Friday, December 19, 2014


It has been a busy time for me and while I have continuously followed what's going on in the IT market, I did not have time to sit down and digest. So before 2014 is over, let's have a look at some recent news and how they fit into current trends:
If I had to summarize what I see going on right now is three major areas of excitement and start-up-activity:
  • Converged and Hyper-Converged Systems, goes hand in hand with the "software defined datacenter" topics and the Server-side SAN solutions.
  • Flash Storage and the question how a future "memory" or "storage" hierarchy will look like?
  • Cloud and all kinds of "managed services". Combined with the question which parts of IT will be on-premises - and what will be off-premises in a future scenario?
Along these lines, here's a writeup of recent news: The article here is a great analysis by industry veteran Jon Toigo about the new storage hype around server-SANs and the proclaimed death of the storage array as we know it. He states that "...there's no such thing as a true storage network, at least not one that fits the ISO model of networks. We have storage fabrics with switched DAS (SANs), and we have DAS with thin file server appliances (NAS). So, the idea that virtual servers won't work with anything but server-side direct attachment is silly."

It's impossible to understand server-SANs without knowing some details about VMware VVOLs (and here), VSANs (see also here), and most recently EVO:Rail Check the respective links for an explanation of each!
Please see my blogpost from Sept. 2013 as well, plus a great comparison of Hyper-Converged solutions here!

So while VSANs let's you control direct attached server storage from VMware, VVOLs provides a new construct (beyond NAS and LUNs) to manage external/SAN storage from VMware. And EVO.Rail (based on VSAN technology) is a complete software bundle from VMware which enables vendors (Dell, HP, and others have announced intents) to build their own "hyper-converged" appliances.

Reminds me of good old days of IBM mainframes where the "IO subsystem" was defined and under control of the base operating system. VMware obviously wants to gain control over the storage side of the datacenter and -in my opinion- they have a fair chance of winning that bet.

On to Flash: Combining the converged and flash hype will result in solutions like the one here: "Nutanix introduced a new all-flash storage appliance and a new feature that enables continuous availability across data centers."
And last week from Flash-leader PureStorage"Pure and Cisco have dreamed up FlashStack converged infrastructure (CI). This is a combination of combine Pure’s 400 Series arrays, Cisco UCS Blade Servers, Nexus switches, VMware vSphere 5 and Horizon 6".
However, this is mostly an unilateral attempt from Pure to hook up with CISCO - you will not find that specific solution on the CISCO CVD (CISCO validated design) site. No surprise; as they already have Invicta (to be integrated into UCS) and have created solutions with Nimble as well.

Closing todays comments with very recent news on AWS (Amazon web services):
"Amazon added storage features at its AWS re:Invent conference in November. They include support for larger and faster volumes on its Elastic Block Store (EBS). The enhancements center on solid-state drive (SSD)-backed EBS, which was launched back in June in all AWS regions. Amazon calls SSD EBS the fastest-adopted service in its Amazon Web Services portfolio."

What if - someday we may start over with a very disruptive and new way of computing? While dating back to Summer, the vision of "The Machine" sounds somewhat appealing to me!

Thursday, September 25, 2014


Networking news this month: Will 25 Gbps Ethernet be the next speed of choice? Read here why there's a couple good reasons to think so: "The next generation of Intel "Grantley" CPUs are due to ship in the third quarter, and servers with these processors will be able to forward data faster than 10 Gbit/s. In the high-density server farms of cloud providers like Google and Microsoft, using multiple 10 GbE would require twice as many Ethernet switches with their associated space, power, and cooling costs."

And on the Fibre Channel side of the market, CISCO quietly (and maybe reluctantly?) roles out a bunch of 16 Gbps products:
A new low-cost 16 Gbps switch (MDS9148S) and a smaller model of the MDS 9710 director (MDS 9106), a 192-port director in a 9U form factor!

Tuesday, August 12, 2014


Lazy summer days - mostly wet and rainy this year. So lots of time to read blogs and follow the IT News-tickers!

Here's what I found to be interesting news in the last couple weeks - sorted by "level of excitement".
First sighting of phase-change memory (PCM) for commercial use in SSD's: at the 2014 "Flash Summit Conference" HGST (subsidiary of Western Digital) did showcase a blazingly fast SSD device not based on Flash memory but PCM, as Computerworld reports here:
" The device, which can be plugged into a server's PCIe slot like any SSD, isn't a new storage product but a platform for demonstrating a low-latency interface that the company developed with future solid-state media in mind. It implemented the experimental communications protocol in a Linux driver on the server and in the SSD's embedded software."
"Where NAND Flash takes about 70 microseconds to respond to a request for data, PCM can do so in about 1 microsecond. However, it will take two to three years of hardware development before PCM gets dense and cheap enough to compete head-on with flash"

Also read the stories on that same subject in "The Register" and the related HGST Press Release.

