[Jool-list] jool setup

[Alberto Leiva]

These don't really address your first question directly, but might
serve as a reference point. They are everything I managed to collect
that is both public and refers to performance:

(https://mail-lists.nic.mx/pipermail/jool-list/2018-July/000199.html)
First off, you're definitively not hitting the performance limit of Jool - it
easily scales to multiple Gb/s of throughput. There must be something else
that is causing your issues.

(https://mail-lists.nic.mx/pipermail/jool-list/2017-October/000158.html)
Jool, even 3.5.4 Jool, withstands T-Rex's torture traffic without
flinching. There are no significant performance issues to worry about. CPU
usage is at 1% at worst and there are no packet drops.
...
I can now say fairly confidently that Jool is pretty darn
fast, even without the latest performance tweaks applied, as evidenced from
the fact that, now that whatever was hobbling before is gone, it is pretty
clear that Jool can keep up to at least this configuration of T-Rex with
flying colors.

(https://mail-lists.nic.mx/pipermail/jool-list/2016-September/000091.html)
> What is the CPU load on the x86 SIIT-BRs from Jool?
Our are practically idle. They are translating about 100Mb/s of mostly
web traffic. The hardware is quite old even, Sun X4170s with 2x
quad-core Intel L5520 CPUs. Less than a quarter of a single CPU core is
used for the entire system (so not only Jool), the remaining 7.75 CPU
cores are idle.

--------

BTW: We're currently working on a performance bug that affects packets
that never traverse physical interfaces:
https://github.com/NICMx/Jool/issues/267
On Sat, Aug 11, 2018 at 1:50 PM Alberto Leiva <ydahhrk at gmail.com> wrote:
>
> > is the setup above feasible for networks with several thousand users
> > (between 5-10k)
>
> Performance-wise, as a developer, I don't really have a means to test
> that level of traffic. Maybe somebody else in the list has that
> information.
>
> Functionality-wise though, Jool won't stop you. Just make sure that
> you have enough IPv4 transport addresses to mask all of that.
>
> Also, I'd suggest that you keep a decent understanding of this:
> https://jool.mx/en/usr-flags-pool4.html#--max-iterations
>
> > is there a latency induced for throughputs of more than a gb ?
>
> Not that I know of. (Why would that happen?)
>
> > exists the possibility of defining a pool of ipv4 addresses when
> > nat64-ing and not doing 1-to-1 specific rules ?
>
> Yes: https://jool.mx/en/pool4.html
> On Sat, Aug 11, 2018 at 1:35 PM Petre Tudor <petre.tudor at cte.ro> wrote:
> >
> > hello
> >
> > i am trying to minimize the usage of the ipv4 addresses by assigning to
> > the users only ipv6 and nat64-ing them to the internet. (the final goal
> > would be to assign routable ipv4 only to those users who really need
> > them and pay them as an extra service; the normal users who don't have
> > specific requirements will only receive an ipv6 address and get nat64
> > for the only-ipv4 destinations.
> >
> > before i start i have a few questions regarding the jool features
> > (please excuse if they are too trivial, I am new in this knowledge area):
> >
> > - is the setup above feasible for networks with several thousand users
> > (between 5-10k)
> >
> > - is there a latency induced for throughputs of more than a gb ?
> >
> > - exists the possibility of defining a pool of ipv4 addresses when
> > nat64-ing and not doing 1-to-1 specific rules ?
> >
> >
> > thanks,
> >
> >
> > petre
> >
> > _______________________________________________
> > Jool-list mailing list
> > Jool-list at nic.mx
> > https://mail-lists.nic.mx/listas/listinfo/jool-list