Thursday, January 9, 2014

Blueprint: Optimizing SSDs with Software Defined Flash Requires a Flexible Processor Architecture

By Rahul Advani, Director of Flash Products, Enterprise Storage Division, PMC

With the rise of big data applications, such as in-memory analytics and database processing where performance is a key consideration, enterprise Solid-State Drive (SSD) use is growing rapidly. IDC forecasts the enterprise SSD segment to be a $5.5 billion market by 20151.  In many cases, SSDs are used as the highest level of a multi-tier storage system, but there is also a trend towards all-SSD storage arrays  as price performance metrics, including dollar per IOP ($/IOP) and dollar per workload ($/workload) make it an attractive option.

Flash-based SSDs are not only growing as a percentage of all storage in the enterprise, but they are also almost always the critical storage component to ensure a superior end-user experience using caching or tiering of storage.  The one constant constraint to the further use of NAND-based SSDs is cost, so it makes sense that the SSD industry is focused on technology re-use as a means to deliver cost-effective solutions that meet customers’ needs and increase adoption.

If you take the Serial Attached SCSi (SAS) market as an example, there are three distinct SSD usage models that are commonly measured in Random Fills Per Day (RFPD) for 5 years, or filling an entire drive xx times every day for 5 years.  There are the read intensive workloads at 1-3 RFPD, mixed workload at 5-10 RFPD and write intensive at 20+ RFPD. Furthermore, different customer bases like the Enterprise and Hyperscale datacenter have different requirements for application optimizations and scale for which SSDs are used in their infrastructure.  These differences in requirement show up typically in terms of number of years of service required, performance, power and sensitivity to corner cases in validation. The dilemma for the SSD makers is how do you meet these disparate needs and yet offer cost-effective solutions to end users.

In enterprise applications, software defined storage has many different definitions and interpretations, from virtualized pools of storage, to storage as a service.  For this article, we will stick to the application of software and firmware in flash-based storage SSDs to help address the varied applications from cold storage to high performance SSDs and caching cost effectively. There are a few key reasons why the industry prefers this approach:
  1. As the risk and cost associated with controller developments have risen, the concept of using software to generate optimizations is not only becoming popular, it’s a necessity.  Controller developments typically amount to several tens of millions of dollars for the silicon alone, and they often require several revisions to the silicon, which adds to the cost and risk of errors.
  2. The personnel skillset required for high-speed design and specific protocol optimizations (SAS or NVMe) are not easy to find.  Thus, software-defined flash, using firmware that has traditionally been deployed to address bugs found in the silicon, is increasingly being used to optimize solutions for different usage models in the industry.  For example, firmware and configuration optimizations for PMC’s SAS flash controller described below cost around 1/10th of the silicon development and the benefits of that are seen at the final product cost.
  3. Product validation costs can also be substantial and cycles long for enterprise SSDs, so time-to-market solutions also leverage silicon and firmware re-use as extensively as feasible.
Supporting these disparate requirements that span cold storage to high-performance SSDs for database applications cost-effectively requires a well-planned, flexible silicon architecture that will allow for software defined solutions.  These solutions need to support software optimizations based around (to name a few):

Different densities and over-provisioning NAND levels
Different types of NAND (SLC/MLC/TLC) at different nodes
Different power envelopes (9W and 11W typical for SAS, 25W for PCIe)
Different amounts of DRAM
Often need to support Toggle and ONFI, in order to maintain flexibility of NAND use

The table below shows the many different configurations that PMC’s 12G SAS flash processor supports:

Using a flexibly architected controller, you can modify features including power, flash density, DRAM density, flash type and host interface bandwidth for purpose-built designs based on the same device. And this allows you to span the gamut from cold storage (cost-effective but lower performance) to a caching adaptor (premium memory usage and higher performance) through different choices in firmware and memory. The key is that firmware and hardware be architected flexibly.  Here are three common design challenges that can be solved with software defined flash and a flexible SSD processor:

