From: Alex Thorlton <athorlton@sgi.com>
To: linux-kernel@vger.kernel.org
Cc: Alex Thorlton <athorlton@sgi.com>, Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
Rik van Riel <riel@redhat.com>,
Johannes Weiner <hannes@cmpxchg.org>,
"Eric W . Biederman" <ebiederm@xmission.com>,
Sedat Dilek <sedat.dilek@gmail.com>,
Frederic Weisbecker <fweisbec@gmail.com>,
Dave Jones <davej@redhat.com>,
Michael Kerrisk <mtk.manpages@gmail.com>,
"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
David Howells <dhowells@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Al Viro <viro@zeniv.linux.org.uk>,
Oleg Nesterov <oleg@redhat.com>,
Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
Kees Cook <keescook@chromium.org>, Robin Holt <holt@sgi.com>
Subject: [PATCH 0/8] Re: [PATCH] Add per-process flag to control thp
Date: Fri, 16 Aug 2013 09:33:56 -0500 [thread overview]
Message-ID: <1376663644-153546-1-git-send-email-athorlton@sgi.com> (raw)
In-Reply-To: <87wqo050fc.fsf@tassilo.jf.intel.com>
In-Reply-To: <87wqo050fc.fsf@tassilo.jf.intel.com>
Here are the results from one of the benchmarks that performs
particularly poorly when thp is enabled. Unfortunately the vclear
patches don't seem to provide a performance boost. I've attached
the patches that include the changes I had to make to get the vclear
patches applied to the latest kernel.
This first set of tests was run on the latest community kernel, with the
vclear patches:
Kernel string: Kernel 3.11.0-rc5-medusa-00021-g1a15a96-dirty
harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l# cat /sys/kernel/mm/transparent_hugepage/enabled
[always] madvise never
harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l# time ./run.sh
...
Done. Terminating the simulation.
real 25m34.052s
user 10769m7.948s
sys 37m46.524s
harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l# echo never > /sys/kernel/mm/transparent_hugepage/enabled
harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l# cat /sys/kernel/mm/transparent_hugepage/enabled
always madvise [never]
harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l# time ./run.sh
...
Done. Terminating the simulation.
real 5m0.377s
user 2202m0.684s
sys 108m31.816s
Here are the same tests on the clean kernel:
Kernel string: Kernel 3.11.0-rc5-medusa-00013-g584d88b
Kernel string: Kernel 3.11.0-rc5-medusa-00013-g584d88b
athorlton@harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l> cat /sys/kernel/mm/transparent_hugepage/enabled
[always] madvise never
athorlton@harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l> time ./run.sh
...
Done. Terminating the simulation.
real 21m44.052s
user 10809m55.356s
sys 39m58.300s
harp31-sys:~ # echo never > /sys/kernel/mm/transparent_hugepage/enabled
athorlton@harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l> cat /sys/kernel/mm/transparent_hugepage/enabled
always madvise [never]
athorlton@harp31-sys:/home/estes04/athorlton/Testing/progs/thp_benchmarks/321.equake_l> time ./run.sh
...
Done. Terminating the simulation.
real 4m52.502s
user 2127m18.548s
sys 104m50.828s
Working on getting some more information about the root of the
performance issues now...
Alex Thorlton (8):
THP: Use real address for NUMA policy
mm: make clear_huge_page tolerate non aligned address
THP: Pass real, not rounded, address to clear_huge_page
x86: Add clear_page_nocache
mm: make clear_huge_page cache clear only around the fault address
x86: switch the 64bit uncached page clear to SSE/AVX v2
remove KM_USER0 from kmap_atomic call
fix up references to kernel_fpu_begin/end
arch/x86/include/asm/page.h | 2 +
arch/x86/include/asm/string_32.h | 5 ++
arch/x86/include/asm/string_64.h | 5 ++
arch/x86/lib/Makefile | 1 +
arch/x86/lib/clear_page_nocache_32.S | 30 ++++++++++++
arch/x86/lib/clear_page_nocache_64.S | 92 ++++++++++++++++++++++++++++++++++++
arch/x86/mm/fault.c | 7 +++
mm/huge_memory.c | 17 +++----
mm/memory.c | 31 ++++++++++--
9 files changed, 179 insertions(+), 11 deletions(-)
create mode 100644 arch/x86/lib/clear_page_nocache_32.S
