Evolution Beats Extinction: Big Data Opens New Niches with Fast Flash Memory

July 20, 2012

65 million years ago, a six-mile-wide asteroid ended the reign of the dinosaurs, reopening ecological niches that were promptly filled by members of the class Mammalia, one of which, a long time later, went on to invent things like writing, the wheel, and information technology.

Big Data—ultra large scale data storage and analysis—is the storage market’s equivalent of that big rock, but rather than causing mass extinction, it’s simply opening up a lot of new ecological niches for storage technologies, especially advanced solutions like Fusion ioMemory modules and the new release of DataCore’s SANsymphony-V storage hypervisor. The advent of Big Data also offers a unique opportunity to re-architect your storage management infrastructure in a way that can prolong the life of storage “dinosaurs” and make it more adaptable in every respect and more easily aligned to business needs.

As profiled in the New York Times, Big Data is transforming business, government, and education. One researcher reported that a study of 179 large companies showed that those adopting the data-driven decision-making that Big Data makes possible “achieved productivity gains that were 5 percent to 6 percent higher than other factors could explain.”

Big Data is more than just big. It’s restless, too, and best used when hot. Let it cool off, and you lose the situational awareness that can lead to big-time financial rewards. It’s not just a matter of storing a gazillion bytes—you can’t possibly store it all, so your retention policies have to change, and the need to widely share data as quickly as possible means your networking strategies have to change as well.

Fortunately, a storage hypervisor can be a big help in adapting to Big Data. Even better, the benefits of this software layer, which insulates you from all the hardware variables that Big Data can throw your way, kick in long before Big Data arrives. A scalable and comprehensive storage hypervisor like DataCore’s SANsymphony-V is an agent of change: you get the pay-off today and a future-proof storage infrastructure. It also, as we’ll see, can give you an even better return on your Fusion-io ioMemory module investments.

SANsymphony-V provides a complete “storage management stack” and gives you a centralized console that enables you to efficiently pool all your storage resources, mirror and replicate data for high availability, cache data near applications for higher performance, automatically allocate space, and direct traffic to the optimal tier.

Resource pooling has the most immediate impact, because you can aggregate all of your storage capacity, without regard for brand, model, or interface, and easily reclaim unused space. These pooled resources can be easily mirrored locally for high availability, or replicated remotely for disaster recovery. Thin provisioning gives you just-in-time storage allocation for highly efficient use of disk space, and RAM caching speeds up “spindle-based” storage dramatically to turbocharge native disk array performance. The fact that all of these advantages are available to every storage resource managed by SANsymphony-V means that older storage that formerly might have been shuffled off to the dinosaur’s graveyard remains useful longer, leading to a higher ROI for all your storage investments.

Fusion-io Fast Flash Memory and DataCore Auto-tiering Software

When it comes to Big Data, however, it’s probably auto-tiering that’s likely to be of most interest to customers who rely on Fusion-io technology. SANsymphony’s auto-tiering can dynamically direct workloads to the right storage resource based either on access frequency or business rules, so that the hottest data gets the most attention. Older storage can be moved down-tier as new hardware is installed, again prolonging its service life. SANsymphony-V also offers a “cloud gateway” to leverage cloud service providers for both disaster recovery and archival of virtually unlimited capacity—a necessity to keep from getting squashed by Big Data.

This enables SANsymphony-V to put Fusion-io’s server class memory tier at the very top of an agile, easily-managed storage hierarchy that offers unprecedented levels of performance and availability. You can easily balance data value and the need for speed against price/capacity constraints—something that Big Data is going to make ever more necessary—and make sure that you get the utmost benefit from ioMemory modules.

The fallout from Big Data is going to transform business computing at every level, so if you don’t want to end up a data dinosaur, now’s the time to transform your infrastructure with a storage hypervisor. A good place to start is Jon Toigo’s Storage Virtualization for Rock Stars series, starting with Hitting the Perfect Chord in Storage Efficiency, which will give you a good overview of how a storage hypervisor can help you increase engineering, operational, and financial efficiency.

Related articles

Leave a Comment » | Application Hosting, Managed Service Hosting, Marketing, Retail IT Solutions | Tagged: , , , , , , , , | Permalink
Posted by david ricketts

Backup vs Archiving

March 29, 2012

There is some confusion amongst SMBs as to the differences between backup and archive. These two processes are mutually exclusive – they cannot occur at the same time and are different processes with different objectives. The most discernable issue around the key differences between the two processes relates to security, compliance and governance.

An archive is just a stored set of organized data and the goal is to achieve an intelligible data set for long periods of time and in a form that enables granular data retrievable. This is important for businesses in highly regulated industries that include healthcare, legal, banking and securities.

Archived data can be stored on multiples types of devices including tape, disk and in the cloud. There are benefits to each; however it is important to determine the length of time for which you will need to keep your archives and the most cost effective means for your business is without sacrificing the integrity of your archives.

Here are the thinks you should consider when thinking about data archiving:
•The archive needs to be able to operate with different data collections while treating them at the same level of integrity — individual data records from a database as well as entire documents
•The access speed of an archive can be slow, but archive should have an extremely high level of reliability
•Data integrity must be maintained over the entire period of the archive existence – there is no point in having an archive that you can’t trust

The key reason for the existence of a backup is to provide an alternative data source in case the primary data source is corrupted or destroyed. Backups are copies of data designed for short-term storage and its most identifiable characteristic is that it will go through frequent replacement and update under controlled circumstances. At that point, the old backup will become less relevant (or irrelevant) for operational purposes and the data will need to be backed up again.

Here are the things you should consider when thinking about data backup:
•The backup needs to be quickly accessible
•The backed up information should survive with full integrity and availability for several months on the backup media
•The backup should be able to span multimedia media (if backup set is larger than media capacity)
•The solution should be intelligent enough to enable different backup sets (full backup, incremental backup, differential backup, etc)

While backup and archive solutions are both very important, they provide two very different functions. It’s important to take the time to understand the difference between the two or consult a managed services provider that can help you better assess your business needs.

1 Comment | Application Hosting, Managed Service Hosting, Marketing | Tagged: , , , , , , , | Permalink
Posted by david ricketts

Printable transistors usher in ‘internet of things’……

November 2, 2011

Printable transistors usher in ‘internet of things’ | WSNblog

Thinfilm, a Norwegian developer of printable memory, has co-announced with California’s PARC a development that takes a big step towards the day when every manufactured object will report in to the internet.

Yes, the “internet of things” – the buzzword of the decade.

Thinfilm and PARC‘s breakthrough is a technology that can print not only memory onto, well, thin films, but can now also print transistors to address and manage that memory.

Since 2006, Thinfilm has been producing low-capacity read/write printable memory, which has been used in such applications as personalized toys and games.

How low is “low-capacity”? Twenty bits – but although that may sound meager, know that Thinfilm’s current products aren’t intended to store an HD video of Laurence of Arabia, but instead, to hold identification and personalization information.

And to do so cheaply. Very cheaply. A few cents per unit cheaply.

Up until Friday’s announcement, Thinfilm’s non-volatile, ferroelectric memory was completely passive – it just sat there, holding those 20 bits in its memory cells. To be rewritten or read, it needed to be accessed by an external device which used one access pad for each memory cell.

All things will soon be talking, you can only imagine the storage and data centre’s that will be needed.

3 Comments | Application Hosting, Managed Service Hosting, Retail IT Solutions | Tagged: , , , , , , , | Permalink
Posted by david ricketts

Follow

Get every new post delivered to your Inbox.

Join 752 other followers