NetApp - On The Edge

F is for FCOE

is for FCoE.

Or Fibre Channel over Ethernet. NetApp announced last week providing a convergence-ready, end-to-end 10G infrastructure solution for FCoE.

NetApp has been the leader in Ethernet and TCP/IP-based storage. Redefining the landscape of file services with a unified architecture for UNIX and Windows networking. Later being the largest supplier of iSCSI-based storage solutions in the industry when we introduced iSCSI support for a new standard for block storage access.

In the storage world, the letter 'F' until recently meant Fibre Channel SAN. A separate high performance storage network for deploying critical applications in the data center. NetApp storage supports traditional Fibre Channel SAN solutions, of course. But the emergence of solutions like iSCSI certainly posed the question more forcefully of "Can I get to a single networking infrastructure for my data center?"

FCoE provides a way. The enabling underlying technology is Data Center Bridging, or DCB. The Fibre Channel networking standard provided a reliable physical transport for the encapsulation of SCSI for SAN storage deployments. DCB brings a set of features to Ethernet that finally allows for the physical fabric convergence that has been elusive to date. Two standards bodies were required to drive towards an FCoE solution. The IEEE driving the Ethernet standard, and T11 driving the requirements around the support needed for storage.

In October 2007, NetApp and several partners demonstrated a prototype FCoE solution pointing the way to the product announcements and solutions available today. Much of the direction in FCoE is tied towards the march of Ethernet to 10 Gb/s and beyond. 

What does this mean practically to you? As technology is refreshed and  you are looking at storage architectures you are now able to look at a single networking infrastructure in your data center. From the storage architect's viewpoint, FCoE provides a storage solution that co-exists with traditional FC-SAN deployments and the simplest path forward toward a single wire standard in the data center. FCoE and FC-SAN can be managed in the same way. From a green perspective, FCoE makes sense. As Ethernet bandwidth continues to leap forward, a single infrastructure can halve the number of ports coming from a host, and reduce the power consumption. All with a physical network that is compatible with TCP/IP, iSCSI and NAS solutions. The convergence-ready aspect of our announcement is that the 10GbE adapter runs FCoE today in initial release, and we are demonstrating and qualifying the other storage protocols now. This makes a lot of sense from many perspectives.

Technology change takes time, standards bodies at their best step in and provide the framework for new products and solutions. Bob Metcalfe, the co-inventor of Ethernet, allegedly quipped once "I don't know what the networking of the future will look like, I only know they will call it Ethernet." (If any reader has any information on whether that quote is true, or where it was first attributed, let me know - because I cannot verify it). It is turning out that not only is that what it will be called, but that it will be Ethernet in actuality also.

I did have the opportunity to meet Metcalfe when he was inducted as a fellow of the Computer History Museum last October. I handed him a bottle of wine as a gift, and when he asked me why I replied "Because of you I have a job. I work at NetApp and we're a leader in networked storage. And Ethernet is the network."

Things Brewing at the IETF

Magnus Westerlund is not only an award winning amateur brewer, he is, with Lars Eggert, co-director of the Transport Area at the IETF. In one sense, I report to them in my capacity as co-chair of the NFS Version 4 Working Group.

I remember when the NFS Version 4 working group started and the decision was made to place it in the transport area as opposed to say the applications area. There we were with TCP/IP, right in the thick of things. Like many working groups, NFS started in recognition of a simple fact - increasing amounts of data were being sent over the wire using some version of NFS, and the IETF was interested in that it play well with others.

There are domain experts for NFS sprinkled throughout the industry and academia. It existed before it became an IETF working group, and protocol change was managed by Sun Microsystems. Why go to the IETF? Frankly, a primary interest NFS marketers wanted was the imprimatur of the IETF on NFS as a standard. But looking back on the real work we've engaged in, I think the IETF brings to bear on any protocol development broad expertise on formal protocol design, security considerations and "play well" behavior on the Internet. And a well established structure for protocol agreement, approval, and publication.

NFS existed before and was in wide use and is one of the two protocols primarily forming the NAS industry as we know it today, the other being the proprietary CIFS (or Windows File Sharing protocol) from Microsoft. The evolution to NFS Version 4 is still happening, with NFS Version 4.1 with support for Parallel NFS (pNFS) in the last stage of the RFC Editor queue ready for release.

I think a fair question to ask is "Can a standards body like the IETF have impact on the industry?" Looking at storage, look no further than iSCSI which was brought into the IETF as a draft proposal by IBM, Cisco and EMC. It evolved rapidly (as far as standards work goes) using the IETF process of feedback and rough consensus to launch a segment of the storage industry that is still growing. The impact of the IETF can be huge.

