public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Andi Kleen <ak@suse.de>
To: Parag Warudkar <kernel-stuff@comcast.net>
Cc: Ray Fucillo <fucillo@intersystems.com>, linux-kernel@vger.kernel.org
Subject: Re: process creation time increases linearly with shmem
Date: Thu, 25 Aug 2005 16:22:08 +0200	[thread overview]
Message-ID: <200508251622.08456.ak@suse.de> (raw)
In-Reply-To: <082520051405.5272.430DD0420003F49F00001498220076139400009A9B9CD3040A029D0A05@comcast.net>


> Would it be worth trying to do something like this?

Maybe. Shouldn't be very hard though - you just need to check if the VMA is 
backed by an object and if yes don't call copy_page_range for it.

I think it just needs (untested) 

Index: linux-2.6.13-rc5-misc/kernel/fork.c
===================================================================
--- linux-2.6.13-rc5-misc.orig/kernel/fork.c
+++ linux-2.6.13-rc5-misc/kernel/fork.c
@@ -265,7 +265,8 @@ static inline int dup_mmap(struct mm_str
 		rb_parent = &tmp->vm_rb;
 
 		mm->map_count++;
-		retval = copy_page_range(mm, current->mm, tmp);
+		if (!file && !is_vm_hugetlb_page(vma))
+			retval = copy_page_range(mm, current->mm, tmp);
 		spin_unlock(&mm->page_table_lock);
 
 		if (tmp->vm_ops && tmp->vm_ops->open)

But I'm not sure it's a good idea in all cases. Would need a lot of 
benchmarking  at least.

-Andi

  reply	other threads:[~2005-08-25 14:22 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-08-25 14:05 process creation time increases linearly with shmem Parag Warudkar
2005-08-25 14:22 ` Andi Kleen [this message]
2005-08-25 14:35   ` Nick Piggin
2005-08-25 14:47   ` Parag Warudkar
2005-08-25 15:56     ` Andi Kleen
  -- strict thread matches above, loose matches on Subject: below --
2005-12-14 14:07 Brice Oliver
2005-12-14 16:21 ` Hugh Dickins
2005-08-24 18:43 Ray Fucillo
2005-08-25  0:14 ` Nick Piggin
2005-08-25 13:07   ` Ray Fucillo
2005-08-25 13:13     ` Andi Kleen
2005-08-25 14:28     ` Nick Piggin
2005-08-25 17:31   ` Rik van Riel
2005-08-26  1:26     ` Nick Piggin
2005-08-26  1:50       ` Rik van Riel
2005-08-26  3:56       ` Linus Torvalds
2005-08-26 11:49         ` Hugh Dickins
2005-08-26 14:26           ` Nick Piggin
2005-08-26 17:00             ` Ray Fucillo
2005-08-26 17:53               ` Rik van Riel
2005-08-26 18:20                 ` Ross Biro
2005-08-26 18:56                   ` Hugh Dickins
     [not found]           ` <8783be660508260915524e2b1e@mail.gmail.com>
2005-08-26 16:38             ` Hugh Dickins
2005-08-26 16:43               ` Ross Biro
2005-08-26 18:07           ` Linus Torvalds
2005-08-26 18:41             ` Hugh Dickins
2005-08-26 22:55               ` Linus Torvalds
2005-08-26 23:10               ` Rik van Riel
2005-08-26 23:23                 ` Linus Torvalds
2005-08-27 15:05                   ` Nick Piggin
2005-08-28  4:26                     ` Hugh Dickins
2005-08-28  6:49                       ` Nick Piggin
2005-08-29 23:33                         ` Ray Fucillo
2005-08-30  0:29                           ` Nick Piggin
2005-08-30  1:03                             ` Linus Torvalds
2005-08-30  0:34                           ` Linus Torvalds

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=200508251622.08456.ak@suse.de \
    --to=ak@suse.de \
    --cc=fucillo@intersystems.com \
    --cc=kernel-stuff@comcast.net \
    --cc=linux-kernel@vger.kernel.org \
    /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