Tony Pearson is a Master Inventor and Senior IT Architect for the IBM Storage product line at the
IBM Executive Briefing Center in Tucson Arizona, and featured contributor
to IBM's developerWorks. In 2016, Tony celebrates his 30th year anniversary with IBM Storage. He is
author of the Inside System Storage series of books. This blog is for the open exchange of ideas relating to storage and storage networking hardware, software and services.
(Short URL for this blog: ibm.co/Pearson )
My books are available on Lulu.com! Order your copies today!
Safe Harbor Statement: The information on IBM products is intended to outline IBM's general product direction and it should not be relied on in making a purchasing decision. The information on the new products is for informational purposes only and may not be incorporated into any contract. The information on IBM products is not a commitment, promise, or legal obligation to deliver any material, code, or functionality. The development, release, and timing of any features or functionality described for IBM products remains at IBM's sole discretion.
Tony Pearson is a an active participant in local, regional, and industry-specific interests, and does not receive any special payments to mention them on this blog.
Tony Pearson receives part of the revenue proceeds from sales of books he has authored listed in the side panel.
Tony Pearson is not a medical doctor, and this blog does not reference any IBM product or service that is intended for use in the diagnosis, treatment, cure, prevention or monitoring of a disease or medical condition, unless otherwise specified on individual posts.
Are you going to the [IBM Edge 2015 conference]? This is IBM's premiere conference covering IBM System Storage, z Systems and POWER Systems.
Here are some secrets for winning prizes while you attend!
Sit in the first FIVE rows of the Techincal Kickoffs - Monday 8:30am
Funding has been approved to give out a few nice prizes. To be eligible, you need to show up on time, and sit in the first five rows of any of the following three Kickoffs. I will be in the one for Storage!
Attend sessions by Edge Event Sponsor companies
Brocade, Cisco and others often present lectures at Technical Edge, and they often give out prizes at those sessions, as part of their sponsorship to the event.
Take a "Selfie" with IBM z13 System mainframe
Yes, we will actually have a z13 System on display at the Solution Center for you to take pictures with. Post it on Instragram, Twitter, Facebook or your other favorite social media websites and be eligible to win prizes.
Get your handwriting analyzed with an IBM POWER8 system
Get your handwriting analyzed at the Solution Center and be eligible to win prizes.
Get your badge scanned at as many booths as you can at the Solution Center
Yes, this means you might get an email from the companies involved, but it will also add you to the list of people eligible for some raffles and drawings for prizes.
Participate in the #IBMEdgeHunt scavenger hunt!
Follow the Twitter hashtag #IBMEdgeHunt to see what else the "Hunt Organizers" have in store during the week!
I arrive Sunday afternoon! Below are some of the hashtags I will be using during the event. You can follow me on @az990tony Twitter handle.
Next week, May 11-15, I will be in Las Vegas, Nevada for the [IBM Edge 2015 conference], covering IBM System Storage, z Systems and POWER Systems. Is this your first time going?
We have sold out, with over 6,000 registrants, that is way more than the 4,200 we had last year. If this is your first time to Edge, then I thought I would get some of my colleagues to help set some expectations.
So, I asked several of my colleagues a few questions, to help provide a variety of viewpoints. Here were my questions:
What should new attendees expect at Edge?
What are the trends that IBM is focused on? How is IBM differentiating themselves in the marketplace?
Why does it matter to our attendees? What's in it for them?
What is the call to action for my readers?
What should new attendees expect at Edge?
"IBM Real-time Compression technology is field-proven and allows seamless scaling as demand for data storage capacity expands. The wave of new applications and data flowing from systems of engagement create a data management challenge. With Real-time Compression, which compresses data in-line and can store up to five times more data in the same physical space, IBM can help to address these challenges. Compression performance is optimized for enterprise-level and cloud workloads. Expect some exciting announcements in regards to this technology!"
-- Ori Bauer,
Director, WW Development and IBM Systems Israel Development Center
"They should expect Demonstrations and Exhibits! One featuring the capabilities of the FlashSystem V9000 through its slick and easy to use graphical user interface. The other featuring breakthrough technology from IBM Almaden Research.
A 'Digital Rack' introducing five configurations of the FlashSystem V9000 and 900 models that address five pain points customers face. A FlashSystem V9000 module showcasing its rich Tier-1 storage features and virtualization capabilities. A full rack / full configuration FlashSystem V9000 deployment illustrating over two Petabytes (2 PB) effective capacity."
-- Bill Bostic
Manager, FlashSystem Development and Exploitation
"The attendees can expect to see how the IBM DS8870 leadership allows clients to achieve the most value from the latest generation of IBM Mainframe, the z13!
Together, the DS8870 and z13 deliver end-to-end FICON speeds using 16Gbps Fibre Channel. These faster links have industry leading reliability as they are protected by new IBM-led standards to make 16 GB FC 300x more reliable. Using z Systems High Performance FICON (zHPF) protocols, DB2 utilities and Log writes can be reduced by up to 68 percent at 100 KM distances and 7 percent at machine room distances. This capability complements the GDPS and TPC-R HyperSwap function for continuous availability by mitigating the distance penalty when the secondary disks are in a send site up to 100 KM away.
Along with better performance and reliability the DS8870 extends the autonomic I/O management function of the z/OS work load manager into the SAN fabric with Fabric I/O Priority Management. For write operations the fabric priority is applied to the Metro Mirror traffic to provide a consistent policy across FCP and FICON sharing the same ISLs."
-- Harry Yudenfriend,
IBM Fellow, Storage Development
"There will be a VersaStack demo at the Cisco booth in the solutions center. There will be a client and IBM Business Partner giving testimony to the value of VersaStack."
-- Eric Stouffer
Director, IBM Storwize Business Line Executive
"Attendees can expect technology previews of exciting new features, like a highly flexible active-active solution for Storwize, next generation of cloud management integration technology for VMware, providing policy-based storage controls to cloud infrastructures that can take full advantage of advanced storage system features, and for integrating cloud storage into your traditional storage infrastructure."
-- Tommy Rickard,
Director, IBM Systems Development, United Kingdom
What are the trends that IBM is focusing on?
"Accelerating applications. The IBM FlashSystem 900 is designed for uncompromising performance, macro efficiency and enterprise reliability.
Radically improving data center efficiency, economics, and performance by exploiting the rich set of FlashSystem V9000 features including virtualization, dynamic tiering, real time compression, thin provisioning, snap shots, cloning, replication, high availability, with the performance of FlashSystem technology."
-- Bill Bostic
Manager, FlashSystem Development and Exploitation
"VersaStack Integrated Infrastructure Solution combines Cisco Network MDS & Nexus, Cisco UCS compute, and Storage with IBM Storwize V7000K, with Cisco UCS Director for single point of management, to address one of the most rapidly growing markets. Storwize improves integrated infrastructure in three key ways - 1) by virtualizing storage to transform utilization, including older or other less capable storage; 2) optimizing speed and cost of devices automatically using EasyTier; 3) squeezing the most data in to the least space with no performance penalty using real time compression. No other integrated infrastructure from the likes of Dell, HP or Oracle has the value of VersaStack."
-- Ian Shave,
Global Business Unit Executive for VersaStack & BD&A, IBM Storage
"Increasing performance of ethernet networks, especially in new cloud deployments, that increases the importance of iSCSI as an enterprise, high-performance storage network. IBM provides rich support for iSCSI and is continuing to invest in this area. Increasing dominance of cloud infrastructures, including private, hybrid, and public forms, that is driving the need for delegated policy-based management to take advantage of storage system features for the software defined environment. IBM provides the most mature, capable, and flexible storage infrastructure, with leading integration into Openstack. VMware and other key cloud infrastructures.
Increasing opportunity for Cloud storage to satisfy traditional storage needs."
-- Tommy Rickard,
Director, IBM Systems Development, United Kingdom
Why does it matter to our attendees? What's in it for them?
"Leading the way in helping the industry and clients exploit flash technology. IBM FlashSystem 900 is the acknowledged technology for application acceleration. That foundation is extended in the FlashSystem V9000 with a rich set of features to enable replacement of disk in the data center. The IBM Data Engine for NoSQL, released last year, uses FlashSystem technology to leverage flash as memory. Now, IBM will be demonstrating the next step to expand to exploitation of flash beyond flash as memory. This technology will dramatically expand flash applicability for NoSQL use cases. It will simplify storage management and accelerate node recovery, while dramatically improving availability and reliability.
Flash technology promises the advantages of better performance, better economics, and better environmentals. More important is the opportunity to radically reshape IT and the ability to deliver new customer value. IBM R&D is focused on delivering leading edge extensible technology as well as blazing the trail to enable the industry and customers exploit it. "
-- Bill Bostic
Manager, FlashSystem Development and Exploitation
"The end-to-end value that only IBM can provide improves resilience, lowers costs and is better able to handle the demands of the emerging Cloud, Analytics, Mobile and Social (CAMS) workloads."
-- Harry Yudenfriend,
IBM Fellow, Storage Development
"Integrated infrastructure speeds time to value with much of the integration and customization laid out in a recipe called a Cisco Validated Design (CVD). This saves time and money for clients and partners. It also provide confidence for these clients in the implementation and use in their environments. Cisco provides a single solution support offering for VersaStack, too, simplifying the technical support for clients and partners."
-- Eric Stouffer
Director, IBM Storwize Business Line Executive
"Cloud architectures are driving the technical agenda for infrastructure. Many clients are making use of cloud technologies, either to satisfy storage needs using public cloud, or to streamline their processes using private cloud. The largest clients, such as some financial clients, are building new data centers modelled on cloud infrastructure, and the growth of cloud investment is defining the technical agenda for these installations."
-- Tommy Rickard,
Director, IBM Systems Development, United Kingdom
What is the call to action for my readers?
"Come to the demonstrations and exhibits at the Solution Center, which runs Monday lunch to Wednesday lunch, including Monday and Tuesday night receptions! This will be your opportunity to see these solutions live, and get to talk to the experts about them."
-- Bill Bostic
Manager, FlashSystem Development and Exploitation
"Check out my session cSY1467: DS8870 Exploitation of the z13 and z/OS I/O Enhancements, which I will present twice on Tuesday.
-- Harry Yudenfriend,
IBM Fellow, Storage Development
"See the VersaStack demo, go to the various sessions on VersaStack, some of which from IBM and the others from Cisco, visit the [IBM on VersaStack" and/or [Cisco on VersaStack] web sites for more information, or watch the YouTube video [New VersaStack Solution by Cisco and IBM]. If you are seller or IBM Business Partner, find a VersaStack Academy near you for more detailed education in person with experts from IBM and Cisco."
-- Ian Shave,
Global Business Unit Executive for VersaStack & BD&A, IBM Storage
If you didn't get into Edge, we are going to have a LiveStream of some of the keynote sessions on our [Digital Event Center] that you can watch from the comfort of your home or office. Go to the [Registration page] for details.
I arrive this Sunday afternoon. If you see me, stop and say "Hi!"
Next week, May 11-15, I will be in Las Vegas, Nevada for the [IBM Edge 2015 conference], covering IBM System Storage, z Systems and POWER Systems.
There are really three conferences in one:
Executive Edge, for business executives, CIO and IT directors
Technical Edge, for storage, system and cloud administrators
Winning Edge, for IBM Business Partners
I am giving presentations this year at both Technical Edge and Winning Edge.
Here is my Technical Edge schedule of what I will be presenting next week:
Software Defined Storage Technical Overview -- Why? What? How?
IBM's Cloud Storage Options
Data Footprint Reduction -- Understanding IBM Storage Efficiency Options
Software Defined Storage Technical Overview -- Why? What? How?
What is big data? Architectures and Practical use cases
IBM's Smarter Storage Strategy
New Generation of Storage Tiering: Less management, lower costs and increased performance
IBM's Smarter Storage Strategy
IBM's Cloud Storage Options
IBM Spectrum Scale (Elastic Storage) Offerings
The Pendulum Swings Back -- Understanding Converged and Hyper-converged environments
IBM Spectrum Storage Integration with OpenStack
I am also part of the Winning Edge track for Cloud and Analytics Sales Enablement (CASE) training. Here is my Winning Edge schedule of what I will be presenting next week:
IBM Offerings for Cloud Infrastructure - Storage
(co-presenting with Elan Freedberg)
We will have some exciting storage demos at the Solutions Center:
Object and Cloud storage
Big data and pervasive Flash
Next generation Tier 1 storage
Data Protection, Archive and Nearline storage
Storage Efficiency with Data Footprint Reduction
The Solution Center demos will be shown at the following times. I will try to hang out here during these times to help answer questions:
Demos at the Solution Center
11:30am - 12:45pm
Solution Center Hours
05:30pm - 07:30pm
11:30am - 01:00pm
Solution Center Hours
05:30pm - 07:30pm
11:30am - 12:30pm
Solution Center Hours
In between presentations and demos, I will be having conversations with clients at breakfast, lunch and dinner, blogging, tweeting, and attending some of the 600 other storage sessions that will be presented at Edge this year!
I got some exciting news today that i would like to share with my readers!
Several years ago, I mentored a young 19-year Tarun Pondicherry from India to work on one of Google's Summer-of-Code project. We worked on a simple blogging system to help teach grade school children in Uruguay how to write their own blogs.
Well, that was six years ago, but I have kept in touch, and today learned that Tarun has been working on an exciting project to teach young kids to write computer programming code.
It's called "LightUp" and the idea is quite simple. Using a simple programming interface, you can program the machine to light up based on what the programming code specifies. It is immediate feedback for the child to explore the world or software logic. Already they have helped kids around the world build over 100,000 circuits!
And speaking of learning new innovations, I will be at the [IBM Edge 2015 conference] next week in Las Vegas. There will be traditional lectures about IBM's latest innovations, mixed with hands-on labs and plenty of exciting demos, because Adults need to learn too!
Every year, March 31 marks "World Backup Day". Sadly, many people forget the importance of backing up their critical information. This is not just true for businesses, non-profit organizations and government agencies, but also for all of your personal information that you keep on computer devices.
My friends over at Cloudwards had developed an awesome infographic related to World Backup Day. Here it is.
(FTC Disclosure: I work for IBM, which has no business relationship with Cloudwards. Cloudwards does not itself provide backup services, but rather reviews services provided by others. This post should not be considered an endorsement of Cloudwards or their reviews.)
Courtesy of: Cloudwards.net
I hope you find this information helpful and informative!
IBM has chosen three particular Software Defined Environments. At one end, IBM is a platinum sponsor of OpenStack which supports x86 servers, POWER systems and z System mainframes. A problem with open source projects like this, however, is that they can be a bit like putting together IKEA furniture from pieces in a box: "Some assembly required."
At the other end, highly proprietary environments from VMware and Microsoft bring enterprise-ready out-of-the-box solutions. However, nobody wants to be limited to just x86-based solutions. IBM offers the best of both worlds, basing its IBM Cloud and SmartCloud software on OpenStack standards, but providing enterprise-ready solutions for x86, POWER Systems and z System mainframes. This includes IBM Cloud Manager with OpenStack, IBM Cloud Orchestrator, and IBM SmartCloud Cost Management software products.
(Analogy: If open source solutions were vanilla ice cream, and proprietary solutions were chocolate ice cream, then IBM Cloud and SmartCloud is vanilla ice cream with chocolate sauce on top! This is the same approach IBM used for WebSphere Application Server, based on Apache web server, and IBM BigInsights, based on Hadoop analytics.)
For some people, software defined can also refer to how the resources are deployed. Rather than using specialized hardware, solutions based on industry-standard hardware can be delivered either as pre-built appliances, services in the Cloud, or as software-only products.
Back in the 1990s, IBM came up with the [Seascape Storage Enterprise Architecture], deciding to focus the design of its storage systems to be based, where possible and practical, on industry-standard components.
Let's review a few products:
IBM SAN Volume Controller (SVC) and Storwize V7000: IBM storage hypervisors were originally designed to run on industry-standard x86 servers. The IBM scientists at Almaden Research Center referred to this as the "COMmodity PArts Storage System" (COMPASS) architecture.
That is still mostly true 12 years later, but SVC and Storwize V7000 does have specialized hardware, including host bus adapter cards and the [Intel® QuickAssist] chip for Real-time Compression.
IBM DS8000 disk system: The DS8000 is based on off-the-shelf IBM POWER servers. Originally, you could only purchase POWER-based servers from IBM, but now thanks to the [OpenPOWER Foundation], you now have more options.
The DS8000 does use some specialized hardware for its host and device adapters, taking advantage of ASICs and FPGAs to optimize performance.
IBM XIV storage system: IBM acquired XIV back in 2008, but its design is very similar to Seascape architecture. All of the Intellectual Property was in the software, installed on industry-standard x86 servers, cache memory, host bus adapters and 7200 RPM nearline disk drives. I joked that the entire hardware bill-of-materials could be ordered directly from the CDW catalog!
IBM FlashSystem: IBM is #1 rank in the All-Flash Array market. Rather than using off-the-shelf commodity Solid-State drives (SSD), the IBM FlashSystem employs specialized hardware based on FPGAs to optimize performance.
IBM FlashSystem came from the recent acquisition of Texas Memory Systems, and was not designed under the IBM Seascape architecture.
Combining the method the resources are controlled and managed with the way storage is deployed results in a quadrant. Let's take a look at this from a storage perspective:
Traditional storage products that are based on specialized hardware that do not support Software Defined Environment APIs.
Storage products that are based on specialized hardware, but have been enhanced to support Software Defined Environment APIs. For OpenStack, this refers to Cinder and Swift interfaces. For VMware, this would include VAAI, VASA and VADP interfaces and vCenter Console plug-ins.
Storage products that are basically software, either installed on pre-built hardware appliances, offered as services in the Cloud, or software you deploy on your own industry-standard hardware. Unfortunately, this category does not support software defined environment APIs, and so proprietary interfaces require administrator-intensive involvement instead.
Storage software for industry-standard hardware. You purchase the appropriate server, cache memory, flash and disk drives as needed. This category could also extend to pre-built appliance versions of this software, or as services in the Cloud. APIs for software defined environments are available to deploy this with self-service automation.
IBM Spectrum Storage is a family of Category IV software offerings. Here are the products announced:
Based on technology from...
