Posts Tagged ‘Power Systems’

IBM DevOps for the Mainframe

March 27, 2015

DevOps is not just for distributed platforms. IBM has a DevOps strategy for large enterprises (usually mainframe shops) too. Nationwide, a longtime mainframe shop, is an early adopter of DevOps and already is reporting significant gains: reduction in critical software defects by 80% and a 20% efficiency gain in its maintenance and support operations in just 18 months.

DevOps, an agile methodology, establishes a continuous feedback loop between software development and deployment/operations that speeds development and deployment while ensuring quality. This is a far cry from the waterfall development methodologies of the mainframe past.

 desz DevOps adoption model

Courtesy of IBM (click to enlarge)

The IBM DevOps initiative, announced last November (link above), taps into the collaborative capabilities of IBM’s Cloud portfolio to speed the delivery of software that drives new models of engagement and business. Software has become the rock star of IT with software-driven innovation becoming a primary strategy for creating and delivering new value to customers. A survey of 400 business and IT executives by the IBM Institute for Business Value showed businesses that are more effective at software delivery are also more profitable than their peers nearly 70% of the time. As such, IBM notes, DevOps provides a way for businesses to remain competitive, applying lean and agile principles to software development to speed the delivery of software that meets new market requirements.

Some mainframe shops, however, continue to operate from a software standpoint as if client/server computing and PCs were still the new game in town. Meanwhile the business units keep complaining about how long it takes to make software changes while long backlogs drag on the IT budget.

DevOps is about continuous software development and deployment. That means continuous business planning, continuous collaborative dev, continuous testing, continuous release and deployment, continuous monitoring, and continuous feedback and optimization in a never ending cycle. Basically, continuous everything.  And it really works, as Nationwide can attest.

But DevOps makes traditional mainframe shops nervous. Mainframe applications are rock solid and crashes and failures almost unheard of. How can they switch to DevOps without risking everything the mainframe stands for, zero failure?

The answer: mainframe DevOps that leads straight into continuous testing, not deployment. The testing can and should be as rigorous and extensive as is necessary to reassure that everything works as it should and anything that will fail has failed. Only then does it go into production.

It would be comforting to the data centers to say that DevOps only addresses systems of engagement; those pesky mobile, collaborative, and social systems that suddenly are making demands on the core mainframe production applications. But that is not correct. DevOps is about integrating systems of engagement with systems of record, the enterprise’s mainframe crown jewels. The trick is to bring together the culture, processes, and tools across the entire software delivery lifecycle, as IBM says, to span it all—mobile to mainframe, slowing down only to conduct as exhaustive testing as the enterprise requires.

Mainframe tools from the era of waterfall methodologies won’t cut it. Rational offers a set of tools starting with Blue Agility. IBM also offers an expanded set of tools acquired through acquisitions such as UrbanCode (release automation) and GreenHat (software quality and testing solutions for the cloud and more) that offer an integrated developer experience on open cloud platforms such as Bluemix to expedite DevOps collaboration, according to IBM.

Expect push back from any attempt to introduce DevOps into a traditional mainframe development culture. Some shops have been developing systems the same way for 30 years or more. Resistance to change is normal. Plan to start gradually, implementing DevOps incrementally.

Some shops, however, may surprise you. Here the mainframe team senses they are falling behind. IBM, of course, has tools to help (see above). Some experts recommend focusing on automated testing early on; when testing is automated DevOps adoption gets easier, they say, and old school developers feel more reassured.

At IBM Edge2015, there are at least 2 sessions on DevOps: Light Up Performance of Your LAMP Apps and DevOps with a Power Optimized Stack; and CICS Cloud DevOps = Agility2. BTW, it is a good time to register for IBM Edge2015 right away, when you can still get a discount. IBM Edge2015, being billed as the Infrastructure Innovation Conference, takes place May 11 – 15 at The Venetian in Las Vegas. DancingDinsosaur will be there. Have just started pouring over the list of sessions on hundreds of topics for every IBM platform and infrastructure subject. IBM Edge2015 combines what previously had been multiple conferences into one.

DancingDinosaur is Alan Radding, a veteran IT analyst and writer. Follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing on Technologywriter.com and here. And join DancingDinsosaur at IBM Edge2015.

Vodafone Spain Picks IBM zSystem for Smarter Cities Initiative

March 19, 2015

The Vodafone initiative, as reported here previously, leverages the most advanced mobile communications technology including citywide sensors and a Global M2M Platform that will enable the connection of thousands of sensors to the intelligent Vodafone Connected City system. The new cloud-based system will run on IBM Linux z Systems. The Linux z Systems were selected for their high security, which protects cloud services while also delivering the speed, availability, and efficiency required to drive mobile services at scale.  To do something at scale you really do want the z System.

 vodafone zsystem running linux

Courtesy of IBM: zSystem and Linux

For Vodafone this represents the beginning of what they refer to as a Smarter Cities services initiative. The effort targets local governments and city councils with populations ranging between 20.000 – 200.000 citizens. The services provided will address customer’s needs in the following key areas: urban vitality, public lighting, energy efficiency, waste management, and citizen communications.

