Breaking News
News & Analysis

Brocade Software Beats Cisco ASICs

9/18/2013 08:00 AM EDT
Page 1 / 2 Next >
More Related Links
View Comments: Newest First | Oldest First | Threaded View
User Rank
Re: Other side of the story
Eetsodi   10/24/2013 1:12:09 PM
Ok, I'll bite. 

I am well-acquanted with some of the better-known ASICs
that are used in switches, tough I do not represnet any

1. SW forwarding by CPU is not new. 10Gbps/Core (even if it
    is a real  number and not, as I suspect, a special case
    under synthetic lab conditions) is not really exciting.

    Current ASIC all support 500Gbps  easily per single chip,
    and most vendors  are getting close to the 1Tbps per
    chip. So "Softwaree beats ASICs" title is questionable.  

   ASIC also give fixed performance even when you enable 
   additional features. IPv4/Ipv6, L2-Switching, MPLS, GRE,
   Security ACL's, Metering/shaping, multicasting,... I could
   go on and on (just look at any user manual of a 
   run-of-the-mill switch/router, including Brocade's).
   Software based packet handling gets slower everytime
   you want to add a feature.

2. 200G for 2-slot server means 10-core Xeons (and I
    have a feeling that to get the 10G  you need the
    top-of-the-line versions -  which is to say the most
    expensive). This is "cheap hardware"? Especially 
    after you add all the supporting  chipsets a Xeon

    Anyway, the cost of edge-routers etc, is really not
    about HW cost.

    The HW cost for an ASIC based switch/router is lower
    than a 2-slot xeon-based server. When you buy a
    Cisco router, most  of the price buys you IOS, not the
    ASIC. Brocade can sell the Vyatta cheaper  becaue it
    charges less for "Brocade-OS", not because of the HW.


3, Note that even in the article it says that Brocade
    will continue to build ASIC-based systems. If SW is so
    much cheaper, why?


Don't take me wrong - I do not seek to attack Software
(I *AM* a Software-engineer) or claim that Software-based
swithing/routing is a bad idea.

I am sure SW-based switches/routers will do well.
They will surely get better and cheaper, and they offer many
advantages (flexibility, Openness to 3rd party modifications,
ability to run applications on-board, etc. etc.) but I think this
artcile has an ovedose of Hype, and that for the next few
years at least, ASIC/NPU vendors are still going to do well,
and will not be replaced wholesale by Vyatta, or any other
Software-only solution.


User Rank
Re: Other side of the story
avdude15   10/2/2013 4:15:13 PM
Notice no customers were named.


Vyatta has a long history of unsupported hype.  I will believe it when actual product is available and can be tested.  There is no sign up this being ready for prime-time on their web site.

Embedded SW Dev
User Rank
Running close to the edge at 10G
Embedded SW Dev   9/19/2013 2:37:03 PM
While I like DPDK and what it enables at a relatively low price, it does still have its limits.

While one can do IPv4 forwarding of small packets at 10Gbps, as processing gets more complicated, other cores will need to handle it. I haven't seen IPv6 performance, if IPv6 ever gets real deployment. When Intel's 40G NIC comes out, it will be interesting to see whether this approach still works at that speed. The early drivers for that NIC have been accepted into the stream for an upcoming Linux kernel, but no hardware for sale yet.

For other comparisons, firewall rules or IPsec VPN processing would be added to the mix, to see how many links can be handled per core while doing that other work. From what I have read about DPDK, cache misses are a killer, so anything needing large tables won't work well. It only works at 10Gbps because the packet can be DMA'ed directly into the cache, starting with Sandy Bridge.

User Rank
Re: Other side of the story
pmcw   9/19/2013 11:48:15 AM
Cisco uses EZchip NP-3 and NP-4 NPU's for Layer 2 and 3 support in its ASR edge routers - not ASICs.  The ASR1000 was initiated with QuantumFlow, but added the NP-4 when it became available.  The ASR5K and 9K were lanuched with EZchip.


The Xeon is commonly used in the control plane, but with DPDK software it can be used in the data plane.  I've not studied the data from Brocade, but I suspect when evaluated in real-life situations, it will prove to be about an order of magnitude slower than the EZCH NP4 - more or less in line with the data produced by Adlink and Lanner.

rick merritt
User Rank
Re: Other side of the story
rick merritt   9/19/2013 11:01:15 AM
The silence from comms ASIC and NPU makers is, so far, deafening!

User Rank
Re: Other side of the story
LarryM99   9/18/2013 7:35:23 PM
I can't help you much on the ASIC side, Rick. It seems to me that the increasing complexity of modern network architectures around SDN and increased security consciousness plays much more into software platforms, especially where routes cross domain boundaries. People will (and should be) concerned about the security implications of this, but increased complexity and flexibility definitely plays to software's strengths in those environments.

rick merritt
User Rank
Other side of the story
rick merritt   9/18/2013 12:10:19 PM
Herrell makes a compelling case. I'd love to hear from someone from the ASIC side of the camp.

Like Us on Facebook
EE Times on Twitter
EE Times Twitter Feed