IBM Spectrum Control™
Simplified control and optimization of storage and data infrastructure
SmartCloud Virtual Storage Center, Tivoli Storage Productivity Center
IBM Spectrum Protect™
Single point of administration for data backup and recovery
Tivoli Storage Manager
IBM Spectrum Accelerate™
Accelerating speed of deployment and access to data for new workloads
XIV storage system
IBM Spectrum Virtualize™
Storage virtualization that frees client data from IT boundaries
SAN Volume Controller
IBM Spectrum Scale™
High-performance, scalable storage manages exabytes of unstructured data
GPFS and codename:Elastic Storage
IBM Spectrum Archive™
Enables easy access to long term storage of low activity data
Linear Tape File System (LTFS)
Last year, IDC recognized IBM as #1 in this new emerging software defined storage market. This announcement reinforces IBM's lead in this area. See the [Press Release] for details.
Well it's Tuesday again, and you know what that means? IBM Announcements!
Today, IBM announced an exciting new addition to the IBM System Storage™ product line, [IBM Spectrum Storage™], a family of software defined storage offerings.
To understand its significance, I need to explain a few things first. Software defined storage is part of a larger concept of software defined environment.
How is software defined environment different than what you have now? In every data center, you need to map business requirements of an application workload with an appropriate set of IT infrastructure, including server, network and storage resources.
The traditional approach involves an application owner or database administrator reviewing the business requirements documented for the application, calling the server, network and storage administrators, who match those requirements to appropriate IT hardware and notify the folks in facilities to rack and stack the gear accordingly.
In a software defined environment, Application Programming Interfaces (API), Service Level Agreements (SLA) and Orchestration workflows can automate the request for the appropriate resources. This is referred as the "Control Plane".
Responding to these requests, the software can provision the appropriate server, network and storage resources required. Server, network and storage virtualization, standard interfaces and deployment technologies exist to make this practical. This is referred to as the "Data Plane".
Any time new a way of doing things is introduced into the world, there could be some resistance. Let's tackle the three most frequently stated objections:
"IT infrastructure resources are rare and expensive! Administrators need to control or approve how resources are doled out!" An objection to self-service automation is the fear that employees would take too much.
If you have a bank account, Automated Teller Machines (ATM) can restrict the amount of cash you can take out, based on what is appropriate per request, or per day, with an upper limit of what you have in your personal checking or savings account. You enter your debit card and PIN into the "Control Plane" keypad and out comes a stack of 20-dollar bills from the "Data Plane" slot. In a software defined environment, you can limit requests through quotas and resource pools.
"Some application workloads are more important than others! Another objection is that every workload will be treated in the same standard way, mission critical workloads and dev/test would be treated alike.
At the gas station, you can select different levels of octane gasoline. You enter your credit card and zip code into the "Control Plane" keypad and selected octane comes out of the "Data Plane" hose. In a software defined environment, resources can be provisioned with different Quality of Service (QoS) levels.
"Different applications require different combinations of resources!" Another objection is the fear that fixed combinations of server, storage and network resources will be stifling to innovation and productivity.
At the vending machine, you can choose which candy bar and which chips to have with whatever soft drink you choose for lunch. You enter your bills and coins into the "Control Plane" slot, select the row letter and column number for your snack of choice, and then fetch your purchases from the "Data Plane" flap. In a software defined environment, a Service Catalog can offer a virtual menu of different server, network and storage resources to be combined together as needed.
These concerns are addressed well enough in software defined environments, in general, and with IBM Spectrum Storage family of products, in particular.
(Nostalgia: I remember the days before self-service automation. At the bank, I had to stand in line at the bank until I could to talk to a human bank teller to get cash from my savings account. At the gas station, human gas attendants would come out and pump the gas for me, check my oil and wash my windshield. And at a restaurant, I felt like I waited an eternity from the time I ordered my meal to the time the human short-order cook had it ready and human wait staff delivered it to my table. These all seem silly today, doesn't it?)
Today in the USA, we honor [Martin Luther King, Jr.] This year marks the 50th anniversary of the largest political demonstration to date in American history. Over 250,000 people went to Washington DC to hear Dr. King give his now famous "I have a dream" speech.
Well it's Tuesday again, and you know what that means? IBM Announcements!
(Update: I thought it was quite clever to announce the new z13 mainframe on January the 13th. A few [triskaidekaphobic] employees pointed out that certain [Greek and Spanish-speaking cultures] consider Tuesday the 13th to be an unlucky day. However, superstitious people should probably not work in IT, as it would be difficult for a worldwide company like IBM to avoid all the numbers that different cultures consider unlucky.)
You are cordially invited to join IBM on January 14 from 2:00pm to 4:30pm Eastern Standard Time (US) when IBM will share a whole new generation of IBM z Systems™ built to meet the needs of your digital business. Join us and learn how IBM z Systems are designed to:
Support the transaction growth and needs of the mobile generation and the Internet of things
Integrate data, transactions and analytics, for in-transaction insights and right-time actions
Provide secure, trusted and efficient cloud services with new economic models
Exploit new modern, open development environments, tooling and skills for greater returns
At this live streaming event, you will hear from a remarkable group of business and technology leaders who will share success stories, best practices and the exciting technology innovations and capabilities of the new generation of IBM z Systems. Go to the Registration page] to participate.
But what does this really mean? Are you thinking BFD?
(Update: For those not familiar with IT acronyms, BFD refers to "Bigger, Faster, Denser" -- the trend in IT to announce new generations that are merely bigger, faster, and/or denser versions of the previous generations. Fortunately, the z13 takes up the same amount of data center floor space -- 2 floor tiles = 2 square meters = 20 square feet -- and weighs approximately the same as the z196 and zEC12, so raised floor struts do not have to be strengthened or reinforced to take in this new system.)
You may have noticed that we are now talking about "z System" instead of "System z". This change was made to line up with IBM's change to "POWER Systems" from "System p". Leadership felt that dropping the stodgy old zEnterprise and giving the mainframe a "hip" new name would attract new emerging digital workloads like Cloud, Analytics, Mobile and Social.
This is not the first time IBM has renamed products in a series. While the IBM mainframe just celebrated its 50th anniversary last year, the "13" refers to the 13th generation of CMOS-based mainframe technology introduced in 1994. Here is a quick table to show you the names that have evolved over the years:
1 to 6
S/390 G1 to G6
zSeries z800 and z900
zSeries z890 and z990
9 to 10
System z9 and z10
System z196 and z114
zEnterprise zEC12 and zBC12
(Note: This change also corresponds to a completely restructuring of IBM into business units, eliminating its former hardware and software groups. The design and development of all mainframe-related hardware, software and middleware will be consolidated under the IBM Systems business unit. I will wait for IBM's 4Q financial results announcement on or after January 20 before I cover this in any more detail.)
The z13 machine itself has some unique differences from previous generations. Instead of a "Multi-chip Module" (MCM) that contained multiple processor and storage controllers on a single slab, the z13 uses Single-Chip Modules (SCM) that are either a single 8-core processor, or a single system controller, allowing them to be field replaceable units (FRU).
Previous generations organized the processors in 1 to 4 vertical "books". The problem was that if you had a single book system, you bought a lot of hardware infrastructure designed to support a full four books. In the new design, processors are organized into horizontal Central Processor Complex (CPC) drawers, with additional hardware infrastructure provided per drawer. This makes the lower-end models more affordable. Each drawer has six processor SCMs and two system controller SCMs, providing 39 to 42 usable cores per drawer. Models ranges from 30 to 141 usable cores, with the option to upgrade from one model to another as your needs grow.
The z13 provides N-2 generation compatibility. This means you can have the z196, zEC12 and z13 all participate in the same Parallel Sysplex. You will also be able to upgrade your z196 or zEC12 to the new z13 system.
The new z13 can have up to 10TB of memory, and this can be assigned entirely to a single Logical Partition, or LPAR. The system can be subdivided up to 85 LPARs, versus 60 on the previous generation. Currently, z/OS v1 can only have up to 1TB per LPAR, and z/OS v2 can only go up to 4TB, so I suspect this 10TB is planning for future OS releases.
The new z13 now offers Simultaneous Multithreading [SMT]. Initially, this will double the number of threads for IFL engines (supporting Linux and z/VM), and zIIP engines supporting DB2, Java, XML and IPsec workloads. IBM is eliminating the zAAP engines, since zIIP engines can do all of that. The new [Preview z/OS v2.2] will take advantage of this SMT capability.
To assist with database, analytics and multimedia workloads, the z13 offers Single Instruction, Multiple Data [SIMD] capability. This allows a single instruction to perform the same update or action across many data fields.
For those clients with zBX models 2 and 3, allowing you to run POWER-based AIX and x86-based Microsoft Windows and Linux operating systems on your mainframe, they will be able to upgrade to [zBX model 4 for the z13 System]. Now that IBM has sold off its x86 server business to Lenovo, I suspect it will also phase out the zBX offerings as well.
To handle emerging workloads of Cloud, Mobile and other Web applications, IBM will offer a new stronger and faster Crypto Express5S cryptographic adapter. The z13 will enhance public key support for constrained digital environments using Elliptic Curve Cryptography (ECC) for users such as Chrome, Firefox, and Apple's iMessage. The z13 will also minimize reformatting of databases with new exploitation of VISA format preserving encryption (FPE) for credit card numbers.
The z13 also made some enhancements for Linux clients. The zAware analytics that analyzes internal traces and logs for z/OS has been extended to support Linux on System z. For those who want to use GDPS Business Continuity and Disaster Recovery services, but don't want to develop z/OS skills for the "K" system, there will now be a Virtual GDPS appliance that will run self-contained z/OS. Lastly, IBM has made a statement of direction that it will support open source Linux KVM as a Linux-only alternative to z/VM hypervisor. OpenStack will support both this new Linux KVM as well as z/VM 6.3 release.
The PCIe bus has been upgraded to Gen3 at 16Gbps, from Gen2 used in the zEC12. These can be used for Coupling Facility Links, which are faster than the legacy 6 Gbps InfiniBand, which are also supported for legacy migration. People with z196 and zEC12 can either carry forward their I/O drawers they have previously purchased, or move the PCiE Gen2 cards into the new Gen3 drawers.
The new z13 will also support 16Gb FICON, using the new FICON Express5S cards. Here is my segue into storage, as you are probably now wondering when I was going to get to the storage part of the announcement!
IBM is also announcing corresponding changes to the DS8870 firmware and accessories to go with the z13 System. This includes:
FICON Dynamic Routing
Reduce cost with improved and persistent performance for supporting I/O devices. This feature will allow SAN directors to have both FICON and FCP share the same Inter-switch Links (ISL). This is especially useful for clients who use FCP with their Linux, z/VM, AIX or Windows workloads.
16Gb Host Adapters
Improve network performance with twice faster FC and FICON adapters, and minimize latency for database log writes with zHyperWrite and Metro Mirror. These 16Gb adapters can auto-negotiate down to 4Gb and 8Gb, so that the DS8870 can connect to both the new z13 mainframe, as well as older models.
Forward Error Correction
Preserve data integrity with more redundancy on the information transmitted via 16Gb adapters.
zHPF Extended Distances improvements
Increase remote data speed with 50 percent better I/O performance when accessing remote disk, typically after a HyperSwap. The "zHPF" acronym is short for z System High Performance FICON.
Improved resiliency capabilities while enhancing the value of FICON Dynamic Routing mentioned above. IBM is extending Workload Manager (WLM) Quality of Service (QoS) optimization that exists now for compute and storage to the SAN Fabric, allowing WLM policies to influence FICON traffic.
IBM zHyperWrite™ capability
Helps you achieve better DB2 log write performance when using Metro Mirror (PPRC) in a HyperSwap-managed environment. Log writes are sent directly to both DASD, freeing up Metro Mirror resources.
But don't just take my word for it, here are reviews of the new system from various journalists:
"They seem a computing odd couple: the mainframe, the old workhorse, and the smartphone, the cool-kid computer of today. But IBM has designed the latest version of the mainframe, which is being introduced on Wednesday, with the smartphone in mind. The new mainframe, the z13, has been engineered to cope with the huge volume of data and transactions generated by people using smartphones and tablets."
-- New York Times
"One customer enthusiastic about such features is Citigroup Inc., a longtime IBM user that favors mainframes for both reliability and security. 'Security is in the DNA of the mainframe,' said Martin Kennedy, Citi's managing director for platforms and storage. Another factor shaping the bank's needs, Mr. Kennedy said, is the rising volume of transactions carried out using smartphones and other mobile devices. Mainframes are particularly good at combining data from a variety of systems and presenting them to a user's mobile app, he said."
-- The Wall Street Journal
"IBM is introducing a new mainframe in a bet that clients will need its souped-up speed and security to handle a surge in consumers using smartphones for everything from banking to checking health-care records. The z13 system can encrypt and analyze data in real time and process 30,000 transactions a second, International Business Machines Corp. (IBM) announced today. That means faster and safer transactions for consumers on mobile phones."
"With the unveiling of the z13, IBM has taken its MobileFirst Platform to deliver even better performance and security than before, as it incorporates the fastest microprocessor in the world, server processors that are twice as fast as existing products, 300 percent additional memory and 100 percent more bandwidth analytics speed. Last year, IBM formed a partnership with Apple to help bring Apple's iDevices to business customers to boost sales, with IBM providing cloud and mobile analytics support."
-- The Street
"'We're driving toward a world where more and more people are using mobile devices, or embedded devices, to interact with systems,' John Birtles, director of IBM z Systems, tells WIRED. 'We need to make sure that those devices are secure, that the transaction's secure, and that our clients get the level of analytics that gives them opportunities to improve their businesses.'"
IBM mainframes are used to process the majority of financial transactions around the world, is well positioned to handle Cloud, Analytics, Mobile and Social workloads. The IBM DS8000 series disk is the #1 market leader for disk storage on mainframe environments.
Well, it's the end of the year, so I thought a recap of year 2014 would be in order.
The year started out with some January announcements, including the IBM FlashSystem 840. IBM is proud to be ranked #1 in All-Flash Arrays, and the IBM acquisition of Texas Memory System has caused all of the other competitors to scramble their own wanna-be offerings. IBM also announced it was going to sell off its System x division to Lenovo.
In February, I wrapped up a project to build a Linux-based PC for a kindergarten class. IBM announced some exciting new things at Pulse 2014 conference, including IBM Bluemix Platform-as-a-Service (PaaS), new IBM SmartCloud Virtual Storage Center offerings, and acquisition of Cloudant Database. Also, on Valentine's day, IBM announced the FlashSystem V840, which combines the software-defined storage features of SAN Volume Controller, with the Microlatency of the FlashSystem 840. IBM sold its 10,000th PureSystems converged expert-integrated system.
In March, I completed a six-month film project ["A Tucson Executive Briefing Center: A Quick Visual Tour"]. I was writer/director/actor for this quick 3-minute film posted on YouTube. I wrote the script and had it reviewed by a professional script reviewer, hired a professional cinemetographer, paid royalties for background music, located a voice-over expert for narration, and trained the actors (all IBM employees) how to read their lines and stand on their mark for the camera. It was a big success!
In April, I presented at the Systems Technical University in Istanbul, Turkey. I had been to Turkey before, but this was my first time to the city of Istanbul itself. The owner of my local [Savaya Coffee] is from Istanbul, and was able to introduce me to someone who was able to arrange for a full tour my first day! Meanwhile, on the other side of the pond, IBMers in New York were celebrating the 50th anniversary of the IBM mainframe, including a cameo appearance on the TV show "Mad Men".
In May, I was busy presenting at the IBM Edge conference in Las Vegas. IBM celebrated the sixth anniversary of IBM ProtecTIER data deduplication device, announced "Codename: Elastic Storage" and new features on the DS8870 disk system, and presented analyst findings that IBM Software Defined Storage was substantially less expensive than competitive offerings.
In July, I took a nice summer vacation, [a road trip across the state of Tennessee]. IBM made a strategic partnership with Apple to offer mobile apps for the data center enterprise for the iOS operating system on iPhones and iPad tablets.
In August, I completed a summer partnership with University of Toronto and IBM Softlayer to build "Concept IBM Watson", a scaled down version of IBM Watson based on my infamous 2011 blog post [How to replicate Watson hardware and systems design for your own use in your basement]. Rather than using three physical servers, however, we had virtual x86 machines running on IBM Softlayer cloud. The system was only asked the simplest "How many...?" questions against a single text document, but proved to the University that teaching analytics by replicating IBM's historic achievement was effective and possible.
In September, I celebrated my eight year "Blogoversary". That's right, I have been blogging for the past eight years! With over 800 posts, and five published books, I countinue to be ranked #1 most-read blog on IBM developerWorks. IBM was ranked #1 for Software Defined Storage!
In October, I presented at the Systems Technical University in Dublin, Ireland. This was my first time in Ireland, and I found Dublin to be quite a beautiful city, with friendly people and delicious food.
The rest of October, and much of November and December, I spent on the road, visiting clients to help close deals! (Sorry folks... Due to SEC black-out rules, I am prohibited from telling you how well I did) Since I am not allowed to talk about on-going discussions that I have with clients, my blog has been noticeably silent during these months. I apologize for any stress or anxiety this might have caused any of my readers!
Despite too-much-candy, too-much-turkey and too-many-cookies that the year-end often brings, I managed to lose twenty pounds on a low-carb, gluten-free, Paleo diet and exercise.
(Note: While Lenovo has officially taken over the System x on October 1st back in the United States, China, and several other countries in Asia and the Americas, it has not yet happened in Europe. This is expected to happen this December. This results in some awkwardness during this period of transition.)
Day 1 started off with some keynote sessions. Amy Purdy, IBM Director of Training Services, was the emcee.
Gareth Tucker, Director of EMEA for Intel
Gareth focused on the strong partnership between IBM, Lenovo and Intel. For example, a client query that took 4 hours with traditional DB2 database on Intel Xeon, but only 90 seconds on DB2 BLU with the new Xeon V2 chip.
10 years ago, some storage vendors warned clients not to use any Intel-based storage devices. Today, over 85 percent of storage is Intel-based, including most of the IBM System Storage portfolio. IBM SoftLayer also uses Intel to offer both bare metal and virtual x86 servers, and was the first cloud provider to use Intel's "Trusted Execution" mode.
Next year, Microsoft will drop support for Windows 2003 server on July 15, 2015. This represents an excellent selling opportunity to get clients to upgrade their x86 server hardware. Intel estimates there are 24 million instances of Windows 2003 worldwide. On average, it takes 150 days to migrate to Windows 2012, so get clients to start now!
