This blog is for the open exchange of ideas relating to IBM Systems, storage and storage networking hardware, software and services.
(Short URL for this blog: ibm.co/Pearson )
Tony Pearson is a Master Inventor, Senior IT Architect and Event Content Manager for [IBM Systems for IBM Systems Technical University] events. With over 30 years with IBM Systems, Tony is frequent traveler, speaking to clients at events throughout the world.
Lloyd Dean is an IBM Senior Certified Executive IT Architect in Infrastructure Architecture. Lloyd has held numerous senior technical roles at IBM during his 19 plus years at IBM. Lloyd most recently has been leading efforts across the Communication/CSI Market as a senior Storage Solution Architect/CTS covering the Kansas City territory. In prior years Lloyd supported the industry accounts as a Storage Solution architect and prior to that as a Storage Software Solutions specialist during his time in the ATS organization.
Lloyd currently supports North America storage sales teams in his Storage Software Solution Architecture SME role in the Washington Systems Center team. His current focus is with IBM Cloud Private and he will be delivering and supporting sessions at Think2019, and Storage Technical University on the Value of IBM storage in this high value IBM solution a part of the IBM Cloud strategy. Lloyd maintains a Subject Matter Expert status across the IBM Spectrum Storage Software solutions. You can follow Lloyd on Twitter @ldean0558 and LinkedIn Lloyd Dean.
Tony Pearson's 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.
The developerWorks Connections Platform is now in read-only mode and content is only available for viewing. No new wiki pages, posts, or messages may be added. Please see our FAQ for more information. The developerWorks Connections platform will officially shut down on March 31, 2020 and content will no longer be available. More details available on our FAQ. (Read in Japanese.)
Just in time for [Cyber Monday], Volume II of my "Inside System Storage" book series is now available. As I mentioned in my post on the [October 7th Launch announcement], I finally got past all the internal restrictions that prevented this volume from being published earlier.
My first book covered my initial 12 months of blogging experience, from September 2006 to August 2007. This book covers the history of my career transition from software engineer developer to marketing strategist.
My second book covers the next 8 months, from September 2007 to April 2008, spanning the acquisitions of XIV and Diligent companies that were part of an overall strategic re-alignment of storage within the broader "Systems and Technology Group" of IBM.
The books come in a variety of formats, including hardcover with dust jacket, paperback, and online eBook (PDF). My publisher, Lulu, now supports ePub format, so I am investigating the time and effort required to build this format from the source files.
Next week, once again, I will be blogging from beautiful Caesars Palace hotel in Las Vegas, Nevada to report on what I see and hear at the 29th annual Data Center Conference. Here are my posts from 12 months ago when I attended this conference in 2009:
Again we will have a Solutions Showcase with a Portable Modular Data Center (PMDC) and various exhibits. I will be manning the booths, stop on by. Plus, on Tuesday, I will be be speaking! My topic will be "Choosing the right storage for your server virtualization environment."
Those of you on twitter can follow me at [@az990tony] and hash tag #LSC29. I will be available for one-on-one consultations sessions. I am arriving Sunday morning, Dec. 5, and staying through Thursday afternoon, December 9.
This week I am in beautiful Las Vegas for the Data Center 2010 Conference. While the conference officially starts Monday, I arrived on Sunday to help set up the IBM Booth (Booth "Z").
(Note: This is my third year attending this conference. IBM is a platinum sponsor for this event. The analyst company that runs this event has kindly asked me not to mention their name on this blog, display any of their logos, mention the names of any of their employees, include photos of any of their analysts, include slides from their presentations, or quote verbatim any of their speech at this conference. This is all done to protect and respect their intellectual property that their members pay for. This is all documented in a lengthy document in case I forget. So, if the picture of the conference backpack appears lopped off at the top, this was done intentionally to comply with their request. The list of sponsors at this event represents a "who's who" of the IT industry.)
The pre-conference orientation is for people who are first-timers, or for those who have not attended this conference in a while. The conference includes 7 keynote presentations and 68 sessions organized into seven "tracks" plus one "virtual track" which crosses the other seven:
Servers and Operating Systems
Cost Optimization "Virtual Track"
Each session is further classified as foundational versus advanced, business versus technical, and practical versus strategic.
The speaker also presented some unique methodologies that will be used this week, including "Magic Quadrant", "MarketScope", "Hype Cycle" and "IT Market Clock" which provide graphical representation to help attendees better understand the conference materials.