As noted above, new low-latency technology like PCM will require new architectures and will have to reside "right next to the CPU" to actually take advantage of the available speed!
To that end, HGST has developed a new low-latency interface dubbed "DC express". 
Watch this excellent 15' video clip here!

So you should really think of PCM as a lower cost DRAM rather than a high performance Flash Array. Will be interesting how this will affect "storage tiers"!?

Now, don't count Flash SSD's out yet: As reported here, there is a whole family of bigger (up to 1.6TB) and faster (12 Gbit/s SAS) SSD's entering the market these days!

Friday, July 25, 2014


It's about time to resume blogging and edit an update to my Blog. I have been "out of IT" for a few month - between Jobs - and now back to the grind.
One of my off-IT activities: Travel Maui

Good thing is that I realized during my time off: there's plenty of great things to do and think outside of IT; sad thing is, I also realized that only in IT, I have enough marketable skills to be able to pay my bills.
So back to IT business...
Topic today is pretty straightforward. Cloud and Flash!
I think those are pretty much the buzzwords that, as someone looking into our industry in summer 2014 would realize, are discussed most frequently.

Now looking at these trends and the technologies cooking in the labs, I've come to the conclusion that the two can be combined in what I believe to be a true statement:
"By 2020, all data will be either stored on Flash or in the Cloud"
There's a couple reasons why I think this statement may become true, listed below are a couple market and technology trends from the last couple weeks which seem to point into that direction.
But the very basic physical reason for it is "latency": Response time for any IO from the cloud is always measured in milliseconds (at least - try a PING if you don't agree) while response time for any IO from a Flash System is always measured in microseconds. Means that Flash will always sit either in the server or right next to it (next like: a couple meters away)!

Let's start with Flash: See these two great articles about function and design of all-flash arrays  (by George Crump of Storage Switzerland) vs. advantages of hybrid storage arrays (by HDS CTO Hu Yoshida). And then add this news from the Samsung lab (Samsung being the #1 provider of NAND Flash) about first shipments of 3D Flash.

On to the Cloud: As the Register article here states: "CIOs will likely increasingly say: dump the data center hardware ship and ship the data up into the cloud."
A couple vendors actually announced functions and plans to that end in the past couple weeks: Netapp ties in with the Microsoft Azure cloud (more details here);
while mighty EMC announced (among a flood of other solutions, plans, products, and the intend to acquire Twinstrata) the availability of a cloud gateway option for the new VMAX3.

As discussed above, cloud data storage will most likely not be based on relatively expensive and fast Flash technology for the years to come. The most obvious candidate for efficient, cheap and reliable cloud storage is rotating disks - HDD. And a second, surprising -but also likely candidate- is good old Tape!
In case you missed the May announcement about IBM's 154TB-Tape demo: Listen to the details here!

Wednesday, April 23, 2014


Well, some of you know that I'm on a two month sabbatical now - away from my previous job at IBM.
So I have not been following the storage market very closely these days - but have focused on other (more?) important things in life - like mountain biking and enjoying hikes with my family.

The great thing is that we had a beautiful spring this year in Zurich with lots of sunshine and warm weather, as you can see in the weather report for March here!

Still, there was a couple things that caught my attention and they are around SDN (software defined networking): While I was doing online research and was trying to figure out, where the industry is going in relation to this topic, I found a great series of blog posts and articles over at the InformationWeek site (thanks folks!).

I have summarized these for you:
First, start here with an industry overview and download the SDN market report (login required).
Then, you can read a detailed analysis by vendor - what their strategies and solutions are:
Part 2: CISCO, Arista and HP
 Details for CISCO ACI (application centric infrastructure), part 1 and part 2.
Part 3: Juniper, Brocade, Dell
Part 4: VMware, Avaya

Monday, March 3, 2014


Two major topics today: Object storage and cloud. And YES, I believe the two are in fact very closely related: Objects (defined as unstructured and permanent, unchanged data) seem to be by far the best fit for data to be stored in the cloud!
To get us started - and if your are like myself still trying to come to grips with the object Hype - here's a great Object Storage 101 for your reference (thanks George Crump!)