Jeff Howard, Vice President of Lenovo Flex and BladeCenter
Jeff was a last-minute stand-in for Adalio Sanchez who is busy getting thousands of employees and hundreds of trailer trucks full of IT equipment from IBM's Raleigh location to Lenovo's new building in Morrisville.
Lenovo's goal is simple: to be the #1 vendor of x86 enterprise servers. Lenovo sees a $44 Billion USD opportunity in x86 servers, with an additional $14B opportunity selling IBM System Storage attached to these servers. Lenovo is already #1 for Personal Computers in the consumer space, and is #1 for customer satisfaction. IBM System x #1 in reliability and up-time for x86 servers. In a client survey of how many clients had an outage lasting four hours or more, less than 1 percent from IBM System x compared to 13 percent for HP servers. That's a big difference!
There is a 40 percent growth in "Converged Systems" such as the Flex System and PureFlex systems. Lenovo will take over the x86-only versions of these, while IBM will retain the POWER-based and Power-and-x86 hybrid models. IBM will also retain the PureApplication and PureData models of the PureSystems line.
Lenovo is also focused on security. Their "Trusted Platform" includes Self-encrypting Drives (SED) managed by IBM Security Key Lifecycle Manager software, and Crypto-assist co-processors.
Jeff also mentioned new reference architectures for VMware's VSAN, Microsoft's Fast-track Data warehouse for SQL Server, SmartCloud Desktop Infrastructure VDI with Atlantis ILIO, and Flex Systems for Hyper-V.
Greg Lotko, VP of IBM Storage Systems Development
Greg is the new VP of Storage Systems Development, about 11 months on the job, but I am glad to hear that he recognizes that IBM System Storage has a huge portfolio of products.
He focused on those areas where IBM is ranked #1:
IBM is #1 for All-Flash arrays.
IBM is #1 for Software Defined Storage (SDS).
IBM is #1 for Tape, including tape drives, tape libraries and virtual tape systems
The weather here in Dublin is great, although I have had not had much time to enjoy the outdoors with all the awesome and interesting sessions inside!
We have a lot to cover, so I will do the quick recap today, and then go in-depth on subsequent posts.
IBM FlashSystem 840 and V840
The FlashSystem now offers a high-voltage 1300W power supply. There are two supplies providing redundancy. In the unlikely event that you are doing maintenance on one of them, the other supply handles all the workload. With the original power supply, the system slowed down the clock speeds to reduce electrical demand. The new power supplies can handle full performance.
Also, the Graphical User Interface (GUI) now holds 300 days of performance data with pan-and-zoom capability. Five predefined graphs showing key performance metrics with additional user-defined metrics available for visualization.
The new v7.4 level of microcode combines features from v7.2.7 and v7.3 into a single code base.
In previous 3-site mirroring implementations, you had A-to-B-to-C cascading. Metro Mirror would get the data from A-to-B, then Global Mirror would copy B-to-C. Multiple Target Peer-to-Peer Remote Copy (PPRC) feature number 7025 allows you to have two separate paths of the data: A-to-B and separately A-to-C. Some folks refer to this as a "star" configuration.
For System z mainframe clients, the new v7.4 introduces new zHyperWrite for DB2 database logs, enhances zGM (XRC) write pacing, and extends Easy Tier automated-tiering API to allow z/OS applications to influence placement on different tiers of storage.
The High Performance Flash Enclosures (HPFE) that IBM introduced last May for the "A" frames are now available for "B" frames. You can have four HPFE in A, and another 4 in B.
DS8870 now offers 600 GB 15K rpm SAS and 1.6 TB 2.5-inch SSD encryption drives for additional capacity and cost performance options to meet data growth demands within the same space. Both support data-at-rest encryption.
Lastly, we have upgraded the OpenStack Cinder driver to the latest Juno release, including features like volume replication and volume retype.
The latest SAN switch is a slim 1U high box that can be configured with 12 or 24 ports. These are 16Bps ports that can auto-negotiate down to 8Gbps, 4Gbps and 2Gbps. These are easy to set up, and can be managed with the IBM Network Advisor management software.
GPFS is the core technology for IBM's "Codename: Elastic Storage" initiative.
You have several options. First, you can purchase just the GPFS software itself. It runs natively on AIX, Windows and Linux, and can be extended to support other operating systems through the use of NAS protocols like NFS or CIFS. Today, the Linux support which was previously just x86 and POWER has been extended to include Linux on System z mainframes as well.
GPFS v4.1 offers "Native RAID" support, with de-clustered RAID in 8+2P and 8+3P configurations. Like the IBM XIV Storage System, this scatters the data across many drives, and can tolerate drive failures better than traditional RAID-5 configurations.
Another option is to get a pre-configured "Converged" appliance that combines servers, storage and hardware. We already offer SONAS and the Storwize V7000 Unified, but IBM now offers the "GPFS Storage Server" running on the new P822L Linux-on-Power servers, RHEL v7, and and GPFS v4.1 with Native RAID to twin-tailed attached DCS3700 expansion drawers. Since GPFS provides the RAID, no need for DCS37000 controllers, saving clients substantial costs.
The IBM Storwize family includes SAN Volume Controller, Storwize V7000, Storwize V7000 Unified, Storwize V5000, Storwize V3700 and Storwize V3500.
The big announcement is that IBM now offers data-at-rest encryption for block data on internal drives in the new generation of Storwize V7000 and V7000 Unified models. There is no performance impact, and no need to purchase new SED-capable drives.
Data-at-rest encryption helps in several ways. First, it protects data if a drive is pulled out and taken away maliciously. Second, it protects data if the drive fails and you want to send it back to the manufacturer for replacement. Third, it allows you to perform a "secure erase" so that the data can be sold or re-purposed without fear of anyone reading previous data.
Initially, the encryption key management is built-in, with the keys stored on a USB memory stick physically attached to the model. In the future, IBM will extend this support to SVC, extend this support to external virtualized drives, and extend this support to IBM Security Key Lifecycle Manager (SKLM).
Other announcements include 16Gbps adapters for SVC, Storwize V7000 and V7000 Unified. The entire Storwize family will also enjoy both 1.8TB 10K RPM 2.5-inch drives, and 6TB 7200RPM 3.5-inch drives
See the Announcement Letter (available later this month) for details.
New TS1150 enterprise tape drives
The anticipation is over! The new TS1150 tape drive has been announced, with 10TB raw un-compressed "JD" media cartridge capacity and 360 MB/sec throughput performance. The new drive is read/write compatible with TS1140 on JC, JY and JK media cartridges.
For the virtual tape libraries for the System z platform, IBM offers two models. The TS7740 had a small amount of disk front ending tape library of physical tape. The TS7720 had a large amount of disk with no tape library.
But then the person carrying the chocolate bar bumped into the person carrying the jar of peanut butter, and the rest is history. IBM will now allow tape attach on TS7720, best of both worlds! Large disk cache plus tape library attach.
Tape-attached TS7720 configurations can have up to eight partitions, with different partitions have different policies. Some might move data from disk cache to tape more aggressively, while other partitions may keep data on disk for longer periods, or indefinitely if needed.
Logical tape volumes can now be up to 25GB in size.
The DCS3700 is IBM's entry-level disk system for sequential-oriented workloads. Today, IBM announced new disk drive options: 400GB 2.5-inch SSD, 800 GB 2.5-inch SSD, and 1.2TB 10K RPM 2.5-inch drive. All of these offer T10 Protection Information (PI) data integrity.
Hello everyone! I am back, fully well-rested from a wonderful 3-week vacation touring the lovely state of Tennessee. Here's a quick recap:
(FCC Disclosure: I mention various companies and products in this blog post. I have no financial interested in any of them, nor have I received any compensation to mention or endorse them here.)
Our first stop was Lynchburg, TN, home of [Jack Daniel's], America's oldest whiskey distillery. Our tour guide, Ron (who both looked and sounded like [John Goodman]) took us first to see how they burn wood to make charcoal, then the natural water spring which supplies the iron-free water used for the whiskey. We then got a whiff of the mash at various stages of fermentation. Lastly, we had samples of Original No. 7, Gentleman's Jack, and Single Barrel.
(A word of caution: Domestic airlines only allow FIVE LITERS of Bourbon, Whiskey or Rum in your checked luggage. That is only six bottles at the 750ml size, of beverages that are between 24 to 70 percent alcohol by volume [ABV]. Anything above 70 percent is considered too flammable to take on the plane. Excess bottles can be custom packed and shipped, but can be quite expensive. Nearly everyone we met drove all the way to Tennessee instead of flying, and now I understand why.)
While in the area, we had a nice lunch at [Miss Mary Bobo's], a boarding house turned into a restaurant. They only serve one meal a day at 1pm, by reservation only. And we were paired up with eight others and served food "family style" a large round table with a [Lazy Susan].
Jack Daniel's is not the only attraction in the area. We also visited [Falls Mill], a grist mill that grinds corn, wheat and rye for the other distilleries. Mo and I visited [Prichard's Distillery], where they make Whiskey, Rye and Rum. We highly recommend their molasses-flavored "Sweet Lucy"!
We stopped at the famous historic landmark, the [Chattanooga Choo Choo], which was formerly a train station, and now renovated into a hotel. We asked to see the inside of one of the train cars converted into a hotel room.
Gatlinburg and Pigeon Forge
We stayed in a cabin in the [Smokey Mountains] near Gatlinburg. In addition to pleasant rides through the National park, we also walked around the small town, looking at all the shops and amusements.
The next town over is Pigeon Forge, and driving down the main parkway is like Las Vegas in a slightly alternate universe. One person called it the Redneck Riviera!
We spent two days at Dollywood theme park, named after its founder, famous country singer Dolly Parton. We arrived after 3pm the first day, so they gave us the second day free!
In addition to roller coaster rides, artisan shops and restaurants, we found zip lines! Mo and I put on harness, attached to a pulley, and zipped over roller coasters, trees and rivers throughout Dollywood park. It was a lot of fun!
We also went to Dolly Parton's other attraction: Stampede. This was a dinner show with horses. It was similar to the Excalibur show we saw in Las Vegas last year during the week of Edge 2013 Conference.
On our way from Gatlinburg, we stopped into Knoxville to have lunch with clients. We had a choice to make, we could either drive up into Kentucky and visit the distilleries in the Bourbon trail, or drive straight to Nashville and spend more time there. We opted for Nashville, saving the Bourbon trail for a future trip.
Our final stop was Nashville, known as Music City. Our hotel was on Broadway, walking distance between Vanderbilt University and the [honky-tonks] downtown.
We had purchased advanced tickets for the [Grand Ole Opry]. This is not your typical concert. Instead, you have no idea who will play until just a few days before. The three hour show had about a dozen different musical acts, some famous, some new to the country music scene.
We went to the Johnny Cash Museum. People with ticket stubs from the Grand Ole Opry get in for a discount!
Searching [TripAdvisor] for things to do in Nashville, I found [The Escape Game]. You pay them money to lock you up in a room with a bunch of strangers, and then collectively as a team you need to figure out how to escape by solving puzzles and clues.
Each room has different themes. First, we tried the "Underground Playground". You know that TV show [Are you Smarter than a Fifth Grader?] Well, the majority of our so-called team were not in this case, and after 60 minutes the referee told us we had failed and unlocked the door.
We had so much fun that we came back two days later to try a different room. This time we tried "The Heist" which is all about art theft. The strangers we were teamed up with were very motivated to get out of the room in time, and we succeeded, getting out in just 54 minutes!
Mo and I had a great time, but are glad to be back home!
Well, it's Tuesday again, and you know what that means? IBM Announcements!
Back in 2007, my blog post [Double Happy Wedding] compared IBM's acquisition for a company that produced data migration software to the practice in Japan of waiting until the bride is five to seven months pregnant to have a wedding. In USA, these are called "shotgun" weddings.
I was in Japan when I wrote that, and the company IBM acquired was Japanese, so the comparison stuck.
Today, IBM announces the latest versions Transparent Data Migration Facility z/OS v5 [TDMF] and z/OS Dataset Migration Facility v3 [zDMF] software products.
(Where better to commemorate this event than in Pigeon Forge, Tenessee, the capital of shotgun wedding venues! Including, and I am not making this up, a replica of the [grand staircase of the Titanic]. Yes, you can book this for a shotgun wedding, while your guests re-arrange the deck chairs. I stopped at a local McDonald's to submit this blog post.)
TDMF software allows you to migrate CKD volumes that are attached to your System z mainframe, including those that are actively being used by applications. zDMF allows you to migrate z/OS data sets, including those currently open by applications.
The migration is hardware-agnostic, supporting CKD volumes on IBM, EMC and HDS disk systems. As many clients are migrating from EMC and HDS disk systems to IBM DS8870, this is a good time to look at TDMF and zDMF to help make the process as transparent as possible.
Of course, if you are not interested in acquiring the software to do this yourself, you can hire IBM Data Mobility Services, which uses TDMF and zDMF to do it for you!
Over time, I have gotten many emails, comments and tweets related to this post. The instructions have been downloaded over 130,000 times!
The letter below was so inspiring that I felt I need to share it. (Published here with permission from the author, who goes by the screen name DaveAlex)
Thought you would like to know that I am working toward an AI Agent hopefully more advanced than "Watson Jr." although I will probably include the software behind it.
The hardware I have on hand is a System X3650M2 which I bought for $250 on eBay. It has four 2.66 GHz Xeons with 6 cores each, and 16 GB RAM. I have another 16 to install when I need it. I will shortly have 4 TB of HDD space on line, plus an addition 3 TB USB3 drive.
Ultimately, I hope to have some of the available knowledge bases on line, Freebase, CYC, etc which will handle specific information perhaps better than the Watson software by itself.
What the target (goal) that I am aiming for is a stationary version of Commander Data of Star Trek, Next generation.
I envision if having some form of self knowledge, being capable of processing graphical data, i.e., facial recognition, gesture interpretation, voice input/output, mathematical processing, with graphical output (display & hardcopy) and several additional features.
As I have studied this project, I am amazed at how much of the required software is already available. The biggest stumbling block is integrating the separate parts.
Back to Hardware. I just bought 2 Dell 2850 servers, each with dual Intel Xeons which can handle some of the tasks. If I need more processing power, I just happen to have about 10 other towers with Pentium IV or dual core processors sitting around, which can be pressed into service as needed. So far, my total cost is less than $1000 US Dollars, and my wife has not thrown me out yet. I continue to watch eBay for additional older used equipment for fractions of the original cost. My friends who follow my project keep telling me that I need to get on with the software, and add hardware as needed; they are absolutely correct, but I can't resist a bargain.
The power consumption is a potential problem, but I have a 4500 Watt solar array to use. The cooling could be a problem too, but my house sits into the side of hill, and can readily duct the air supply pass the sub-surface wall, perhaps with old Processor cooling fins glued to the wall.
I hope to get some hobby programmers involved in the project, it is a bit beyond my programming capabilities. I hope that I can live long enough to see it come to fruition; I am 78 now, and mentally in very good condition.
Wow! He is 78 years old! While others his age are playing shuffleboard at the nursing home, he is out there learning new things about the latest technology. I wish him the best of luck on this! If you would like to reach out to DaveAlex, send me a note or comment below, and I will forward them on to him.
Continuing my coverage of the [IBM Edge2014 conference], IBM's premiere conference for System Storage and related products, I attended keynote sessions on Tuesday morning, titled "Delivering on the Promise of the Future: Made with IBM".
Once again, Stephen Leonard, IBM General Manager, STG Sales, served as emcee for this general session. Yesterday, the executives focused on the "What" and "Why" for new IT initiatives. Today, they want to tackle "How" to accomplish all this.
Robert LaBlanc, IBM Senior Vice President, Software and Cloud Solutions
Robert estimates that 70 percent of enterprises will pursue dynamic hybrid clouds by 2015. Big data and analytics represents a $17 trillion USD opportunity, about 25 percent of the total IT industry.
IBM helps companies extend what they already have to what they need. In the future, people will ask "Who remembers building a private cloud stick-by-stick?" Today, IBM supports the deployment of patterns of expertise that can work on-premise IBM PureSystems. These can easily be moved or deployed off-premise to IBM SoftLayer private and public cloud offerings.
Snehal Antani, CIO of GE Capital
IT has shifted from the "back office" to the very core of business. Technology now allows GE Capital to go quickly from whiteboard to roll-out.
Not everyone is on-board. At GE Capital, people are encouraged to be like [Tigger", the adorable character from Winnie the Pooh stories, to lead efforts of innovation and collaboration. Cynics are tagged as [Eeyores], always finding a reason or excuse why plans won't work. Finally, we have "Kings and Queens", eager to be offended that any changes are needed at all.
Snehal also mentioned their "No squirrel" policy. If you have seen the movie "Up!", you know that the dog was constantly distracted by squirrels, or things he thought were squirrels. Many IT people fall the latest "shiny object" in technology.
Arvind Krishna, IBM General Manager of Development and Manufacturing
Arvind feels that "data" is the new base of new business value, in the same manner as steam, electricity and hydrocarbons had done in past centuries. In the past, most data was stored in databases, but today over 90 percent is unstructured.
In 2008, there were more "things" than people attached to the Internet, and this [Internet of Things] is expected to exceed 1 trillion items by 2015.
Have you ever wondered how the NFL plans each year's football game schedule, balancing 32 teams across five television networks? There are over 800 quadrillion possible combinations!
Borrowing the analogy from Snehal from GE Capital, the football teams are the Eeyores, and the networks are the Kings and Queens. This year, three of the games will be played in London, England. With IBM's help, the NFL was able to finish the 2014 schedule earlier than before.
Maria Winans, IBM Vice President, Social Business
Maria started with an interesting anecdote:
Lily Robinson, age 3, sent a letter asking a local grocery chain Sainsbury why their "tiger bread" was not called "giraffe bread" as it looked more like the spots on a giraffe. A manager provided a nice reply. Her parents posted it on social media, the conversation went viral, and [Sainsbury changed the name of their product] to "giraffe bread".
This is an example of "People-centric" engagement, rather than dealing with consumers in marketing segments or categories of gender or race. People will share personal data with companies they trust. Smarter companies use this data to provide the right experience at exactly the right time.
Maria explained IBM AlwaysOn Engagement Center which allows companies to track social mentions. For example, there were over 52 million social mentions of IBM Edge 2014 so far during its first two days!