The Welcome Reception was sponsored by VCE, formerly known as Acadia, the coalition comprised of VMware, Intel, Cisco and EMC. I joked that this should be "VICE" so that Intel does not feel left out.
While we enjoyed drinks and snacks, we listened to live music from the all-violin band [Phat Strad].
The CEO of VCE, Michael Capellas, recognized me from across the room and came over to ask me how IBM was doing. We had a nice friendly chat about the IT industry and the economy.
Continuing my coverage of the Data Center 2010 conference, Monday I attended four keynote sessions.
The first keynote speaker started out with an [English proverb]: Turbulent waters make for skillful mariners.
He covered the state of the global economy and how CIOs should address the challenge. We are on the flat end of an "L-shaped" recovery in the United States. GDP growth is expected to be only 4.7 percent Latin America, 2.3 percent in North America, 1.5 percent Europe. Top growth areas include 8.0 percent India and 8.6 percent China, with an average of 4.7 growth for the entire Asia Pacific region.
On the technical side, the top technologies that CIOs are pursuing for 2011 are Cloud Computing, Virtualization, Mobility, and Business Intelligence/Analytics. He asked the audience if the "Stack Wars" for integrated systems are hurting or helping innovation in these areas.
Move over "conflict diamonds", companies now need to worry about [conflict minerals].
He proposed an alternative approach called Fabric-Based Infrastructure. In this new model, a shared pool of servers is connected to a shared pool of storage over an any-to-any network. In this approach, IT staff spend all of their time just stocking up the vending machine, allowing end-users to get the resources they need.
Crucial Trends You Need to Watch
The second speaker covered ten trends to watch, but these were not limited to just technology trends.
Virtualization is just beginning - even though IBM has had server virtualization since 1967 and storage virtualization since 1974, the speaker felt that adoption of virtualization is still in its infancy. Ten years ago, average CPU utilization for x86 servers of was only 5-7 percent. Thanks to server virtualization like VMware and Hyper-V, companies have increased this to 25 percent, but many projects to virtualized have stalled.
Big Data is the elephant in the room - storage growth is expected to grow 800 percent over the next 5 years.
Green IT - Datacenters consume 40 to 100 times more energy than the offices they support. Six months ago, Energy Star had announced [standards for datacenters] and energy efficiency initiatives.
Unified Communications - Voice over IP (VoIP) technologies, collaboration with email and instant messages, and focus on Mobile smartphones and other devices combines many overlapping areas of communication.
Staff retention and retraining - According to US Labor statistics, the average worker will have 10 to 14 different jobs by the time they reach 38 years of age. People need to broaden their scope and not be so vertically focused on specific areas.
Social Networks and Web 2.0 - the keynote speaker feels this is happening, and companies that try to restrict usage at work are fighting an uphill battle. Better to get ready for it and adopt appropriate policies.
Legacy Migrations - companies are stuck on old technology like Microsoft Windows XP, Internet Explorer 6, and older levels of Office applications. Time is running out, but migration to later releases or alternatives like Red Hat Linux with Firefox browser are not trivial tasks.
Compute Density - Moore's Law that says compute capability will double every 18 months is still going strong. We are now getting more cores per socket, forcing applications to re-write for parallel processing, or use virtualization technologies.
Cloud Computing - every session this week will mention Cloud Computing.
Converged Fabrics - some new approaches are taking shape for datacenter design. Fabric-based infrastructure would benefit from converging SAN and LAN fabrics to allow pools of servers to communicate freely to pools of storage.
He sprinkled fun factoids about our world to keep things entertaining.
50 percent of today's 21-year-olds have produced content for the web. 70 percent of four-year-olds have used a computer. The average teenager writes 2,282 text messages on their cell phone per month.
This year, Google averaged 31 billion searches per month, compared 2.6 billion searches per month in 2007.
More video has been uploaded to YouTube in the last two months than the three major US networks (ABC, NBC, CBS) have aired since 1948.
Wikipedia averages 4300 new articles per day, and now has over 13 million articles.
This year, Facebook reached 500 million users. If it were a country, it would be ranked third. Twitter would be ranked 7th, with 69% of their growth being from people 32-50 years old.
In 1997, a GB of flash memory cost nearly $8000 to manufacture, today it is only $1.25 instead.
The computer in today's cell phone is million times cheaper, and thousand times more powerful, than a single computer installed at MIT back in 1965. In 25 years, the compute capacity of today's cell phones could fit inside a blood cell.
