Re: [RFC PATCH] alispinlock: acceleration from lock integration on multi-core platform

From	Ling Ma <ling.ma.program@gmail.com>
Newsgroups	linux.kernel
Subject	Re: [RFC PATCH] alispinlock: acceleration from lock integration on multi-core platform
Date	2016-01-14 09:20 +0100
Message-ID	<qQLip-4lJ-3@gated-at.bofh.it> (permalink)
References	(3 earlier) <qNRu1-6Yg-1@gated-at.bofh.it> <qNRDJ-71N-5@gated-at.bofh.it> <qNUrU-sc-23@gated-at.bofh.it> <qOO14-4T5-1@gated-at.bofh.it> <qQ7En-1Fv-21@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

[Multipart message — attachments visible in raw view] - view raw

Alan,

The attachment  (alispinlock.tar.bz2) in last email includes our
sample cases for spinlock.
The attachment (lock_test.tar.bz2) in this email includes the patch on
kernel 4.3v ,
which has been applied to actual real kernel locks:
when we run the user space program (thread.c) on 72cores E5-2699v3,
it cause many hot kernel spinlocks from __kmalloc and kfree  respectively
with original spinlock cpu cost 25% and  92715428576 cycles after
lock/unlock 1000000 times
with ali spinlock cpu cost 15% and  48475891244 cycles after
lock/unlock 1000000 times.
So we say in the real world workload the ali spinlock improve
performance by 1.9x
(92715428576 cycles/48475891244 cycles)

Thanks
Ling

the

2016-01-12 21:50 GMT+08:00 One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>:
> On Sat, 9 Jan 2016 06:44:15 +0800
> Ling Ma <ling.ma.program@gmail.com> wrote:
>
>> The attachment (alispinlock.tar.bz2) includes original spinlock and
>> alispinlock ,
>> we compare them on 70 cores based on kernel 4.3, the alispinlock can
>> improve performance upto 3x.
>>
>> the link: https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1035940.html
>> indicates when we introduce the idea for real application(user space
>> application  caused the bottle neck from  kernel spinlock )
>> the spinlock performance is improved by 1.9x (perf top -d1 also tell
>> us the spinlock cost time is reduced from 25% to 15%).
>>
>> Appreciate your comments
>
> So this has not been applied to actual real kernel locks (ie converted
> some of the hot kernel locks to it) and then benchmarked with a real
> world workload. This is just for the theoretical locking overhead ?
>
> Alan

Thread

Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform Peter Zijlstra <peterz@infradead.org> - 2016-01-05 22:20 +0100
  Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk> - 2016-01-05 22:50 +0100
    Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform Peter Zijlstra <peterz@infradead.org> - 2016-01-06 09:20 +0100
      Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform Peter Zijlstra <peterz@infradead.org> - 2016-01-06 09:30 +0100
        Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk> - 2016-01-06 12:30 +0100
          Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform Ling Ma <ling.ma.program@gmail.com> - 2016-01-08 23:50 +0100
            Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk> - 2016-01-12 15:00 +0100
              Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform Ling Ma <ling.ma.program@gmail.com> - 2016-01-14 09:20 +0100
    Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform Ling Ma <ling.ma.program@gmail.com> - 2016-01-09 00:10 +0100
  Re: [RFC PATCH] alispinlock: acceleration from lock integration on  multi-core platform Ling Ma <ling.ma.program@gmail.com> - 2016-01-09 00:00 +0100

csiph-web