The process is not just for clients, customers and consumers. It can be used to engage individual employees to drive business outcomes, or individual citizens to deliver sustainable economic growth and improve living standards.
This was a nice balance, combining IBM executives with client testimonials.
For those on Twitter, my handle is @az990tony and the hashtag for this event was #ibmedge.
Continuing my coverage of the [IBM Edge2014 conference], IBM's premiere conference for System Storage and related products, I attended EdgeTalks: Innovation That Impacts Our World that offered a series of inspiring talks styled after the famous [TED] conferences.
Surjit Chana, IBM Chief Marketing Officer (CMO) and VP of Strategy for IBM Systems and Technology Group, served as emcee to introduce the speakers.
Ron Finley, Renegade Gardener
Back in 2003, "South Central" was [renamed to South Los Angeles]. But as everyone in IT knows, merely renaming something doesn't fix any of its problems. Ron was tired of seeing empty lots filled with old mattresses, used condoms and discarded tires, and wanted to beautify his immediate surroundings by planting vegetables in his front yard.
Ron's army of volunteers, the [L.A. Green Grounds], filed a petition. As of October 2013, it is now legal to grow food on your parkway in Los Angeles.
Ron explained that South Los Angeles is a [food desert], where it is nearly impossible to get healthy, organic food. He is concerned the "drive-thrus" of fast food restaurants kill more of his neighbors than [drive-by] shootings.
Ron has discovered this problem is not limited to Los Angeles. The American food system is designed to fill you with processed food and chemicals, made worse by a health care system happy to cut you open or prescribe you more chemicals and drugs. Everywhere processed food goes, chronic disease follows. The USA exports obesity to the rest of the world.
"To change a community, and you must first change the composition of the soil." -- Ron Finley
The rise in cancer, diabetes, and childhood cardiac arrests inspired Ron to start the [Ron Finley Project] consisting of community farms, a marketplace that accepts EBT, SNAP and other government food programs, and portable "container cafes" based on standard shipping containers that could be placed near a garden to help sell the food grown locally.
John Wilbanks, Chief Commons Officer at Sage Bionetworks and Senior Fellow in Entrepreneurship for Faster Cures
We live in the age of cheap data. John prefers the term "cheap data" rather than "big data". Mapping the first human genome cost $3 Billion USD, now John can get his own genome mapped for about $1200.
John feels this cheap data changes the way we justify our opinions. From baseball scouts to the analytics demonstrated in the movie [Moneyball]. President Barack Obama used social media to help win elections. And cheap data is coming to health and medicine.
John gave an interesting example. A grad student wanted to study alcoholism among undergraduate students. The traditional method would have been to gather privacy permission slips from volunteers. Instead, he "friended" 4,000 undergraduates, and looked on social media containing the [distinctive color of red beer cups] for photos taken on Monday through Wednesday, indicative of a drinking problem. This innovative approach allowed the grad student to complete his research in less than six weeks.
Cheap data doesn't mean we have wisdom. John explained the wrong way of doing things. There are several machine-learning apps for smartphones to check for melanoma. Take a photo of your suspected mole, and the app will determine if it detects skin cancer, and recommend a biopsy. Incentives to sell apps, and to perform biopsies, result in 90 percent false positive rates. There is no financial incentive to improve accuracy.
Sharing is the innovation that converts cheap data into wisdom. Get the world's smartest people to compete to create wisdom. Collaborating with IBM on Dialogue for Reverse Engineering Assessments and Methods [DREAM] platform, a competition for modeling breast cancer was launched. Requiring all participants to share their code in real-time allowed the accuracy of the model to jump three orders of magnitude in just nine days. Over 60 teams participated. The winning team was awarded an article and cover of [Science Translational Medicine] magazine.
John feels that there are very few genius [data scientists] in the world, and they are isolated, hideously overpaid, managing hedge funds or search engines, but would probably rather be looking for cures for cancer.
Progress is not made if every company only has its own people looking at its own data. John wants data to shared amongst the world's scientists to create wisdom. However collaboration flies in the face of the competition that all the reward systems are based on in health care.
As an experiment, John wanted to make his own genome public. However, that requires "informed consent" for others to use his private health information, and it took him six months of legal and ethical rules to develop a system for him to provide this consent for public use.
In much the same way that gardens and fields were the first [commons] shared by farmers, John feels we need to cultivate the public domain, the "digital commons". This can truly transform medicine and health care.
Peter Singer, Technology Expert and Best-selling Author
The first web page appeared in 1991, and now there are over 30 trillion pages. Over 98 percent of military communications occur over civilian internet communications. The [Internet of Things] adds everything from smart cars to medical devices into the equation.
But along with all the benefits the web has brought society, there are also risks. Every second, nine new pieces of malware are discovered. An astounding 97 percent of Fortune 500 have admitted to being hacked. Over 100 governments have established a cybermilitary force.
(Instead of Powerpoint slides, Peter had a slideshow of his personal collection of the world's best and worst cybersecurity art. Studies show that audiences remember 60 percent more if they are looking at pictures when they hear a speaker.)
While IT folks are good at dealing with both hardware and software, they traditionally don't do well with "wetware", the human side of things. Essential cybersecurity terms and concepts are often misunderstood.
Business leaders over-react to some threats, but completely ignore others. Consider that 70 percent of cybersecurity decisions at companies are made by executives who have no training in cybersecurity. No single MBA program offers cybersecurity courses.
There is a shortage of talent to deal with cybersecurity. Hiring managers are only satisfied with 40 percent of the employees they hire in this Cybersecurity space.
Incentives help explain why some industries like financial services do security well, while others like health care do poorly.
In an effort to find which employees do not take cybersecurity seriously enough, Companies have resorted to sending [phishing] emails to their own employees. Those that click are caught, and must attend mandatory training, or are subject to dismissal. Unfortunately, senior executives are twice as likely to click on phishing emails than the general workforce.
Peter recommends companies focus on resilience. You can never build high enough walls to eliminate threats. Instead, focus on bouncing back after attacks, similar to the anti-bodies in the human body deal with illness.
Ben Franklin said that an ounce of prevention is worth a pound of cure. Peter cited a studied that found proper cyberhygiene would have prevented 94 percent of attacks. The most successful foreign military attack on the U.S. military happened when a soldier saw a memory stick in a parking lot, and was curious enough to connect it to the secure military network to see what it contained.
We need to build an ethic. We teach our kids to cover your mouth when you cough. This does not protect your child in any way, but is an ethic to avoid spreading disease. We need to teach the same ethics related to cybersecurity.
All three were excellent talks focused on innovation. Ron Finley used gardening in otherwise empty urban spaces to help grow people as well as food. John Wilbanks used innovation to help bring the smartest minds to determine models for identifying cancer from genomes. Peter Singer marveled at the innovation of the Internet, and how proper cyberhygiene is needed to keep it secure.
These talks were recorded and available on this [98-minute YouTube video]. For those on Twitter, my handle is @az990tony and the hashtag for this session was #ibmedgetalks.
Continuing my coverage of the [IBM Edge2014 conference], IBM's premiere conference for System Storage and related products, here are my notes from the afternoon of Day 1 at the general keynote sessions.
Stephen Leonard, IBM General Manager, STG Sales, served as emcee for the general session.
Tom Rosamilia, IBM Senior Vice President, STG and ISC
Tom (my fifth-line manager, BTW) started off with a joke: "All this talk about Cloud, but it has to run on hardware somewhere!"
Tom insists it is imperative for clients to build an infrastructure that enables business growth. However, less than 10 percent of clients are ready for Cloud, Analytics, Mobile or Social (CAMS) initiatives. Clients need to embrace these new workloads, ensure right-time decision making, and integrate front-office with back-office IT systems.
Tom is also proud that IBM's Software Define Storage solutions manage over 1 [Yottabyte] of information today. That's a billion Petabytes, in case you were wondering. If all of this data was stored on 1TB disk drives, instead of a mix of disk and tape, it would take over one million city blocks to house all the data centers required.
Tom indicated that data is to the 21st century what steam was for the 18th century, electricity was for the 19th century, and hydrocarbons were for the 20th century.
Tom invited Mike Reagan, CIO of Cleveland Clinic in Abu Dhabi, to say a few words on why Infrastructure matters to his IT environment. The [Cleveland Clinic in Abu Dhabi] is a 364-bed multi-specialty facility, the first US-hospital replicated outside of North America.
Mike explained their great success partnering with IBM to develop a private cloud solution. Each patient has a bedside tablet that can be used to control the entertainment, lighting, temperature and window shades. It can also be used to Skype with family and friends. The facility is four times the floorspace of the Sands Expo that this event is being helenovo 61 CES awardsld in.
Jamie Thomas, IBM General Manager, Storage and Software Defined Systems
Jamie feels that data is all about security and economics. Storage admins must become the new [data scientists] for IT.
It is important to integrate traditional "Systems of Record" with new "Systems of Engagement" workloads. Her focus areas are Software Defined Storage, Flash technologies, and storage virtualization. Specific examples included:
Mike talked about how important Electronic Health Record [EHR] systems and advanced clinical diagnostics are to help make the right medical decisions.
Greg explained that Citi was operating at global scale in 100 countries. Citi partnered with IBM to deploy commodity compute servers, 10GbE/40GbE Ethernet networking and IBM Software Defined Storage to achieve Cloud economics and Cloud scale. Citi can't afford for server, storage and network admins to work separately.
Rather than contesting [Hewlett-Packard CEO Meg Whitman's FUD about this deal], Adalio took the high road, and focused on IBM's success in the x86 server space. New offerings include the X6 architecture, including PureSystems and the NextScale dense computing platform.
Adalio invited Christian Teismann, Lenovo, on stage. Christian re-iterated that IBM and Lenovo are both committed to a smooth transition, continuing IBM's roadmap for the x86 server platform, and full consideration for the x86 servers and related storage, software, service and maintenance.
IBM has had a strong relationship with Lenovo already with the acquisition of IBM's PC division, and now this deal brings together Chinese supply chain efficiency with Western ideals and design principles. Lenovo has about 46,000 employees, nearly 4,000 R&D engineers, and will acquire an additional 7,500 IBMers when the deal completes.
Adalio then invited two clients to join him on stage: Ron Grabyan, Manager of Data Warehousing Services at [Southern California Edison], and Rohit Lal, IT Direction of Coca-Cola.
Ron indicated that actionable insights must be fast for productivity. He mentioned the funny [MetLife television commercial featuring Charlie Brown and Lucy] declaring that term-life insurance should cost only "five cents" per month. In the same manner, end users often request that response times should be short. IBM was able to get response times from 40 seconds down to "5 seconds" by helping Ron deploy SAP HANA. Another process that took 53 minutes was down to 1 minute 20 seconds.
Rohit talked about their exciting new "Coke One North America" (CONA) project. This will provide consolidated IT services for 6 different Coca-Cola bottlers in North America. With $46 Billion USD in revenue serving 1.8 billion servings of beverage per day, the use of Analytics, SAP HANA and private cloud were critical to their business.
The industry recognizes Lenovo as a major x86 player, having had 20 quarters of growth outpacing the market. Lenovo has [won 61 CES 2014 awards], more than the other top five x86 vendors combined. IBM x86 servers are ideal for Enterprise solutions, Cloud, HPC, embedded designs, and IT infrastructure deployments. IBM is #1 in x86 server customer satisfaction, #1 in x86 server up-time, and boasts the #1 fastest x86-based supercomputer. IBM and Lenovo want to take this to the next level: #1 leadership in every x86 category.
For those on Twitter, my handle is @az990tony and the hashtag for this event is #IBMEdge.
Continuing my coverage of the [IBM Edge2014 conference], IBM's premiere conference for System Storage and related products, here are my notes from the morning of Day 1.
IBM Storage Trends and Directions
Clod Barrera, IBM Chief Technical Strategist for IBM System Storage, and Axel Koester, IBM Chief Technologist and Executive IT Specialist for IBM System Storage, co-presented the first session of the conference.
Nearly all storage users are struggling with the combined effects of significant capacity growth, data as both an asset and potential liability, and the lack of staff and expertise to exploit new technology.
In addition to [Systems of Record], representing the traditional workloads of databases and on-line transaction processing (OLTP), we are now seeing [Systems of Engagement], which represent new workloads such a mobile apps, social business, and big data analytics.
We are now at a tipping for Flash. IBM FlashSystem can perform I/O in about 100 microseconds, which is roughly 10x faster than solid state drives (SSD), and 50x faster than spinning disk. For those clients who value performance, this can easily justify its use.
Take for example an IBM Power system running DB2 PureScale application with 43,000 transactions per second, including 13,000 updates per second, that result in 1.3 million IOPS to the back-end storage. This can be accomplished with either (a) all-disk 5,000 spinning disk spindles, (b) hybrid 2,500 spinning disk spindles combined with 128 solid state drives (SSD), or (c) IBM FlashSystem.
The comparisons are astounding. The IBM FlashSystem solution is 11x less expensive then the hybrid system, and 14x less expensive than the all-disk solution. The solution also uses 26x less energy, and 80x less space in the data center.
Clod also feels that Software Defined Storage has come of age. IBM has three offerings in this area. The first, code-named Elastic Storage, represents IBM's General Parallel File System (GPFS) and GPFS-based products like SONAS and Storwize V7000 Unified. The second is the IBM SmartCloud Virtual Storage Center and Storwize family of storage hypervisors. The third is IBM XIV Storage System.
Software Defined Storage can be used in private, hybrid and public clouds. In 2013, only 22 percent of storage was Cloud, but this is expected to grow to 50 percent by 2017.
IBM will support a range of Software Defined Environments, from the highly proprietary VMware, to the open source OpenStack foundation. Where applicable, IBM will provided added value above and beyond the basic OpenStack infrastructure.
Axel Koester presented storage futures. He works closely with IBM Research and described some of the projects they are working on:
120PB file system solution that involved a grid of IBM POWER 775 servers. Instead of traditional RAID, the system used GPFS Native Raid, which offers an 8+3 Reed Solomon protection scheme.
Multi-cloud storage that allows you to access storage from multiple public providers without having the bottleneck of a single master scheduler.
Phase Change RAM (PCRAM) which does not rely on capturing an electrical charge. This will be 12x faster than PCIe Flash, and 275x faster than consumer SSD.
Liquid state storage. Rather than solid state, metal is kept in its liquid state to store binary information.
Finally, he mentioned IBM Research's success at storing a single bit of information in just 12 atoms. To do this, the folks at Almaden Research Center had to manually move the atoms into place using the needle of a scanning tunneling microscope [STM] to nudge each atom into position.
Axel gave a great example of scale. An atom compared to a tennis ball is like a tennis ball compared to the entire planet Earth. If an atom was the size of a tennis ball, the point of the STM needle would be the size of Mount Everest, but upside down.
IBM's Smarter Storage Strategy
In previous years, my session on Storage Strategy was scheduled on Wednesday or Thursday, and attendees would comment "Why wasn't this sooner in the week? Everything makes more sense now!"
This time, I was featured immediately after Clod and Axel's keynote session, resulting in hundreds of attendees in a large standing-room-only ballroom. The session was repeated Thursday morning for those who were turned away.
IBM's storage strategy has three main themes.
First, IBM is focused on data-intensive solutions such as big data analytics. This means storage needs to be efficient to manage the growth in a cost-effective manner. IBM offers real-time compression and data deduplication to be capacity-efficient, Flash, Nearline drives and tape to be energy-efficient, and extremely easy-to-use graphical user interfaces and automation to be labor-efficient.
Second, IBM wants to optimize business critical workloads. IBM wants to eliminate the manual effort needed to balance between performance versus cost. IBM Easy Tier, I/O priority manager, and FlashSystem solutions are just a few examples.
And third, IBM wants to help you start quickly, and add value, by deploying private, public and dynamic hybrid cloud environments. IBM is not limiting its solutions to just VMware, but rather supporting other server hypervisors including KVM, Hyper-V, PowerVM and z/VM. IBM is a platinum sponsor for OpenStack foundation, and IBM storage systems support Cinder interfaces.
For those on Twitter, my handle is @az990tony and the hashtag for this event is #IBMEdge.
When IBM designed the DS8870, it changed the bulk power supplies and batteries used in the previous DS8800 model to highly energy-efficient [DC-UPS]. In addition to reducing the overall energy consumption of the DS8870, it also gave the engineers space above the units to put 4U of standard 19-inch rack equipment.
The High Performance Flash Enclosure provides an ultra-dense and ultra-high-performance option. Each HPFE can delivers up to 250,000 IOPS and up to 3.4 GB/s bandwidth.
Up to thirty 387 GB Enterprise Multi-Level Cell (eMLC) flash cards provide up to 11.6 TB of raw capacity, about 9.2 TB usable, in only 1U of 19-inch rack space. A pair of very powerful integrated SAS RAID engines manage RAID-5 across the flash cards. The HPFE attaches directly to GX++ slots in the two DS8870 POWER7+ controllers, rather than using the Device Adapter (DA) loops.
You can have up to four of these HPFE in the "A" frame of your DS8870. Each HPFE can have either 16 or 30 flash cards. For 16 cards, you would have two spare plus two 6+P RAID-5 ranks. For 30 cards, you would add another two 6+P RAID-5 ranks.
Easy Tier Enhancements
Easy Tier is IBM's market-leading sub-volume automated tiering inside the DS8870 disk system. There were several enhancements in this announcement.
The first enhancement is to "Easy Tier Server", a feature that coordinates caching of active blocks of data inside the server's own internal Flash. This had supported Power Systems with EXP30 Ultra drawers, and now expanded to support IBM [Flash Adapter 90].
The second enhancement is to the three-level (Flash,Enterprise,Nearline) tiering algorithm. Inside the DS8870, the new HPFE flash cards will be part of the "Flash Tier" along with solid state drives (SSD) attached to the DA loops. Internal inter-tier load-balancing will take into account the faster nature of the flash cards in the HPFE, and move the busiest blocks accordingly. We we refer to this as "micro-tiering" within the Flash Tier.
Broader Solid State Drive options
Not everybody likes the 400GB solid state drives IBM offered for the DA loops, so IBM is now offering a smaller 200GB and a larger 800GB options as well.
Enhanced Concurrent Code Load
The new DS8870 R7.3 firmware release drastically cuts the activation time of concurrent code load in half.