See [interview of Ray Kurzweil] on the Singularity for more details.
The Virtualization Scenario: 2010 to 2015
The third keynote covered virtualization. While server virtualization has helped reduce server costs, as well as power and cooling energy consumption, it has had a negative effect on other areas. Companies that have adopted server virtualization have discovered increased costs for storage, software and test/development efforts.
The result is a gap between expectations and reality. Many virtualization projects have stalled because there is a lack of long-term planning. The analysts recommend deploying virtualization in stages, tackle the first third, so called "low hanging fruit", then proceed with the next third, and then wait and evaluate results before completing the last third, most difficult applications.
Virtualization of storage and desktop clients are completely different projects than server virtualization and should be handled accordingly.
Cloud Computing: Riding the Storm Out
The fourth keynote focus on the pros and cons of Cloud Computing. First they start by defining the five key attributes of Cloud: self-service, scalable elasticity, shared pool of resources, metered and paid per use, over open standard networking technologies.
In addition to IaaS, PaaS and SaaS classifications, the keynote speaker mentioned a fourth one: Business Process as a Service (BPaaS), such as processing Payroll or printing invoices.
While the debate rages over the benefits between private and public cloud approaches, the keynote speaker brings up the opportunites for hybrid and community clouds. In fact, he felt there is a business model for a "cloud broker" that acts as the go-between companies and cloud service providers.
A poll of the audience found the top concerns inhibiting cloud adoption were security, privacy, regulatory compliance and immaturity. Some 66 percent indicated they plan to spend more on private cloud in 2011, and 20 percent plan to spend more on public cloud options. He suggested six focus areas:
Test and Development
Prototyping / Proof-of-Concept efforts
Web Application serving
SaaS like email and business analytics
Select workloads that lend themselves to parallelization
The session wrapped up with some stunning results reported by companies. Server provisioning accomplished in 3-5 minutes instead of 7-12 weeks. Reduced cost of email by 70 percent. Four-hour batch jobs now completed in 20 minutes. 50 percent increase in compute capacity with flat IT budget. With these kind of results, the speaker suggests that CIOs should at least start experimenting with cloud technologies and start to profile their workloads and IT services to develop a strategy.
That was just Monday morning, this is going to be an interesting week!
Continuing my coverage of the Data Center 2010 conference, Monday I afternoon included presentations from IBM executives.
Blueprint for a Smart data center
Steve Sams, IBM Vice President, Global Site and Facilities Services, is well known at this conference. In charge of designing and building data center facilities for IBM and its clients, he has lots of experience in various datacenter configurations.
The presentation was an update from last year's [Data Center Cost Saving Actions Your CFO Will Love]. 70 cents of every IT dollar is spent on just keeping the existing systems running, leaving only 30 percent to handle growth and business transformation. Over 70 percent of datacenters are more than seven years old, and may not be designed to handle today's density in IT equipment.
Many companies wanting to virtualize are stalled. IBM's Server Virtualization Analytics services can help cut this transformation time in half, with an ROI of only 6-18 months for complex Wintel environments. This is just one of the 17 end-to-end datacenter analytics tools IBM offers. The results have been 220 percent more VM instances per admin FTE than traditional deployments. IBM drinks its own champagne, having saved over $4 Billion USD in its own datacenter consolidation and virtualization projects.
Want to Cut the Cost of Storage in Half? Here’s How
The speaker of this session started out with a startling prediction: the amount of storage purchased in the five years 2010-2014 will be 25x what was purchased in 2009, on a PB basis. Most attempts to stem this capacity growth have failed. Therefore, the focus to cut storage costs need to be elsewhere.
The first concern is poor utilization. Utilization on DAS averages 10 percent, SANs 40-50 percent. Thin provisioning can raise this to 60-75 percent. Thin Provisioning was first introduced for the mainframe storage in the 1990s by StorageTek which IBM resold as the IBM RAMAC Virtual Array (RVA), but many credit 3PAR for porting this over to distributed operating systems in 2002. Other options include data deduplication and compression to reduce the cost of storing data on disk.
The second approach is use of storage tiering. In this case, the speaker felt SATA was 3x cheaper ($/GB) but can also be 3x lower performance. Moving data between faster FC/SAS 10K and 15K RPM drives to slower 7200 RPM drives can offer some cost reductions.
Implementing "quotas" in email, file systems or other applications is one of the worst financial decisions an IT department can make, as it merely shifts the storage management from experts (IT staff) to non-experts (end users).
