Post Magazine

December 2013

Issue link:

Contents of this Issue


Page 41 of 51

STORAGE OUTLOOK By Steve Modica CTO Small Tree Oakdale, MN 40 Looking back… and ahead I often get asked to talk about the future. I get to see products being developed that are really exciting (people are often trying to sell them to me). I've seen three or four generations of solid state drives (SSD), many derivatives of "smart" network cards that could subvert some of the worst problems with the TCP stack, and some really amazing protocol technologies (FCoE, Infiniband). Intel has released several technologies like QPI interconnects — so CPUs can share memory and IO hardware — and some really amazing IO offload technologies. In each case, when I see all this cool stuff, I have to spend time thinking about it. I have to try and understand how it works, whether it will be available in a reasonable amount of time, what it will cost, and how we can integrate it? Will it work with our (Small Tree) products? Do I even need these improvements? For example, if the disks are the bottleneck, a faster network card isn't going to help.There's always a "scoping" period where we're trying to decide if any of this makes sense? Once we get through all of that and make our decision, we have to commit on several levels. We have to commit to writing software, testing samples, putting together price book entries and setting up demos for customers and trade shows. It's actually a huge investment even before a customer ever hears about the new technology from Small Tree. So now that we're approaching the end of another year, I thought it would make sense to consider some of the things that I was really excited about but haven't yet panned out. For me, there were two specifically. First, I was really excited about FCoE. FCoE is great technology. It's built into our cards, so we get super fast offloads. It uses the Fibre Channel protocol, so it's compatible with legacy Fibre Channel.You can buy one set of switches and do everything: Fibre Channel, 10Gb and FCoE (and even iSCSI if you want). So what's the problem? Well, the first problem is that the switches are too darn expensive! I've been waiting for someone to release an inexpensive switch and it just hasn't happened. Without that, I'm afraid the protocol will take a long time to happen. So as things stand today, FCoE has not taken off like I expected it would. I'm not sure it's going to. I'm disappointed. Second, solid state drives. I'm quite sure SSDs are the way of the future. I'm also quite sure SSDs will be cheaper and easier to fabricate than complex spinning disks. So why haven't they exploded yet? Where are the 2TB and 4TB SSD drives that fit into a 3.5-inch form factor? Why aren't we rapidly replacing our spinning disks with SSDs as they fail? As I understand it, we're constrained by the number of factories that can crank out the NAND flash chips. Even worse, there are so many things that need them, including iPhones, desktop devices, SATA Post • December 2013 disks, SAS disks, and PCIE disks. With all of these things clawing at the market for chips, it's no wonder they are a little hard to come by. I'm not sure things will settle down until things "settle down" (i.e., a certain form factor becomes dominant). What does this mean for you heading into 2014? It means that for the foreseeable future (i.e., next year), we're still going to be seeing 3.5-inch drives and iSCSI for block storage. Were there any good news stories to consider for 2013? Why yes! In fact, there were two that I can think of. First, I'm really happy with Thunderbolt. Small Tree spent a lot of time updating our drivers to match the new spec. Once this work was done, we had some wonderful new features. Our cards can now seamlessly hotplug and unplug from a system. So customers can walk in, plug in, connect up and go. Similarly, when it's time to go home, they unplug, drop their laptop in their backpack, and go home. I think this opens the door to Small Tree's ThunderNET line takes advantage of Thunderbolt connectivity. allowing a lot more 10Gb Ethernet use among laptop and iMac users. Additionally, Apple's added Thunderbolt bridging. So now, if you have a couple of Macs you want to connect quickly and without spending a lot of money, just run a Thunderbolt cable between them. It's fast, doesn't involve much hardware, and it's as easy to setup as an Ethernet port. I can see that the new Thunderbolt 2 products that are coming are going to be very slick. I can't talk about any of them, but I think they are going to help make Thunderbolt a very popular technology going forward. Second, I've been very pleased with Apple's new server message block (SMB) implementation. Apple's moving away from the Apple Filing Protocol (AFP) as their primary form of sharing storage between Macs, and the upshot for us has been a much better SMB experience for our customers. It's faster and friendlier to heterogeneous environments. I look forward to seeing more customers moving to an open SMB environment from a more restrictive (and harder to performance tune) AFP environment.

Articles in this issue

Links on this page

Archives of this issue

view archives of Post Magazine - December 2013