In effect, Vodafone is becoming a SaaS provider by leveraging their new zSystem. Vodafone’s customers for this are the government groups that opt to participate. The company announced the effort at the World Mobile Congress in Barcelona at the beginning of the month.

One of the initial participants will be Seville, the capital of the province of Andalucía, where a control and development center will be established by Vodafone. The telco will invest more than 243 million euros over two years on telecommunications infrastructure, encouraging the development of the technology sector and developing projects to create strategic growth in the region.

Initially, the center will focus on creating smart city solutions that can easily and efficiently be used by cities ranging from 20,000 to 150,000 residents; cities that otherwise may not have the funds to invest in smart city infrastructure projects on their own. This center is also expected to help make the Andalucía territory of Spain a leader in the development of Big Data and smart solutions.

IBM is delivering the full stack to Vodafone: a set of cloud services that include an enterprise zSystem Linux server (IBM zBC12), v7000 storage, IBM intelligent operations, an information services solution, and more.  Vodafone opted for the z and Linux to enable cost-efficient, highly secure cloud services while also delivering the speed, availability and efficiency required to drive mobile services at scale. IBM Intelligent Operations software will provide monitoring and management of city services. IBM’s MobileFirst platform will be used to create citizen-facing mobile applications while IBM Information Server and Maximo asset management software will round out the IBM stack.

Overall, IBM, the zSystem, and Linux brought a number of benefits to this initiative. Specifically, the zSystem proved the least expensive when running more than seven vertical services as Vodafone is planning. An example of such a vertical service is the public lighting of a city. This also is where scalability brings a big advantage. Here again, the zSystem running Linux delivers scalability along with greater security and regulatory compliance. Finally, another critical capability for Vodafone was the zSystem’s ability to isolate workloads.

In short, the zSystem’s security and regulation compliance; reliability, resilience, and robustness; strong encoding and workload isolation, workload management and ability to meet SLAs; scalability; and high efficiency clinched the Vodafone deal.

This could prove a big win for IBM and the zSystem. Vodafone has mobile operations in 26 countries, partners with mobile networks in 54 more, and runs fixed broadband operations in 17 markets. As of the end of 2014, Vodafone had 444 million mobile customers and 11.8 million fixed broadband customers. Vodafone Spain’s 14.811.000 mobile customers and 2.776.000 broadband ones will certainly take maximum advantage of the zSystem’s scalability and reliability.

…as a follow up to last week’s report on recent success coming from the OpenPower Foundation that string continued this week at the OpenPOWER Inaugural Summit with the OpenPOWER Foundation announcing more than ten hardware solutions spanning systems, boards, cards, and a new microprocessor customized for the Chinese market.  Built collaboratively by OpenPOWER members, the new solutions exploit the POWER architecture to provide more choice, customization and performance to customers, including hyperscale data centers.

Among the products and prototypes OpenPOWER members revealed are:

  • Firestone, a prototype of a new high-performance server targeting exascale computing and projected to be 5-10x faster than today’s supercomputers. It incorporate technology from NVIDIA and Mellanox.
  • The first GPU-accelerated OpenPOWER developer platform, the Cirrascale RM4950, resulting from collaboration between NVIDIA, Tyan, and Cirrascale.
  • An open server specification and motherboard mock-up combining OpenPOWER, Open Compute and OpenStack by Rackspace and designed to run OpenStack services.

Other member-developed new products leverage the Coherent Accelerator Processor Interface (CAPI), a hallmark feature built into the POWER architecture. DancingDinosaur initially covered CAPI here.

Reminder: it is time to register for IBM Edge2015 in Las Vegas May 10-15. Edge2015 combines all of IBM’s infrastructure products with both a technical track and an executive track.  You can be sure DancingDinosaur will be there. Watch for upcoming posts here that will highlight some of the more interesting sessions.

DancingDinosaur is Alan Radding, a veteran IT analyst and writer. Follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing on Technologywriter.com and here.

OpenPOWER Starts Delivering the Goods

March 13, 2015

Are you leery of multi-vendor consortiums? DancingDinosaur as a rule is skeptical of the grand promises they make until they actually start delivering results. That was the case with OpenPOWER last spring when you read here that the OpenPOWER Foundation was introduced and almost immediately forgotten.

 power8 cpu blocks

IBM POWER8 processor, courtesy of IBM (click to enlarge)

But then last fall DancingDinosaur reported on NVIDIA and its new GPU accelerator integrated directly into the server here. This too was an OpenPOWER Foundation-based initiative. Suddenly, DancingDinosaur is thinking the OpenPOWER Foundation might actually produce results.

