[j-nsp] RE-S-X6-64G-BB

raf raph at futomaki.net
Mon May 23 12:39:28 EDT 2016



Le 21/05/2016 à 22:26, Saku Ytti a écrit :
> All vendors are pimping this like it's something customers have been
> crying for ages. But who actually is planning to use their routers are
> general purpose compute?
> What advantages can it have?

I see some good point using this approach. These are mainly side effects 
however.
The first good effect is all platform will converge and use x86 
processors. (ok we all agree this is waste of power but as the soft is 
so optimized...)
So we will converge on one processor target which it a good news for the 
stability of the software, test and so on. We can hope for a real one OS 
for all platform. :)
Other thing I saw; is that we it will allow separating components of the 
NOS in multiple VMs with real QOS between VMs.
We could imagine running a vm dedicated to RR for example.

> It will obviously not affect the
> reliability of the system positively, while virtualisation is quite
> proven and safe, there's still occasionally issues where one VM can
> impact another VM.
I think the contrary. As I say it should allow running much better 
isolated process. And perhaps snmpd will not kill the enitre control 
plane...
OK this also possible inside one OS with a good software architecture 
but it is more complicated with the actual code.

--
Raphael Mazelier




More information about the juniper-nsp mailing list