  • Protocol communication between the flash devices:  Not only does NAND from different vendors (ONFI and toggle protocols) differ, but even within each of these vendor’s offerings, there can be changes to the protocol.  Examples are changing from five to six bytes of addressing, or adding prefix commands to normal commands.  Having the protocol done by firmware allows the flexibility to adapt to these changes.  Additionally, having a firmware-defined protocol allows flash vendors to design in special access abilities.
  • Flash has inconsistent rules for order of programming and reading: A firmware-based solution can adapt to variable rules and use different variations of flash, even newer flash that might not have been available while developing the hardware.  By having both the low-level protocol handling, as well as control of the programming and reading all in firmware, it allows for a solution that is flexible enough to use many types and variations of flash.
  • Fine-tuning algorithms/product differentiation: Moving up to the higher level algorithms, like garbage collection and wear leveling, there are many intricacies in flash. Controlling everything from the low level up to these algorithms in firmware allows for fine-tuning of these higher level algorithms to work best with the different types of flash.  This takes advantage of the differences flash vendors put into their product so they can be best leveraged for diverse applications.

A flexible architecture that can support software defined flash optimizations is the key to supporting many different of usage models, types of NAND and configurations. It also helps reduce cost, which will accelerate deployment of NAND-based SSDs and ultimately enhance end-user experience.

Source: 1. IDC Worldwide Solid State Drive 2013-2017 Forecast Update, doc #244353, November 2013.

About the Author

Rahul Advani has served as Director of Flash Products for PMC’s Enterprise Storage Division since July 2012. Prior to joining PMC, he was director of Enterprise Marketing at Micron Technology, director of Technology Planning at Intel, and a product manager with Silicon Graphics. He holds a BS in Electrical Engineering from Cornell University and he received his PhD in Engineering and management training from the Massachusetts Institute of Technology.

About PMC

PMC® (Nasdaq: PMCS) is the semiconductor innovator transforming networks that connect, move and store big data. Building on a track record of technology leadership, the company is driving innovation across storage, optical and mobile networks. PMC’s highly integrated solutions increase performance and enable next-generation services to accelerate the network transformation.

IBM's Watson Delivers Cloud-based Services

IBM unveiled three new Watson services delivered over the cloud.  The company has established a new IBM Watson Group to build additional cognitive computing services, software and apps into the marketplace that analyze, improve by learning, and discover answers and insights to complex questions from massive amounts of disparate data. IBM plans to invest more than $1 billion in the initiative. The first Watson cloud services are:

  • Watson Discovery Advisor is designed to accelerate and strengthen research and development projects in industries such as pharmaceutical, publishing and biotechnology where it will be initially marketed. The service will scan and analyze millions of technical articles, journals and studies to determine context and synthesize vast amounts of data.  The goal is to help researchers uncover new perspectives from relevant data sources that could be overlooked, given the enormous volume of information available.
  • Watson Analytics delivers visualized Big Data insights, based on questions posed in natural language by any business user. Watson uses sophisticated analytics and a natural language interface to prepare the data, discover the most important relationships and presents the results in an easy to interpret interactive visual format.
  • Watson Explorer helps users across an enterprise uncover and share data-driven insights more easily, while empowering organizations launch Big Data initiatives faster.  The service provides data discovery, navigation and search capabilities that are secure, unified and span a broad range of applications, data sources and data formats – both inside and outside an enterprise. 

"Watson is the solution to today’s influx of information, delivered from the cloud and ready to be the ultimate advisor for faster, more accurate decisions,” said Michael Rhodin, Senior Vice President, IBM Watson Group. “By bringing a new generation of Watson-powered services to the marketplace, IBM is transforming industries and professions. These new cognitive computing innovations are designed to augment users’ knowledge, be it the researcher exploring genetic data to create new therapies or a business executive who needs evidence-based insights to make a crucial decision."

In November 2013, IBM announced plans to make it Watson technology available as a development platform in the cloud.  The idea is to enable software application developer to build a new generation of apps that leverage Watson's cognitive computing intelligence and ability to ingest both structured and unstructured data.