For example, IBM introduced a new range of systems capable of handling massive amounts of computational data faster at nearly 20 percent better price/performance than comparable Intel Xeon v3 Processor-based systems. The result:  a superior alternative to closed, commodity-based data center servers. Better performance and at a lower price. What’s not to like?

The first place you probably want to apply this improved price/performance is to big data, which generates 2.5 quintillion bytes of data across the planet every day. Even the miniscule portion of this amount that you actually generate will very quickly challenge your organization to build a sufficiently powerful technology infrastructures to gain actionable insights from this data fast enough and at a price you can afford.

The commodity x86 servers used today by most organizations are built on proprietary Intel processor technology and are increasingly stretched to their limits by workloads related to big data, cloud and mobile. By contrast, IBM is designing a new data centric approach to systems that leverages the building blocks of the OpenPOWER Foundation.

This is plausible given the success of NVIDIA with its GPU accelerator. And just this past week Altera demonstrated its OpenPOWER-based FPGA, now being used by several other Foundation members who are collaborating to develop high-performance compute solutions that integrate IBM POWER chips with Altera’s FPGA-based acceleration technologies.

Formed in late 2013, the OpenPOWER Foundation has grown quickly from 5 founders to over 100 today. All are collaborating in various ways to leverage the IBM POWER processor’s open architecture for broad industry innovation.

IBM is looking to offer the POWER8 core and other future cores under the OpenPOWER initiative but they are also making previous designs available for licensing. Partners are required to contribute intellectual property to the OpenPOWER Foundation to be able to gain high level status. The earliest successes have been around accelerators and such, some based on POWER8’s CAPI (Coherence Attach Processor Interface) expansion bus built specifically to integrate easily with external coprocessors like GPUs, ASICs and FPGAs. DancingDinosaur will know when the OpenPOWER Foundation is truly on the path to acceptance when a member introduces a non-IBM POWER8 server. Have been told that may happen in 2015.

In the meantime, IBM itself is capitalizing on the OpenPower Foundation. Its new IBM Power S824L servers are built on IBM’s POWER8 processor and tightly integrate other OpenPOWER technologies, including NVIDIA’s GPU accelerator. Built on the OpenPOWER stack, the Power S824L provides organizations the ability to run data-intensive tasks on the POWER8 processor while offloading other compute-intensive workloads to GPU accelerators, which are capable of running millions of data computations in parallel and are designed to significantly speed up compute-intensive applications.

Further leveraging the OpenPOWER Foundation at the start of March IBM announced that SoftLayer will offer OpenPOWER servers as part of its portfolio of cloud services. Organizations will then be able to select OpenPOWER bare metal servers when configuring their cloud-based IT infrastructure from SoftLayer, an IBM company. The servers were developed to help organizations better manage data-intensive workloads on public and private clouds, effectively extending their existing infrastructure inexpensively and quickly. This is possible because OpenPOWER servers leverage IBM’s licensable POWER processor technology and feature innovations resulting from open collaboration among OpenPOWER Foundation members.

Due in the second quarter, the SoftLayer bare metal servers run Linux applications and are based on the IBM POWER8 architecture. The offering, according to IBM, also will leverage the rapidly expanding community of developers contributing to the POWER ecosystem as well as independent software vendors that support Linux on Power and are migrating applications from x86 to the POWER architecture. Built on open technology standards that begin at the chip level, the new bare metal servers are built to assist a wide range of businesses interested in building custom hybrid, private, and public cloud solutions based on open technology.

BTW, it is time to register for IBM Edge2015 in Las Vegas May 10-15. Edge2015 combines all of IBM’s infrastructure products with both a technical track and an executive track.  You can be sure DancingDinosaur will be there. Watch for upcoming posts here that will highlight some of the more interesting sessions.DancingDinosaur is Alan Radding, a veteran IT analyst and writer.

Follow DancingDinosaur on Twitter, @mainframeblog. See more of his IT writing on Technologywriter.com and here.

Software Licensing for IBM System z Distributed Linux Middleware

October 10, 2014

DancingDinosaur can’t attend a mainframe conference without checking out at least one session on mainframe software pricing by David Chase, IBM’s mainframe pricing guru. At IBM Enterprise2014, which wraps up today, the topic of choice was software licensing for Linux middleware. It’s sufficiently complicated to merit an entire session.

In case you think Linux on z is not in your future, maybe you should think again.  Linux is gaining momentum in even the largest z data centers. Start with IBM bringing new apps like InfoSphere, BigInsights (Hadoop), and OpenStack to z. Then there are apps from ISVs that just weren’t going to get their offerings to z/OS. Together it points to a telltale sign something is happening with Linux on z. And, the queasiness managers used to have about the open source nature of Linux has long been put to rest.