create mode 100644 arch/x86/lib/clear_page_nocache_64.S
--
1.7.12.4
next prev parent reply other threads:[~2013-08-16 14:34 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-02 19:46 Alex Thorlton
2013-08-02 19:53 ` Dave Jones
2013-08-02 20:00 ` Alex Thorlton
2013-08-02 20:13 ` Kirill A. Shutemov
2013-08-02 20:34 ` Alex Thorlton
2013-08-02 23:59 ` Kirill A. Shutemov
2013-08-03 19:35 ` Kees Cook
2013-08-04 14:19 ` Oleg Nesterov
2013-08-05 2:36 ` Andi Kleen
2013-08-05 15:07 ` Alex Thorlton
2013-08-16 14:33 ` Alex Thorlton [this message]
2013-08-16 14:33 ` [PATCH 1/8] THP: Use real address for NUMA policy Alex Thorlton
2013-08-16 17:53 ` Dave Hansen
2013-08-16 18:17 ` Alex Thorlton
2013-08-16 18:52 ` Kirill A. Shutemov
2013-08-27 16:50 ` Alex Thorlton
2013-08-27 17:01 ` Robin Holt
2013-09-04 15:43 ` Alex Thorlton
2013-09-04 17:15 ` Alex Thorlton
2013-09-05 11:15 ` Ingo Molnar
2013-09-09 16:48 ` Alex Thorlton
2013-09-10 7:47 ` [benchmark] THP performance testcase Ingo Molnar
2013-09-13 13:06 ` [PATCH 0/9] split page table lock for PMD tables Kirill A. Shutemov
2013-09-13 13:06 ` [PATCH 1/9] mm: rename SPLIT_PTLOCKS to SPLIT_PTE_PTLOCKS Kirill A. Shutemov
2013-09-13 15:20 ` Dave Hansen
2013-09-13 13:06 ` [PATCH 2/9] mm: convert mm->nr_ptes to atomic_t Kirill A. Shutemov
2013-09-13 13:06 ` [PATCH 3/9] mm: introduce api for split page table lock for PMD level Kirill A. Shutemov
2013-09-13 13:19 ` Peter Zijlstra
2013-09-13 14:22 ` Kirill A. Shutemov
2013-09-13 13:06 ` [PATCH 4/9] mm, thp: change pmd_trans_huge_lock() to return taken lock Kirill A. Shutemov
2013-09-13 13:06 ` [PATCH 5/9] mm, thp: move ptl taking inside page_check_address_pmd() Kirill A. Shutemov
2013-09-13 13:06 ` [PATCH 6/9] mm, thp: do not access mm->pmd_huge_pte directly Kirill A. Shutemov
2013-09-13 13:06 ` [PATCH 7/9] mm: convent the rest to new page table lock api Kirill A. Shutemov
2013-09-13 13:06 ` [PATCH 8/9] mm: implement split page table lock for PMD level Kirill A. Shutemov
2013-09-13 13:24 ` Peter Zijlstra
2013-09-13 14:25 ` Kirill A. Shutemov
2013-09-13 14:52 ` Peter Zijlstra
2013-09-13 13:36 ` Peter Zijlstra
2013-09-13 14:25 ` Kirill A. Shutemov
2013-09-13 15:45 ` Naoya Horiguchi
2013-09-13 19:57 ` Dave Hansen
2013-09-13 13:06 ` [PATCH 9/9] x86, mm: enable " Kirill A. Shutemov
[not found] ` <20130828091814.GA13681@gmail.com>
2013-08-28 9:32 ` [PATCH 1/8] THP: Use real address for NUMA policy Peter Zijlstra
2013-08-16 19:46 ` Peter Zijlstra
2013-08-16 19:49 ` Alex Thorlton
2013-08-16 14:33 ` [PATCH 2/8] mm: make clear_huge_page tolerate non aligned address Alex Thorlton
2013-08-16 14:33 ` [PATCH 3/8] THP: Pass real, not rounded, address to clear_huge_page Alex Thorlton
2013-08-16 14:34 ` [PATCH 4/8] x86: Add clear_page_nocache Alex Thorlton
2013-08-16 14:34 ` [PATCH 5/8] mm: make clear_huge_page cache clear only around the fault address Alex Thorlton
2013-08-16 18:02 ` Dave Hansen
2013-08-16 14:34 ` [PATCH 6/8] x86: switch the 64bit uncached page clear to SSE/AVX v2 Alex Thorlton
2013-08-16 14:34 ` [PATCH 7/8] remove KM_USER0 from kmap_atomic call Alex Thorlton
2013-08-16 14:34 ` [PATCH 8/8] fix up references to kernel_fpu_begin/end Alex Thorlton
2013-08-16 14:47 ` [PATCH 0/8] Re: [PATCH] Add per-process flag to control thp Peter Zijlstra
2013-08-16 15:04 ` Alex Thorlton
2013-08-04 14:44 ` Rasmus Villemoes
2013-08-28 13:56 ` Andrea Arcangeli
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=1376663644-153546-1-git-send-email-athorlton@sgi.com \
--to=athorlton@sgi.com \
--cc=akpm@linux-foundation.org \
--cc=davej@redhat.com \
--cc=dhowells@redhat.com \
--cc=ebiederm@xmission.com \
--cc=fweisbec@gmail.com \
--cc=hannes@cmpxchg.org \
--cc=holt@sgi.com \
--cc=keescook@chromium.org \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=mtk.manpages@gmail.com \
--cc=oleg@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=sedat.dilek@gmail.com \
--cc=srikar@linux.vnet.ibm.com \
--cc=tglx@linutronix.de \
--cc=viro@zeniv.linux.org.uk \
/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
all inboxes | Powered by JetHome®