That said, Lars and Magnus host a transport area dinner at each IETF, and last Wednesday at the Monks Cafe (a phenomenal selection of beer) in Stockholm, Lars asked a provoking question "What should the IETF stop doing? And what should it start doing?" It was a rather unexpectedly animated discussion. I think two or three things stood out. First, the IETF must start recognizing more quickly emerging trends for data transport on the Internet, and embrace new approaches for sharing. This came up around peer to peer technologies like Bittorrent that see IETF activity in the LEDBAT working group. Other trends are occurring around collaboration that bear embracing. Second, related standards can impact the IETF. David Black of EMC reminded people of a discussion we had last meeting of lossless Ethernet standards and the need for the IETF to assess their impact on the basic protocols in use in what is informally called TCP/IP. Third, is the opportunity cost of managing working groups whose charter is not gaining traction at producing results, to cut the group as soon as possible and make way for something more important.

It's not all serious at the IETF, I think several of of choked or spurted when one individual stated "My job is to collapse the Internet." At least I thought that was what they said. Certainly something to stop doing.

One thing of interest to storage professionals is STORM, a proposed restart in the small of the iSCSI working group to pick up fixes and new SCSI command support as needed since the original, successful iSCSI specification was released.

As standards bodies go, I like the IETF. People passionate about protocols getting together in a collaborative forum to improve applications and infrastructure for the Internet. I do think the Transport Area is the coolest place to be, if only to have access to someone to play Santa Claus around the holidays.

For more background on the IETF, feel free to browse the library of IETF Journals edited by my friend Mirjam Kuehne.

Inspiration

Inspiration - for a blog entry - can take many forms. Today it took the form of a venture capitalist.

For a technologist, Silicon Valley is a cool and sometimes strange place - and I found out a long time ago this was where I belong. The hub of innovation in computing, with engineers, companies, and infrastructure (such as sources of funding) to be found as no where else in the world. People have written books about their experience here. Through a couple of connections I ended up having a coffee at Caffè del Doge with a VC today. We chatted about - you guessed it, storage.

Storage is an exciting field to work in today. With disks getting big and cheap, coupled to continued innovations around storage efficiency (at NetApp that means deduplication on top of thin provisioning, RAID DP, and fast efficient snapshots among other things) people are storing more and more stuff. This stuff is getting increasingly interesting (for example, vast quantities of rich media being access on-line by millions of people). Leading to interesting problems in scale, performance and cost. And problems are what interest engineers. But storage today is not just about disks.

Our talk turned, no surprise, to Flash. Repeat after me "Flash changes everything." I had talked once before about drivers of innovation here, and one pure driver is technology change and disruption. I mentioned over coffee that Flash is a textbook disruption in that it is not a panacea. Large amounts of cheap random access memory changes how one views a broad class of problems. When the amount of direct access memory gets large enough, it disrupts the traditional storage equation. But the technology itself has interesting behaviors around wear and read vs. write performance. The bigger questions (from an investor point of view, like say a VC) are where the disruptions will occur in the data center and network, what will the future application infrastructure look like, and where will Flash provide the most customer value?

Again, I love Silicon Valley, it was either driving up to a sushi party in Oakland Friday to catch up with a lot of the original BSD crowd, or on our way to a Sharks game Saturday night (they won) where Steve Kleiman said that predictions about how technology disruptions like Flash will affect things are less predictions and more possibilities. And, engineers love technology possibilities. Because they provide fresh viewpoints to existing problems, and present in turn new problems to solve in exploiting the "new" technology itself.

Kostadis Roussos is one of our truly original thinkers here in NetApp. He stepped back from the trends in Flash and storage and came up with some basic conclusions on where this stuff is heading, and was able to articulate it in a fairly bold way. But that is a NetApp internal conversation. 

As I mentioned to the crowd at the recent FAST conference reception, there were a good number of students at the conference entering the storage industry at a time of great change. So many opportunities for innovation!

And Silicon Valley is a great place to be in the middle of this time.

In an example of poor planning on my part, I failed to grab a picture to post with this blog, so after saying hello to Bryan and Mark at Modernbook Gallery a couple blocks away, I went back to Caffè del Doge and ordered a cappuccino and took a couple pictures. In one of those Silicon Valley quirks, one of the investors in Caffè del Doge is a CTO from another start up success here. That made five shots of espresso in a couple hours - this blog nearly wrote itself. They really do make great coffee, stop by.