Send the link below via email or IMCopy
Present to your audienceStart remote presentation
- Invited audience members will follow you as you navigate and present
- People invited to a presentation do not need a Prezi account
- This link expires 10 minutes after you close the presentation
- A maximum of 30 users can follow your presentation
- Learn more about this feature in our knowledge base article
Do you really want to delete this prezi?
Neither you, nor the coeditors you shared it with will be able to recover it again.
Make your likes visible on Facebook?
You can change this under Settings & Account at any time.
SDN: Status Quo and Status Grow
Transcript of SDN: Status Quo and Status Grow
Smart protocols carry more data (tags, communities, targets, etc)
Logic and Policy package up your "App".
PBR == Early SDN
We are at an inflection point: Networks will get easier to interface with, but the complexity will increase under the covers. (THINK: Car Engines) The Catalysts Deterministic forwarding in special purpose networks
Do one thing very well; when regular protocols are not cut for the job.
Flexible Tap's; no MAC learning, special monitoring networks should cost less than the network on which they serve.
Simplify the network and automate tasks.
Increase capabilities in security in virtual environments, allow for self provisioning and best of all: RAPID PROTOTYPING.
Time to Market Well Defined Networking Clearly Articulated, Understood, and Taught The Method Matters AKA: Hypervisor Networking Lot's of new things happening as once.
Important to understand your team's current capabilities and what you will ask of everyone across the organization. Beyond the product comes the troubleshooting and management.
Find niche places where products can be introduced without affecting all production traffic.
Enable new technologies and solve problems. Protocols are Software Transport and access networks can get common control planes and elements can become commodity.
This applies to a select corner case. In most situations we want more intelligence, not less.
Money is either spent on smart products or smart people. Age old paradigm of CAPEX vs OPEX.
Control plane on the side vs distributed. It's possible to put your eggs in one basket and watch that basket.
Flexibility in forwarding behaviour without all the fat of existing protocols. Just don't trim too much. (ie. Fast re-route, fast convergence, etc)
A place of "Truth" needs to exist. RIB or FIB. When You Want to Make Changes to Your Network Does the network change need to happen dynamically?
How can we quantify "dynamic"; every day, every week, or in non-deterministic fashion?
Do we have the tools to prevent bad stuff from happening? ie. Safe Upper Limits, hold-down timers, protocol anomalies, etc
How complex did this "simple program" become? Published specifications; APIs, multiple languages can allow for a new "Lingua-Franca" in networking. It's good to speak more [languages,protocols].
Be wary of black boxes; they bring mystery.
We can find "mechanics" that understand today's problems; but we need to invest in new "engineers" to build the new network. (ie. Overlays vs Transport)
The life of a packet should be explained in a paragraph; no more, no less. Lot's of problems to solve: (security, tenancy, simplicity, automation, and flexibility).
Interesting angle: vnic security and vnic port span
Loadable Kernel Modules
Overlay (GRE, STT, IPIP, IPSEC, etc)
Other encap models: VXLAN, CAPWAP, etc
Cloud Model: many VLANS to provision on ToR and Agg from Hypervisor. MVRP makes it easy for OpenStack/Linux to "join traditional networks" SDN++ The Next Steps We want flexible topologies, automation, performance efficiency, and understandable.
There are key projects that can use smart networking features today; be it SDK on Routers, OFP to ToRs, or Hypervisor internetworking.
Small steps in engineering without reinventing the wheel.
Networks change the world for the better, let's be part of the change