[j-nsp] EX Routing Throughput

[Eugeniu Patrascu]

On Sat, Oct 10, 2009 at 7:05 AM, Richard A Steenbergen <ras at e-gerbil.net> wrote:
>
> On Fri, Oct 09, 2009 at 11:06:02AM +0400, Pavel Lunin wrote:
> > As the other have already said, the main difference between 3200 and 4200 is
> > virtual chassis. But I'd like to note that it is not just a fun gadget which
> > allows to have a solid fully redundant control plane for up to 10 switches.
> > You should also keep in mind that 4200 have one more PFE onboard and 2x
> > 64Gbit full duplex (!) VC ports. So they have almost doubled performance in
> > compare with 3200.
>
> FYI the other differences are:
>
> 600MHz vs 1GHz PPC processor
> 512MB vs 1GB DRAM
>
> Not sure if there is anything else floating around other than the PFE
> bits you mentioned, but those are what I've noticed.
>
Maybe a bit late, but this is the most I saw on an EX4200 on 10GE
ports under test.

root> show interfaces xe-0/1/0 statistics
Physical interface: xe-0/1/0, Enabled, Physical link is Up
  Interface index: 153, SNMP ifIndex: 164
  Link-level type: Ethernet, MTU: 1514, Speed: 10Gbps, Duplex:
Full-Duplex, BPDU Error: None, MAC-REWRITE Error: None, Loopback:
Disabled,
  Source filtering: Disabled, Flow control: Enabled
  Device flags   : Present Running
  Interface flags: SNMP-Traps Internal: 0x0
  Link flags     : None
  CoS queues     : 8 supported, 8 maximum usable queues
  Current address: 00:19:e2:56:bc:58, Hardware address: 00:19:e2:56:bc:58
  Last flapped   : 2009-04-23 11:07:31 UTC (00:25:34 ago)
  Statistics last cleared: Never
  Input rate     : 7618850816 bps (14880568 pps)
  Output rate    : 7618851328 bps (14880569 pps)
  Input errors: 0, Output errors: 0
  Active alarms  : None
  Active defects : None

  Logical interface xe-0/1/0.0 (Index 92) (SNMP ifIndex 165)
    Flags: SNMP-Traps Encapsulation: ENET2
    Input packets : 0
    Output packets: 820
    Protocol eth-switch
      Flags: None


 The PFE and the CPU were not showing any usage, maybe 1% or so.

Eugeniu