The speaker recommended using archive instead. Keeping backup tapes for long-term is not archive, backups should not be older than eight weeks old.
Interactive polls of the audience gave some interesting insight:
When asked expected storage capacity "compound annual growth rate" (CAGR) for the next few years, 26 percent estimate 35-50 CAGR, 30 percent estimate 50-75 CAGR, and 15 estimate greater than 75 percent CAGR.
For thin provisioning, 43 percent of the audience already are using it, and 33 percent plan to next year.
Similarly , 41 percent of audience is using data deduplication for their primary data, and 30 percent plan to next year.
For automated tiering that moves portions of data automatically between fast and slow tiers of storage to optimize performance, like IBM's Easy Tier, 20 percent are already using it, and 44 percent plan to next year.
41 percent already have some archiving for file systems, 17 percent plan to next year.
Only 6 percent have an all-disk backup/replication environment, but 20 percent plan to adopt this next year.
The downsize of trying to squeeze out costs with these approaches and technologies is that there can be negative impact to performance. The speaker suggested a balanced approach of adding lower cost storage to existing fast storage to meet both capacity and performance requirements.
Smarter Infrastructures Deliver Better Economics
Elaine Lennox, IBM Vice President and Business Line Executive for System Software, presented the "3 D's" of a Smarter Infrastructure: design, data and delivery.
Design: new technologies and approaches are forcing people to reconsider the design of their applications, their infrastructure and their facilities.
Data: on average, companies store 17 copies of the same piece of production data. Data needs to be managed better in the future.
Delivery: new types of cloud computing are changing the way IT services can be delivered, and how they are consumed by end users.
Roadmap to Enterprise Cloud Computing
This was a combo vendor/customer presentation. Rex Wang from Oracle presented an overview of Oracle's service and product offerings, and then Jonathan Levine, COO of LinkShare, presented his experiences deploying Oracle ExaData.
Rex presented Oracle's "Cloud maturity model" that has its customers go through the following steps:
Silo: each application on its own stack of software, server and storage.
Grid: virtualization for shared infrastructure and platforms (internal IaaS and PaaS).
Private cloud: self-service, policy-based management, metered chargeback and capacity planning.
Hybrid Cloud: workloads portable between private and public clouds, offering federation, cloud bursting, and interoperability.
Rex felt the standard "Buy vs Rent" argument in the business world applies to IT as well, and that there could be break-even points over long-term TCO analysis that favors one over the other. He cited internal research that showed 28 percent of Oracle customers have internal or private cloud, and 14 percent use public cloud. 25 percent use Application PaaS, 21 percent database PaaS, 5 percent Identity management PaaS, 10 percent Compute IaaS, 18 percent storage IaaS, and 15 percent Test/Dev IaaS.
Rex felt that in all the hype around taking a single host and dividing it into multiple VMs, people have forgotten that the opposite approach of taking multiple instances into clusters is also important. He also felt you have to look at the entire "Application Lifecycle" that goes from:
IT sets up the equipment as an internal PaaS or IaaS
Developers write the application
End users are trained and use the application
Application owners manage and monitor the application
IT meters the usage and does chargeback to each application owner
Oracle's ExaData and ExaLogic compete directly against IBM's Smart Analytics System, IBM CloudBurst, and IBM Smart Business Storage Cloud.
Next up was Jonathan Levine, COO of [LinkShare], a subsidiary of Rakutan in Japan. This is an [Affiliated Marketing] company. Instead of pay-per-view or pay-per-click web advertising, this company only gets paid when the "end user" actually buys something when clicking on web advertising.
The business runs on an 8TB data warehouse and 1 TB OLTP database, ingesting 50GB daily, with 400 million transactions per day with 8.5 GB/sec throughput.
They discovered that the Oracle ExaData did not work right out of the box. In fact, it took them about a year to get it working for them, roughly the same amount of months it took them on their last Oracle 10 to Oracle 11 conversion.
Part of their business allows advertisers and web content publishers to generate reports on activity. Jonathan indicates that if the response is longer than 5 seconds, it might as well be an hour. He called this the "Excel" rule, that results need to be as fast as local PC Microsoft Excel pivot table processing.
With the new Exadata, they met this requirement. Over 84 percent of their transactions happen under 2 seconds, 9 percent take 2-4 seconds, and another 4 percent in the 4-8 second range. They hope that as they approach the winter holiday season that they can handle 2-3x more traffic without negatively impacting this response time.