And Chris Mellor -over at the Register- points out that object storage is ".. headed towards mainstream status, with ViPR, Black Pearl and EVault leading the way. Others, though, held back. As of the year end, we saw IBM doing nothing much with objects, NetApp apparently standing still with its StorageGRID, and Dell exiting the field." Read the details here!

Now, expanding the focus and looking beyond objects and storage only, using cloud services may not be the nirvana many CxO's are dreaming about: Forbes recently had a great article about this and made the point very well by listing the following checkmark items for cloud management:

This means that at any moment a CIO must be able to answer the following questions:
  1. Are all the applications and services in our control running properly?
  2. Are all the applications and services running in the cloud or as SaaS running properly?
  3. Is there a network problem in the network under our control?
  4. Is there a network problem in the public Internet?
  5. Is there a network problem in the network of the cloud or SaaS provider?
I like numbers 2. and 4.!

Still, cloud becomes more popular and less expensive by the week - as the most recent price war between the cloud "behemoths" Amazon and Microsoft shows:


Wednesday, February 19, 2014


Two articles on the long-running competition between FC and FCoE caught my attention this past weeks:
The major argument for high-speed 16 Gbps native FC connections these days are high-performance (and more importantly: low-latency) SSD and Flash storage systems: Evaluator Group recently did a benchmark to compare the two technologies with a series of state-of-the-art SSD Systems and here's what they found:
"The resulting validation found the FC environment provided 2 to 10 times faster responses as workloads surpassed 80% SAN utilization and 20-30% less CPU utilization than FCoE."
for the complete Report, please refer to the Website here (registration required).

At the same time, the adoption of 10 GbE is obviously picking up speed (as reported here), so -as so many times before in our industry- the lower cost datacenter connectivity (10 GbE) may be just "good enough" in the long run!

Monday, January 6, 2014

January 2014

Welcome to 2014 (or MMXIV)!

I'll spare you another round of forecasts about what might and might not happen in the storage industry in 2014, there have been plenty of those lists published in the past couple weeks!
Instead, let me summarize a couple noteworthy news for you - which of course is also a way to hint at what -I personally believe- will be important trends in 2014!
One battle certainly to continue is the battle over the control over storage or rather the "location of the intelligence" in storage: remember 10 years ago: common wisdom was that most of the intelligence would be located in the SAN and the back-end storage would be mere commodity (EMC Invista!). Well, it turned out that customers preferred to invest in sophisticated storage controllers while the network became a commodity...
Fast forward to 2013: There is a lot of hype around SDS (Software Defined Storage), which would relegate the "intelligence" to some "open source" storage controller running on a commodity server.
Hypervisor vendors like VMware and Microsoft on the other hand are integrating more of the storage controls into their hypervisors and hope to make storage intelligence obsolete. And obviously related to that is the discussion and battle about block or file access to storage.
The article here outlines reasons why VMware needs to step up efforts on NFS!
But watch out, on the block side of the protocol segment, the FCIA is finalizing 32Gbps Fibre Channel - or Gen6 Fibre Channel as they are going to call it.

According to "The Register", 2013 was the year "..when Google made Tape cool again"!
Now there is more exciting news to be expected in 2014: Read this summary from the Fujitsu "IT Global Summit" and the "Nanocubic coating" being introduced for magnetic tape!
So watch this space for announcements from IBM during 2014!

Talking about IBM, there's two recent news that clearly show the direction my company is taking: First, the beta availability of ICStore, a unique implementation of "cloud gateway" technology for our Storwize platform providing data protection " ..that will allow organizations to use multiple cloud storage services interchangeably, reducing dependence on any single cloud vendor and ensuring that data remains available even during service outages."

And second, the rollout of WaaS ("Watson as a Service") in late 2013:
“The next generation will look back and see 2013 as a year of monumental change,” said Stephen Gold, vice president of the Watson project at IBM.
This is the start of a shift in the way people interact with computers.”
IBM is wielding Watson in a fight to control the world of cloud computing — huge collections of computer servers connected over the Internet — with other big technology companies like, Google and Microsoft. It is no coincidence that IBM discussed its Watson news the same week Amazon was hosting clients at a conference here to pitch its own computing cloud, called Amazon Web Services or A.W.S."
This is definitely a key element of IBM's plans to resume revenue growth in 2014!
And by the way: Probably the last acquisition IBM made in 2013 is immediately related to cloud services: Aspera, a company with ".. an Emmy-award-winning, high-speed bulk data transfer protocol."

So all the best to you for 2014 and let's hope that the European economy continues on the positive trend that we seem to have started in Q3 2013!