llvm dev - Jun 2016 - LLD: Using sendfile(2) to copy file contents

On Mon, Jun 6, 2016 at 12:11 PM, Matt Godbolt <matt at godbolt.org> wrote:
>
> On Mon, Jun 6, 2016 at 1:41 PM Rui Ueyama via llvm-dev <
> llvm-dev at lists.llvm.org> wrote:
>
>> As to leave an opportunity for the kernel, I think mmap+write would be
>> enough. Because the kernel knows what address is mmap'ed, it can
detect
>> that write's source is actually a mmap'ed file and if
that's the case it
>> can optimize as it does for sendfile. It seems that Linux doesn't
do that
>> now, though.
>>
>
> Pardon my ignorance here, but how might the kernel in general know what
> the "source" of a write is?
>
The kernel knows where all mmap'ed files are mapped. So, it can decides
whether a memory address is in a mmap'ed region or not, no?

Also, in terms of the async_io option, in my (non-llvm)
experimentation
> with reading very large files the aio subsystem is not well-supported or
> optimized  (hence the lack of Glibc support).
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20160606/3bc5d1e0/attachment.html>

Perhaps I misunderstand: the kernel can tell (upon a page fault) what
memory address is being written to, and likewise upon a page fault which
memory has been read from. But it can't put these things together to infer
"process A is reading from X and writing to Y": it sees the reads and
writes in isolation, and indeed only at page granularity and when a page
fault happens.

On Mon, Jun 6, 2016 at 2:18 PM Rui Ueyama <ruiu at google.com> wrote:
> On Mon, Jun 6, 2016 at 12:11 PM, Matt Godbolt <matt at godbolt.org>
wrote:
>
>>
>> On Mon, Jun 6, 2016 at 1:41 PM Rui Ueyama via llvm-dev <
>> llvm-dev at lists.llvm.org> wrote:
>>
>>> As to leave an opportunity for the kernel, I think mmap+write would
be
>>> enough. Because the kernel knows what address is mmap'ed, it
can detect
>>> that write's source is actually a mmap'ed file and if
that's the case it
>>> can optimize as it does for sendfile. It seems that Linux
doesn't do that
>>> now, though.
>>>
>>
>> Pardon my ignorance here, but how might the kernel in general know what
>> the "source" of a write is?
>>
>
> The kernel knows where all mmap'ed files are mapped. So, it can decides
> whether a memory address is in a mmap'ed region or not, no?
>
> Also, in terms of the async_io option, in my (non-llvm) experimentation
>> with reading very large files the aio subsystem is not well-supported
or
>> optimized  (hence the lack of Glibc support).
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20160606/7cacf483/attachment.html>

What I mean is doing something like this.

  int in = open(infile, O_RDONLY, 0);
  int out = open(outfile, O_WRONLY | O_CREAT, 0644);
  void *buf = mmap(NULL, filesize, PROT_READ, MAP_PRIVATE, in, 0);
  write(out, buf, filesize);

By write, I mean write system call and not a general read or write.

On Mon, Jun 6, 2016 at 12:20 PM, Matt Godbolt <matt at godbolt.org> wrote:
> Perhaps I misunderstand: the kernel can tell (upon a page fault) what
> memory address is being written to, and likewise upon a page fault which
> memory has been read from. But it can't put these things together to
infer
> "process A is reading from X and writing to Y": it sees the reads
and
> writes in isolation, and indeed only at page granularity and when a page
> fault happens.
>
> On Mon, Jun 6, 2016 at 2:18 PM Rui Ueyama <ruiu at google.com> wrote:
>
>> On Mon, Jun 6, 2016 at 12:11 PM, Matt Godbolt <matt at
godbolt.org> wrote:
>>
>>>
>>> On Mon, Jun 6, 2016 at 1:41 PM Rui Ueyama via llvm-dev <
>>> llvm-dev at lists.llvm.org> wrote:
>>>
>>>> As to leave an opportunity for the kernel, I think mmap+write
would be
>>>> enough. Because the kernel knows what address is mmap'ed,
it can detect
>>>> that write's source is actually a mmap'ed file and if
that's the case it
>>>> can optimize as it does for sendfile. It seems that Linux
doesn't do that
>>>> now, though.
>>>>
>>>
>>> Pardon my ignorance here, but how might the kernel in general know
what
>>> the "source" of a write is?
>>>
>>
>> The kernel knows where all mmap'ed files are mapped. So, it can
decides
>> whether a memory address is in a mmap'ed region or not, no?
>>
>> Also, in terms of the async_io option, in my (non-llvm) experimentation
>>> with reading very large files the aio subsystem is not
well-supported or
>>> optimized  (hence the lack of Glibc support).
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20160606/78782f74/attachment.html>