Continuing my coverage of the Data Center 2010 conference, Tuesday morning I attended several sessions. The first was a serious IT discussion with Mazen Rawashdeh, Technology Executive from eBay, and the second was a lighthearted review of the benefits from Cloud Computing from humorist Dave Barry, and the third focused on re-architecting backup strategies.
eBay – How One Fast Growing Company is Solving its Infrastructure and Data Center Challenges
"It is not the strongest of the species that survives, nor the most intelligent that survives. It is the one that is the most adaptable to change." -- Charles Darwin
So far, this has been the best session I have attended. eBay operates in 32 countries in seven languages, helping 90 million users to buy or sell 245 million items in 50,000 categories. Let's start with some statistics of the volume of traffic that eBay handles:
$2000 traded every second
cell phone sold every six seconds
pair of shoes sold every nine seconds
a major appliance sold every minute
93 billion database actions every day
50 TB of daily ingested daily
code changes to the eBay application are rolled in every day
In 2007, eBay discovered a disturbing trend, that infrastructure costs matched linear growth to business listing volume, which was an unsustainable model. Mazen Rawashdeh, eBay Marketplace Technology Operations, presented their strategy to break free from this problem. They want to double the number of listings without doubling their costs. They are 2 years into their 4 year plan:
Switched from expensive 12U high servers consuming 3 Kilowatts over to open source software on commodity 1-2U server hardware. Mazen owns all the costs from cement floor up to the web server.
Replaced team-optimized key performance indicators (KPI) with a common KPI. The server team focused on transactions per minute. The storage team was focused on utilization. The network team was focused on MB/sec bandwidth. The problem is that changes to optimize one might have negative impact to other teams. The new KPI was "Watts per listing" that allowed all teams to focus on a common goal.
Focused on changing the corporate culture for communicating clear measurable goals so that everyone understands the why and how of this new KPI. You have to spend money to save money in the long run. Consider costs at least 36 months out.
Changed from purchasing servers and depreciating them over 3 years to a lease model with server replacement tech refresh every 18 months. It is a bad idea to keep IT equipment after full depreciation, as energy savings alone on new equipment easily justifies 18-month replacement.
Adopted storage tiers. Storage is purchased not leased because it is more difficult to swap out disk arrays. They have 10-40 PB of disk. They do not use traditional backup, but rather use disk replication across distant locations. They are quick to delete or archive data that does not belong on their production systems.
Their results so far? They have reduced the Watts per listing by 70 percent over the past two years. They were able to double their volume with a relatively flat IT budget.
The Wit and Wisdom of Dave Barry, Humorist and Author
Dave Barry is a humor columnist. For 25 years he was a syndicated columnist whose work appeared in more than 500 newspapers in the United States and abroad, including the [Funny Times] that I subscribe to. In 1988 he won the Pulitzer Prize for Commentary about the election and politics in general. Dave has also written a total of 30 books, of which two of his books were used as the basis for the CBS TV sitcom "Dave's World," in which Harry Anderson played a much taller version of Dave.
I first met Dave about ten years ago at a SHARE conference in Minneapolis, MN. It was good to see him again.
Backup and Beyond
The analyst covered the "Three C's" of backup: cost, capability and complexity. There are many ways to implement backup, and he predicts that 30 percent of all companies will re-evaluate and re-architect their backup strategy, or at least change their backup software, by 2014 to address these three issues. Another survey indicates that 43 percent of companies are considering backup the primary reason they are investigating public cloud service providers.
The top three primary backup software vendors for the audience were Symantec, IBM, and Commvault. An interactive poll of the audience offered some insight:
There appears to be shift away from using disk to emulate tape (Virtual Tape Library) and instead use direct disk interfaces.
Some of the recommended actions were:
Exploit backup software features. On average, people keep 11 versions of backup, try cutting this down to four versions. IBM Tivoli Storage Manager allows this to be done via management class policies.
Implement a separate archive. Once data is archived and backed up, it reduces the backup load of production systems. Any chance to backup semi-static data less frequently will help.
Switch to capacity-based pricing which will allow more flexibility on server options to run backup software.
Implement data deduplication and compression, such as with IBM ProtecTIER data deduplication solution.
Consider a tiered recovery approach, where less critical applications have less backup protection. Many keep 1-2 years of backups, but 90 percent of all recoveries are for backups from the most recent 27 days. Reduce backup retention to 90 days.