At some point, you will need to think about IBM’s software pricing for Linux middleware. Should you find yourself getting too lost in the topic, check out these links recommended by Chase:

To begin, software for Linux on z is treated differently than traditional mainframe software in terms of pricing. With Linux on z you think in terms of IFLs.  The quantity of IFLs represent the number of Linux engines subjected to IBM’s IPLA-based pricing.

Also think in terms of Processor Value Units (PVUs) rather than MSUs. For a pricing purposes, PVUs are analogous to MSUs although the values are different. A key point to keep in mind: distributed PVUs for Linux are not related to System z IPLA value units used for z/VM products. As is typical of IBM, those two different kinds of value units are NOT interchangeable.

Chase, however, provides a few ground rules:

  • Dedicated partition
    • Processors are always allocated in whole increments
    • Resources are only moved between partitions “explicitly” (e.g. by an operator or a scheduled job)
  • Shared pool:
    • Pool of processors shared by partitions (including virtual machines)
    • System automatically dispatches processor resources between partitions as needed
  • Maximum license requirements
  • Customer does not have to purchase more licenses for a product than the number of processors on the machine (e.g. maximum DB2 UDB licenses on a 12-way machine is 12)
    • Customer does not have to purchase more “shared pool” licenses for a product than the number of processors assigned to the shared pool (e.g. maximum of 7 MQSeries licenses for a shared pool with 7 processors). Note: This limit does not affect the additional licenses that might be required for dedicated partitions.

With that, as Chase explains it, Linux middleware pricing turns out to be relatively straightforward, determined by:

  • Processor Value Unit (PVU) rating for each kind of core
  • Any difference for different processor technologies (p, i, x, z, Sun, HP, AMD, etc—notice that the z is just one of many choices, not handled differently from the others
  • Number of processor cores which must be licensed (z calls them IFLs)
  • Price per PVU (constant per product, not different based upon technology)

Then it becomes a case of doing the basic arithmetic. The formula: # of PVUs x the # of cores required x the value ($) per core = your total cost.  Given this formula it is to your advantage to plan your Linux use to minimize IFLs and cores. You can’t do anything about the cost per PVU.

Distributed PVUs are the basis for licensing middleware on IFLs and are determined by the type of machine processor. The zEC12, z196, and z10 are rated at 120 PVUs. All others are rated at 100 PVUs. For example, any distributed middleware running on Linux on z this works out to:

  • z114—1IFL, 100 PVUs
  • z196—4IFLs, 480 PVUs
  • zEC12—8 IFLs, 960 PVUs

Also, distributed systems Linux middleware offerings are eligible for sub-capacity licensing. Specifically, sub-capacity licensing is available for all PVU-priced software offerings that run on:

  • UNIX (AIX, HP-UX, and Sun Solaris
  • i5/OS, OS/400
  • Linux (System i, System p, System z)
  • x86 (VMware ESX Server, VMware GSX Server, Microsoft Virtual Server)

IBM’s virtualization technologies also are included in Passport Advantage sub-capacity licensing offering, including LPAR, z/VM virtual machines in an LPAR, CPU Pooling support introduced in z/VM 6.3 APAR VM65418, and native z/VM (on machines which still support basic mode).

And in true z style, since this can seem more complicated than it should seem, there are tools available to do the job. In fact Chase doesn’t advise doing this without a tool. The current tool is the IBM License Metric Tool V9.0.1. You can find more details on it here.

If you are considering distributed Linux middleware software or are already wrestling with the pricing process, DancingDinosaur recommends you check out Chase’s links at the top of this piece. Good luck.

DancingDinosaur is Alan Radding. Follow DancingDinosaur on Twitter, @mainframeblog. You can check out more of my work at Technologywriter.com

Real-Time Analytics on z Lead at IBM Enterprise2014 Opening Day

October 8, 2014

Users have always been demanding about performance. But does the 5-minute rule noted by Tom Rosamilia in the opening keynote at IBM Enterprise2014 go too far? It now seems users expect companies to respond, or at least acknowledge, their comments, questions, or problems in five minutes. That means companies need to monitor and analyze social media in real-time and respond appropriately.

Building on client demand to integrate real-time analytics with consumer transactions, IBM yesterday announced new capabilities for its System z. Specifically, IBM is combining the transactional virtues of the z with big data analytic capabilities into a single, streamlined, end-to-end data system. This real-time integration of analytics and transaction processing can allow businesses to increase the value of a customer information profile with every interaction the customer makes.  It also promises one way to meet the 5-minute rule, especially when a customer posts a negative comment on social media.

With the new integrated capability you can apply analytics to social sentiment and customer engagement data almost as the transactions are occurring. The goal is to gain real-time insights, which you can do on the mainframe because the data already is there and now the real time analytics will be there. There is no moving of data or logic.  The mainframe already is doing this when it is being used for fraud prevention. This becomes another case where the mainframe can enable organizations to achieve real-time insights and respond within five minutes. Compared to fraud analysis the 5-minute expectation seems a luxury.