Nobody likes warmstarts either. These are a necessary evil for some error conditions, but the clever engineers upstairs have figured out ways to reduce the number of warmstarts and eliminate the need to perform a warmstart after certain events to prevent any application impact to the attached host.
Multi-Target Remote Mirror
By now you know that IBM has the market-leading remote mirroring services for high-end disk systems, using less bandwidth and maintaining better concurrency than high-end systems from other vendors.
The DS8870 R7.2.7 firmware release can now support multi-target remote mirror. In previous releases, if you wanted three-site disaster recovery, you relied on Metro/Global Mirror, where site "A" had a Metro Mirror to a bunker site "B", and then site "B" had a Global Mirror to site "C". Not everybody liked this.
Some clients have asked for a "star" configuration, where "A"-to-"B" and "A"-to-"C" are independent of each other. A SCORE request is available for the following configurations:
Two Metro Mirror
One Metro Mirror and one Global Copy
Two Global Copy
While Metro Mirror can support up to 300km distance, and Global Copy can go any distance around the planet, there is no reason why you can't have one or both copies in the same building, or on campus nearby, for use with HyperSwap.
OpenStack Cinder interface support
Last but not least, the DS8870 now offers full support for OpenStack Havana and Icehouse releases. Support is provided through the OpenStack Cinder driver currently available for download. IBM is a platinum sponsor of the OpenStack foundation.
International Technology Group [ITG] has just published a series of papers about IBM SmartCloud Virtual Storage Center (VSC) and SAN Volume Controller/Storwize storage hypervisor virtualization technology detailing the cost benefit advantages over EMC and VMware.
IBM delivers up to 72% lower storage TCO than EMC storage virtualization and management solutions in large enterprises ... and up to 35% lower storage TCO than VMware tools in mid-sized environments
Also, you can watch an interview with the study's author, International Technology Group Managing Director, Brian Jeffery, live from next week's IBM Edge Conference in Las Vegas. Brian will be interviewed on [TheCUBE by Wikibon] on Monday afternoon. Watch it live on May 19!
I will be at Edge next week. If you plan to be there, I would be glad to discuss these ITG findings with you and your clients in person.
Jamie Thomas, IBM General Manager of Storage and Software Defined Environments
Jamie announced [IBM Elastic Storage], a new offering that is available as a software defined storage solution, based on IBM's General Parallel File System (GPFS) technology already deployed at 45,000 installations.
IBM Elastic Storage provides a global name view across data center locations. It can manage up to a Yotabyte of information, combining Flash, disk and tape resources. It supports OpenStack interfaces, Hadoop and standard POSIX file system conventions.
IBM Elastic Storage provides automated tiering to move data from different storage media types. Infrequently accessed files can be migrated to tape and automatically recalled back to disk when required. Unlike traditional storage, it allows you to smoothly grow or shrink your storage infrastructure without application disruption or outages.
IBM Elastic Storage software can run on a cluster of x86 and/or POWER-based servers, and can be used with internal disk, commodity storage, or advanced storage systems from IBM or other vendors.
IBM partnered with various clients in different industries in a special beta program. Jamie led a client panel to discuss their experiences with IBM Elastic Storage:
Alan Malek, Director of IT, Cypress Semiconductor.
"Total cycle time is key". Over the past 31 years, they bought whatever file storage was available. Now, with IBM Elastic Storage, the performance was very consistent for their engineering workloads with full load balancing.
Russell Schneider, Principal Storage Consultant, Jeskell.
Russell's company works with a lot of federal agencies, "Big Data has become Bigger Data". For example, research on Global Warming and Climate Change requires a large amount of storage across agencies.
In another example, when the tsunami hit Japan a few years ago, an agency here in the USA realized they had 14PB of data stored as a single copy in a data center at sea level less than a mile from the coast. They realized they needed to have a secondary copy, and an option to cache to a third location depending on regional disasters.
Matthew Richards, Products, OwnCloud.
For those not familiar with OwnCloud, it provides a Dropbox-like file sharing service, but in the Enterprise, with on-premise storage. It has been fully tested and certified with IBM Elastic Storage to provide a secure file sharing platform.
With IBM Elastic Storage, they were able to scale linearly up to 20,000 users, and are now testing 100,000 users. The need to have intelligent access to files at scale is what Matthew likes about IBM Elastic Storage.
Dr. Michael Factor, IBM Distinguished Engineer at IBM Research
Michael started out explaining there are three areas for storage: block, file and object. The fastest growing type of data is unstructured fixed content with associated metadata. This is ideal for object storage. Michael has been working with OpenStack Swift, an open source interface defined for object storage. He defined "storlets" as follows:
Storlets extend an object store by moving computation to the data -- filtering, transforming, analyzing -- instead of bringing data to the computation.
Storlets have been deployed on a variety of European Union research projects. For example, in partnership with Phillips, a pathology storlet can count the number of cancer cells in an image. By bringing the computation to the data, it eliminates having to transfer large amounts of data over the network.
Storlets can run on-premise and on IBM's SoftLayer IaaS cloud offering.
Bruce Hillsberg, IBM Director of Storage Systems at IBM Research
Bruce led another panel discussion, this time of IBM storage experts:
Vincent Hsu, IBM Fellow and CTO of Storage.
The problem is the isolation of data into "storage silos". Isolation causes problems in managing large amounts of data at scale, and costs more as storage is not fully utilized. IBM Elastic Storage brings everything together, eliminating storage silos.
Michael explained how IBM works with clients all over the world to ensure that storage solutions meet client requirements. For example, storlets can be used to use rich metadata to manage photographs, and display them based on GPS satellite location, or other content that makes it easier to manage these images.
IBM Elastic Storage will support OpenStack Cinder and Swift interfaces. IBM is a platinum sponsor of OpenStack foundation, and is now its second most prolific contributor, with hundreds of full-time employees working on this.
Tom Clark, IBM Distinguished Engineer, Chief Architect, Storage Software, Cloud & Smarter Infrastructure.
Storage Management is a critical piece of Software Defined Storage. This is done in three ways:
The use of analytics to optimize the deployment of storage, based on workload requirements. Storage admins set policies, and then IBM Elastic Storage analytics gather metrics and then optimize data placement and movement based on these policies. IBM Elastic Storage has 70 percent lower TCO that competitive offerings.
The focus on backup services. Backups are not just for data protection, but rather can be used to duplicate or replicate data for testing, for training, and for other purposes. IBM Elastic Storage is fully supported by IBM Tivoli Storage Manager.
Being able to support Hybrid Cloud environments, where some data can be on-premise, and other data off-premise. Storage Management challenges will need to deal with this possibility. IBM Elastic Storage is well positioned for this.
Carl Kraenzel, IBM Distinguished Engineer, Director of Watson Cloud Technology and Support.
Watson is ground-breaking technology, and IBM Elastic Storage technology was at the heart of the Watson that was first introduced in 2011.
To consider IBM Elastic Storage based on lower-cost and higher-scalability is not the full picture. Rather, this is an important platform for Cognitive Computing, which we are just at the tip of the iceberg in exploring. IT systems need to be aware of the context of what we are doing.
While the Grand Challenge demonstration on Jeopardy! was exciting, it is time we stop playing games and apply IBM Elastic Storage to business, to help with health care and medical research, and other problems in society. IBM has already deployed this at Anderson Cancer Center and Memorial Sloan Kettering Cancer Center, for example.
Tom Rosamilia provided closing remarks. IBM Elastic Storage is not just for new workloads in Cloud, Analytics, Mobile and Social (CAMS) but also traditional workloads as well. IBM Elastic Storage provides "data democracy" and allows for "better rested storage administrators" that make fewer mistakes.
Tom opened the floor for questions from the audience:
Q1. Data integrity, not just security but also quality? IBM Elastic Storage has end-to-end data integrity checking built-in.
Q2. How does IT transition from full control to auto-pilot? IBM allows you to tap into existing storage. This is not rip-and-replace. With storage virtualization, IBM hides the complexity that normally requires full control over specific assets.
Q3. Storage admins would rather have a root canal without Novocaine than move their data. What is IBM doing to offer automation to help storage admins move to this new infrastructure? IBM storage virtualization breaks that hard link between applications and specific storage devices. IBM Elastic Storage eliminates application downtime previously associated with data movement.
Tom Rosamilia assured the audience that IBM is fully committed to its storage portfolio. IBM Elastic Storage is not just about the profoundness of what IBM announced today, but also where IBM is investing in the future of storage.
Marking the occasion, here is an important letter from our Vice President, Laura Guio:
May 6, 2014
To Whom it may concern
Subject: ProtecTIER Development Update:
This year marks the sixth anniversary of IBM's acquisition of Diligent Technology. Over the past six years IBM has emerged as a leader in enterprise class data deduplication. Our highly scalable, dual node hardware redundancy and gateway design are unique characteristics in the industry. IBM fundamentally believes in the importance of cost saving data deduplication technology and continues to enhance our solution, improve value and increase investment protection for our installed base.
First, it is important to note what IBM has done most recently. IBM is among the first to integrate flash technology along with deduplication to boost performance and lower cost. Integration of the IBM FlashSystem 840 for metadata was completed the day the system was publically announced. The speed of technology integration is a result of our flexible gateway design which simplifies technology adoption. It also is enabled by our global development team providing a 24x7 system design, product test and integration environment.
Secondly, IBM has recently released ProtecTIER Mainframe Edition which enables the same enterprise class deduplication capability now for IBM System z. Another distinctive feature of ProtecTIER is its ability to sustain high throughput for both read and write operations. Most deduplication methodologies have an inherent read performance penalty. Since mainframe tape operations are much more read intensive than distributed systems, we were one of the first to market with a practical deduplication offering for all mainframe tape applications.
That's just what we've done getting out of the starting blocks in 2014. Our development team continues to enhance ProtecTIER. We're also working on refreshing the entire ProtecTIER product line with new model enhancements. A new gateway design is underway which will improve performance of the existing DD5. We expect this to be available as an upgrade, providing investment protection for existing ProtecTIER clients. The SM2 product family is also being redesigned to extend its capacity range. Along with hardware changes, we will widen the disk support matrix offering enhanced flexibility and new levels of price performance.*1*
We expect 2014 to be a busy year for IBM deduplication. We have development facilities around the world in Europe, North America, Central America and Asia, working on ProtecTIER. IBM continues to market, sell, and support ProtecTIER as our strategic offering for cost-reducing deduplication technology. Any suggestion that ProtecTIER is fading away is wishful thinking by our competitors. We are working to expand our markets as we have demonstrated by our recent introduction of ProtecTIER into the mainframe. Furthermore, we are looking to expand the use cases for ProtecTIER, which can now be attached as a NAS file system, to other areas besides pure backup. We're excited about what we are delivering today and where we can provide leadership by leveraging deduplication for customer storage environments.
Vice President, Business Line Executive Storage Systems
IBM Systems and Technology Group
*1*: IBM's statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBM's sole discretion. The development, release, and timing of any future features or functionality described for our products remains at our sole discretion.
To learn more about IBM ProtecTIER, consider attending the [IBM Edge conference], May 19-23, 2014 at the Venetian Hotel in Las Vegas. I'll be there to explain Data Deplication technology as part of my "Data Footprint Reduction" presentation!
Well, it's Tuesday again, and you know what that means? IBM announcements!
Today's announcements are all about the Storwize family, IBM's market-leading Software Defined Storage offerings. Having sold over 55,000 systems, and managing over 1.6 Exabytes of data, IBM continues to be the #1 leader in storage virtualization solutions. The Storwize family consists of the SAN Volume Controller (SVC), Storwize V7000, Storwize V7000 Unified, Flex System V7000, Storwize V5000, Storwize V3700 and V3500.
SAN Volume Controller 2145-DH8
The new 2145-DH8 model is a complete repackaging of this popular storage system. The previous model, the 2145-CG8, was 1U-high x86 server per node, and each node required a separate 1U-high UPS to provide battery protection for its cache. Nobody liked this. The new 2145-DH8 instead is a 2U-high node with two hot-swappable batteries, eliminating the need for UPS altogether. Thus, an SVC node-pair using the 2145-DH8 models takes up the same 4U space, but with fewer cables. The SVC can now also support standard office 110/240 voltage sources.
The new model sports an 8-core processor with 32GB RAM. Since these are 2-socket servers, IBM offers that option to add a second 8-core processor and additional 32GB RAM to help boost Real-time Compression. Each node can have optionally one or two hardware-assisted compression cards which use the Intel QuickAssist chip to boost compression performance.
While the Real-time Compression was in fact, real-time, performed in-line to the read/write I/O process, at latency comparable to uncompressed data for applications, the compression process on older models was entirely software-based, consuming some of the CPU resources, which lowered the maximum IOPS of the solution. With the added cores, added RAM, and hardware-assisted compression chips, IBM resolves that concern. In fact, the new 2145-DH8 with compression can provide more IOPS than an older 2145-CG8 without compression.
The previous model 2145-CG8 allowed you to put up to 4 small SSD drives in the node itself, which were treated the same as externally Flash drives for purposes of having a high-speed storage pool for select volumes, or automated sub-LUN tiering with Easy Tier. The new model 2145-DH8 allows you to attach up to 48 Solid State Drives (SSD) via 12Gb SAS cables. These are housed in the new 2U-high 24F enclosures that can offer up to 38.4 TB of Flash per SVC I/O group.
IBM also re-designed the host/device ports to use Hardware Interface Card (HIC) slots. In the 2145-CG8, you had four FCP ports, two 1GbE Ethernet ports, with options to add two 10GbE Ethernet ports or four additional FCP ports. If you had mostly an FCoE or iSCSI environment, you didn't need the FCP, and if you were mostly a FCP Storage Area Network (SAN) environment, then most of the Ethernet ports went unused. To solve this, the 2145-DH8 can allow you to have up to six HIC cards that are either FCP, Ethernet, or SAS. There are three 1GbE fixed Ethernet ports which can be used for iSCSI and administration.
If you have SVC today, you can upgrade non-disruptively by either swapping out your current SVC engines with the new 2145-DH8 engines, or you can add the new 2145-DH8 engines to your existing SVC cluster. Either way, there is no outage to your applications!
This is the next generation of the popular Storwize V7000. The previous generation had a 4-core processor and 8GB RAM per canister. The new model has an 8-core processor with 32GB of RAM per canister, with the option to double these to boost Real-time compression. There are two canisters per control enclosure, which gives you 64GB to 128GB of RAM per Storwize V7000 I/O group.
The new Storwize V7000 comes with one hardware-assisted compression chip on the mother board of each canister, with the option to add a second chip per canister.
Each canister offers three HIC slots, which can be used for the additional hardware-assist compression chip, FCP or Ethernet ports.
To accommodate these HIC slots, new canisters were needed. Instead of the flat wide style top and bottom, we now have taller, thinner canisters that sit side to side. This side-to-side design is similar to our existing Storwize V5000 and V3700 models.
The previous model could support up to 9 expansion enclosures per control enclosure. The Storwize V7000 can have up to 24 drives in its control enclosure, and now attach up to 20 expansion enclosures, which allows up to 504 drives per control enclosure, and up to a maximum of 1,056 drives per Storwize cluster.
If you have previous models of Storwize V7000, you can add the new Storwize V7000 into the same cluster, or virtualize the previous storage for migration purposes.
The new software applies new capabilities to both new generation hardware as well as the older models, so people with existing gear can benefit as well.
In prior releases, the sub-LUN automated tiering was limited to two levels: Flash and HDD. This lumped all 15K, 10K and 7200 RPM drives into a common HDD category. In the new v7.3.0 code, you can now have three levels: Flash, Enterprise HDD, and Nearline HDD, or two HDD levels: Enterprise and Nearline. The Enterprise level combines 15K and 10K RPM drives, similar to what is done on the IBM System Storage DS8000 disk systems.
The new code is also able balance your storage pools, and can be used with uniform or mixed storage pools to eliminate performance hot spots.
The new code has been enhanced to detect the hardware-assisted compression chip on the new SVC and Storwize V7000 models, and use those if available.
For the Storwize V3700 and V5000 models, the new code allows up to nine expansion enclosures per control enclosure. In the previous models, the V3700 allowed only four expansions, and the V6000 only six expansions per control enclosure. The V3700 can now support up to 240 drives, and the V5000 can support up to 480 drives.
IBM Storwize V7000 Unified File Module software v1.5
For Storwize V7000 Unified clients, there is new software for the File Modules that provide NFS, CIFS, FTP, HTTPS and SCP protocol capability. The new v1.5 code now adds NFS v4 and SMB 2.1 levels of support. Most NFS users are still on NFSv3, but about 20 percent of NFS users are using NFS v4 which offers stateful access. The SMB 2.1 for CIFS was introduced by Microsoft in Windows 7 and Windows Server 2008 R2.
Deterministic ID mapping allows you to map Windows userids to UNIX/Linux group and owner id numbers. In the past, the problem is that this mapping is different on each machine, so people often had to stand up a Windows System for Unix Services (SFU) server to provide consistent ID mapping. Now, with v1.5 code, you will no longer have to do this. The deterministic ID mapping will can now replicate the mapping to each machine without an SFU server.
Active Cloud Engine allows up to ten Storwize V7000 Unified to be connected across distance to form a single global name space. WAN caching, however, was restricted to a single site having write capabilities, while the others were read-only. In v1.5 release, IBM now supports multiple independent writers at different locations on the same fileset.
Security enhancements include multi-tenancy, configurable password policies, session policies, and hardened boot and SSH configurations. With NFS v3/v4, you can now use [Kerberos] for security.
Finally, I am please to see that we now have Cinder support for files on the Storwize V7000 Unified on the OpenStack Havana release that just came out last month. The OpenStack Cinder interface can assign LUNs to virtual machines, but the new Havana release allows NAS systems to dole out files that act as LUNs, such as OVA or VMDK files. The advantage is that these files can managed by Active Cloud Engine, cached locally across global name space, have policies place them on appropriate storage tiers, and inactive Virtual Machine images can be migrated to less expensive disk or tape.
Before dinner, I was able to catch up with my colleagues from across the pond. Here I am pictured with Ola Surowiec, a Power Systems sales specialist from Scotland.
The dinner was set up as self-service buffet style, with choices of European, Asian, and Middle Eastern cuisine. This is largely the heritage of the Ottoman empire to provide a fusion of flavors from its neighbors.