IBM said its goal is to create a cloud-hosted marketplace where application providers can tap into its library of resources for Watson-powered intelligence.  IBM will supply a developer toolkit, educational materials and access to Watson's application programming interface (API). IBM is already working with partners on applications for smarter online shopping comparisons, medical equipment supply chain management, and personalized healthcare recommendations.

ZTE Demos Optical Transport Path Computation with China Mobile

ZTE announced a demonstration of a SDN path computation element (PCE) control solution for optical transport networks.

The test was conducted by ZTE in partnership with China Mobile and the Research Institute of Telecommunications Transmission of the Ministry of Industry and Information Technology.

ZTE said its PCE solution fulfilled functions including integrated PCE, multi-domain service scheduling and optical/electrical hybrid scheduling on ZTE’s WASON (WDM Automatic Switch Optical Network) system.  The path calculation of multi-domain multi-layer OTN and resource assignment are seen as key enablers for intelligent management and control of optical networks, more efficient service scheduling, and improved resource utilization.

Peak Raises $4 Million for its VAR Cloud Services

Peak (formerly PeakColo) secured $4 million in new funding for its enterprise-class IaaS cloud services for channel partners.

Peak offers cloud computing to its large ecosystem of value-added resellers (VARS), distributors, agents and service providers who white-label or re-sell Peak’s cloud as their own solution. With cloud nodes located in eight geographies across the United States and Europe including Silicon Valley, Seattle, Denver, Chicago, New Jersey, New York, Atlanta, and the United Kingdom, Peak is able to address a wide range of services including disaster recovery, production workloads, storage and backup in the cloud.

The new funding came from Peak's current investment group, Meritage Funds and Sweetwater Capital.

EE and Vodafone to Bring LTE to Channel Tunnel

The Channel Tunnel will be covered by LTE services offered by EE and Vodafone by summer 2014.  2G and 3G services are also set to go live in the North Running Tunnel (UK to France) in March 2014.

Separately, EE announced that 2 million customers are now using its network -- twice the target set for 2013. The network is now delivering average speeds of 24-30 Mbps in twenty cities across the UK.

 “We’re incredibly proud of being the first UK operator to bring 4G to the UK and, in just over a year, exceeding our target by reaching two million 4G customers across the country. We continue to have particular success converting our existing base to 4G, with approximately two out of three new 4G customers moving over from Orange and T-Mobile plans," stated Olaf Swantee, CEO of EE.

Finisar to Acquire u2t Photonics AG for 100G Coherent

Finisar agreed to acquire u2t Photonics AG for approximately $20 million in cash. Finisar will also assume net debt of approximately $7 million.

Photonics AG, which is based in Berlin, Germany, supplies ultra high speed optical components up to 100 GHz. Its product portfolio includes TELCORDIA qualified portfolio of photodetectors, highly integrated photoreceivers and modulators supporting advanced transmission formats at 40 Gbps and 100 Gbps and beyond offers superior performance serving the requirements from transponder vendors, line card and system designers as well as test equipment vendors.  In calendar year 2013, u2t had total revenues of approximately $33 million.  The company was founded in 1998.

Finisar said the acquisition adds u2t's Indium-Phosphide (InP)-based 100G high speed receivers and photodetectors to its existing portfolio of high speed optics technologies. In addition, this acquisition will consolidate Finisar's previously announced partnership with u2t on InP-based IQ Mach-Zehnder modulators for 100G coherent applications. These receiver, photodiode and modulator technologies and products, when combined with Finisar's narrow-line width tunable lasers, will provide a full suite of optical components and enable Finisar to offer its customers vertically integrated modules for the 100G coherent metro and long haul markets.