By incorporating social media into the real time analytic analysis on the mainframe you can gain an indication of how the business is performing in the moment, how you stack up to your competitors, and most importantly, meet the 5-minute response expectation.  Since we’re talking about pretty public social sentiment data, you also could monitor your competitors’ social sentiment and analyze that to see how well they are responding.

And then there are the more traditional things you can do with the integration of analytics with transactional data to provide real-time, actionable insights on commercial transactions as they occur. For example you could take advantage of new opportunities to increase sales or prevent customer churn.

According to IBM this is being driven by the rise of mobile and smartphones, numbering in the billions in a few years. The combination of massive amounts of data and consumers who are empowered with mobile access is creating a difficult challenge for businesses, IBM noted in the announcement. Consumers now expect an immediate response—the 5 minute rule—to any interaction, at any time, and through their own preferred channel of communication. Unfortunately, many businesses are trying to meet this challenge and deliver instantaneous, on-demand customer service with outdated IT systems that can only provide after-the-fact intelligence.

Said Ross Mauri, General Manager, System z, IBM Systems & Technology Group: “Off-loading operational data in order to perform analytics increases cost and complexity while limiting the ability of businesses to use the insights in a timely manner.” The better approach, he continued, is to turn to an end-to-end solution that makes analytics a part of the flow of transactions and allows companies to gain real time insights while improving their business performance with every transaction.

Of course,  Mauri was referring specifically to the System z.  However, Power Systems and especially the new POWER8 machines, which have a strong presence here at IBM Enterprise2014, can do it too. Speaker after speaker emphasized that the Power machines are optimized for lightning fast analytics, particularly real time analytics.

Still, this was a z announcement so IBM piled on a few more goodies for the z. These include new analytics capabilities for the mainframe to enable better data security and provide companies with the ability to integrate Hadoop big data with the z. Specifically, IBM is delivering:

  • IBM InfoSphere BigInsights for Linux on System z – Combines open-source Apache Hadoop with IBM innovations to deliver enterprise grade Hadoop for System z clients;
  • IBM DB2 Analytics Accelerator – Enhances data security while delivering 2000 times the response time for complex data queries.
  • New capabilities in Linux and the cloud for system z, such as IBM Elastic Storage for Linux on System z, which extends the benefits of Elastic Storage to the Linux environment on z servers, and IBM Cloud Manager with OpenStack for System z, which enables heterogeneous cloud management across System z, Power and x86 environments.

Many of these pieces are available now.  You can meet the 5-minute rule sooner than you may think.

Alan Radding is DancingDinosaur. Follow him on Twitter, @mainframeblog, or check out his website, Technologywriter.com

 

IBM Builds Out POWER8 Systems

October 3, 2014

Just in time for IBM Enterprise 2014, which starts on Monday in Las Vegas, IBM announced some new Power8 systems and a slew of new capabilities. Much of this actually was first telegraphed earlier in September here, but now it is official. Expect the full unveiling at IBM Enterprise2014.

The new systems are the Power E870 and the Power E880. The E870 includes up to 80 POWER8 cores in 32-40 nodes and as much as 4TB of memory. The Power 880 will scale up to 128 POWER8 cores and promises even more in the next rev. It also sports up to 16TB of memory, again with more coming. This should be more than sufficient to perform analytics on significant workloads and deliver insights in real time. The E880 offers also enterprise storage pools to absorb varying shifts in workloads and handle up to 20 virtual machines per core.

Back in December, DancingDinosaur referred to the Power System 795 as a RISC mainframe.  It clearly has been superseded by the POWER8 E880 in terms for sheer performance although the E880 is architected primarily for data analytics. There has been no hint of a refresh of the Power 795, which hasn’t even gotten the Power7 + chip yet. Only two sessions at Enterprise2014 address the Power System 795. Hmmm.

The new POWER8 machines boast some impressive benchmarks as of Sept. 12, 2014: AP SD 2-tier, SPECjbb2013, SPECint_rate2006 and SPECfp_rate2006).  Specifically, IBM is boasting of the fastest performing core in the industry: 1.96x or better than the best Intel Xeon Ivy Bridge and 2.29x better than the best Oracle SPARC. In each test the new POWER8 machine ran less than 2/3 of the cores of the competing machine, 10 vs. 15 or 16 respectively.

In terms of value, IBM says the new POWER8 machines cost less than competing systems, delivering 1000 users per core, double its nearest competitor. When pressed by DancingDinosaur on its cost analysis, IBM experts explained they set up new Linux apps on an enterprise class POWER8 system and priced out a comparably configured system from HP based on its published prices. For the new POWER8 systems IBM was able to hold the same price point, which turned out to be 30% less expensive for comparable power given the chip’s increased performance. By factoring in the increase in POWER8 performance and the unchanged price IBM calculated it had the lowest cost for comparable performance. Recommend you run your actual numbers.