The city of Istanbul is considered the border between Europe and Asia, with one side of the city on the "European" side, and the other side of the Bosphorus strait being the "Asian" side.
With a population of over 14 million, Istanbul forms one of the largest urban agglomerations in Europe, second largest in the Middle East and the third-largest city in the world by population within its city limits.
The entertainment started with two [belly dancers], one male and one female. (IBM is an equal opportunity employer!) For those not familiar with this particular form of performance art, it is improvised folk dances based on torso articulation and abdominal movements.
I have seen dancers before in Egypt, the country that most people associate with the origin of belly dancing, but the Turkish version is considered more energetic and athletic. Certainly both of our dancers were quite flexible.
This was followed by a live cover band that played the latest English-language hits. Several Americans at the table asked "Wait? We come all the way to Turkey and the local band sings the songs in English?"
In the corner, attendees were invited to dress up as their favorite sultan to take photograph. Here for example, are some of the members of the STU event team. Mo McCullough, Don Meyer, Marlin Maddy, Glenn Anderson and Alex Abderrazag pose with two lovely local ladies in full costume.
The word "sultan" derives from the Arabic word meaning "strength", "authority" or "power". Sultans ruled the Turkish empire from 1299 to 1922.
The [Topkapi palace], where I visited earlier in the week, contains clothing on display of the sultans and princes from the second half of the 15th century to the early 20th century.
New Generation Storage Tiering: Less Management, Lower Investment and Increased Performance
This was not just an update to my session last year in Brussels, Belgium. Rather, I decided to start over and focus I/O density as the metric to focus my efforts, armed with real data from Intelligent Storage Tiering Analysis (ISTA) studies done at various clients. From that, I was able to talk about storage tiering on three fronts:
Storage tiering between Flash and disk. IBM FlashSystem and IBM Easy Tier on DS8000 and Storwize family for hybrid Flash-and-disk configurations.
Storage tiering between disk and tape. HSM and Information Lifecycle Management (ILM) on SONAS, Storwize V7000 Unified and LTFS-EE.
Storage tiering automation across your entire environment. ISTA studies can help identify a target mix of Tier 0, Tier 1, Tier 2 and Tier 3 storage. SmartCloud Virtual Storage Center can recommend or perform the movement of LUNs to more appropriate tiers, based on age and I/O density measurements.
Next Generation FlashSystem 840 and V840, Architecture Deep Dive
Detlef Helmbrecht, from the IBM Advanced Technical Skills team in Germany, presented this deep dive in our latest IBM FlashSystem offerings. He started with an analogy. Latency is like a single car driving down an empty highway. IOPS, on the other hand, is like a lot of cars stuck in slow traffic, with all lanes filled on the autobahn. While there are more cars transported on a full highway, the individual cars are not driving very fast. Flash versus disk has similar comparisons.
Detlef explained the differences between the previous FlashSystem 810/820 with the new 840, as well as talk about the FlashAdapter 90 now available as a PCIe card.
Finally, we talked about SAN Volume Controller combined with Flash, and the new FlashSystem V840 which combines SVC and FlashSystem 840 to have an incredibly function-rich, robust solution.
Data Footprint Reduction - Understanding IBM Storage Efficiency Options
My last session of the week! This session covered all of the various technologies for data footprint reduction, including Thin Provisioning, Space-efficient FlashCopy and snapshots, Real-time compression and data deduplication. Frankly, I wasn't expecting many people to attend the last session of the last day, but nearly 50% of the seats were filled, so I was quite pleased on the turn-out.
Fun Fact: Istanbul is considered by TripAdvisor in 2014 as the #1 most popular city to visit in Europe!
Johann Weiss, Jim Blue and I joined several other local experts to answer questions and respond to comments and suggestions attendees had about IBM System Storage products and solutions. Here is a sample:
I would like to add 1TB of Flash to our FlashSystem 810 and have the system automatically re-stripe across this new capacity non-disruptively?
How can I have XIV systems at two datacenters in an active/active configuration that would allow me to vMotion from one location to the other non-disruptively?
Put them behind the SAN Volume Controller in Stretched Cluster mode.
What about a similar active/active but for NAS?
IBM N series.
I would like HyperSwap on the SVC/Storwize family like the DS8000 offers for AIX?
When will IBM offer a multi-frame XIV?
The "Hyper-Scale" set of features lets you logically connect 144 XIV frames together and treat as a single system. There is no need to physically bolt them together, since the communication is done over standard network switches.
When will IBM devices have native FCoE support?
All IBM System Storage products work within an FCoE framework today, either with native FCoE support, or through Top-of-Rack switches splitting out the traffic between IP and FCP traditional networks. IBM Storwize and N series products support FCoE natively, and any disk behind virtualized by SAN Volume Controller or Storwize can be access via FCoE hosts because of this support.
What is FLAPE?
FLAPE is the combination of Flash and Tape. Both of these technologies are improving over 40 percent year-to-year, but disk is slowing down to 20 percent improvement. It is possible to combine Flash and tape systems, such as IBM LTFS-EE or IBM ProtecTIER TS7600 series.
Only the Storwize V7000 Unified supports file modules to add NAS capabilities, what can IBM offer us that is smaller for NAS deployments, perhaps a Storwize V5000 Unified or Storwize V3700 Unified?
Consider the IBM N3000 series.
Other storage vendors indicate that RAID-5 and RAID-6 are running out of steam, are no longer practical to protect ever growing capacities of disk. What is IBM planning in this area?
IBM XIV Storage System was one of the first to offer a distributed RAID that addresses many of the RAID-5/RAID-6 drive rebuild concerns. IBM DCS3700 and DCS3860 also have Dynamic Disk Pooling to reduce drive rebuild impact. Lastly, IBM GPFS now offers Native RAID support, used in the IBM GPFS Storage Server.
Is it true that GPFS is NFS only?
Do not confuse GPFS the file system with the various storage offerings that are based on GPFS. IBM SONAS and Storwize V7000 Unified, both based on GPFS, support CIFS, NFS, HTTPS, SCP and FTP. IBM GPFS Storage Server can be configured to access GPFS natively, or you can run NFS v3/v4 server to make those protocols available. With Microsoft [Windows Storage Server], you can provide CIFS access to any GPFS-based storage solution.
LTFS-EE sounds like an exciting alternative to IBM Tivoli Storage Manager HSM space management for moving data from disk to tape. Do you agree?
Yes, we agree. However, TSM HSM space management supports a broader set of file systems. LTFS-EE only provides disk-to-tape movement for IBM GPFS.
Why does the DS8000 implementation of Easy Tier sub-LUN automated tiering support three tiers, but SVC/Storwize only support two tiers?
The same software engineering team works on both, but develop new features for the DS8000 first, get it working, then port it over to the Storwize family. At times, there might be gaps between what is supported on the latest DS8000 version and what is available on Storwize family products.
In an SVC Stretched Cluster, I would like to have the third quorum disk connected over the IP network, rather than FCP.
Personally, I enjoy these interchanges. They are sometimes called "Birds-of-a-Feather" or BOF at some conferences, "Free-for-All" at others. At IBM conferences, they are often titled "Meet the Experts". Whatever you call it, the questions and feedback on what clients are thinking are quite useful for product planning and prioritization of future planned features.
Step Right Up! Take your presentation skills to the next level
Glenn Anderson presented this session under the guise of "Professional Development". Whether you are new to public speaking and looking for some guidance, or are an experienced A-list celebrity looking to gain a few pointers, this session covered it all.
Some of my favorites:
Presentations are not Documentation! If a presentation had all the information to stand on its own, nobody would even bother to listen to the speaker. Many new presenters have 3-4 lines for titles, and too many words in small font to ensure they cover all the details to speak on. Don't do it. My rule of thumb is that 50 percent of the information is conveyed verbally, and the other 50 percent visually from the presentation.
Simplicity is the ultimate sophistication. I couldn't agree more. I try to focus on my core message in my presetations. I am a big fan of the [KISS principle] which stands for "Keep it simple, stupid!"
VOICE - Victory over inconsistent conscious energy! There is nothing more painful than hearing a public speaker who talks to softly, too loudly, or in a monotone manner. Mix it up! If you want to capture someone's attention, whisper! Vary your volume for effect.
Presenting is like Pouring Wine. At cocktail parties, the hosts will walk around with the bottle, and refill the glasses of those who are actively drinking the wine, but leave alone those who haven't sipped a drop. Public speakers need to focus on the needs of those in the audience paying close attention, and ignore people who are asleep, paying attention to their laptops and smartphones, or otherwise distracted.
Don't memorize - Extemporize. Too often, new speakers try to memorize their entire presentation. This doesn't go well, and can end up looking like an actor on live stage forgetting his next line. Instead, focus on getting the general idea across in a more natural conversational tone.
Building Open Clouds on POWER Systems
Mandie Quartly presented the excitement of building a cloud using IBM's new Linux-only line of PowerLinux™ servers, KVM, virsh, virtio and OpenStack interfaces. Jeff Scheel was on hand to interject bits of wisdom throughout her session.
IBM is investing heavily into the Linux side of all of its servers, and the latest investments have been focused on the POWER systems.
Storage Clouds in the Big Blue Sky
Dick Vogelsang presented this session focused mostly on the "Self-service" aspect of Cloud Storage. While this sounded like it would be similar to my session from yesterday, it was actually quite different.
Vogelsang explained SmartCloud Storage Access, and compared this to how competitors are providing (or not providing) self-service provisioning of file spaces and LUNs. He gave examples based on VMware, Hyper-V, and OpenStack Foundation.
It is interesting the angle or spin that each speaker gave to each topic!
Continuing coverage of the [Systems Technical University 2014] conference, we had an early morning awards ceremony to celebrate top sellers that led big wins in Europe for FlashSystems, XIV, Power Systems, and PureSystems.
Afterwards, there were several breakout sessions on day 2.
Storage Technology Futures -- fresh from IBM research labs, tomorrow in your datacenter
Axel Koester presented several projects from IBM Research labs that have contributed to actual products, including the incredible scalability of [PERCS] that was incorporated into IBM General Parallel File System (GPFS).
Cloud Storage and Active Cloud Engine
My presentation started off explaining the taxonomy of cloud storage. There are basically four kinds of cloud storage: persistent storage, ephemeral storage, hosted storage, and reference storage. Each of these has unique access patterns and service level requirements.
IBM has three distinct cloud storage offerings, so I covered IBM XIV Storage Systems, SONAS and Storwize V7000 Unified with Active Cloud Engine, and Linear Tape File System (LTFS) Enterprise Edition (LTFS-EE).
FlashSystem competitive overview
Henrik Wilken provided an excellent presentation comparing IBM FlashSystems to the dozen or more competitors that offer all-flash or hybrid flash-and-disk combinations.
IBM Tivoli Storage Productivity Center
From 2001 to 2003, I was the chief architect for what is now called Tivoli Storage Productivity Center. It continues to be the top most requested topic for briefings at the IBM Tucson Executive Briefing Center.
I presented an overview of Tivoli Storage Productivity Center, with a brief update on what's new in TPC 5.2.1 and the SmartCloud Virtual Storage Center v5.2.1 releases.
IBM Archive Storage Solutions - Data Retention for Government Compliance and Industry Regulations
I can't believe it has been nine years since I was on the Product Development Team for the IBM DR550 Data Retention storage solution!
In this session, I explained the lessons we learned from the DR550, its successor the Information Archive, and how we now position System Storage Archive Manager (SSAM) software as their replacement. SSAM was recently certified by KPMG to meet a variety of US, European and International laws.
I presented IBM's Smarter Storage Strategy. This is focused on three key areas:
Data-intensive Solutions. Storage is needed for Big Data analytics. IBM is focused on efficiency in all dimensions: capacity efficiency with data footprint reduction techniques, energy efficiency, administrator efficiency with ease-of-use interfaces, and reduced complexity.
Business-critical workloads. Storage needs to allow business to prioritize which applications and workloads are most critical, and automate Quality of Service (QoS) for each application based on its business importance. The result is a balance between performance and cost across the spectrum of applications.
Start quickly and add value. IBM is committed to support private, hybrid and public cloud deployments. Storage needs to support not just VMware, but also Hyper-V, KVM, PowerVM and z/VM. That is why IBM is a platinum sponsor for the OpenStack foundation.
Eric Aquaronne presented an excellent session on OpenStack foundation, an open source collaboration of various companies to bring a consistent Cloud-management standard across compute, storage and network resources.
Replication for Business Continuity and Disaster Recovery
I have been involved with Business Continuity and Disaster Recovery my entire 28-year career at IBM System Storage, so when I was asked to cover BC/DR in 75 minutes, I focused just on aspects related to disk-to-disk replication.
I divided the presentation into three sections:
Business priorities. You need to prioritize which business processes are most important, and prioritize your recovery accordingly.
Technical implementation. Once priorities are set, there are seven "Business Continuity Tiers" to choose from. BC Tier 1 is the least expensive, recovering from physical tapes stored in an off-site vault. The fastest recovery is BC Tier 7, which automates the storage, server and network fail-over to a secondary site in as little as 30 minutes.
Ongoing management. Just setting up a BC/DR implementation is not enough. It needs to be monitored to ensure that it continues to provide the protection you expect. BC/DR exercises should be performed one or more times per year to ensure that everyone has the skills and procedures documented to succeed in the event of a real disaster.
Of these seven BC tiers, BC Tier 6 is focused on storage replication, such as Metro or Global mirror available on our DS8000, XIV Storage System, SONAS and SAN Volume Controller. BC Tier 7 involves system automation, such as Tivoli Distributed Disaster Recovery Manager and GDPS.
What is Big Data? Architectures and Practical Use Cases
This session was an expanded version of the one I gave in Belgium last year. Big Data is a big topic, and there are a variety of "big data" related sessions at this conference. I focused on three key areas:
The change in the role of Storage Administrator. In the past, most of the data was structured and stored in databases, managed by database administrators. However, in today's environment, over 80 percent of the data is unstructured, outside of traditional relational databases, so either the database administrators need to learn new skills, or storage administrators will need to step up and help manage this unstructured data content.
The change in the role of Business Analyst. We are no longer just looking at the financial consequences of patterns and trends. The new role of Data Scientist needs to apply statistical models, show some business acumen, and be able to "tell a story" that is supported by the data when communicating findings to Business and IT leaders.
The change in the role of Decision Maker. In the past, Decision Support Systems were available only to the top-level business executives. Now, empowered employees have access to real-time analytics that can help them make decisions and take immediate actions.
This session packed the house, with standing room only. I would like to offer a special thanks to IBM VP Bob Sutor, Stephen Brodsky, Linton Ward, and Ralph McMullen in helping me finalize my presentation.
The first official day of the [Systems Technical University 2014] conference had keynote sessions in the morning. The conference features experts from IBM Power Systems, IBM System x, IBM PureSystems, and IBM System Storage.
The keynote sessions were started with Amy Purdy, IBM Director of Technical Training Services, the group that is running this conference.
This conference is not focused on System z solutions, as many of the System z clients were in New York City for this birthday event, but it came up several times during the keynote sessions.
(FTC Disclosure: I work for IBM, and this blog post may be considered a paid, celebrity endorsement of IBM products and services. IBM has business relationship with both Intel and Amazon mentioned during the course of the keynote sessions, but I have no financial stake in either company. I was the chief architect for DFSMS, the storage management component of the z/OS mainframe operating system, and was part of the team that ported Linux to the System z mainframe.)
Nicolas Sekkaki, IBM Vice President of Systems and Technology Group in Europe, discussed IBM's commitment to client's privacy, the x86 and POWER server platforms, and a variety of mind-bogging announcements. He is focused on three trends: Big Data, Cloud, and Mobile.
IBM is focusing its hardware efforts on high-value, high-margin solutions such as System Storage, POWER Systems and System zEnterprise mainframe environments. Did you know that 65 percent of the world's business transactions are processed by either POWER systems or System zEnterprise mainframe?
IBM is also extending its continued focus on Linux and Open Source initiatives. For the System zEnterprise mainframes, 78 percent of our clients run Linux on System z. Over 290 clients have added the "zBX" option that allows them to run Windows and AIX on the mainframe as well. It is now less expensive to run workloads on System zEnterprise -- about 1 dollar per day per server -- than public cloud offerings from Amazon Web Services. Linux on POWER also has lower Total Cost of Ownership (TCO) than Linux-x86.
Nicolas also mentioned major changes for the POWER Systems, starting with the [OpenPOWER Consortium], formed by IBM, Google, Mellanox, NVIDIA and Tyan.
The move makes POWER hardware and software available to open development for the first time as well as making POWER Intellectual Property licensable to others, greatly expanding the ecosystem of innovators on the platform. The consortium will offer open-source POWER firmware, the software that controls basic chip functions. By doing this, IBM and the consortium can offer unprecedented customization in creating new styles of server hardware for a variety of computing workloads.
IBM POWER has switched from being "Big Endian" to being "Bi-Endian", allowing operating systems to choose between "Big Endian" or "Little Endian" modes. The Big Endian mode allows for Linux compatibility with the System zEnterprise mainframe, and the Little Endian mode for compatibility with Linux-x86.
Thorston Kahrmann, Intel Account Director for EMEA, presented Intel's rich history of collaboration with IBM, from technologies like BlueTooth and PCiE Generation 3, to platforms like BladeCenter and NeXtScale, to Industry Standards.
IBM had a lot of "firsts" in the x86 server area, including the first 16-processor server, the first to offer hot-swap memory, and over 100 leading performance benchmarks.
The latest Intel Xeon chip is the E7 version 2. For example, changing from DB2 v10.1 on the old E7, to running DB2 BLU columnar acceleration on the new E7 version 2, resulted in a 148 times increase in performance. A query on a 10TB database that previously took four hours was completed in under 90 seconds.
Thorston also wanted to remind the audience that nearly every System Storage product from IBM, from the high-end XIV, SAN Volume Controller, SONAS and FlashSystem V840, to midrange and entry level Storwize products, are all based on Intel's x86 processors.
Louise covered the findings from the latest 2012 CEO study, gathering insight from 1709 CEO interviews. The major focus areas for CEOs are:
Empowering employees through company-wide values
Engaging customers as individuals, rather than via demographics
Amplifying innovation with strategic and tactical partnerships
With smartphones, tablets and ubiquitous Internet access, everyone is now a technologist, so that IT is now becoming a competitive differentiator. IT projects and Business projects are no longer separate. If your IT department is seen as an expense, it will continue to get its budget cut. If, however, your IT department is part of your revenue stream, then it can be viewed as an asset.
