With the Advent of HCI, SDS, NVMe, NVMe-oF and SCM, is Fibre Channel Dead (Again) Among this TLA Salad?
You better believe it isn’t
Fibre Channel is a resilient technology. No, no, I don’t mean in the sense that you’re thinking. Sure, it is resilient in that sense too. However, I’m talking about resiliency with regards to resisting the attacks from alternative technologies that position themselves as ‘Fibre Channel killers’. Truth is, Fibre Channel has been declared ‘dead’ by proponents of such technologies several times since its birth in the ’90s, and it’s not like Fibre Channel is that old. It first happened circa 2002, and the technology in question was iSCSI. Ironically, iSCSI has the honor of being one of the technologies that have purportedly killed Fibre Channel more than once.A little backstory
Back in 2002, iSCSI worked at a whooping 1 Gbps, right on the heels of the industry’s transition from fast Ethernet (which operated at 100 Mbps) to gigabit ethernet, while Fibre Channel was just transitioning from 1 Gbps to 2 Gbps speeds — we were just releasing the Brocade SilkWorm 3800 and 3200 switches based on our ‘Bloom’ ASIC, and our first Fibre Channel director, the Brocade SilkWorm 12000. Why, then, would anyone consider iSCSI as a viable alternative to Fibre Channel for a Storage Area Network? Well, the message is typically the same: Fibre Channel is expensive, Fibre Channel is complex, it requires dedicated infrastructure and specialized skills; whereas IP/Ethernet is affordable, ubiquitous and everyone knows how to manage an Ethernet network, plus everyone already has an Ethernet network! Those statements are all half-truths. A wise man once said “’Tis better to have loved and lost than never to have loved at all”, and the same man also said, “A lie which is half a truth is ever the blackest of lies”.
“A lie which is half a truth is ever the blackest of lies.” — Alfred Lord Tennyson
Of course, we all know what happened: Fibre Channel continued to be the dominant storage networking technology — particularly for mission-critical applications that required the highest levels of performance and availability — and iSCSI became an alternative for some environments where performance and reliability weren’t necessarily at the top of the requirements list, and instead ubiquitous connectivity to a shared storage pool was the main goal. After all, server virtualization was pushing hard to break out of the test and development environment, and it required all the physical servers to be able to access a shared storage pool. And that’s exactly what storage area networks had been born to facilitate.The convergence wars
Enter 2008, and it was Fibre Channel over Ethernet’s (FCoE) turn to claim that the death of Fibre Channel was imminent, this time when the industry was riding the transition to 10 gigabit Ethernet and Fibre Channel ‘only’ delivered 8 gigabits of bandwidth. Once again, the proponents of convergence — that was the operative ‘buzz word’ at the time¬ — would make the same arguments: Fibre Channel is expensive, Fibre Channel is complex, it requires dedicated infrastructure and specialized skills; whereas IP/Ethernet is affordable, ubiquitous and everyone knows how to manage an Ethernet network, plus everyone already has an Ethernet network! The sense of déjà vu was hard to shake off.
The converged promised land
And once again, eleven years later, we all know what happened: Fibre Channel continued to be the dominant storage networking technology — particularly for mission-critical applications that required the highest levels of performance and availability. FCoE found its place where it made the most sense, at the edge of the network, where the consolidation of disparate I/O interfaces for storage and networking was highly desirable: to this day, many blade server architectures still use FCoE to save space and energy consumption within their chassis, but no one thinks anymore — not even Cisco — that SANs and LANs will converge in One Big Network™ and that everything will be Ethernet forevermore.The cycle of life
But if history does one thing, it’s repeat itself. All. The. Time. So now, as we ride the flash transition towards a world where NVMe has replaced SCSI, the proponents of Fibre Channel slayers are once again positioning several Ethernet-based technologies as alternatives and making the same arguments all over again: Fibre Channel is expensive, Fibre Channel is complex, it requires dedicated infrastructure and specialized skills; whereas IP/Ethernet is affordable, ubiquitous and everyone knows how to manage an Ethernet network, plus everyone already has an Ethernet network!
However, over the last several years, we have seen Fibre Channel under attack not only by alternative protocols for traditional block-based SANs, but also by completely new and innovative shared storage architectures that claim to entirely forgo the need to deploy a ‘legacy’ block-based storage network and to purchase expensive, ‘monolithic’ storage arrays. Ain’t that something. Of course, I’m talking about alternative architectures like Hyperconverged Infrastructures and Software-Defined Storage.
HCI and SDS promise to deliver us from the chains of managing storage arrays or a storage network altogether. They are complementary technologies: in general, HCI just adds the hypervisor layer to an underlying SDS infrastructure, combining both compute and storage in building blocks or ‘nodes’ that can be stitched together over a network. The internal storage of all the different nodes is virtualized and made available to the hypervisors in a fully integrated way. In fact, these technologies are often called Virtual SANs (VSAN) or server SANs. Their main benefit is that they promise to integrate the provisioning of storage resources into the workflow of provisioning virtual machines and therefore greatly simplify storage provisioning and operations altogether, since there’s no external storage array or a storage network to actually configure, provision, monitor and manage. On paper, these are definitely great benefits and are really appealing to IT admins and, more importantly, IT directors and CIOs.
Monolithic storage array
There is a lot to be said about the advantages and disadvantages of ‘traditional’, ‘monolithic’ storage arrays connected to any form of storage network versus distributed server-based virtual SANs, but that is potentially a topic for a different article. Ultimately, new technologies rarely completely replace and eradicate previous ones, they simply come and take their rightful place in the market: that from which they solve real customer problems, not those made up by vendors to try to prop the technology they are trying to promote. Before the emergence of iSCSI, FCoE, HCI, SDS and an assortment of other TLAs, Fibre Channel was the only option to deploy a shared storage pool, which is the foundation for virtualization and cloud; it was the only game in town. In fact, it was the technology created — by Brocade and other vendors — to enable just that, which certainly fueled its skyrocketing growth of the ’00s and early ’10s. However, choice is a good thing. Now customers have a wealth of options to look at when they want to build an IT environment, and they can choose the best protocol and/or architecture depending on their needs at any given time, or for any particular application. But choice also means uncertainty and doubt, and it’s more important than ever to have clear, concise and accurate information — as opposed to half-truths — to be able to make a good, informed choice about the storage infrastructure you are going to deploy to build your IT services on.
Before I go off on a tangent, however, I’ll leave it here for today. In the next article of this series I will discuss how flash has revolutionized storage over the last decade, and how NVMe has opened a door for new Ethernet-based storage networking alternatives to claim, once again, that Fibre Channel is dead.
Want to see more on the performance differences between fabrics with all-flash, check out this ESG paper: The Performance Benefits of Fibre Channel Compared to iSCSI for All-flash Storage Arrays Supporting Enterprise Workloads