Storage

iSCSI is the future of storage

iSCSI is here to stay and will eventually supplant a significant portion of the installed base of Fibre Channel SANs out there. Further, as organizations make their initial forays into block-level shared storage, iSCSI will beat Fibre Channel more often than not.

This week, HP announced their $360 million acquisition of LeftHand networks. Last year, Dell surprised the tech industry with a $1.4 billion purchase of the formerly independent EqualLogic.  With these iSCSI snap-ups by true tech titans, iSCSI has officially arrived, is here to stay, and, I believe, will become the technology of choice for most organizations in the future.

This is not to say that iSCSI has been sitting in the background up to this point.  On the contrary, the technology has taken the industry by storm.  Both of these companies based their entire business hopes on the possibility that organizations would see the intrinsic value to be found in iSCSI's simplistic installation and management.  To say that both companies have been successful would be an understatement.

I'm a big fan of both EqualLogic and LeftHand Networks offerings, having purchased an EqualLogic unit in a former life.  At that time, I narrowed my selection down to two options - LeftHand and EqualLogic.  Both solutions had their pros and cons, but both were more than viable.

It's not all about EqualLogic and LeftHand, though.  The big guns in storage have finally jumped feet first into the iSCSI fray with extremely compelling products of their own.  Previously, these players, including EMC and NetApp, simply bolted iSCSI onto existing products.  Lately, even the biggest Fibre Channel vendors are releasing native iSCSI arrays aimed at the mid-tier of the market.  EMC's AX4, for example, is available in both native iSCSI and native Fibre Channel versions and is priced in such a way that any organization considering EqualLogic or LeftHand should make sure to give the EMC AX4 a look.  To be fair, the iSCSI-only AX4:

  • Does not support SAN copy for SAN to SAN replication
  • Is not as easy to install or manage as one of the aforementioned devices, but isn't bad either
  • The bandwidth to the array does not increase as additional space is added
  • It does not include thin provisioning, although this was rumored to be rectified in a future software release
  • The AX4 supports up to 64 attached hosts

But, the price per TB is simply incredible and a solution based on a different vendor would not have been attainable.  This year, I purchased just shy of 14 TB of raw space on a pair of AX4 arrays-4.8 TB SAS and 9 TB SATA-for under $40K. For the foreseeable future, I don't need SAN copy and space can be managed in ways other than through thin provisioning.  Over time, we'll run about two dozen virtual machines on the AX4 along with our administrative databases and Exchange 2007 databases.  By the time I need additional features, the AX4 will be due for replacement anyway.

iSCSI started out at the low end of the market, helping smaller organizations begin to move toward shared storage and away from direct attached solutions.  As time goes on, iSCSI is moving up the food chain and, in many cases, is supplanting small and mid-sized Fibre Channel arrays, particularly in organizations that have never had a SAN before.  As iSCSI continues to take advantage of high-speed SAS disks and begins to use 10Gb Ethernet for a transport mechanism, I see iSCSI continuing to move higher into the market.  Of course, faster, more reliable disks and faster networking capabilities will begin to close the savings gap between iSCSI and Fibre Channel, but iSCSI's reliance on Ethernet for an underlying transport mechanism brings major simplicity to the storage equation and I doubt that iSCSI's costs will ever surpass Fibre Channel anyway, mainly due to the expensive networking hardware needed for significant Fibre Channel implementations.

Even though iSCSI will continue to make inroads further into many organizations, I don't think that iSCSI will ever completely push Fibre Channel out of the way.  Many organizations rely on the raw performance afforded by Fibre Channel and the folks behind Fibre Channel's specifications aren't sitting still.  Every year brings advances to Fibre Channel, including faster disks and improved connection speeds.

In short, I see the iSCSI market continuing to grow very rapidly and, over time, supplanting what would have been Fibre Channel installations.  Further, as organizations continue to expand their storage infrastructures, iSCSI will be a very strong contender, particularly as the solution is updated to take advantage of improvements to the networking speed and disk performance.

About

Since 1994, Scott Lowe has been providing technology solutions to a variety of organizations. After spending 10 years in multiple CIO roles, Scott is now an independent consultant, blogger, author, owner of The 1610 Group, and a Senior IT Executive w...