Sadly, over 75 percent of IT projects fail, either are way over budget, delivered late, or some combination of the two. Business leaders are pushing for IT improvements, but often CIOs are too afraid to take the risks to move the business forward. Louise cited three reasons for this, which she called the three C's:
The IT and Business leaders did not full understand the context of the project.
The content of the project was not properly defined between IT and Business architects.
The collaboration between IT and Business personnel was not properly established.
Louise wrapped up her session with asking a simple question: How much is the cost of a light bulb. Some might focus on the cost of the bulb itself, while others might add the cost of maintenance, having ladders and personnel to replace them as needed, and others might include the electricity consumed. Both Business and IT leaders need to focus on Total Cost of Ownership (TCO) in their planning.
I have arrived safely to Istanbul, Turkey for the [Systems Technical University 2014] conference. The conference will feature experts from IBM Power Systems, IBM System x, IBM PureSystems, and IBM System Storage.
Here is the view from my hotel window. Up until the 19th century, this was open countryside. Around 1890, the Bomonti brothers from Switzerland set up a brewery, which was moved to this section of town in 1902, becoming the first Turkish brewery. In 1934, the brewery was nationalized and became the Istanbul Tekel Beer Factory. The Hilton Bomonti hotel where the conference is being held is named after these brothers.
Since this is my first time to Istanbul, and I did not have meetings until later in the afternoon for the conference, I decided to a bit of sightseeing.
(A special thanks to Gail Godbey of [Encounter Tours/Kaletours] who organized this entire tour of sightseeing for me on such short notice!)
The hippodrome was a stadium for horse and chariot racing, but now is just a square with a few obelisks. This one is the Thutmosis Obelisk from Egypt. The word hippodrome comes from the Greek hippos, meaning horse, and dromos, meaning path or way. Hippodromes were common features of Greek cities in the Hellenistic, Roman and Byzantine eras. My tour guide Erol Azor did a great job explaining everything.
My favorite stop of the day was the Blue Mosque, named after the blue tiles used on the dome. It is 43 meters high, making it one of the tallest mosques in the city. There are over 3,000 mosques here in Istanbul. In Turkish, this place is called Sultan Ahmet Camii after the Sultan Ahmet that had it built from 1609-1616. There are six minarets. The legend goes that the Sultan asked for a "gold" minaret, but the word for "gold" in Arabic sounds a lot the number six in Turkish, so that is why there are six of them.
Right next to the Blue Mosque is the Hagia Sofia, which was a Christian church first, then converted to a mosque, and now is a musuem. It was closed on Mondays, so all I could do was take pictures from the outside. Tulips are in full bloom throughout the city this month of April. If you notice, the minaret on the right is different color. Often, new sultans would add a minaret to an existing mosque, using whatever materials were available at the time. Kind of like adding a bedroom to an existing house.
Underneath the ground is the Basilica Cistern which held the drinking water for the city. The water came in on viaduct, and was kept underground. Today, it has a foot of water, and some fish, for people to admire the architecture employed.
Of course, no visit to Istanbul is complete without stopping at the Grand Bazaar. With over 4,000 tiny shops, it is a madhouse of gold and silver jewelry, blue jeans, leather goods, scarves, persian rugs, and antiques. Some places offered me free samples of Turkish delight, which are delicious cubes of flavored gelatin.
My day ended at the Topkapi palace. The word Topkapi is Turkish for "Cannon Gate", as this castle sits overlooking the peninsula and bosphorus strait that separates the Europe side from the Asian side of the city. Like the palace of Versaille in France, or Buckingham palace in England, the Topkapi palace was home to 36 sultans from 1299 to 1922.
You can spend hours here. There are beautiful gardens and various buildings surrounded by five kilometers of castle wall. Inside the buildings are displays of the family jewels, the clothes the sultans wore, their weapons, and religious relics.
It was good to get a flavor of the city, and a sense of the Turkish culture.
Next week, April 8-11, I will be presenting a variety of topics at the [Systems Technical University 2014] conference in Istanbul, Turkey. The conference will feature experts from IBM Power Systems, IBM System x, IBM PureSystems, and IBM System Storage.
Here are the titles and abstracts of the eight topics that I will be presenting next week, in chronological order, along with some related sessions for each topic:
IBM Smarter Storage Strategy
Do you want to understand more about IBM's initiatives for building a smarter planet and how that relates to the data economics of your organization? This session will explain it all, including how IBM's design approach and strategy for its various storage products and solutions for efficiency for data intensive solutions, optimization of business critical workloads, and agility to start quickly and add value. I will also position the features and capabilities of IBM's various disk and tape systems in this context.
Clod Barrera will present IBM Storage Strategy - Traditional and New Methods for Storage Deployment. My session is Tuesday morning and will focus on how IBM Storage Strategy is aligned with IBM's business initiatives including Cloud, Analytics, Mobile and Social Business (CAMS). Clod's presentation will be more technical in nature, featuring Flash storage, scale-out grids, object storage directions, and Software Defined Environments.
Axel Koester will present Storage Technology Futures - fresh from IBM research labs, tomorrow in your datacenter. Axel's presentation will focus on what IBM Research is working on, based on industry trends.
Pat O'Rourke will present Power Systems Trends and Direction, which will focus on IBM's strategy for the POWER Systems product line.
Replication for Business Continuity and Disaster Recovery (BC/DR)
Replication of disk storage systems can be used as part of an overall Business Continuity and Disaster Recovery plan. This session will provide an overview of the technologies involved, and other considerations.
Markus Oscheka and Ralf Wohlfarth will present IBM Storage Systems integration into VMware Site Recovery Manager, a more focused session that offers Business Continuity and Disaster Recovery for VMware environments.
Deniz Erguvan will present Disaster Recovery Solution Design with PowerVM and Storage Virtualization.
Thomas Vogel and Torsten Rothenwaldt will present Native IP replication with SVC / Storwize v7.2. This new feature was announced last October 2013.
Thomas Vogel and Torsten Rothenwaldt will also present New HA and DR concepts with SVC enhanced stretched cluster, focused on data federation across data centers.
What is big data? Architectures and Practical Use Cases
Do you understand the storage implications of big data analytics? This session will explain what big data is, and cover the Information Infrastructure and practical use cases.
Ajay Dholakia will present Taming Big Data: An overview of key technologies and architectures. Ajay will focus more on the hardware components (servers, networks, storage), whereas my presentation will focus on the roles of the storage administrator, data scientist and decision maker.
Axel Koester will present BIG DATA at CERN : Analyzing petabytes in seconds(!) at the European particle collider facility, a specific use case.
Jean-Armand Broyelle will present Big Data on Power: come and touch reality!, which will focus on the capabilities to process big data on POWER systems.
Cloud Storage and the Active Cloud Engine™
This session will cover private and public cloud storage options, including XIV, SONAS, Storwize V7000 Unified and Linear Tape File System (LTFS) Enterprise Edition. The use of Active Cloud Engine for local space management and global WAN caching to access files, SmartCloud Storage Access for self-service provisioning, and file-and-sync solutions will also be explained.
Eric Aquaronne and Jeff Borek will present Storage Cloud to energize your company. My session will focus on the technologies involved, whereas theirs will provide a product demo and practical implementation advice.
Mo McCullough will present XIV Overview and Update, Thomas Luther will present SONAS overview and Updates, and Nils Haustein will present Linear Tape File System Enterprise Edition (LTFS-EE) explained. These other topics will all go into more deep dive on each product solution than what I will cover in my high-level overview.
IBM Tivoli Storage Productivity Center
Why is Tivoli Storage Productivity Center (TPC) the #1 most requested topic at the IBM Tucson Executive Briefing Center? One of the chief architects of this product will cover the latest features, and why this product will greatly help your storage admin staff.
Clod Barrera will present Software Defined Storage - Storage for Software Defined Environments which will provide a broader view, while mine is focused specifically on how TPC plays a role in SDS.
Thomas Luther will present TPC for Replication 5.2 Overview and updates, will focus specifically on the Replication support in the latest release.
IBM Archive Storage Solutions - Data Retention for Government Compliance and Industry Regulations
This session will cover the various offerings IBM has for archive solutions, including IBM System Storage Archive Manager (SSAM), N series, and WORM tape storage systems.
Nils Haustein will present Next generation archive storage solutions which will focus specifically on SSAM software, with focus on migration procedures from other archive solutions.
New Generation of Storage Tiering: Less management, lower investment and increased performance
Confused on how to implement storage tiering between Flash, Disk, Tape storage system resources? This session will cover the various techniques and technologies available.
Levi Norman will present IBM FlashSystem Overview, focused on this particular tier of storage.
Axel Koester will present Storage Portfolio Selection Guide: What (not) to use when, providing an overview of the IBM System Storage portfolio, whereas I am focused more on the technologies that make up each tier of storage, and how to take advantage of them to balance cost and performance.
Data Footprint Reduction
Data Footprint Reduction is the catchall term for a variety of technologies designed to help reduce storage costs. This session will cover four techniques for data footprint reduction: thin provisioning, space-efficient snapshots, data deduplication and real-time compression. It will also discuss the IBM storage products that provide these capabilities. Come to this session to learn how these technologies work, and how they will benefit your data center.
bi Relation session:
Antoine Maille will present Demonstrate the TurboCompression Effect, a live demo of the technologies I will be discussing.
Johann Weiss will present The Storwize family - easy to manage, function rich and cloud ready, which will include a discussion of Real-time compression.
Mathias Defiebre and Erik Franz will present ProtecTIER with IBM FlashSystem (or maybe with Storwize). ProtecTIER is IBM's strategic data deduplication solution, which can act as a gateway in front of a variety of back-end storage options.
If you will be at this conference all week, look for me and say "Hello!"
Well, it's Tuesday again, and you know what that means! IBM Announcements!
Starting today, April 1, 2014, the IBM Executive Briefing Centers (EBC) are adopting a new self-hosted model. In the past, each briefing was assigned a "Briefing Host", a member of the EBC staff, who acted as [master of ceremonies] for the day (or more) for the clients. At some locations, if there were three rooms, there would be three or more briefing hosts so that concurrent briefings could be held.
However, the method does not scale. Having a person per briefing means that you are limited to the number of total concurrent briefings. Inspired by self-service provisioning and scalability of the Cloud, IBM has adopted a new methodology.
In the new model, the visiting client rep, sales rep, or IBM Business Partner will be handed instructions and a map. This will include the agenda, the schedule, biographies of each speaker, the locations of the nearest restrooms, and so on.
I can take partial credit for the idea. In 2012, I made the analogy that having briefing centers at each development lab made a lot of sense, because it allowed clients to interact directly with the engineers and executives that made development decisions. I also made the analogy that having a fully-staffed EBC was like a fire department, whether you have five briefings per month, or fifty, you need a team that is ready, staying abreast of the latest technological changes.
In my post, [Like animals in the zoo], I argued there are two kinds of zoos, the self-guided kind, where visitors are handed a map, versus the docent-guided kind, where a member of the zoo staff introduces you to each animal.
The EBC briefing hosts in this analogy were the docents, and the animals that people came to visit were the engineers and executives.
As for the fire department, IBM management flipped the analogy around. They argued that many smaller communities had "volunteer fire departments", eliminating the need to keep full-time employees doing nothing but playing cards and sliding down brass poles in between fire fighting sessions. When a fire happens, phones calls are made, and this will help get everyone notified to get involved.
In my past 28 years at IBM, I have to say that you know you have good analogies when they can be used in both directions. The zoo analogy was used to prevent management from consolidating all of the EBC staff to Austin, TX. The fire department analogy helped us keep all of our lab equipment to run demonstrations.
The new self-hosted model will address both scheduling and scalability issues. We often had two-day and three-day briefings, and scheduling the rooms, and the briefing managers, based on their availability, was quite challenging.
There are three advantages to the new method:
A coordinator will merely assign rooms, no longer worrying if a briefing host is available for those days. Now, each EBC location can run at full capacity, limited only by real estate and floor space.
Subject matter experts, like myself, that often did double-duty serving as briefing hosts as needed, will have more free time. I personally will be doing more "outbound briefings" to attend conferences and visit clients at their location, eliminating the time I need to be in Tucson to host "inbound" briefings.
The awkward silence that happens when the client rep, sales or IBM Business Partner invites all the clients and presenters, but forgets to invite the briefing host, is completely eliminated.
Recently, a client asked how to backup their IBM PureData System for Analytics devices. IBM had [acquired Netezza in November 2010], and later renamed their TwinFin devices as the IBM PureData for Analytics, powered by Netezza.
The [IBM PureData System for Analytics] is incredibly fast for performing deep, ad-hoc analytics. However, the people who use them are "data scientists", not backup experts.
Likewise, there are backup administrators who may not be familiar with the unique characteristics of this expert-integrated system to know what backup options are available.
As with the rest of the IBM PureSystems line, the IBM PureData System for Analytics (or, PDA for short) has a combination of servers, storage and switches inside.
In a full-frame PDA, there are two servers in Active/Passive mode, these coordinate activity to FPGA-based blade servers, which have parallel access to hundreds of disk drives, storing nearly 200 TB of compressed database data. A system can span up to four frames.
But what do you backup? And why? You don't need to worry about backing up the Linux operating system or NPS server code, that is considered firmware and if anything every got corrupted, IBM would help restore it for you. System-wide metadata, such as the host catalog and global users, groups, and permissions should be backed up periodically to protect against data corruption.
There are a number of reasons to backup your user databases:
As part of firmware upgrade/downgrade
To transfer data to another system
Protect against hardware failure / disaster
Protect against data corruption
The PDA has three backup formats. You can backup the entire user database in compressed format, backup individual tables in compressed format, or export to a text-format file.
Compressed format is faster, but can only be restored to the same PDA, or a PDA that has the same or higher level of NPS firmware. The text-format is slower, but can be used to restore to lower levels of NPS firmware, or to other database systems.
There are basically two methods to backup your PDA. The first is called the "Filesystem" method. Basically, you can attach an external storage device to the NPS server, and use the built-in command line interface (CLI) to store the backups onto its file system.
On NPS version 6, the nzhostbackup will backup the /nz/data directory which stores the system tables, database catalogs, configuration files, query plans, and cached executable code for the SPU blade servers.
(I have heard that the nzhostbackup will get deprecated in NPS version 7, but I only have access to version 6. As always, [RTFM] for your specific NPS code level.)
The nzbackup with the users parameter will backup the global users, groups and permissions. This is included in the /nz/data backup contents from the nzhostbackup command, but you may want to backup and restore these separately.
The nzbackup with the db parameter will backup a user database in compressed format. To backup individual tables, use the CREATE EXTERNAL TABLE command, which can create compressed or text-format exports.
You may find that your databases are so large, they will exceed the limits of the filesystem on the external storage device. For SAN or NAS deployments, I recommend the IBM Storwize V7000 Unified with IBM General Parallel File System (GPFS). However, if you are using something else, you may need to use the "nz_backup" scripts provided which split up the backup images into smaller pieces that most other filesystems can handle.
The PDA comes with 10GbE Ethernet ports that you can attach a NAS storage device over a Local Area Network (LAN), or add Fibre Channel Protocol (FCP) ports and connect over a Storage Area Network (SAN). To keep things simple, I will refer to whichever network you decide as the "Backup Network" in the drawings.
The second method for backup is called the "External Backup Software" method. As you have probably guessed, it involves sending the backups to a supported software product like IBM Tivoli Storage Manager (or, TSM for short).
In this case, the PDA acts as a client node, similar to a laptop, desktop, or application server with internal disk. Backup data is sent over the LAN to the designated TSM server, and the TSM server in turn writes over the SAN to its storage hierarchy of disk, virtual tape and/or physical tape resources.
Backups can be done by command "on demand", or automated on a schedule. For the /nz/data directory, direct the nzhostbackup command to send the backup copy to local disk, then use TSM's dsmc archive command to transfer this backup copy to the TSM server.
For nzbackup with the users or db parameters, you can send the data directly to the appropriate TSM server by specifying the connector and connectorArgs parameters.
To reduce traffic on the TSM Server, an intermediary "TSM Proxy Node" can be put in between. In this case, the PDA sends the backup to the Proxy Node, the Proxy Node uses a "LAN Free Storage Agent" to send the backups directly to the virtual tape and/or physical tape, and then notifies the TSM Server to updates its system catalog to record which tape holds these new backups.
Another configuration involves installing the TSM LAN Free storage agent directly on the PDA. While this will require FCP ports to be added and consume more CPU resources on the NPS server, it eliminates most of the LAN traffic, allowing the PDA to send its backups directly to virtual or physical tape.
My how time flies! It has been nearly a year since our new Tucson Executive Briefing Center had its [Ribbon Cutting Ceremony].
To celebrate this achievement, IBM asked me to write and direct a short film to remind everyone we are here to help clients solve problems, determine an appropriate strategy and make solid purchase decisions.
I have produced other videos for IBM. See my October 2013 blog post [Incorporating Videos] for other examples. This was my first time as writer/director for a project.
This video won't win any Oscars, but I would still like to thank the Academy, my colleagues IBM VP Calline Sanchez, Lee Olguin, Joe Hayward and Kris Keller agreeing to be filmed on camera. Behind the scenes, I want to thank IBM Fellow John Cohn for his superb narration, Andrew Greenfield as cinematographer and editor, Shelly Jost as creative consultant selecting the musical tracks, and Denise White for reviewing the screenplay. Finally, I want to thank our producer, Bill Terry, for funding this effort.
What do you think? Will it go viral? Enter your comments below!
Well it's Tuesday again, and you know what that means? IBM announcements! Many of the announcements were made by IBM Executives at the [IBM Pulse 2014 conference].
IBM BlueMix is the newest cloud offering from IBM, providing Platform-as-a-Service (PaaS) offering based on the Cloud Foundry open source project that promises to deliver enterprise-level features and services that are easy to integrate into cloud applications.
This week, my fifth-line manager Tom Rosamilia, IBM Senior Vice President IBM Systems & Technology Group and Integrated Supply Chain made two announcements at Pulse. First, in additional to x86-based servers, SoftLayer will also offer POWER-based servers to run AIX, IBM i and [Linux on POWER] applications.
