Archive for April, 2013

Can Flash Replace Hard Disk for Enterprise Storage?

Earlier this month IBM announced a strategic initiative, the IBM FlashSystem, to drive Flash technology deeper into the enterprise. The IBM FlashSystem is a line of all-Flash storage appliances based on technology IBM acquired from Texas Memory Systems.

IBM’s intent over time is to replace hard disk drive (HDD) for enterprise storage with flash. Flash can speed the response of servers and storage systems to data requests from milliseconds to microseconds – an order of magnitude improvement. And because it is all electronic—nothing mechanical involved—and being delivered cost-efficiently at even petabyte scale, it can remake data center economics, especially for transaction-intensive and IOPS-intensive situations.

For example, the IBM FlashSystem 820 is the size of a pizza box but 20x faster than spinning hard drives and can store up to 24 TB of data. The entry-level IBM FlashSystem, with an approximate street price for an entry 820 (10 TB usable RAID 5) runs about $150K (or $15 per gigabyte).  At the high end, you can assemble a 1 PB FlashSystem that fits in one rack and delivers 22 million IOs per second (IOPS). You would need 630 racks of high capacity hard disk drives or 315 racks of performance optimized disk to generate an equal amount of IOPS.

For decades storage economics has been driven by the falling cost per unit of storage, and storage users have benefited from a remarkable ride down the cost curve thanks to Moore’s law. The cost per gigabyte for hard disk drive (HDD) has dropped steadily, year after year. You now can buy a slow, USB-connected 1TB consumer-grade disk drive for under $89!

With low cost per gigabyte storage, storage managers could buy cheap gigabytes, which enabled backup to disk and long-term disk archiving. Yes, tape is even cheaper on a cost per gigabyte basis but it is slow and cumbersome and prone to failure. Today HDD rules.

Silicon-based memory, however, has been riding the Moore’s Law cost slope too. In the last decade memory has emerged as a new storage media through memory-based storage in the form of RAM, DRAM, cache, flash, and solid state disk (SSD) technology. Prohibitively expensive to use for mass storage initially, the magic of Moore’s law combined with other technical advances and mass market efficiencies have made flash something to think about seriously for enterprise production storage.

The IBM FlashSystem changes data center economics. One cloud provider reported deploying 5TB in 3.5 inches of rack space compared to deploying 1300 hard disks to achieve 400k IOPS and it did so at one-tenth the cost.  Overall, Wikibon reports an all Flash approach will lower total system costs by 30%; that’s $4.9m for all flash compared to $7.1m for hard disk.  Specifically, it reduced software license costs 38%, required 17% few servers, and lowered environmental costs by 74% and operational support costs by 35%.  At the same time it boosted storage utilization by 50% while reducing maintenance and simplifying management with corresponding labor savings. Combine flash with compression, deduplication, and thin provisioning and the economics look even better.

For data center managers, this runs counter to everything they learned about the cost of storage. Traditional storage economics starts with the cost of hard disk storage being substantially less than the cost of SSD or Flash on a $/GB basis. Organizations could justify SSD, only by using it in small amounts to tap its sizeable cost/IOPS advantage for IOPS-intensive workloads.

Any HDD price/performance advantage is coming to an end. As reported in PC World, Steve Mills, IBM Senior Vice President noted:  Right now, generic hard drives cost about $2 per gigabyte. An enterprise hard drive will cost about $4 per gigabyte, and a high-performance hard drive will run about $6 per gigabyte. If an organization stripes its data across more disks for better performance, the cost goes up to about $10 per gigabyte. In some cases, where performance is critical, hard-drive costs can skyrocket to $30 or $50 per gigabyte.

From a full systems perspective (TCO for storage) Flash looks increasingly competitive. Said Ambuj Goyal, General Manager, Systems Storage, IBM Systems & Technology Group: “The economics and performance of Flash are at a point where the technology can have a revolutionary impact on enterprises, especially for transaction-intensive applications.” But this actually goes beyond just transactions. Also look at big data analytics workloads, technical computing, and any other IOPS-intensive work.

Almost every major enterprise storage vendor—EMC, NetApp, HP, Dell, Oracle/Sun—is adding SSD to their storage offerings. It is time to start rethinking your view of storage economics when flash can replace HDD and deliver better performance, utilization, and reliability even while reducing server software licensing costs and energy bills.

Advertisements

, , , , , , , , , , , , ,

Leave a comment

IT Chaos Means Opportunity for the CIO

Hurricanes, hybrid superstorms, earthquake-tsunami combinations, extreme heat, heavy snow in April are just a few signs of chaos. For IT professionals specifically, chaos today comes from the proliferation of smartphones and BYOD or the deluge of data under the banner of big data. A sudden shift to the deployment of massive numbers of ARM processors or extreme virtualization might trigger platform chaos.  A shortage of sufficient energy can lead to another form of chaos. Think of it this way: chaos has become the new normal.

Big consulting firms have latched onto the idea of chaos. Deloitte looks to enterprise data management to create order out of chaos. At Capgemini, the need of organizations to increasingly deal with unstructured processes that ordinary Business Process Management (BPM) solutions were not designed to cope with can be enough to lead to chaos. Their solution: developing case management around a BPM solution – preferably in conjunction with an Enterprise Content Management system – solves many of the problems

Eric Berridge, co-founder of Bluewolf Group, a leading consulting firm specializing in Salesforce.com implementations, put it best when he wrote in a recent blog that CIOs must learn to harness chaos for a very simple reason: business is becoming more chaotic. Globalization and technology, which have turned commerce on its head over the past 20 years, promise an even more dizzying rate of change in the next decade.

Berridge’s solution draws on the superhero metaphor. The CIO has to become Captain Chaos, the one able to overcome a seemingly insurmountable level of disarray to deliver the right value at the right time. And you do that my following a few straightforward tips:

First, don’t build stuff you don’t absolutely have to build. You want your organization to travel as light as possible. If you build systems you are stuck with them. Instead, you want to be able to change systems as fast as the business changes in response to whatever chaos is swirling at the moment. That means you need to aim for an agile IT infrastructure, probably one that can take tap a variety of cloud services and turn them on and off as needed.

Then, recognize the consumerization of IT and the chaos it has sparked.  This is not something to be resisted but embraced and facilitated in ways that give you and your organization the measure of control you need. Figure out how to take advantage of the consumerization of IT through responsive policies, elastic infrastructure, and flexible security capabilities.

Next, encourage the organization’s R&D and product development groups to also adopt agile methods and approaches to innovation, especially through social media and other forms of collaboration. Even encourage them to go a step further by reaching out to customers to participate.  Your role as CIO at this point is to facilitate interaction among the parties who can create successful innovation.

Finally, layer on enough just-in-time governance to enable the organization to manage the collaboration and interactivity. The goal is to rein in chaos and put it to work. To do that you need to help set priorities, define objectives, execute plans, and enforce flexible and agile policies—all the things that any successful business needs to do but do so in the context of a chaotic world that is changing in ways you and top management can’t predict.

As CIO this puts big demands on you too. To start, you have to keep your finger on the pulse of what is happening with the world at large, in business and with technology. That means you need to figuratively identify and place sensors and monitors that can tip you off as things change. You also can’t master every technology. Instead you need to identify an ever-changing stable of technology masters you can call on as needed and familiarize yourself with the vast amount of resources available in the cloud.

In the end, these last two points—a stable of technology masters you can call upon and deep familiarity with cloud resources—will enable you to deliver the most value to your organization despite the chaos of the moment. At that point you truly become Captain Chaos, the one your organization counts on to deal with ever changing chaos.

, , , , , , , , , , , , ,

Leave a comment