The recent announcement also included the first fruits of the OpenPower Foundation, an accelerator from NVIDIA.  The new GPU accelerator, integrated directly into the server, is aimed at larger users of big data analytics, especially those using NoSQL databases.  The accelerator is incorporated into a new server, the Power System S824L, which includes up to 24 POWER8 cores, 1 TB of memory and up to 2 NVIDIA K40 GPU accelerators.  It also includes a bare metal version of Ubuntu Linux. IBM reports it runs extracting patterns for a variety of analytics, big data, and technical computing workloads involving large amounts of data 8x faster.

Another new goodie, one based on OpenStack, is IBM Power Virtualization Center (PowerVC), billed as new advanced virtualization management that promises to simplify the creation and management of virtual machines on IBM Power Systems servers using PowerVM or PowerKVM hypervisors. By leveraging OpenStack, it should enable IBM Power System servers to integrate into a Software Defined Environment (SDE) and provide the necessary foundation required for the delivery of Infrastructure as a Service (IaaS) within the Cloud.

Finally, as part of the Power8 announcements, IBM unveiled Power Enterprise Pools, a slick capacity-on-demand technology also called Power Systems Pools.  It offers a highly resilient and flexible IT environment to support of large-scale server consolidation and meet demanding business applications requirements. Power Enterprise Pools allow for the aggregation of compute resources, including processors and memory, across a number of Power systems. Previously available for the Power 780 and 795, it is now available on large POWER8 machines.

Am off to IBM Enterprise2014 this weekend. Hope to see you there. When not in sessions look for me wherever the bloggers hang out (usually where there are ample power outlets to recharge laptops and smartphones). Also find me at the three evenings of live performances: 2 country rock groups, Delta Rae and The Wild Feathers and then, Rock of Ages. Check out all three here.

Alan Radding is DancingDinosaur. You can follow this blog and more on Twitter, @mainframeblog. Also, find me at Technologywriter.com.

Mobile Steps Up at IBM Enterprise2014

September 23, 2014

According to eMarketer, by 2017, mobile phone penetration will rise to 69.4% of the global population. The global smartphone audience, eMarketer reports, surpassed 1 billion in 2012 and will total 1.75 billion in 2014 and will continue a fast-paced trajectory through 2017.

OK, mobile and smartphones are hot, driving everything from the Internet of Things, (IoT) to shifts in mainframe peak volume trends. Between IoT and mobile you very well could looking at the future of the mainframe. IBM’s latest mainframe win, announced Sept. 11, identified the government of Croatia adopting the IBM z12EC 703 as the foundation for a new mobile government solution that enables citizens to choose to receive myriad messages and conduct official business on their mobile and smart devices while getting real time alerts.

Mobile transaction volumes already are starting to skew z/OS software usage and trigger new pricing programs. If you haven’t pinned down your mobile mainframe and Power Systems strategy, plan to get over to IBM Enterprise2014, Oct. 6-10 at the Venetian in Las Vegas. There you will find a wide range of mobile-related sessions for the System z, Power, and System i platforms.

You could start with Planning Your Mobile Enterprise Strategy: Future Directions in Enterprise Mobile Application Development by Ian Robinson. Here Robinson looks out the next 12-18 months at a new generation of mobile devices—including smartphones, tablets, wearables and other technologies comprising the IoT—being adopted in large numbers by consumers and employees while introducing considerable challenges and opportunities for enterprise IT managers and application developers. This session reviews the latest mobile trends and highlights where IBM MobileFirst software and services can help enterprise IT strategists prepare their organizations as mobile enterprises. BTW, last week IBM MobileFirst was highly endorsed by both Gartner and IDC.

You also will want to check out Robinson’s session on The MobileFirst Portfolio: IBM’s End-to-end Solution for the Enterprise Mobile App Development Lifecycle. Here he notes that the emerging era of enterprise mobile apps is radically different from traditional software delivery, leading many CIOs and IT managers to completely redefine their enterprise application strategies due to the rapid growth of smartphones and tablet devices among end users. In this session he describes IBM’s MobileFirst portfolio, an industry-leading set of products and capabilities designed to support the entire mobile app lifecycle, from design and development through to testing, integration, optimization, and deployment. Using real MobileFirst client examples, this session also highlights where IBM System z, Power Systems and PureSystems can play an essential role in supporting an enterprise mobile strategy.

A different take on mobile is IBM Electronic Support Engagement—Mobile Service Request, Support Portal, Twitter, Blogs and Wikis by Julie Craft.  Including a demo, she details all the ways you can use IBM electronic support tools from a mobile and social perspective. She presents new mobile apps as well as enhancements to service request that make working with IBM Support easier and saves time. In this session you are invited to voice your views on ways IBM can improve its interfaces to enhance your experience. She reports you’ll even have an opportunity to follow along on your mobile devices.

