If you're doing this kind of thing you really should spend $5K for a
vmetro PCI analyzer and learn how to use it. It will answer your
questions.
ron
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
If you're doing this kind of thing you really should spend $5K for a
vmetro PCI analyzer and learn how to use it. It will answer your
questions.
ron
To Unsubscribe: send mail to majord...@freebsd.org
with "unsubscribe freebsd-hackers" in the body of the message
>>If the mapping is being done via a device mapping, then the region will
>> be marked non-cacheable.
>
>I remember that he said he created a character device /dev/tulip to
>represent the network card. Actually, his work borrowed a lot from the
>Cornell U-Net project (now the basis of VIA?). C
>>If the mapping is being done via a device mapping, then the region will
>> be marked non-cacheable.
>
>I remember that he said he created a character device /dev/tulip to
>represent the network card. Actually, his work borrowed a lot from the
>Cornell U-Net project (now the basis of VIA?). Ca
On Thu, 1 Jul 1999, David Greenman wrote:
> >A graduate student here implements a mmap() interface to a TCP/IP network
> >card. He notices that it takes much longer time to copy from mmapp()'ed
> >area to another user area than it takes to copy the same amount of data
> >from kernel space to us
On Thu, 1 Jul 1999, David Greenman wrote:
> >A graduate student here implements a mmap() interface to a TCP/IP network
> >card. He notices that it takes much longer time to copy from mmapp()'ed
> >area to another user area than it takes to copy the same amount of data
> >from kernel space to use
>A graduate student here implements a mmap() interface to a TCP/IP network
>card. He notices that it takes much longer time to copy from mmapp()'ed
>area to another user area than it takes to copy the same amount of data
>from kernel space to user space. The students here have no idea why this
>c
>A graduate student here implements a mmap() interface to a TCP/IP network
>card. He notices that it takes much longer time to copy from mmapp()'ed
>area to another user area than it takes to copy the same amount of data
>from kernel space to user space. The students here have no idea why this
>co
hmm
Unfortunatly Linux is nt relevent to FreeBSD so we can't comment
directly..
it is possible that the mmapped region is marked non-cachable,
which migh tmake a difference.
I have no idea where "memcpy_to_iovec" in Linux is copying to
so it's hard to comment.
julian
On Thu, 1 Jul 1999, Zhih
hmm
Unfortunatly Linux is nt relevent to FreeBSD so we can't comment
directly..
it is possible that the mmapped region is marked non-cachable,
which migh tmake a difference.
I have no idea where "memcpy_to_iovec" in Linux is copying to
so it's hard to comment.
julian
On Thu, 1 Jul 1999, Zhihu
A graduate student here implements a mmap() interface to a TCP/IP network
card. He notices that it takes much longer time to copy from mmapp()'ed
area to another user area than it takes to copy the same amount of data
from kernel space to user space. The students here have no idea why this
could
A graduate student here implements a mmap() interface to a TCP/IP network
card. He notices that it takes much longer time to copy from mmapp()'ed
area to another user area than it takes to copy the same amount of data
from kernel space to user space. The students here have no idea why this
could
12 matches
Mail list logo
