public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Rik van Riel <riel@redhat.com>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	linux-mm <linux-mm@kvack.org>, shak <dshaks@redhat.com>,
	jakub@redhat.com, drepper@redhat.com
Subject: Re: [PATCH] lazy freeing of memory through MADV_FREE
Date: Mon, 23 Apr 2007 06:44:45 -0400	[thread overview]
Message-ID: <462C8E1D.8000706@redhat.com> (raw)
In-Reply-To: <462C8BFF.2050405@yahoo.com.au>

[-- Attachment #1: Type: text/plain, Size: 1847 bytes --]

Use TLB batching for MADV_FREE.  Adds another 10-15% extra performance
to the MySQL sysbench results on my quad core system.

Signed-off-by: Rik van Riel <riel@redhat.com>
---

Nick Piggin wrote:

>> 3) because of this, we can treat any such accesses as
>>    happening simultaneously with the MADV_FREE and
>>    as illegal, aka undefined behaviour territory and
>>    we do not need to worry about them
> 
> Yes, but I'm wondering if it is legal in all architectures.

It's similar to trying to access memory during an munmap.

You may be able to for a short time, but it'll come back to
haunt you.

>> 4) because we flush the tlb before releasing the page
>>    table lock, other CPUs cannot remove this page from
>>    the address space - they will block on the page
>>    table lock before looking at this pte
> 
> We don't when the ptl is split.

Even then we do.  Each invocation of zap_pte_range() only touches
one page table page, and it flushes the TLB before releasing the
page table lock.

> What the tlb flush used to be able to assume is that the page
> has been removed from the pagetables when they are put in the
> tlb flush batch.

All the tlb flush code seems to assume is that the tlb entries
should be invalidated.

> I'm not saying there is any bugs, but just suggesting there
> might be.

Jakub found a potential bug, in that I did not use an atomic
operation to clear the page table entries.  I've attached a
new patch which simply uses ptep_test_and_clear_dirty/young
to get rid of the dirty and accessed bits.

It uses the same atomic accesses we use elsewhere in the VM
and the code is a line shorter than before.

Andrew, please use this one.

-- 
Politics is the struggle between those who want to make their country
the best in the world, and those who believe it already is.  Each group
calls the other unpatriotic.

[-- Attachment #2: linux-2.6-madv_free-lazytlb.patch --]
[-- Type: text/x-patch, Size: 697 bytes --]

--- linux-2.6.20.x86_64/mm/memory.c.orig	2007-04-23 02:48:36.000000000 -0400
+++ linux-2.6.20.x86_64/mm/memory.c	2007-04-23 02:54:42.000000000 -0400
@@ -677,11 +677,14 @@ static unsigned long zap_pte_range(struc
 						remove_exclusive_swap_page(page);
 						unlock_page(page);
 					}
-					ptep_clear_flush_dirty(vma, addr, pte);
-					ptep_clear_flush_young(vma, addr, pte);
+					ptep_test_and_clear_dirty(vma, addr, pte);
+					ptep_test_and_clear_young(vma, addr, pte);
 					SetPageLazyFree(page);
 					if (PageActive(page))
 						deactivate_tail_page(page);
+					/* tlb_remove_page frees it again */
+					get_page(page);
+					tlb_remove_page(tlb, page);
 					continue;
 				}
 			}

  reply	other threads:[~2007-04-23 10:45 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-04-17  7:15 [PATCH] lazy freeing of memory through MADV_FREE Rik van Riel
2007-04-19 21:15 ` [PATCH] lazy freeing of memory through MADV_FREE 2/2 Rik van Riel
2007-04-20 21:03   ` Andrew Morton
2007-04-20 21:24     ` Ulrich Drepper
2007-04-21  7:37       ` Hugh Dickins
2007-04-21 16:32         ` Ulrich Drepper
2007-04-20 20:57 ` [PATCH] lazy freeing of memory through MADV_FREE Andrew Morton
2007-04-20 21:38   ` Rik van Riel
2007-04-20 22:06     ` Andrew Morton
2007-04-20 23:52       ` Rik van Riel
2007-04-21  0:48         ` Eric Dumazet
2007-04-21  3:58           ` Rik van Riel
2007-04-21  7:12         ` Jakub Jelinek
2007-04-23  4:36           ` Nick Piggin
2007-04-22  2:36         ` Nick Piggin
2007-04-22  2:50           ` Nick Piggin
2007-04-22  6:31           ` Rik van Riel
2007-04-23  0:16             ` Nick Piggin
2007-04-23  3:53               ` Rik van Riel
2007-04-23  3:58                 ` Nick Piggin
2007-04-23 10:07                   ` Nick Piggin
2007-04-23 10:12                     ` Rik van Riel
2007-04-23  3:59                 ` Rik van Riel
2007-04-23  9:20                   ` Rik van Riel
2007-04-23 10:21                     ` Nick Piggin
2007-04-23 10:31                       ` Rik van Riel
2007-04-23 10:35                         ` Nick Piggin
2007-04-23 10:44                           ` Rik van Riel [this message]
2007-04-24  1:15                             ` Nick Piggin
2007-04-24  1:58                               ` Rik van Riel
2007-04-24  2:16                                 ` Nick Piggin
2007-04-24  4:42                                 ` Paul Mackerras
2007-04-24  5:13                                   ` Rik van Riel
2007-04-24  2:53                           ` Rik van Riel
2007-04-24  3:08                             ` Andrew Morton
2007-04-23 10:44                       ` Jakub Jelinek
2007-04-23 11:45                     ` Rik van Riel
2007-04-23  4:28           ` Rik van Riel
2007-04-21  7:24     ` Hugh Dickins
2007-04-21 18:06       ` Rik van Riel
2007-04-22  8:18 ` Andrew Morton
2007-04-22  9:16   ` Christoph Hellwig
2007-04-22 16:55     ` Ulrich Drepper

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=462C8E1D.8000706@redhat.com \
    --to=riel@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=drepper@redhat.com \
    --cc=dshaks@redhat.com \
    --cc=jakub@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nickpiggin@yahoo.com.au \
    /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