"We are pleased with the acquisition by Finisar. During our collaboration to acquire the assets of COGO Optronics GmbH and develop the InP modulator technology from the Fraunhofer Heinrich-Hertz-Institute (HHI), we realized that Finisar's technical strength, ability to cost effectively commercialize technology and global access to customers and markets would combine extremely well with our industry leading technology and design capabilities. Furthermore, the acquisition provides a one-of-a-kind opportunity for our employees and innovative technologies to make a greater impact on the optical communication markets," said Andreas Umbach, CEO and Co-Founder of ut2.

Riverbed Confirms Unsolicited Buyout Bid from Elliot Mgt for $19 per Share

Riverbed Technology confirmed an unsolicited proposal from Elliott Management Corporation to acquire all outstanding shares of Riverbed for $19.00 per share in cash.

Riverbed said its Board will review the offer and communicate its views in due course.

  • Shares is Riverbed closed on Wednesday at $19.53, up $9.41%.

OpenDaylight Summit Scheduled for February 4-5 in Santa Clara

The OpenDaylight Project will host a conference in Santa Clara, California, February 4-5, 2014, to unite developers and users across enterprises, carriers and equipment providers for a collaborative and educational SDN and NFV experience.

Keynote speakers for The OpenDaylight Summit include:

  • Neela Jacques, executive director for OpenDaylight, Commencement.
  • Christos Kolias, senior research scientist, OpenFlow/SDN technical lead, network architecture at Orange.
  • Jun Park (Ph.D), senior systems architect at Bluehost.
  • Erik Ekudden, vice president and head of technology strategies, Ericsson, “Accelerating the Network with Open Source Software.”
  • Vijoy Pandey, chief technology officer of Network OS and a distinguished engineer at IBM, “Building an Open Adaptive and Responsive Data Center using OpenDaylight.” 
  • A user panel “Forming and Norming for SDN/NFV: Where to Support Innovation and Where to Simplify Life with Standards” featuring Open Networking User Group co-founder Nick Lippis, Open Networking Foundation MEC chair Marc Cohn, Open Networking Research Center’s executive director Dr. Guru Parulkar and ETSI’s NFV group leader Christos Kolias, moderated by Neela Jacques.
  • Inder Gopal, chairman, OpenDaylight board of directors, “OpenDaylight: What’s Next?”

A panel with OpenDaylight developers to discuss what’s on the road map for 2014, moderated by David M. Meyer, chair of the OpenDaylight Technical Steering Committee.

Calix Issues Q4 Revenue Warning

Calix now expects revenue for Q4 2013 to be in the range of $93.5 to $94.5 million and non-GAAP earnings per share of 2 to 4 cents per share, down from previous guidance of revenue between $97 and $103 million and non-GAAP earnings in the range of 3 to 8 cents per share.

Calix said it saw a greater than anticipated decline in traditional year-end "budget flush" customer spending patterns than the company historically has experienced.

Final results are expected after the market closes on February 11.

Convergys to Acquire Stream for Customer Mgt - $820 Million

Convergys Corp. agreed to acquire Stream Global Services, both providers of customer management services, for a total enterprise value of $820 million in cash.

Convergys said the deal will expand and strengthen its U.S. and global presence in the $55 billion outsourced customer management services industry. When combined, total company revenue is expected to exceed $3 billion, creating the second largest customer management services provider in the world.

Convergys will finance the deal using funds managed by Ares Management and Providence Equity Partners, as well as from LiveIt, the BPO investment arm of Ayala Corp. Convergys also announced the transaction is expected to add approximately $0.35 in diluted earnings per share (EPS) in the first 12 months after close, excluding one-time charges, intangible amortization and integration costs.

“This acquisition is an important step forward in our plan for strategic growth and value creation,” said Andrea Ayers, president and CEO of Convergys. “We believe this combination will strengthen Convergys by diversifying our client base and enabling us to offer a wider range of customer transactions in a more cost effective manner from multiple geographies, at scale. Our plan is to build upon the best practices and management teams from both companies to deliver superior customer benefits and enhanced value for our clients and shareholders, and provide new opportunities for our employees,” Ayers said.