Finally, here’s a look at a hardware platform-specific mobile session: Mobile to Go, Overview of Mobile Technologies on IBM i by Tim Rowe, Alison Buterill. Android, Blackberry, iPhone, iPad, tablet, and on and on. So many mobile devices, so many applications. Employees want to work 24X7. They want access to email, to development, data, and the system. And they want to use their own interface from wherever they happen to be. How can you deliver the right interface to the right person at the right time? What is available to make the job easier? This session explores the various IBM i solutions that can help you deliver on the request to “Make Mine to Go”. A related session, Test Drive IBM i Mobile Access, provides a preview of the IBM i Mobile Access Solution in the form of a lab that offers a guided, self-paced, interaction with the solution. You can explore the 5250 interface, run SQL Queries, interact with Printed Output and the IFS and much more. Maybe, they suggest, you can take the lab from your own mobile device. Other sessions address mobile on the Power platform.

Without changing the mainframe’s basic role mobile is poised to dramatically alter mainframe computing. The z will continue as the always available, highly secure and scalable backend resource that delivers information on request and handles volumes of transactions.

Finally, don’t miss three evenings of live performances: 2 country rock groups, Delta Rae and The Wild Feathers and then, Rock of Ages. Check out all three and more here.

Alan Radding is DancingDinosaur. Look for me at Enterprise2014. You can follow this blog and more on Twitter, @mainframeblog. Also, find me on Technologywriter.com.

IBM Enterprise2014 to Drive Advanced Mainframe Capabilities

August 27, 2014

The summer is winding down, and IBM Enterprise2014 (October 6-10, 2014 at the Venetian in Las Vegas, October 6-10, 2014 at the Venetian in Las Vegas) will be here in a little over a month.  It combines the IBM System z Technical University and the IBM Power Systems Technical University at one North American location. The advanced capabilities being featured at Enterprise2014 include: cloud, big data, and much more. Let’s look at a sampling of the z-oriented cloud and big data sessions. Subsequent posts will look at POWER and other topics.

The event also will include announcing the winner of the Mainframe Mobile App Throwdown, details here. Mobile is hot and poised to drive a lot of activity through the mainframe. The next generation of mobile apps will need to integrate with core applications running on the mainframe. DancingDinosaur readers know how to do that. Top prize for the Throwdown is an iPad, a pass to the IBM Enterprise2014 conference in Las Vegas, and even a week with IBM experts to help turn the app from a concept to reality. DancingDinosaur will be there to publicize the winners here. But the competition closes Sept. 17 so sign up soon.

For Mainframe Mobile App Throwdown ideas check out the session details at Enterprise2014. For example, Taking Analytics Mobile with DB2 Web Query and More! by Doug Mack digs into mobile features added to DB2 Web Query. He discusses how to sync a mobile device up with your favorite dashboards, or use the mobile app to organize and access reports offline. Leverage REST-based Web Services and application extensions to customize the user interface for reporting functions or schedule the reports to run in the background.

Now, let’s look at a sampling of the cloud and big data sessions.

How Companies Are Using IBM System z for Cloud—Fehmina Merchant describes how organizations are building secure and robust private clouds on System z to deliver their critical IT services with agility and at lower costs.  The session will examine the unique capabilities of zEnterprise as a platform for private cloud computing, in effect providing the ultimate in virtualization, security, scalability and reliability. It also will cover how the newest IBM SmartCloud technologies can automate and optimize the deployment and management of services in the cloud. In addition, the session will offer some specific real-life examples and use-cases to illustrate how a private cloud built on zEnterprise and SmartCloud provide flexible IT service delivery at the lowest cost. The session will end with a live demonstrations of the latest IBM SmartCloud tools.

Should mainframe shops even care about cloud computing? That’s a question DancingDinosaur gets asked frequently. Glenn Anderson answers it in zEnterprise—Cutting Through the Hype: Straight Talk About the Mainframe and Cloud Computing. In this session he promises to explain why the cloud is relevant to a System z enterprise and helps z data center managers cut through the marketing hype.

For zLinux there is The Elephant on the Mainframe—Using Hadoop to Analyze IBM System z Data by Christopher Spaight. He describes the zEnterprise portfolio as including a rich set of options for the analysis of structured, relational data. But what, he asks, if the business needs to analyze data that is unstructured or semi-structured or a mix of relational and non-relational records? Many are looking to Hadoop in these situations. This session lays out the mainframer’s options for using Hadoop both on and off platform, and walks through several use cases for when it makes sense to use Hadoop. BTW, Hadoop on z is called zDoop.

Finally, HDFS, Hive and All That Big Data “Stuff” for IBM System z by Karen Durward looks at how the System z participates in the world of HDFS, Hive and more Big Data stuff. This session focuses on not only why z/OS data should be integrated into a Big Data environment but the various ways to do it. She will describe the latest on z/OS data integration with Big Data, Linux on System z as a Big Data platform, and more.

