Continuing with my theme from yesterday of “purpose-built” blade servers, today we take a quick look at a new offering from Fujitsu.  Now, as you may have noticed, my site has traditionally been focused on blade servers from Cisco, Dell, HP and IBM but this offering from Fujitsu is so interesting, I figured I would write something up.Titled under the PRIMERGY SX label, Fujitsu’s storage blades combines Data ONTAP-vTM software from NetApp, blade hardware and an unknown hypervisor to create a “fully integrated virtual storage appliance.”   The storage solution supports iSCSI, CIFS and NFS protocol and is based on Data ONTAP-vTM features such as SnapShot, FlexVol, SnapRestore and FilerView.

The storage blades come in two flavors:

PRIMERGY SX960 S1 – a storge blade that can hold up to 10 additional hot-plug SAS or SATA HDD/SSD.  These drives offer high capacity with up to 5 TB SATA HDDs, 3 TB with top-quality 2.5- inch SAS drives and up to 640 GB with power-saving 2.5-inch SATA SSDs.  The only catch is that you can only fit 2 of these storage blades into a single chassis.

PRIMERGY SX940 S1 -a storge blade that can hold up to 4 additional hot-plug SAS or SATA HDD/SSD.  These drives offer high capacity of up to 584 GB with high quality SAS drives, up to 2 TB with SATA HDDs.

I understand that Fujitsu is nearly non-existent in North America, but overseas they are well-known.  As well, the purpose of this post to showcase that Fujitsu is putting NetApp’s software expertise onto a blade footprint to be used as a single purpose – to create a virtual storage array.  As blade servers become more more mainstream, I expect to see more vendors team up to offer these types of integrated solutions.

For more information on Fujitsu’s servers, please visit:
http://ts.fujitsu.com/products/standard_servers/blade/bx400/storageblades.html

A special thanks to Chris Mellor for his write-up on this Fujitsu offering as seen on theregister.co.uk. Сайт знакомств

Last week, Blade.org invited me to their 3rd Annual Technology Symposium  – an online event with speakers from APC, Blade Network Technologies, Emulex, IBM, NetApp, Qlogic and Virtensys.  Blade.org is a collaborative organization and developer community focused on accelerating the development and adoption of open blade server platforms.   This year’s Symposium focused on ”the dynamic data center of the future”.   While there were many interesting topics (check out the replay here), the one that appealed to me most was “Shared I/O” by Alex Nicolson, VP and CTO of Emulex.  Let me explain why. 

While there are many people who would (and probably will) argue with me, blade servers are NOT for all workloads.  When you take a look at the blade server ecosystem today, the biggest bottleneck you see is the limitation of on board I/O.  Without compromising server slots, the maximum amount of expansion you can achieve on nearly any blade server is 8 I/O ports (6 Ethernet + 2 storage.)  In addition, blade servers are often limited to 2 expansion cards so if a customer has a requirement for “redundant physical adapters” the amount of expansion is reduced even more.    Based on these observations, if you could remove the I/O from the server  the blade server limitations would be eliminated allowing for the adoption of blade servers into more environments.  This could be accomplished with shared I/O.  

When you stop and think about the blade infrastructure design, no matter who the vendor is, it has been the same for the past 9 years.  YES, the vendors have come out with better chassis designs that allow for “high-speed” connectivity, but the overall design is still the same: blade server with CPUs, Memory and I/O cards all on one system board.  It’s time for blade server evolution to a design where I/O is shared.The idea behind Shared I/O is simple: separate the I/O from the server.  Instead of having storage adapters inside a blade server, you would have an I/O Drawer outside containing the blade chassis with the I/O adapters for the blade servers.  No more I/O bottlenecks on your blade servers.  Your I/O potential is (nearly) unlimited!  The advantages to this design include:

• More internal space for blade server design.  If the I/O – including the LAN on Motherboard – was moved off the server, there would be substantial space remaining for more CPUs, more RAM or even more disks.
• Standardized I/O adapters no matter what blade vendor is used.  This is the thought that really excites me.  If you could remove the I/O from the blade server, you would be able to have IBM, Dell, HP and even Cisco in the same rack using the same I/O adapter.  Your investments would be limited to the blade chassis and server.  Not only that, but as blade server architecture changes, you would be able to KEEP the investments you make into your I/O adapters OR on the flip side of that, as I/O adapter speeds increase, you could replace them and keep your servers in place without having to buy new adapters for every server.
• Sharing of I/O adapters means FEWER adapters are needed.  In order for this design to be beneficial, the adapters would need to have the ability to be shared between the servers.  This means that 1 storage HBA may provided resources for 6 servers, but as I/O adapter throughput continues to increase, this may be more of a desire.  Let’s face it – 10Gb is being discussed (and sold) today, but this time next year, 40Gb may be hot and in 3 years, 100Gb may be on the market.  Technology will continue to evolve and if the I/O adapters were separated from the servers, you would have the ability to share the technology across all of your servers.

Now, before you start commenting that this is old news and that companies like Xsiogo have been offering virtual I/O products for a couple of years – hear me out.  The evolution I’m referring to is not a particular vendor providing proprietary options.  I imagine a blade ecosystem across all the vendors that allow for a standardized I/O platform providing guidelines for all blade servers to connect to a shared I/O drawer made by any vendor.  Yes, this may be an unrealistic Nirvana, but look at USB.  All vendors provide them natively out of the chassis without any modifications, so why can’t we get to the same point with a shared I/O connectivity?

So, what do you think.  Am I crazy, or do you think blade server technology will evolve to allow for a separation of I/O.  Share you thoughts in the comments below.

Since the hit movie AVATAR surpassed the $1 Billion Revenue mark this weekend I thought it would be interesting to post some information about how the movie was put together – especially since the hardware behind the magic was the HP BL2x220c.

According to an article from information-management.com, AVATAR was put together at a visual effects production house called Weta Digital located in Miramar, New Zealand.  Weta’s datacenter sits in a 10,000 square foot facility however the film’s computing core ran on 2,176 HP BL 2x220c Blade Servers.  This added up to over 40,000 processors and 104 terabytes of RAM.  (Check out my post on the HP BL 2x220c blade server for details on this 2 in 1 server design by HP.)

The HP blades read and wrote data against 3 petabytes of fast fiber channel disk network area storage from BluArc and NetApp.  According to the article, all of the gear was  connected by multiple 10-gigabit network links. “We need to stack the gear closely to get the bandwidth we need for our visual effects, and, because the data flows are so great, the storage has to be local,” says Paul Gunn, Weta’s data center systems administrator.  

The article also highlights the fact that the datacenter uses water cooled racks to keep the racks and storage cooled.  Suprisingly, the water cooled design, along with a cool local climate, allows Weta to run their datacenter for less cost than running air conditioning (all they pay for is the cost of running water.)  In fact, they recently won an energy excellence award for building a smaller footprint that came with 40% lower cooling cost.

Summary of Hardware Used for AVATAR:

• 34 racks – each with 4 HP BladeSystem Chassis, 32 servers (16 BL2x220c)
• over 40,000 processors
• 104 TB RAM

Since I don’t want to re-write the excellent article from information-management.com, I encourage you to click here to read the full article.