sendfile for raw disk (was: zero copy TCP)

> > Both, but I may do either way, depending on which way is easier. > > If we can directly DMA from a disk drive to a NIC, that will be great. > > If the current implementation requires preloaded buffer, that works. > > So, where can I look for the patch? > > > > Please see sendfile(2).

Re: zero copy TCP (Thanks)

Thanks for all people who have responded to this thread. -Jin To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message

Re: zero copy TCP

Alfred <[EMAIL PROTECTED]> wrote: > > I heard that zero copy TCP is already in FreeBSD, isn't it? > > I could not find any information in searching the entire website. > > Before I am going to spend some silly time working on it, > > I would like to know what is the status for "ZERO COPY TCP" in >

zero copy TCP

I heard that zero copy TCP is already in FreeBSD, isn't it? I could not find any information in searching the entire website. Before I am going to spend some silly time working on it, I would like to know what is the status for "ZERO COPY TCP" in FreeBSD right now. If it already exists, how can I

possible doing context switch between network and link layers?

Hi, Try to control the NIC output, instead of dropping the packet, I would like to do context switch on current sending process. tsleep() seems not to be a right mechanism for this purpose because it will panic in the kernel wherever between the network and link layers the tsleep() is put -- e.g