Then, when you have absorbed all the technology you can enjoy three evenings of live performances: 2 country rock groups, Delta Rae and The Wild Feathers and then, Rock of Ages. Check ‘em out here.

Alan Radding is DancingDinosaur. Look for me at Enterprise2014. You can follow this blog and more on Twitter, @mainframeblog. Find Alan Radding on Technologywriter.com.

IBM POWER8 CAPI for Efficient Top Performance

August 21, 2014

IBM’s Power Systems Power8 Coherent Accelerator Processor Interface (CAPI) is not for every IT shop running Power Systems. However, for those that aim to attach devices to their POWER8 systems over the PCIe interface and want fast, efficient performance CAPI will be unbeatable.  Steve Fields, IBM Distinguished Engineer and Director of Power Systems Design introduces it here. Some of it gets pretty geeky but slides #12-17 make the key points.

DancingDinosaur first covered CAPI here, in April, shortly after its introduction. At that point it looked like CAPI would be a game changer and nothing since suggests otherwise. As we described it then, CAPI sits directly on the POWER8 board and works with the same memory addresses that the processor uses. Pointers de-reference the same as the host application. CAPI, in effect, removes OS and device driver overhead by presenting an efficient, robust, durable and, most importantly, a direct interface. In the process, it offloads complexity.

In short, CAPI provides:

  • SMP Coherence Protocol transported over PCI Express interface
  • Provides isolation and filtering through the support unit in the processor (“CAPP”)
  • Manages caching and address translation through the standard POWER Service Layer in the accelerator device
  • Enables accelerator Functional Units to operate as part of the application at the user (direct) level, just like a CPU

What you end up with is a coherent connected accelerator for just a fraction of the development effort otherwise required. As such, CAPI enables more efficient accelerator development. It can reduce the typical seven-step I/O model flow (1-Device Driver Call, 2-Copy or Pin Source Data, 3-MMIO Notify Accelerator, 4-Acceleration, 5-Poll/Int Completion, 6-Copy or Unpin Result Data, 7-Return From Device Driver Completion) to just three steps (1-shared memory/notify accelerator, 2-acceleration, and 3-shared memory completion). The result is an easier, more natural programming model with traditional thread-level programming and no need to restructure the application to accommodate long latency I/O.  Finally it enables apps otherwise not possible, such as those requiring pointer chasing (e.g. Java garbage-collection).

Other advantages include an open ecosystem for accelerators built using Field Programmable Gate Arrays (FPGA). The number and size of FPGAs can be based on application requirements, and FPGAs can attach to other components, such as private DRAM, flash memory, or a high-speed network.

Driving the need for CAPI is the insatiable demand for performance.  For that, acceleration is required, which is complicated and resource-intensive to build. So IBM created CAPI, not just for pure compute but for any network-attached or storage-attached I/O. In the end it eliminates the overhead of the I/O subsystem, allowing the focus to be on the workload.

In one example IBM reported it was able to attach an IBM Flash appliance to POWER8 via the CAPI interface. As a result it could generate Read/Write commands from applications and eliminate 97% of code path length, a savings of 20-30 cores per 1M IOPS. In another test IBM reported being able to leverage CAPI to integrate flash into a server; the memory-like semantics allowed the flash to replace DRAM for many in-memory workloads. The result: 5x cost savings plus large density and energy improvements. Furthermore, by eliminating the I/O subsystem overhead from high IOPS flash access, it freed the CPU to focus on the application workload.

Finally, in a Monte Carlo simulation of 1 million iterations, a POWER8 core with FPGA and CAPI ran a full execution of the Heston pricing model for a single security 250x faster than the POWER8 core alone. It also proved easier to code, reducing the lines of C code to write by 40x compared to non-CAPI FPGA.

IBM is just getting started with CAPI. Coming up next will be CAPI working with Linux, mainly for use with analytics. Once Linux comes into the picture, expect more PCIe card vendors to deliver products that leverage CAPI. AIX too comes into the picture down the road.

Plan to attend IBM Enterprise2014 in Las Vegas, Oct. 6-19. Here is one intriguing CAPI presentation that will be there: Light up performance of your LAMP apps with a stack optimized for Power, by Alise Spence, Andi Gutmans, and Antonio Rosales. It will discuss how to leverage CAPI with POWER8 to create what they call a “killer stack” that brings together continuous delivery with exceptional performance at a competitive price. Other CAPI sessions also are in the works for Enterprise2014.

DancingDinosaur (Alan Radding) definitely is attending IBM Enterprise2014. You can follow DancingDinosaur on Twitter, @mainframeblog, or check out Technologywriter.com. Upcoming posts will look more closely at Enterprise2014 and explore some session content.


Follow

Get every new post delivered to your Inbox.

Join 734 other followers

%d bloggers like this: