From: Peter Zijlstra <peterz@infradead.org>
To: torvalds@linux-foundation.org, paulmck@linux.vnet.ibm.com,
tglx@linutronix.de, akpm@linux-foundation.org, riel@redhat.com,
mgorman@suse.de, oleg@redhat.com, mingo@redhat.com,
minchan@kernel.org, kamezawa.hiroyu@jp.fujitsu.com,
viro@zeniv.linux.org.uk, laijs@cn.fujitsu.com, dave@stgolabs.net
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Peter Zijlstra <peterz@infradead.org>
Subject: [RFC][PATCH 0/6] Another go at speculative page faults
Date: Mon, 20 Oct 2014 23:56:33 +0200 [thread overview]
Message-ID: <20141020215633.717315139@infradead.org> (raw)
Hi,
I figured I'd give my 2010 speculative fault series another spin:
https://lkml.org/lkml/2010/1/4/257
Since then I think many of the outstanding issues have changed sufficiently to
warrant another go. In particular Al Viro's delayed fput seems to have made it
entirely 'normal' to delay fput(). Lai Jiangshan's SRCU rewrite provided us
with call_srcu() and my preemptible mmu_gather removed the TLB flushes from
under the PTL.
The code needs way more attention but builds a kernel and runs the
micro-benchmark so I figured I'd post it before sinking more time into it.
I realize the micro-bench is about as good as it gets for this series and not
very realistic otherwise, but I think it does show the potential benefit the
approach has.
(patches go against .18-rc1+)
---
Using Kamezawa's multi-fault micro-bench from: https://lkml.org/lkml/2010/1/6/28
My Ivy Bridge EP (2*10*2) has a ~58% improvement in pagefault throughput:
PRE:
root@ivb-ep:~# perf stat -e page-faults,cache-misses --repeat 5 ./multi-fault 20
Performance counter stats for './multi-fault 20' (5 runs):
149,441,555 page-faults ( +- 1.25% )
2,153,651,828 cache-misses ( +- 1.09% )
60.003082014 seconds time elapsed ( +- 0.00% )
POST:
root@ivb-ep:~# perf stat -e page-faults,cache-misses --repeat 5 ./multi-fault 20
Performance counter stats for './multi-fault 20' (5 runs):
236,442,626 page-faults ( +- 0.08% )
2,796,353,939 cache-misses ( +- 1.01% )
60.002792431 seconds time elapsed ( +- 0.00% )
My Ivy Bridge EX (4*15*2) has a ~78% improvement in pagefault throughput:
PRE:
root@ivb-ex:~# perf stat -e page-faults,cache-misses --repeat 5 ./multi-fault 60
Performance counter stats for './multi-fault 60' (5 runs):
105,789,078 page-faults ( +- 2.24% )
1,314,072,090 cache-misses ( +- 1.17% )
60.009243533 seconds time elapsed ( +- 0.00% )
POST:
root@ivb-ex:~# perf stat -e page-faults,cache-misses --repeat 5 ./multi-fault 60
Performance counter stats for './multi-fault 60' (5 runs):
187,751,767 page-faults ( +- 2.24% )
1,792,758,664 cache-misses ( +- 2.30% )
60.011611579 seconds time elapsed ( +- 0.00% )
(I've not yet looked at why the EX sucks chunks compared to the EP box, I
suspect we contend on other locks, but it could be anything.)
---
arch/x86/mm/fault.c | 35 ++-
include/linux/mm.h | 19 +-
include/linux/mm_types.h | 5 +
kernel/fork.c | 1 +
mm/init-mm.c | 1 +
mm/internal.h | 18 ++
mm/memory.c | 672 ++++++++++++++++++++++++++++-------------------
mm/mmap.c | 101 +++++--
8 files changed, 544 insertions(+), 308 deletions(-)
--
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:[~2014-10-20 22:41 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-20 21:56 Peter Zijlstra [this message]
2014-10-20 21:56 ` [RFC][PATCH 1/6] mm: Dont assume page-table invariance during faults Peter Zijlstra
2014-10-20 21:56 ` [RFC][PATCH 2/6] mm: Prepare for FAULT_FLAG_SPECULATIVE Peter Zijlstra
2014-10-20 21:56 ` [RFC][PATCH 3/6] mm: VMA sequence count Peter Zijlstra
2014-10-22 11:26 ` Kirill A. Shutemov
2014-10-22 11:39 ` Peter Zijlstra
2014-10-22 11:53 ` Kirill A. Shutemov
2014-10-22 12:15 ` Peter Zijlstra
2014-10-22 13:44 ` Peter Zijlstra
2014-10-23 12:36 ` Kirill A. Shutemov
2014-10-23 14:22 ` Peter Zijlstra
2014-10-23 15:05 ` Kirill A. Shutemov
2014-10-20 21:56 ` [RFC][PATCH 4/6] SRCU free VMAs Peter Zijlstra
2014-10-20 23:41 ` Linus Torvalds
2014-10-21 8:07 ` Peter Zijlstra
2014-10-24 15:16 ` Christoph Lameter
2014-10-24 15:51 ` Peter Zijlstra
2014-10-24 17:08 ` Christoph Lameter
2014-10-21 8:22 ` Peter Zijlstra
2014-10-23 10:14 ` Lai Jiangshan
2014-10-23 11:03 ` Peter Zijlstra
2014-10-24 3:33 ` Lai Jiangshan
2014-10-24 7:26 ` Peter Zijlstra
2014-10-20 21:56 ` [RFC][PATCH 5/6] mm: Provide speculative fault infrastructure Peter Zijlstra
2014-10-21 8:35 ` Kirill A. Shutemov
2014-10-21 10:41 ` Peter Zijlstra
2014-10-21 19:00 ` Peter Zijlstra
2014-10-20 21:56 ` [RFC][PATCH 6/6] mm,x86: Add speculative pagefault handling Peter Zijlstra
2014-10-21 0:07 ` [RFC][PATCH 0/6] Another go at speculative page faults Andy Lutomirski
2014-10-21 8:11 ` Peter Zijlstra
2014-10-21 16:23 ` Ingo Molnar
2014-10-21 17:09 ` Kirill A. Shutemov
2014-10-21 17:56 ` Peter Zijlstra
2014-10-23 10:40 ` Lai Jiangshan
2014-10-23 11:04 ` Peter Zijlstra
2014-10-24 7:54 ` Ingo Molnar
2014-10-24 13:14 ` Peter Zijlstra
2014-10-28 5:32 ` Namhyung Kim
2014-10-21 17:25 ` Peter Zijlstra
2014-10-22 12:35 ` Ingo Molnar
2014-10-22 7:34 ` Davidlohr Bueso
2014-10-22 11:29 ` Kirill A. Shutemov
2014-10-22 11:45 ` Peter Zijlstra
2014-10-22 11:55 ` Kirill A. Shutemov
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=20141020215633.717315139@infradead.org \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=dave@stgolabs.net \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=minchan@kernel.org \
--cc=mingo@redhat.com \
--cc=oleg@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=riel@redhat.com \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.org \
--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;
as well as URLs for NNTP newsgroup(s).