As more enterprises and telcos are moving their infrastructure to private cloud, the more they raise needs for advanced networking to meet their modern, dynamic and virtualized architectures. This trend is fueled by the recent flux of telcos now looking for a carrier-grade private cloud solution to virtualize their IT. These needs from the community took central place in the OpenStack Summit a couple of weeks ago.
But while the OpenStack community only now gets to address the next-gen networking needs for the private cloud, the major public cloud providers the likes of Amazon and Google have long been facing these challenges.
Amazon’s cloud networking strategy
Amazon, on last week’s AWS re:Invent annual event in Las Vegas, shared some of its networking strategy for managing its global IT deployment, with 11 regions and 28 AZ (Availability Zones) across 5 continents. You can read the full technical details in this great article, but the interesting point I find beyond the details is that Amazon realized that traditional networking backbone and paradigms cannot meet the challenges it’s facing, and therefore innovatively reached out to explore the next gen networking for its organization. One such example was cutting costs of high-end networking equipment. Instead:
it buys routing equipment from original design manufacturers… that it hooks up to a custom network-protocol software that’s supposedly more efficient than commodity gear
Another interesting example was achieving network virtualization by utilizing single-root I/O virtualization (SR-IOV) and supporting multiple virtual functions on same infrastructure while maintaining good network performance.
Amazon didn’t come out with its internal networking strategy for no reason. Amazon’s strategy has been to externalize its networking capabilities as cloud services for its end customers. 5 years ago they offered VPC (Virtual Private Cloud), logically isolated AWS clusters which can be connected to the customer’s data center using VPN. On last year’s AWS re:Invent Amazon announced its “Enhanced Networking” for AWS cloud, where it provided SR-IOV support on its new high-end instances. Then March this year they announced support for VPC peering within a region, to enable private connectivity between VPCs.
Google’s take on cloud networking
While the Stackers had their conference and announcements in Paris a couple of weeks ago, Google ran it’s own Cloud Platform Live event in San Francisco, where it announced its Google Cloud Interconnect. Google has been investing in its networking for over a decade, and is now starting to externalize some of it as network cloud services, much in response to Amazon’s aforementioned networking services.
Google’s first important announcement was made March at the Open Networking Summit with the launch of Andromeda – Google’s network virtualization stack, which now got a new release and increased performance. With its Cloud Interconnect Google also responded to Amazon with its own capabilities around VPN connectivity (to be GA in Q1 2015) and Direct Peering. It is interesting to note that Google specifically targets Telcos, namely access network operators and ISPs, offering to meet the demanding carrier-grade challenge of the Telecommunications industry with their global infrastructure and services.
Public clouds heading for network virtualization
Amazon and Google own massive infrastructure and cater for massive and diverse workloads. As such they face the networking challenges and limitations ahead of the market, and lead with innovation around next gen networking and virtualization. I expect we shall see more work around SDN and network virtualization to meet these challenges, with the private clouds following and perhaps also taking the lead with telco-driven carrier-grade requirements and workloads.
Follow Dotan on Twitter!