
2009-06-04 21:39 ` Brian R Cowan
2009-06-05 11:35 ` Steve Dickson
2009-06-05 12:46 ` Trond Myklebust
2009-06-05 13:03 ` Brian R Cowan
2009-06-05 13:05 ` Tom Talpey
[not found] ` <4A29144A.6030405@gmail.com>
2009-06-05 13:30 ` Steve Dickson
2009-06-05 13:52 ` Trond Myklebust
[not found] ` <1244209956.5410.33.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-06-05 13:57 ` Steve Dickson
[not found] ` <4A29243F.8080008-AfCzQyP5zfLQT0dZR+AlfA@public.gmane.org>
2009-06-05 16:05 ` J. Bruce Fields
2009-06-05 16:35 ` Trond Myklebust
[not found] ` <1244219715.5410.40.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-06-15 23:08 ` J. Bruce Fields
2009-06-16 0:21 ` NeilBrown
[not found] ` <99d4545537613ce76040d3655b78bdb7.squirrel-eq65iwfR9nKIECXXMXunQA@public.gmane.org>
2009-06-16 0:33 ` J. Bruce Fields
2009-06-16 0:50 ` NeilBrown
[not found] ` <02ada87c636e1088e9365a3cbea301e7.squirrel-eq65iwfR9nKIECXXMXunQA@public.gmane.org>
2009-06-16 0:55 ` J. Bruce Fields
2009-06-17 16:54 ` J. Bruce Fields
2009-06-17 16:59 ` [PATCH 1/3] nfsd: track last inode only in use_wgather case J. Bruce Fields
2009-06-17 16:59 ` [PATCH 2/3] nfsd: Pull write-gathering code out of nfsd_vfs_write J. Bruce Fields
2009-06-17 16:59 ` [PATCH 3/3] nfsd: minor nfsd_vfs_write cleanup J. Bruce Fields
2009-06-16 0:32 ` Link performance over NFS degraded in RHEL5. -- was : Read/Write NFS I/O performance degraded by FLUSH_STABLE page flushing Trond Myklebust
[not found] ` <1245112324.7470.7.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-06-16 2:02 ` J. Bruce Fields
[not found] ` <4A291D83.1000508@RedHat.com>
2009-06-05 13:50 ` Tom Talpey
2009-06-05 13:54 ` Trond Myklebust
2009-06-05 13:58 ` Tom Talpey [this message]
2009-06-05 13:56 ` Brian R Cowan
2009-06-24 19:54 ` [PATCH] read-modify-write page updating Peter Staubach
2009-06-25 17:13 ` Trond Myklebust
[not found] ` <1245950029.4913.17.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-07-09 13:59 ` Peter Staubach
2009-07-09 14:12 ` [PATCH v2] " Peter Staubach
2009-07-09 15:39 ` Trond Myklebust
[not found] ` <1247153972.5766.15.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-07-10 15:57 ` Peter Staubach
2009-07-10 17:22 ` J. Bruce Fields
2009-08-04 17:52 ` [PATCH v3] " Peter Staubach
2009-08-05 0:50 ` Trond Myklebust
2009-05-29 17:48 ` Read/Write NFS I/O performance degraded by FLUSH_STABLE page flushing Peter Staubach
2009-05-29 18:21 ` Trond Myklebust
2009-05-29 17:01 ` Chuck Lever
2009-05-29 17:38 ` Brian R Cowan
2009-05-29 17:42 ` Trond Myklebust
[not found] ` <1243618968.7155.60.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 17:47 ` Chuck Lever
2009-05-29 18:15 ` Trond Myklebust
2009-05-29 17:51 ` Peter Staubach
2009-05-29 18:25 ` Brian R Cowan
2009-05-29 18:43 ` Trond Myklebust
2009-05-29 17:55 ` Brian R Cowan
2009-05-29 18:07 ` Trond Myklebust
[not found] ` <1243620455.7155.80.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 18:18 ` Brian R Cowan
2009-05-29 18:29 ` Trond Myklebust
[not found] ` <1243621769.7155.97.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 20:09 ` Brian R Cowan
2009-05-29 20:21 ` Trond Myklebust
[not found] ` <1243628519.7155.150.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 21:55 ` Brian R Cowan
2009-05-29 22:03 ` Trond Myklebust
[not found] ` <OFBB9B2C07.CC3D028B-ON852575C5. <1243634634.7155.160.camel@heimdal.trondhjem.org>
[not found] ` <1243634634.7155.160.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 22:20 ` Brian R Cowan
2009-05-29 22:36 ` Trond Myklebust
[not found] ` <OF061E0258.9581352B-ON852575C <1243636593.7155.188.camel@heimdal.trondhjem.org>
[not found] ` <1243636593.7155.188.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org>
2009-05-29 23:02 ` Brian R Cowan
2009-05-29 23:13 ` Trond Myklebust
2009-05-29 17:57 ` 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=4A292479.4060008@gmail.com \
--to=tmtalpey@gmail.com \
--cc=SteveD@redhat.com \
--cc=linux-nfs@vger.kernel.org \
--cc=trond.myklebust@fys.uio.no \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.