Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end

From	"Wangnan (F)" <wangnan0@huawei.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end
Date	2016-03-23 11:10 +0100
Message-ID	<rfNTI-1NT-5@gated-at.bofh.it> (permalink)
References	<rcxBM-2ly-3@gated-at.bofh.it> <rcxBN-2ly-17@gated-at.bofh.it> <rfNK3-1u8-7@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw


On 2016/3/23 17:50, Peter Zijlstra wrote:
> On Mon, Mar 14, 2016 at 09:59:43AM +0000, Wang Nan wrote:
>> Convert perf_output_begin to __perf_output_begin and make the later
>> function able to write records from the end of the ring buffer.
>> Following commits will utilize the 'backward' flag.
>>
>> This patch doesn't introduce any extra performance overhead since we
>> use always_inline.
> So while I agree that with __always_inline and constant propagation we
> _should_ end up with the same code, we have:
>
> $ size defconfig-build/kernel/events/ring_buffer.o.{pre,post}
>     text    data     bss     dec     hex filename
>     3785       2       0    3787     ecb defconfig-build/kernel/events/ring_buffer.o.pre
>     3673       2       0    3675     e5b defconfig-build/kernel/events/ring_buffer.o.post
>
> The patch actually makes the file shrink.
>
> So I think we still want to have some actual performance numbers.

There are some numbers. You can find them from:

http://lkml.iu.edu/hypermail/linux/kernel/1601.2/03966.html

Thank you.

Thread

Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end Peter Zijlstra <peterz@infradead.org> - 2016-03-23 11:00 +0100
  Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-23 11:10 +0100
    Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-03-23 20:30 +0100
      Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-24 05:00 +0100
        Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end Alexei Starovoitov <alexei.starovoitov@gmail.com> - 2016-03-24 18:40 +0100
  Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-25 13:30 +0100
    Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-25 13:40 +0100
      Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-25 15:20 +0100
        Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end Peter Zijlstra <peterz@infradead.org> - 2016-03-27 17:30 +0200
          Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end pi3orama <pi3orama@163.com> - 2016-03-27 17:40 +0200
            Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-28 03:10 +0200
              Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-28 04:10 +0200
                Re: [PATCH 3/5] perf core: Prepare writing into ring buffer from end "Wangnan (F)" <wangnan0@huawei.com> - 2016-03-28 05:00 +0200

csiph-web