Brocade has now jumped into the fray. The company has always been strong in the data center, but more on the storage side. Its Foundry acquisition gave it credentials in the enterprise WAN side of data center networking, and it has an OEM deal with IBM that’s offered it some new paths to market. Still, it’s fair to say that Brocade hasn’t kept up in this space, and more fair to say that it has lost some opportunity to steal share from its arch-rival Cisco. UBS also lowered its estimates on Cisco to reflect business-model transition, a fancy way of saying that management is distracted and things are in a state of flux.

Brocade’s strategy, which it calls the “Virtual Enterprise”, is built on an architecture that Brocade says is open and extensible, and is in turn called CloudPlex. I have to admit that “Virtual Enterprise” based on “CloudPlex” seems like an attempt to link all the right buzzwords to an announcement, and that cynical view may be somewhat validated by the fact that the new stuff associated with CloudPlex isn’t yet available.  Unlike rival-for-Cisco-market-share-castoff Juniper, Brocade didn’t tie its new architecture to a single new product, or to any specific future one either.

Spinning an architecture in advance of having specific execution to support it isn’t necessarily bad, though.  My surveys have consistently said that enterprises and service providers alike need to understand the ecosystem that a vendor’s vision represents before they worry too much about boxes, speeds and feeds.  The problem in this case is that the details on CloudPlex are sketchy themselves, and it’s not at all clear just how the concept links virtualization to the cloud. That’s particularly true when Brocade doesn’t supply virtualization/cloud software except through partnerships. I think Brocade could tell a strong story here, but they’ve not done it yet.

HP announced disappointing results, a contrast not only to Street expectations but to competitor Dell’s recent numbers. The problem, says the company, is softness in the consumer PC sector and the fact that HP doesn’t sell much to businesses relative to their total PC sales. The real issue, I think, is the company’s management agony and a nearly total loss of focus on business.

I was particularly unmoved by the CEO’s promise to get something going with cloud computing. Where has he been, anyway? This is no time to start laying out your cloud strategy; competitors have been doing that for over a year. HP’s decision to buy Palm is another point of future challenges; they’re not sustaining their momentum in their core markets, so how do they expect to take on Android and Apple in the tablet and smartphone space? This is a company that’s been on a roll for years, and it’s now at serious risk to lose credibility and market share. They have perhaps two quarters now to turn things around, after which they’re probably going to risk permanent damage.

The cloud also figures in the Juniper announcement. The company has been talking about their “Stratus” project for several years, and they’ve finally started delivering on the new data center fabric officially called QFabric, with the nodal element, the QFX3500. The details and the roadmap are impressive, and it’s very possible that Juniper has something here that will change the game, change some minds, and produce significant competitor angst. We’ll cover this in detail in our March Netwatcher, but let me summarize here.

The Juniper QFabric architecture consists of three elements, the primary of which are the nodes. These are essentially line cards in a basic case, designed to be linked to each other as an entry strategy or for full QFabric configurations linked back to the interconnect box. The links are made with multi-homed fiber and the result is a semi-mesh of the nodes that has a large cross-sectional bandwidth. The nodes learn the configuration and connectivity and use this to propagate a forwarding table both at Level 2 and 3, and this table then creates the full forwarding path decision so that no matter what route is taken from source to destination within the mesh, there are no further forwarding decisions needed. The configuration has a current maximum capacity of 40 Tbps and it’s fully non-blocking, lossless, has microsecond-level delay and negligible jitter.

The QFabric can be partitioned into virtual networks, and can host services that are created by attaching engines that perform the service processing. Security is an obvious example of a service. Services are created by routing data paths through the appropriate engine(s) on the way to the destination. A director device creates a black-box virtual device abstraction for the management plane and to the outside world so the structure is opaque and opex and configuration complexity are reduced.

While it’s not possible to sustain microsecond-scale latency over WAN distances, you can connect QFabric paths with a decent-performing IP/MPLS connection and thus extend the fabric beyond a single data center. This means that a cloud computing offering (either to support a service, a private cloud, or an operator IT application/feature hosting platform) could in theory be created and maintained as a single QFabric. The whole process is operationally linked vertically to the Junos Space cloud feature and management platform, and you can also use Space to create applications and service features that become services of a QFabric cloud.

What’s interesting about this beyond the obvious in-data-center benefits of cost and footprint is the notion that QFabric might become the architecture for private, public and hybrid clouds.  So far, nobody has really articulated how you’d build a service provider cloud, for example, and with the WAN extensions QFabric could be just that. The capability could generate some really valuable cloud, content, and mobile engagement for Juniper and thus could pre-empt plans by competitors like Cisco to get a lead in defining how a provider cloud would look.

Since QFabric is also likely to be a compelling migration option for companies with two years or less of undepreciated data center switch assets, and at least a consideration for companies with three or even four years remaining, it could boost Juniper’s market share and credibility in the critical data center networking space. Which, obviously, neither Cisco nor HP would like.  Both these arch-rivals have their own quarterly performance issues to work through, and Cisco named a COO (Gary Moore) to help them streamline its operations processes. There may be a window for Juniper to put the hurt on both companies while they’re distracted.

The new chip is a family, the first member of which is Trio. It is based on a “Network Instruction Set Processor” model that builds software on the device using instructions customized for network behavior control rather than general-purpose instructions, as NPs do. In this respect, the chip is almost like an ASIC, but unlike an ASIC it’s programmable at the primitive NISP-instruction level, so new features can be added right down to the instruction level. It’s this architecture that accounts for the considerable improvements in performance, scalability, power efficiency, etc. that Juniper has demonstrated (through independent lab tests).

The software (Junos Space) is centered on a complete restructuring of the Juniper Junos operating system, and it extends Junos to cover not only Juniper devices but also independent software development, and even a new device client (Junos Pulse) that will provide security and identity management, VPN control, and connection control.

The software side of the announcement is the most critical because it is based on middleware to create what is, in effect, a platform-as-a-service cloud on which operators can build service features and service management components.The software there can then leverage software running on the routers through the old Juniper PSDP program, and through that could even, in theory, be linked to special “primitives” programmed into the new Trio NISP chip.

From a selfish vendor perspective, the most important thing is that Juniper ties the service layer development downward into its devices (through its router development programs like the old PSDP) and even potentially down into the chips themselves. That creates a value circle for them and it also lets operators build differentiation by linking their service solutions tightly into the network, giving better integration, operations, and performance than OTT players could achieve.

Juniper released applications for Ethernet activation, surveillance and monitoring, and problem management in the network. These are built on the Junos Space architecture. This new model is so radical that frankly it’s hard to believe it came out of Juniper, never known either for software or for making game-changing moves. This is clearly one such move, though, because it will at the minimum catalyze the whole service-layer marketplace.

Juniper also announced an expansion of its IBM OEM deal to include the SRX, which offers security control and falls under the Junos Space software umbrella at least in a development sense.

Finally, BLADE Network Technology announced it would license Junos for blade server switches, possibly the first porting of a network OS to another platform. Just assimilating all of this will no doubt create some headaches, but early indications from operators suggest they’re very interested, and there is also surprising early interest among large enterprises, particularly in the cloud computing potential.

Amazon is also more of a “true cloud,” in that it offers greater flexibility and elasticity and imposes no major restrictions on applications (an x86 image is required). SaaS is also likely an early market for cloud computing because by nature it is incremental to current IT plans.

For cloud computing to be successful, though, it will have to move outside of these simple sideline and overflow missions and take on more mainstream applications. We believe that this can happen only by having enterprises adopt private cloud architectures for their own data centers, which would facilitate integration of public cloud resources.