Second, SoftLayer will support PureApplication Patterns of Expertise. What is a pattern of expertise? It can be as simple as a virtual machine encapsulated in [Open Virtual Format], to more dynamic architectures, packaged with required platform services, that are deployed and managed by the system according to a set of policies.
Patterns simplify and automate tasks across the lifecycle of the application. Customers and partners alike are [seeing significant reductions in cost and time] across the application lifecycle with the deployment of a PureApplication System.
Also, this week at Pulse, Robert LaBlanc, IBM Senior Vice President of Software and Cloud Solutions, announced [IBM plans to Acquire Cloudant] which offers an open, cloud Database-as-a-Service (DBaaS) that helps organizations simplify mobile, web app and big data development efforts.
When I introduced [SmartCloud Virtual Storage Center] back in October 2012, I mentioned that it was a great solution for large enterprise that have all of their disk behind SAN Volume Controller (SVC).
To reach smaller accounts, IBM has announced two new offerings:
IBM SmartCloud Virtual Storage Entry for customers that have less than 250TB of disk behind two or four SVC nodes. It is priced per terabyte, by the amount of capacity that is virtualized.
IBM SmartCloud Virtual Storage for Storwize Family for customers that have other Storwize family products (Storwize V7000 or V5000, for example). It is priced per the number of storage enclosures that are managed by the Storwize family hardware.
I am not stranger to the Sugar learning platform, developed as part of the One Laptop per Child [OLPC] project.
As I mentioned in my post [Helping Young Students - part 1], I was part of the OLPC development team back in 2008, helped local volunteers deploy laptops to children in Nepal and Uruguay, mentored a college student in India, and learned a lot of Python programming language in the process.
Sugar is now developed by Sugar Labs, a nonprofit spin-off of OLPC. The code is free and open source desktop environment for many other machines, including as a "Desktop Environment" for Fedora Linux.
I kept my 40GB hard drive partitioned as follows. On the extended partition, sda5 will hold my system utilities, like Clonezilla and SystemRescue, and sda6 is my swap space, increased to 1500MB. Partition sda1 has Edubuntu 12.04 on it, and I will use sda2 to install Fedora with Sugar.
[Sugar-on-a-stick], is so named because it is designed so that each child has their own LiveUSB. This can run on PC with Windows or Mac OS without affecting those operating systems, allowing a child to use Sugar in the classroom, then take the stick home and continue on their home PC.
A 2GB or greater USB memory stick can hold both Fedora and Sugar, and use that to boot your desktop. Unfortunately, it requires 1GB of RAM, and I have only 512MB.
Can I just run Sugar natively on a Fedora install? Yes, thanks to the [Sugar not "on a stick"] instructions, I can install Fedora first, then just:
Fedora Desktop Edition - this is a LiveCD that requires 1GB RAM.
Fedora Network Install - this is a bootable CD that then uses the Internet to download the rest of the files required. Use this if you (a) have a fast Internet connection, or (b) do not have a DVD drive on your system.
Fedora Install DVD - this has all the software on the DVD itself.
I chose method 3 and downloaded the appropriate ISO file. While F17 only requires 512MB of RAM to run, the graphic installer requires 768MB, and is fully explained in this [29-step F17 installation guide].
To get around this, select "Troubleshooting" which then lets you select low-graphics/text mode installation that ran well under 512MB. I installed both LXDE and Sugar, and everything worked fine!
Why both LXDE and Sugar? Well, Sugar is quite a different environment, and I wanted LXDE as an alternative for the admin and teacher to use.
"Unlike most other desktop environments, Sugar does not use the 'desktop', 'folder' and 'window' metaphors. Instead, Sugar's default full-screen activities require users to focus on only one program at a time. Sugar implements a novel file-handling metaphor (the Journal), which automatically saves the user's running program session and allows him or her to later use an interface to pull up their past works by date, activity used or file type."
Fedora Upgrader tool (FedUp) command line interface
Fedora upgrade script
As you can probably guess from the title of this post, I chose method 2 "FedUp" as it seemed to be the least invasive. I was unsure if method-1 "Clean Install" of F18 would work with 512MB of RAM, and I have been through enough horrors of failed yum upgrades on my own Red Hat Enterprise Linux [RHEL] at work to avoid method 3. Method 4 is just a script to automate the steps of method 3.
The steps are fairly straightforward. First, install the FedUp package, run "yum update" to ensure you have all the latest kernel and F17 packages for everything else, and reboot.
Then run the fedup-cli command, which upgrades all the packages to F18 level and creates a special kernel level that will then finish the install after the second reboot. It took a while, so I let it run unattended. I put the debug log on partition sda5 in case anything went wrong.
What could go wrong? Well, it turns out that fedup works by updating the Grub2 boot loader configuration, but my grub2 resides on sda1 partition instead, owned by my existing Edubuntu. The reboot did not give me the option to run the specialized kernel to finish the process.
Fixing this was a hot mess, but I managed to configure Grub2 on Fedora, and complete the upgrade and get everything working as before. However, even though it just came out last year, [F18 version is already out of support]! This means I get a second chance to do FedUp, this time to F19 release. Oh boy! Fun!
While the second time went smoother, the problem was that F19 doesn't seem to run well in 512MB of RAM, and chances are F20 won't either.
So what have I learned from this?
Fedora is fully supported, has been around over 10 years, with a vibrant and helpful community.
Sugar is designed for kids, so adding a traditional desktop environment like XFCE or LXDE can be useful for administrator or teacher.
Offering multiple Linux versions in a dual-boot or triple-boot approach may complicate the Grub2 loader configuration and maintenance.
Fedora's "rolling upgrade" approach means that someone will need to consider upgrading to later versions at least every school year or semester to maintain support. Running fedup-cli or any of the other upgrade methods may be too complicated for your average teacher.
If you have any experience with Fedora or Sugar in the classroom, comment below!
Next week, thousands will convene in Las Vegas for [IBM Pulse 2014], an IBM conference that will focus on Cloud, Service and Storage Management.
To lead up to this event, my colleague Steve Wojtowecz, or 'Woj' as we like to call him, IBM VP of Storage and Network Management Software Development, has a five part series that is worth a read. Here are some excerpts:
"Storage-as-a-utility will pick up momentum. Call it [storage-as-a-service], or a storage / back-up cloud, or whatever name you prefer, deployments of this capability will ramp up dramatically."
"Making something simple look complex is easy, making something complex look simple is hard. Like it or not, we all like things simple and easy to grasp."
"Any data that a company is willing to store should be important enough to (1) be protected and backed up as part of a disaster recovery (DR) plan and (2) used for analytics for new business opportunities."
"Hybrid (specifically hybrid storage and data protection clouds) is no longer hype. Nearly every IT shop speculated that hybrid cloud storage was the future of enterprise storage and in 2014 the future is here."
"... the industry will see accelerated adoption in enterprises (private cloud), as an off-premise managed service (public cloud), and across both (hybrid cloud) based on cost, compliance, security and criticality of data to the enterprise."
"IT teams used to thinking of enterprise data as “their baby” are going to have to get comfortable with the idea that the baby is now living somewhere else."
"Line of business organizations have been using analytics to uncover new revenue streams and business opportunities for years. Now, this technology is being turned inward and applied to the data center itself to drive operational efficiency."
"This level of insight and predictability starts to dabble into the notion of cognitive computing as applied to storage and the data it holds."
"Operational analytics will also be applied for productivity / performance gains for the infrastructure itself, like auto-tiering data for priority applications across heterogeneous hardware platforms."
For more insights into these predictions, attend [IBM Pulse 2014] in Las Vegas, next week, February 23-26.
Sadly, I won't be there in person. Although I helped launch the original IBM Pulse back in 2008, I have only been invited once to come back, and that was as a last minute replacement for another speaker in 2012. Unfortunately, I could not accept because of my [near-death experience].
The second solution, "With V" (for Valentine's Day, of course) is a storage virtualization solution that not only contains the technology from the FlashSystem 840 above, but also borrows technology from our SAN Volume Controller to provide added functionality, like Real-time Compression, Remote Mirroring and Thin provisioning.
From the photo, the marketing people staggered the various components to give it a stylized [Dagwood Sandwich] effect. I can assure you that these are just standard 19-inch rack components that fit into 6U of space in standard IT racks.
Starting top to bottom, we have the first FlashSystem V840 Control Enclosure, its 1U-high UPS, a second FlashSystem V840 Control Enclosure and its UPS, and finally a 2U-high FlashSystem V840 Storage Enclosure.
You can have up to a dozen Flash modules, either 2TB or 4TB size, for a maximum of 40TB usable RAID-protected capacity. These can be protected with AES 256-bit encryption. The FlashSystem modules are front-loaded, and slide in and out for easy maintenance.
The system is fully redundant and hot-swappable with concurrent code load to ensure high availability.
(Update: In the comments, readers thought that this was nothing more than just a two-node SVC with FlashSystem 840. There are differences, so I have added the following table.)
SVC with FlashSystem 840
Cabling from controllers to storage
Through SAN fabric ports
Direct attach from V840 Controllers to V840 Storage Enclosures
Call Home Support
GUI screen branding
The system is fully VMware-certified, supporting VAAI interfaces, and an SRA for VMware's Site Recovery Manager (SRM). With Real-time Compression, you can get up to 80 percent capacity savings for workloads like Virtual Desktop Infrastructure (VDI). That in effect gives you up to 5x (200TB) of virtual capacity in 6U of rack space!
You can either keep it as an All-Flash array, or you can virtualize external IBM and non-IBM disk systems, and use the Flash capacity in the Storage Enclosure for IBM's Easy Tier automated sub-volume tiering and data migration. With or without external storage, the FlashSystem V840 can provide local and remote mirroring and point-in-time copies.
(This series started with my post [Kindergarten desktop - The Challenge]. I have a 512MB RAM system with 40GB disk drive that I will install Linux and educational software for a class full of kindergarten children.
First, I re-partitioned the 40GB hard drive as follows. On the extended partition, sda5 will hold my system utilities, like Clonezilla and SystemRescue, and sda6 is my swap space. This gives me three primary partitions to install three flavors of Linux to try out.
The first was [LinuxKidX], which actually started out as a Portuguese-language effort in Brazil. It was then translated to the English language to extend its reach. It is based on the KDE desktop familiar to users of OpenSUSE Linux.
Many of the education software were similar or the same as those from Edubuntu I mentioned in my last post. However, not everything was translated, and unless you are able to read Portuguese, you may not want this one.
Next, I wanted to look at [Qimo for Kids], but first I had to look for the distribution, as the mirrors listed seemed to be unavailable. I was able to find an qimo-2.0-desktop.iso on CNET.com
Unlike Edubuntu, Qimo fits on a CD-ROM for older PCs that may not have DVD drives. Based on lightweight XFCE desktop, the LiveCD runs comfortably in 512MB, with a kid-friendly app launcher at the bottom of the screen. However, Qimo 2.0 is based on Ubuntu 10.04 (Lucid Lynx) LTS, with long term support expiring this May 2013. The Firefox 3.6.3 was too old to run Gmail.
Why hasn't Qimo been enhanced since 2010? It looks like you can just install the packages qimo-session and qimo-wallpaper on newer levels of Ubuntu.
Third, I tried Foresight Linux for Kids 1.0 release. The most recent Foresight is 2.5.3, but Linux for Kids is still at the 1.0 level. The "installer" was very outdated, so the website suggested following the [power-user install HOWTO].
The HOWTO can be a bit intimidating, but I was able to install just fine in 512MB of RAM. Foresight detected I had pre-configured a swap space, and used that to help finish the install process.
Like the others, it had many of the same educational software as before. A key difference is the [Conary package management]. Most systems use either Debian (DEB) or Redhat Package Manager (RPM), but this one is different, and the use of Conary may reduce the number of software applications available.
So what have I learned from these?
All of them seemed to have the same set of educational software: gCompris, eToys, Tux for math and typing.
I want a Linux that uses traditional package management, either DEB or RPM.
The 512MB RAM does not seem to be a difficult limitation. While installation may have been more complicated, they all ran well in 512MB.
If you have had any experience with any of these three distros, please comment below.
However, I was speaking to various clients in Winnipeg, Canada Tuesday and Wednesday this week, so marketing moved the announcement date to today to accommodate my schedule. Sometimes, being the #1 most influential IBM employee in storage comes in handy!)
Here, then, is a quick review of the storage portion of today's announcements.
IBM FlashSystem 840
The [IBM FlashSystem 840] offers twice the capacity as its predecessors, the 810 and 820, with up to 48TB in a dense 2U package.
(Quick recap of previous models: Both the FlashSystem 810 and 820 supported ECC-protected memory and Variable-striped RAID (VSR). The [FlashSystem 810] supported RAID-0 striped across the modules, and the [FlashSystem 820] supported two-dimensional 2D-RAID across modules for higher availability. Fellow blogger Jim Kelley (IBM) on his Storage Buddhist blog has a great post on this: [IBM FlashSystem: Feeding the Hogs].
The new FlashSystem 840 in effect replaces both, so you can choose RAID-0 striping or 2D-RAID, along with your ECC-protected memory and Variable-striped RAID. It offers hot-swappable Flash modules, redundant components, and non-disruptive concurrent code load (CCL).
The FlashSystem 840 also introduces military-grade AES-XTS 256 bit encryption to provide added protection to your data.
For host attachment, you have some great choices: 16Gb/8Gb/4Gb auto-negotiated Fibre Channel (FCP), 40Gb InfiniBand QDR, and 10Gb FCoE. Whatever you decide, you get 90 microsecond writes, and 135 microsecond reads.
Since its introduction just over a year ago, IBM has sold FlashSystem to over 1,000 clients! For more on how this compares to other all-flash arrays, read my previous post about [IBM FlashSystem].
Adding SAN Volume Controller provides some key advantages, including Real-time compression, Thin provisioning, FlashCopy point-in-time copies, Stretched Cluster support, Easy Tier sub-LUN automated tiering, and remote copy services like Metro Mirror (synchronous) and Global Mirror (asynchronous).
Adding the SVC also changes the host attachment options: 8Gb/4Gb/2Gb Fibre Channel (FCP), 1Gb and 10Gb iSCSI, and 10Gb FCoE. Depending on the options and features you choose, the SVC layer adds a modest 60 to 100 microseconds to each read and write.
Each SVC node dedicates four of its six cores, and 2GB of its 24GB cache, to use with compression. Those interested in beefing up compression performance, either with FlashSystems or with any other disk, can choose the "Compression Hardware Upgrade Boosts Base I/O Efficiency" (affectionately known as the CHUBBIE) RPQ 8S1296 for SVC systems with software version 18.104.22.168 or higher. Basically, this RPQ adds another 6-core CPU and another 24GB of cache, so that each node can dedicate 8 cores for compression, and 26GB of cache for compression processing. Initial test results show this can increase performance 3x!
IBM Network Advisor
The [IBM Network Advisor v12.1] management software provides comprehensive management for data, storage and converged networks. This single application can deliver end-to-end visibility and insight across different network types--it supports Fibre Channel SANs (including Gen 5 Fibre Channel platform), IBM FICON and IBM b-type SAN FCoE networks--and provides new features to manage your Brocade and IBM b-type SAN switches.
Cisco MDS 9710 Multilayer Director
The [Cisco MDS 9710 Multilayer Director] is mainframe-ready, with full support for System z FICON and Fibre Channel protocol (FCP) environments. This director supports eight module slots for a maximum of 384 ports.
Last week, in my post [IT Support for the Holidays], I mentioned that I was scrubbing computers in preparation to give them to charity. A local reader asked if I would be willing to donate one of the computers to her kindergarten class. She teaches a class of 20 kids, at the very same elementary school that I went to when I was that age.
So here is the beefiest machine of the set.
Make/Model: Sony PCV-RC850
Processor: 2.4GHz Intel 32-bit
Hard disk: 40GB
Removable media: CD/DVD-ROM and CD/DVD-RW
Keyboard/mouse: standard PS/2
Sound: headphone jack
Ethernet port: 100Mbps
USB ports: two
IBM likes grand challenges, like [Deep Blue computer] to play chess against Grandmaster Garry Kasparov, and the [Watson computer] to play against two experts on the game show Jeopardy! My "Kidergarten Desktop" challenge is certainly on a smaller scale--to install software on this machine that will neet the following requirements
Have age-appropriate educational software and games for the students to learn reading, writing and math. This will also help them be more technology-savvy, learn the [QWERTY keyboard], and be more computer literate.
Have software for the teacher to use for her own job, after the kids have gone for the day, including submitting grades, sending email to parents, typing up lesson plans, data collection, researching the latest trends in education, for example.
Require minimal maintenance, be easy to rescue, repair and recover if necessary.
The 512MB is not enough to run Microsoft Windows 7, but certainly enough to run some flavors of Linux. Inspired by this review of [Top 6 Linux Distributions for Children], I thought I would give a few a spin.
Many of these have LiveCD/LiveDVD/LiveUSB versions that can be booted directly to try them out, and install directly to hard disk if you like it. Unfortunately, this often requires 1GB of memory or more, so I will need a different approach.
I had already scrubbed the [Windows XP] and replaced with [Linux Mint 12 LXDE]. Can I just install the Edubuntu-desktop on Linux Mint? While Linux Mint is Ubuntu-based, it is not binary compatible, so I will need to install fresh.
The [Edubuntu] LiveDVD requires 1GB of memory to try out, so to get this installed, I used the "Alternate Ubuntu 12.04" installer DVD.
Edubuntu recommends 20GB of disk space to run, so I have partitioned the 40GB drive as follows:
For this machine, I will have three users configured:
admin - Administrator (that would be me for now) assigned to the "wheel" group to allow special priveleges
teacher - Teacher will have her own userid/password, so that she can do her own work
student - One userid/password shared by all students. This should eliminate kindergarten students from having to remember a userid and password that is unique to them. They are only five and six years old, after all!
Ubuntu's [Alternate Installer] uses basic graphic mode that can run in 512MB, and once installed, I was then able to install the Edubuntu Desktop and both preschool and primary-level educational software, to account for all learning ability levels of the children.
This system does not boot USB files natively, and getting Grub2 boot loader to boot ISO files was more difficult than I imagined. I was able to extract the necessary files over to sda2 hard disk to get them to work. I took "Clonezilla" full system backups to a separate SSH server over my local subnet.
Well, that's my start. Any suggestions? Has anyone done this before? Please enter comments below.