FCoE seems to be a harbinger of network divergence rather than convergence. After discussion with QLogic and hearing about 16Gbit/s Fibre Channel and InfiniBand as well as FCoE, ideas about an all-Ethernet world seem as unreal as the concept of a flat earth. This train of thought started when talking with Scott Genereux, QLogic' …
I came to this conclusion myself as well about a month ago after attending a local Brocade conference where they went over their road map among other things. The marketing folks
at least up till now have been pretty successful at in implanting the impression that the world is moving to CNA. But it seems clear that as your article states we're not going to see true converged networking based on ethernet for a very long time, if ever.
Another topic I had been thinking about which I didn't see raised in your article is the integration of CNA adapters into servers, specifically when we might see market penetration of servers with CNA-ready NICs onboard, to the same degree that we see GigE today. I suspect that too is many many years down the road. Basically I want an ethernet interface that I don't have to worry about what kind of switch it's plugged into. If it's ethernet it should just work.
With an iron curtain between fiber channel and ethernet core switching technologies well intact(Why did Brocade buy Foundry anyways?) it seems the fantasy of CNA will remain
Only IF you believe in Fibrechannel
What you say is true...if, and only if, you believe that Fibrechannel is the only storage choice.
If you have FibreChannel, then FCoE doesn't look great. If you are using iSCSI or NFS then FCoE looks awful.
FCoE is a technology that joins these two worlds. No one wants it, no one understands its purpose but its like VoIP convergence all over a again. FCoE is to storage what H323 was to voice, not perfect but a workable transition.
smells like wishful thinking by FC vendors...
...FC vendors who are very afraid of Cisco.
Ethernet is not the end-all, be-all. Strictly speaking, for storage it clearly is trumped rather handily by numerous technologies including Fiber Channel and Infiniband. But technical superiority does not guarantee success.
iSCSI is pulling a ton of market share away from FC not because it is better, but because it is *good enough* for many uses and it's a lot cheaper especially when you stop paying for HBAs and overpriced array-specific MPIO software. (*cough* PowerPath) FCoE might do the same, maybe, if it can be proven to be sufficiently better than iSCSI to bother with.
Hardly any server taps 4Gbit FC as it is. 8Gbit FC and 20+ Gbit Infiniband are very niche technologies, or implemented by fools. --And there's not too many fools left, besides government agencies. :) Here in the US I'm sure we'll see some 'stimulus' funding ridiculous IT projects.
The day in which we completely eliminate FC switches may not be when we go to 10GbE iSCSI and/or FCoE, or something new that truly enables convergence, but it is definitely coming. QLogic is rightfully scared about no one buying their HBAs anymore (FC or iSCSI)-- and get real, no one buys their FC switches to begin with.
Users see through the hype
You make some great points. I think confusion stems from the notion that FCoE is a one-size-fits all technology. It is not. There are plenty of users that like Fibre Channel and have no need or desire to move storage to Ethernet. These users will continue to use Fibre Channel for a long time. There are also plenty of users that do not use Fibre Channel (only 20% of servers are SAN-attached), but instead use NAS or iSCSI. So why would they switch to FCoE if they have no storage management schemes to leverage and are already “converged” onto ethernet? They probably won’t. Also, simply upgrading Ethernet to 10G by itself reduces much of the cabling complexity and operating costs that FCoE claims to address (provided it is power efficient and low cost). With that said, many users will adopt FCoE, but they will be careful to make sure all the new pieces (lossless ethernet, driver stacks ported to new controller architectures, switch management ported to Ethernet switches) work before they deploy it for storage, much less converge all their server traffic on it. I believe the likely scenario is that users who deploy FCoE will do so because they are already using Fibre Channel and want to migrate their storage networks to an all Ethernet scheme. Convergence at the server is something to consider after the kinks have been worked out down the road.
Brocade's Take -- Hear Here! (or something like that)
Completely agreed on more than a couple points. Have a couple of pieces here illustrating same, one is a video of CTO Dave Stevens discussing FCoE reality from the (financial) analyst day. It's the featured video on our YouTube channel here: http://www.youtube.com/brocadevideo.
The other is a blog post from SVP of Products and Offerings Marc Randall posted just today, and addressing the organizational issues brought up on page two here. It's available on our Wingspan blog here: http://community.brocade.com/home/community/brocadeblogs/wingspan/blog/2009/06/25/what-you-do-speaks-so-loudly . You can tell from the title, "“What you do speaks so loudly…” where this is going.
Ultimately, we are supportive (we have launched FCoE products and will continue to do so) but pragmatic about "convergence", looking to and developing for future needs while supporting the current and near-term.
Thanks for helping your readers keep their feet on the ground and their productivity in focus with this piece.
Brocade Public Relations/Social Media
Server Ports = Most Ports on Any Network
Whether SAN or LAN, the highest number of ports in any network are the access ports. In a SAN, hundreds or thousands of server ports are multiplexed out of a handful of storage array ports. In between might be some number of inter-switch link ports.
So if you want to consolidate a network with the biggest ROI, consolidate at the edge first. This is why Ethernet has been so successful. Four 100BT Fast Ethernet ports were consolidated to one GigE port. Now servers with four GigE ports and two 4Gb FC ports can consolidate down to two 10GigE FCoE ports. That is real savings, not in the CNAs, but in the access layer switch ports.
As for CNAs, all of the major vendors who make LAN on Motherboard silicon are looking at 10GigE LOMs which support FCoE. FCoE will become a feature of the NIC, much like other hardware based protocol offload is today. Then customers will be able to make a simple choice based on protocol. To leverage existing FC storage, and existing FC storage drivers and multipathing software, using FCoE. To access file storage, use NFS. If you want to buy new iSCSI based storage (or leverage iSCSI ports on existing storage), choose iSCSI.
Too many people think FCoE is a new form of iSCSI which will require end to end iSCSI storage arrays, dedicated networks, and server adapters. FCoE is not about that. It is not about introducing new protocols, but leveraging a single wire type. The very fact that it does not replace everything (or force replacement of everything), is what makes it a good solution.
- Vid Hubble 'scope scans 200,000-ton CHUNKY CRUMBLE ENIGMA
- Bugger the jetpack, where's my 21st-century Psion?
- Google offers up its own Googlers in cloud channel chumship trawl
- Interview Global Warming IS REAL, argues sceptic mathematician - it just isn't THERMAGEDDON
- Apple to grieving sons: NO, you cannot have access to your dead mum's iPad