Time to Ditch the Definition of SDN

Time to Ditch the Definition of SDN

Time to Ditch the Definition of SDN

While at a stoplight looking at the random news feeds on Linkedin I ran across a post of a recent blog post by the ONF and the subsequent conversation where my friend Ivan Pepenlnjak commented. So I threw in my two cents and quickly regretted it because Linkedin has an amazing ability to frustrate me as it updated the comment counter but ate my post and then disappeared. Awesome. So I’m going to post what I remember of it here. Let me also disclaim this isn’t a response to a response and so on, the blog post simply mustered up enough energy in me to write a disappearing comment on LinkedIn. I really like Dan Pitt, few have made such a difference in networking by promoting new ways to think about networking like Dan has. He is merely pointing out the accepted definition of SDN, not defining it. My disagreement of the opinionated definition of SDN is simply where my thinking has landed after being involved in both ops/dev on both sides of the approach. We have centralized with one or two protocols vs whatever makes sense to the use case.

Quick review, OpenFlow is not a framework, architecture or philosophy, but a wire protocol that can be used to program a local or remote forwarding tables of an IP endpoint (presumably dwdm lambdas now too last I read the draft). SDN is where things get squirrely. There is this long running assumption that SDN is only SDN if it uses a centralized controller and programs remote endpoints/datapaths. I’m as guilty as the rest, before trying to guess the state of remote endpoints from a controller to deal with the nearly infinite number of states an endpoint can be in. I have also used that definition where it was convenient being one controller with lots of remote endpoints. If that works for you go nuts. Im not saying its bad in some cases, the traffic alignment of wireless controllers often make a lot of sense to have a central cluster to insert into the datapath since it needs to traverse that path anyways etc. Of course even here good opposing arguments can be made.

My only criticisms of OpenFlow is it punts on state and it doesn’t have simple to use defaults. That said I haven’t had time to follow the drafts like I once did. Linux networking has become more and more interesting as time goes on. The appeal for me is it abstracts much of the irrelevant complexities. I really like IPVlan. Offering both a low level and higher order abstraction, in the case of Linux IPRoute2 and Netlink makes it useful to a wider set of developers and users with a lower technical barrier to entry. Regarding state, introducing latency to network state is pretty insurmountable if performance is relevant in any way. The races conditions abound and eventually will cascade into failure. Dealing with state locally is hard enough, shipping it north is race condition central.

Too Many Contradictions

To say, SDN is only SDN if it programs remote datapaths hasn’t made much sense for a while.

  • If I use a local controller or process and program OVS using OF is that not SDN?
  • If I use a local controller or process and program the configuration using NetConf is that not SDN?
  • If I use a de-centralized controller or process and program the configuration using OpenFlow is that not SDN?
  • If I use a logically-centralized controller or process and program the configuration using OpenFlow is that not SDN?
  • If I use a local controller or process and program the datapath using Netlink is that not SDN?
  • If I use a local controller or process and program the datapath configuration using NetConf is that not SDN?
  • If I use a local controller or process and program the datapath using IPRoute2 is that not SDN?
  • If I use a local controller or process and program packet forwarding policy using Ip Tables or HA Proxy is that not SDN?
  • If I use a local or remote route server and program a custom next hop of a prefix is that not SDN?
  • If I use a local controller or process and program the network using open source software and standardized APIs is that not SDN?

You get my point. What is SDN? Well, software programming networks? Haven’t we always had that? Yes, but this time its different 🙂 or I am just old, or both.

  1. SDN shouldn’t be one particular architecture, protocol or definition and if we really want to be honest with the conversation, the true adoption of “SDN” has been provisioning and de-provisioning mostly ports but some paths in conjunction with compute orchestration.
  2. Let’s ditch definitions for emerging nascent disruptions. Its obvious the ingredients of SDN include being open and programmatic. Open could be argued but I personally wouldn’t attempt to defend anything beyond those two because there are too many holes in those ships and it starts to sound like religion.

Discounting an innovation because it doesn’t fit an academic definition will always lose.

angry_panda_vs_chef

How we deal with configuration and packet forwarding in networks needs to be flexible enough to capture the rapidly changing converged infra models. Interestingly, you have projects like P4 (and the startup to make money from it Barefoot) from some of the same folks that brought you OpenFlow. Rather then trying to get ODM/OEMs to conform to a specification, its seems to be looking to redefine networking hardware. I haven’t looked much but I assume that rather then fixed length fields everything is essentially a TLV. We could use more of that thought in routing protocols too if the technical debt can stay lower then previous attempts. The density and time scales of compute have and will continue to change exponentially. Devops has been the answer for systems engineers and will likely continue to be for converged infra as networking evolves towards that model.

So lets keep it simple and inclusive, changing configurations line by line by hand like many of us did for a long time vs. programmatically changing the state the network. The new edge is the server, those will be managed in some form or fashion much more like compute. I also think containers on switches will have a significant impact for the vendor packaging apps and the user consuming or writing their own just like they would any other system. Aligning solutions to that only makes sense. Through all of this the emerging x-factor is packaging and simplicity in the user experience. Gone are the days of the week long OpenStack install, or Devstack dependency hell. What will ultimately decide what adopts and what doesn’t is the people, not the technology.

About the Author

Brent SalisburyI have over 20 years of experience wearing various hats from, network engineer, architect, ops and software engineer. More at Brent's LinkedInView all posts by Brent Salisbury →

  1. FrankFrank08-16-2015


    I agree – definitions of SDN that focus on the technology completely miss out on what it really is, a set of newly enabled use cases. As an alternative definition, here’s my personal one:

    Allow the network state and
    forwarding paths to dynamically reflect business use cases by moving functionality out of static configurations and into dynamic configurations and real-time protocols.

    • Brent SalisburyBrent Salisbury08-17-2015


      Thanks for the comment, static -> dynamic is an important point. All orchestration, regardless of the platform will require netops to be removed from the provisioning/deprovisioning process. What those who want to remove netops from the process forget is troubleshooting and integration into physical networks both involve significant experience that dev/devops generally have no clue about.

  2. Rishi RajRishi Raj09-22-2015


    Hi ,

    First of all I apologize to have hijacked this link to post query .

    I have been using OVS recently and I noticed the following –

    1) I did not insert the openvswitch kernel module

    2) Using “ovs-vsctl add-br br0” command , I tried to add a bridge – which failed for obvious reasons. There is an error log that is displayed on ovs-vsctl screen as well.

    3) However there are entries that are left in the ovs database – “ovsdb-client dump”. I can see addition to the bridge , port , interface and openvswitch tables – all entries pertaining to the bridge “br0”.

    Ideally an application has to delete the bridge “br0” from the DB after hitting an error like this.

    I see that the ovs-vsctl can detect these errors through checks for the field in the interface table entry “ofport”.

    The question is how can a remote management interface for any proprietary schemas get to know about application processing failures . ( what does the ODL do if it tries to create a bridge with OVS and the kernel module was not inserted )

    Thanks and regards,
    Rishi Raj

    • not menot me10-12-2015


      This is the pile of shit named software defined.
      Networking and storage are going to end up with as many reboots and upgrades as all the flimsy shit we have on Android phones.
      I don’t see redundant routing engines anywhere in the close vincinity and the same goes for a immediate-failover NOX controller etc.

      I’m sure we’ll struggle through it and have a few shinier things in the future.
      But the issue you hit in OVS is symptomatic.

      Excuse the anon post, normally I’d give my name but it’s too depressing and I hope in this way I’ll not remember having written this thing while it’s turned into JSON driven non-validated truth.