[ih] vm vs. memory

Toerless Eckert tte at cs.fau.de
Tue Oct 24 09:29:09 PDT 2017


Hmm... what are the redeeming qualities of NAT ? The fact that
we'll look back with nostalgia at the days when users only had to
rely on NAT to get access to the global village because what they
do now is worse ?

https://ripe75.ripe.net/presentations/22-2017-10-23-death-of-transit.pdf

Oh well, federated AOL-TNG, but hey, the Internet was fun while it lasted,
i promise to switch off the lights when i leave.

Sorry, off-topic. Nice summary for the evolution of memory virtualization.
Still trying to get to the next level @home, IOMMU virtualization
config for virtualized PCI 3D graphics. VT-d over RoCEv3 anybody ? *grin*

On Tue, Oct 24, 2017 at 02:12:06PM +0200, Paul Vixie wrote:
> 
> 
> Joe Touch wrote:
> ...
> > IMO, they?re no more a stop-gap to networking than VM is to memory.
> >
> > But we?re digressing from the original thread...
> 
> that's hard to say, but i've forked the thread anyway.
> 
> vm is an example of something that started as a workaround but 
> introduced us to a whole different way of thinking about memory. we now 
> have systems in production that always have physical RAM enough for 
> their work load, and who have no backing store for RAM (paging or 
> swapping) but which still depend on virtual memory for other reasons:
> 
> 1. linear address space; all processes think they have addresses 
> starting from 0.
> 
> 2. page-level protection; various parts of memory are only readable, or 
> writable, or executable, when needed, and at certain privilege levels.
> 
> 3. occasional sharing and/or persistence (memory mapped files).
> 
> 4. occasional distributed persistence (networked virtual memory).
> 
> i think a lot of things that begin as stop-gaps turn out to have many 
> purposes beyond that initial stopped gap, and would have been invented 
> anyway, if somewhat later, for those other reasons.
> 
> LISP may be an example. NAT certainly is.
> 
> i mention this because not all ideas which were terrible $originally 
> remain terrible in $internet_history.
> 
> -- 
> P Vixie
> 
> _______
> internet-history mailing list
> internet-history at postel.org
> http://mailman.postel.org/mailman/listinfo/internet-history
> Contact list-owner at postel.org for assistance.



More information about the Internet-history mailing list