linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: chuck.lever@oracle.com
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
	Andrew Morton <akpm@osdl.org>,
	Trond Myklebust <Trond.Myklebust@netapp.com>,
	Steve Dickson <steved@redhat.com>,
	linux-mm@kvack.org
Subject: Re: Checking page_count(page) in invalidate_complete_page
Date: Fri, 29 Sep 2006 23:17:17 +0200	[thread overview]
Message-ID: <1159564637.13651.44.camel@lappy> (raw)
In-Reply-To: <451D89E7.7020307@oracle.com>

On Fri, 2006-09-29 at 17:02 -0400, Chuck Lever wrote:
> Peter Zijlstra wrote:
> > On Fri, 2006-09-29 at 16:34 -0400, Chuck Lever wrote:
> > 
> >> One option that hasn't been entertained is to remove the "batched LRU
> >> add" logic all together.  Just gut lru_cache_add -- it should send
> >> pages immediately to be added to the LRU list.  This is a bit slower, 
> >> but it fixes the invalidation problems, and makes the icky 
> >> lru_add_drain_all() a no-op.
> > 
> > That would bring some larger machines to their knees contending on
> > zone->lock.
> > 
> 
> Versus calling lru_add_drain_all() every time a file system tries to 
> invalidate an inode's cached pages?

Surely not all filesystems are that broken? From what I gather from this
discussion its only NFS.

But even then, you can run quite a few workloads without invalidating
inodes often.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2006-09-29 21:17 UTC|newest]

Thread overview: 56+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <4518333E.2060101@oracle.com>
2006-09-25 21:10 ` Andrew Morton
2006-09-25 22:30   ` Chuck Lever
2006-09-25 22:53     ` Andrew Morton
2006-09-25 22:57     ` Steve Dickson
2006-09-25 23:14       ` Nick Piggin
2006-09-25 22:40   ` Chuck Lever
2006-09-25 23:02     ` Andrew Morton
2006-09-25 22:50   ` Steve Dickson
2006-09-25 22:51   ` Nick Piggin
2006-09-25 23:14     ` Chuck Lever
2006-09-25 23:21       ` Nick Piggin
2006-09-26  0:01         ` Chuck Lever
2006-09-26  0:13           ` Nick Piggin
2006-09-26  1:33             ` Chuck Lever
2006-09-26  1:48               ` Nick Piggin
2006-09-28 16:26                 ` Chuck Lever
2006-09-28 16:36                   ` Andrew Morton
2006-09-28 16:40                     ` Andrew Morton
2006-09-28 16:42                       ` Chuck Lever
2006-09-28 17:03                         ` Andrew Morton
2006-09-28 17:09                           ` Chuck Lever
2006-09-29  0:37                             ` Nick Piggin
2006-09-29 20:34                               ` Chuck Lever
2006-09-29 20:45                                 ` Peter Zijlstra
2006-09-29 21:02                                   ` Chuck Lever
2006-09-29 21:17                                     ` Peter Zijlstra [this message]
2006-09-29 21:44                                       ` Andrew Morton
2006-09-29 21:48                                         ` Chuck Lever
2006-09-29 22:29                                           ` Andrew Morton
2006-09-29 23:05                                             ` Chuck Lever
2006-10-01  4:21                                             ` Chuck Lever
2006-10-02 12:01                                               ` Steve Dickson
2006-10-02 13:25                                                 ` Trond Myklebust
2006-10-02 16:57                                                   ` Andrew Morton
2006-10-02 17:02                                                     ` Steve Dickson
2006-10-02 18:20                                                       ` Andrew Morton
2006-10-02 19:02                                                         ` Steve Dickson
2006-10-03  2:14                                                           ` Chuck Lever
2006-10-03  4:18                                                             ` Trond Myklebust
2006-10-03  4:24                                                               ` Andrew Morton
2006-10-03 18:50                                                               ` Chuck Lever
2006-10-03 19:10                                                                 ` Trond Myklebust
2006-10-03 19:21                                                                   ` Chuck Lever
2006-10-03 21:37                                                                   ` Andrew Morton
2006-10-04 19:29                                                                     ` Chuck Lever
2006-10-04 19:43                                                                       ` Andrew Morton
2006-10-04 19:53                                                                         ` Steve Dickson
2006-09-28 16:41                     ` Chuck Lever
2006-09-26  6:25               ` Nick Piggin
2006-09-26 13:12                 ` Chuck Lever
2006-09-27  4:47                   ` Nick Piggin
2006-09-27  8:25                     ` Andrew Morton
2006-09-27  8:39                       ` Nick Piggin
2006-09-27 16:03                         ` Andrew Morton
2006-09-27 15:54                     ` Chuck Lever
2006-09-25 22:56   ` 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=1159564637.13651.44.camel@lappy \
    --to=a.p.zijlstra@chello.nl \
    --cc=Trond.Myklebust@netapp.com \
    --cc=akpm@osdl.org \
    --cc=chuck.lever@oracle.com \
    --cc=linux-mm@kvack.org \
    --cc=nickpiggin@yahoo.com.au \
    --cc=steved@redhat.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