From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Andrew Morton <akpm@linux-foundation.org>,
Andrea Arcangeli <aarcange@redhat.com>,
linux-mm@kvack.org
Cc: Andi Kleen <ak@linux.intel.com>,
"H. Peter Anvin" <hpa@linux.intel.com>,
linux-kernel@vger.kernel.org,
"Kirill A. Shutemov" <kirill@shutemov.name>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCH, RFC 0/9] Introduce huge zero page
Date: Thu, 9 Aug 2012 12:08:11 +0300 [thread overview]
Message-ID: <1344503300-9507-1-git-send-email-kirill.shutemov@linux.intel.com> (raw)
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
During testing I noticed big (up to 2.5 times) memory consumption overhead
on some workloads (e.g. ft.A from NPB) if THP is enabled.
The main reason for that big difference is lacking zero page in THP case.
We have to allocate a real page on read page fault.
A program to demonstrate the issue:
#include <assert.h>
#include <stdlib.h>
#include <unistd.h>
#define MB 1024*1024
int main(int argc, char **argv)
{
char *p;
int i;
posix_memalign((void **)&p, 2 * MB, 200 * MB);
for (i = 0; i < 200 * MB; i+= 4096)
assert(p[i] == 0);
pause();
return 0;
}
With thp-never RSS is about 400k, but with thp-always it's 200M.
After the patcheset thp-always RSS is 400k too.
H. Peter Anvin proposed to use a "virtual huge zero page" -- a pmd table
with all pte set to 4k zero page. I haven't tried that approach and I'm
not sure if it's good idea (cache vs. tlb trashing). And I guess it will
require more code to handle.
For now, I just allocate 2M page and use it.
Kirill A. Shutemov (9):
thp: huge zero page: basic preparation
thp: zap_huge_pmd(): zap huge zero pmd
thp: copy_huge_pmd(): copy huge zero page
thp: do_huge_pmd_wp_page(): handle huge zero page
thp: change_huge_pmd(): keep huge zero page write-protected
thp: add address parameter to split_huge_page_pmd()
thp: implement splitting pmd for huge zero page
thp: setup huge zero page on non-write page fault
thp: lazy huge zero page allocation
Documentation/vm/transhuge.txt | 4 +-
arch/x86/kernel/vm86_32.c | 2 +-
fs/proc/task_mmu.c | 2 +-
include/linux/huge_mm.h | 10 +-
include/linux/mm.h | 8 ++
mm/huge_memory.c | 228 +++++++++++++++++++++++++++++++++++-----
mm/memory.c | 11 +--
mm/mempolicy.c | 2 +-
mm/mprotect.c | 2 +-
mm/mremap.c | 3 +-
mm/pagewalk.c | 2 +-
11 files changed, 226 insertions(+), 48 deletions(-)
--
1.7.7.6
--
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>
next reply other threads:[~2012-08-09 9:08 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-09 9:08 Kirill A. Shutemov [this message]
2012-08-09 9:08 ` [PATCH, RFC 1/9] thp: huge zero page: basic preparation Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 2/9] thp: zap_huge_pmd(): zap huge zero pmd Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 3/9] thp: copy_huge_pmd(): copy huge zero page Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 4/9] thp: do_huge_pmd_wp_page(): handle " Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 5/9] thp: change_huge_pmd(): keep huge zero page write-protected Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 6/9] thp: add address parameter to split_huge_page_pmd() Kirill A. Shutemov
2012-08-16 19:42 ` Andrea Arcangeli
2012-08-17 7:49 ` Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 7/9] thp: implement splitting pmd for huge zero page Kirill A. Shutemov
2012-08-16 19:27 ` Andrea Arcangeli
2012-08-17 8:12 ` Kirill A. Shutemov
2012-08-17 16:33 ` Andrea Arcangeli
2012-08-31 14:06 ` Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 8/9] thp: setup huge zero page on non-write page fault Kirill A. Shutemov
2012-08-09 9:08 ` [PATCH, RFC 9/9] thp: lazy huge zero page allocation Kirill A. Shutemov
2012-08-10 3:49 ` [PATCH, RFC 0/9] Introduce huge zero page Wanpeng Li
2012-08-10 3:49 ` Wanpeng Li
2012-08-10 10:33 ` Kirill A. Shutemov
2012-08-11 1:10 ` Wanpeng Li
2012-08-11 1:10 ` Wanpeng Li
2012-08-16 19:20 ` Andrew Morton
2012-08-16 19:40 ` Andrea Arcangeli
2012-08-16 23:08 ` H. Peter Anvin
2012-08-16 23:12 ` Andi Kleen
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=1344503300-9507-1-git-send-email-kirill.shutemov@linux.intel.com \
--to=kirill.shutemov@linux.intel.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=hpa@linux.intel.com \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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;
as well as URLs for NNTP newsgroup(s).