14 comments
JV711
JV711

What? Who writes these articles, salesmen for iSCSI products? You can do iSCSI today in Linux or Solaris or on Network Appliance. Its the future, like 2006 is the future. internal SATA DAS = 52Mb/sec read iSCSI = theoretical maximum 12.5MB/sec. Nominal throughout = 4-6 MB/sec WHY WOULD ANYONE BUY iSCSI if they can understand those numbers? And gigE, or 10gigE isn't 10/100 times fast than 100Mbit. Folks, iSCSI is too slow. fiber channel for the enterprise, or go back to the drawing board.

traj82
traj82

Yes truely Iscsi is the future

krautenstrauch
krautenstrauch

Interesting omission of NetApp. Certainly a major player and highly rated. Also, no discussion of FCoE? FCoE will offer a way for enterprises with a huge FC investment to make the transition to next-generation Ethernet networks for storage. I do agree that Ethernet is the future of storage. Convergence of data and application traffic just makes sense.

sjsouchek
sjsouchek

I've worked with NetApp for about the last 5 years. iSCSI is great, between the flex clones and snapshots, life is good, but I still LOVE the way FC fails over with the head. There's a little hesitation using iSCSI, which sucks for busy DB's, and I understand why, but the FC failover is flawless. or cheap test or diskless OS, there is nothing better.

sjoerd
sjoerd

I totally agree. iSCSI is the way to go when you are considering new storage. Implementation is much easier and cheaper. No need to hier storage consultants when you want to change something. I think Lefthand is basically a software solution running on relative standard hardware. EqualLogic is a hardware and software solution with a higher availability in one box. Lefthand campus SAN and synchronous replication are nice though. I'd see a future where slowly but surely FC will start to lose market-share. Personally I compare it to token ring ;-).

quintus
quintus

I think if we're looking into our crystal balls, there may be much debate around its impacts, but iSCSI won't be alone in a couple of years, and I would have liked to see some commentary here how Fibre Channel over Ethernet (FCoE) fits into your longterm vision of the storage industry. http://fcoe.com/

FWS1
FWS1

iSCSI still has a long way to go. If you are deploying it in a Microsoft environment, the iSCSI initiator (the servers side) still has some serious issues with the way it sees the NICs that invariably will corrupt the configuration. Furthermore, iSCSI arrays are very particular about the exact type of switches they are connected to (general specifications are not enough). When you consider an iSCSI solution, you need to add about $15K for switches, and proper server NICs (for low end solutions). Optimizing throughput is another story. As of now, and contrary to what you might be let to believe, iSCSI solutions that work after a near plug-n-play installation are likely to fail and are far from being optimized.

denniscorreya
denniscorreya

I totally agree with this outlook especially for applications that are not real time/OLTP also the low cost of ownership is a definite bonus. This might be a debate once 10mips FC surfaces however. Regards, Dennis

nomasil
nomasil

What other bolt-on type of products do you see? I have Fibre Storage and I would like to add an iSCSI access to it, the only solution I have found so far is an ATTO iPBridge which allows me to provide iSCSI connectivity to my native storage. It is great that all this new native storage is coming out, but it does not help if I don't have the budget for new storage!

kris
kris

The theoretical limit of iSCSI is not 12.5 mb/s, there is no theoretical limit to the throughput other than that put in place by the physical limits of physics itself. With your 12.5mb/s you're assuming a 100 megabit ethernet connection, iSCSI is capable of running over 1 gigabit (125mb/s), and 10 gigabit (1250mb/s) ethernet TODAY! In the near future iSCSI will run over 100 gigabit ethernet (12500mb/s). At the end of the day you can't argue against the economics of commodity servers and commodity ethernet. Regards, Kris

edv
edv

We have had also this problems without jumbo frames and with some storage systems, returned it to the manufacturer and bought a WUDSS based iSCSI-storage with 10GBit NIC. Now we take 35...60 MB/s from ESX 3.5 client with 1GB iSCSI-HBA and 65...83 Megabyte from HW-supported Windows iSCSI Initiator with 1GB Broadcom NIC. This makes altogether about 200 megabytes/second. That's more tricky than FC but not impossible. Our old drawing board is on the shelf only ;-)

bill
bill

With ISCSi you are commited with that type of connectivity Equallogic/LeftHand (only ISCSi connectivity), NetApp I believe there is FC and ISCSI. Why buy a system that you have to forklift upgrade when you can make a long term investment from a manufacturer that has a modular approach where when new transport technologies are released you just change a PCI card or add one? Take a look at Compellent if you are looking to start ISCSi and continue to adapt (add FC, FCoE is released, etc.). www.sidepath.com/storage/index.aspx

Dail
Dail

I expected Cisco to have some decent iSCSI kit at this stage. I know they were working on it. They will probably just buy it

rajakovilraj
rajakovilraj

We got a similar setup.. we have a Clariion CX300 and we needed iSCSI implementation for testing purpose ( latter will be moved to production ). We just added the Stonefly storage concentrator ( now acquired by DNF ) as a host via brocade switch.. and our iSCSI SAN is ready! :).. This is not mentioned in the compatibility matrix of both the companies.. but it works fine. All we have to do is, a manual registration in Navisphere.. Thats all. The iSCSI performance is much much better than our other CX3-10C.

Editor's Picks