Re: TCP mmap (was Re: [PATCH] f_op->poll() without lock_kernel())

From: Alan Cox (alan@lxorguk.ukuu.org.uk)
Date: Sat Apr 22 2000 - 06:17:36 EST


> ok i'll bite.
>
> i think that this might drive up TLB activity when you operate at scale
> (1000s of tcp sessions), to the point that you don't get a win from the
> technique.

The TLB activity is clean, the card should be DMAing into the ring buffer
so we dont actually reference it from the CPU. In fact you could do
disk->network and the reverse without the data touching CPU cache

> i've been playing with a ring buffer technique for userland buffering in
> which i share the buffer amongst all the sockets. it's actually the first
> real use of readv() i've seen.
>
> it's pretty nice -- requires very little memory per-session, great for
> handling idle sessions and such... unlike the usual userland buffering
> technique which is to allocate a 4k buffer per session and chew ram and
> TLB entries.
>
> i will send you a reference to the code when i release it.

That sounds like the V7 Unix tty layer. It really does.

Alan

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Sun Apr 23 2000 - 21:00:20 EST