Consider adopting a "Unified Recovery Management" strategy that protects laptops and desktops, remote office and branch offices, mission critical applications, and provide for business continuity and disaster recovery.
regularly test your recovery to validate your procedures and assumptions of your recoverability.
While the conference is divided into seven major tracks, it quickly becomes obvious that many of these IT datacenter issues overlap, and that approaches and decisions in one area can easily impact other areas.
Continuing my coverage of the [Data Center 2010 conference], Tuesday afternoon I presented "Choosing the Right Storage for your Server Virtualization". In 2008 and 2009, I attended this conference as a blogger only, but this time I was also a presenter.
The conference asked vendors to condense their presentations down to 20 minutes. I am sure this was inspired by the popular 18-minute lectures from the [TED conference] or perhaps the [Pecha Kucha] night gatherings in Japan where each presenter speaks while showing 20 slides for 20 seconds each, This forces the presenters to focus on their key points and not fill the time slot with unnecessary marketing fluff. This also allows more vendors to have a chance to pitch their point of view.
Mastering the art of stretching out a week-long event into two weeks' worth of blog posts, I continue my
coverage of the [Data Center 2010 conference], Tuesday afternoon I attended several sessions that focused on technologies for Cloud Computing.
(Note: It appears I need to repeat this. The analyst company that runs this event has kindly asked me not to mention their name on this blog, display any of their logos, mention the names of any of their employees, include photos of any of their analysts, include slides from their presentations, or quote verbatim any of their speech at this conference. This is all done to protect and respect their intellectual property that their members pay for. The pie charts included on this series of posts were rendered by Google Charting tool.)
Converging Storage and Network Fabrics
The analysts presented a set of alternative approaches to consolidating your SAN and LAN fabrics. Here were the choices discussed:
Fibre Channel over Ethernet (FCoE) - This requires 10GbE with Data Center Bridging (DCB) standards, what IBM refers to as Converged Enhanced Ethernet (CEE). Converged Network Adapters (CNAs) support FC, iSCSI, NFS and CIFS protocols on a single wire.
Internet SCSI (iSCSI) - This works on any flavor of Ethernet, is fully routable, and was developed in the 1990s by IBM and Cisco. Most 1GbE and all 10GbE Network Interface Cards (NIC) support TCP Offload Engine (TOE) and "boot from SAN" capability. Native suppot for iSCSI is widely available in most hypervisors and operating systems, including VMware and Windows. DCB Ethernet is not required for iSCSI, but can be helpful. Many customers keep their iSCSI traffic in a separate network (often referred to as an IP SAN) from the rest of their traditional LAN traffic.
Network Attached Storage (NAS) - NFS and CIFS have been around for a long time and work with any flavor of Ethernet. Like iSCSI, DCB is not required but can be helpful. NAS went from being for files only, to be used for email and database, and now is viewed as the easiest deployment for VMware. Vmotion is able to move VM guests from one host to another within the same LAN subnet.
Infiniband or PCI extenders - this approach allows many servers to share fewer number of NICs and HBAs. While Infiniband was limited in distance for its copper cables, recent advances now allow fiber optic cables for 150 meter distances.
Interactive poll of the audience offered some insight on plans to switch from FC/FICON to Ethernet-based storage:
Interactive poll of the audience offered some insight on what portion storage is FCP/FICON attached:
Interactive poll of the audience offered some insight on what portion storage is Ethernet-attached:
Interactive poll of the audience offered some insight on what portion of servers are already using some Ethernet-attached storage:
Each vendor has its own style. HP provides homogeneous solutions, having acquired 3COM and broken off relations with Cisco. Cisco offers tight alliances over closed proprietary solutions, publicly partnering with both EMC and NetApp for storage. IBM offers loose alliances, with IBM-branded solutions from Brocade and BNT, as well as reselling arrangements with Cisco and Juniper. Oracle has focused on Infiniband instead for its appliances.
The analysts predict that IBM will be the first to deliver 40 GbE, from their BNT acquisition. They predict by 2014 that Ethernet approaches (NAS, iSCSI, FCoE) will be the core technology for all but the largest SANs, and that iSCSI and NAS will be more widespread than FCoE. As for cabling, the analysts recommend copper within the rack, but fiber optic between racks. Consider SAN management software, such as IBM Tivoli Storage Productivity Center.
The analysts felt that the biggest inhibitor to merging SAN and LANs will be organizational issues. SAN administrators consider LAN administrators like "Cowboys" undisciplined and unwilling to focus on 24x7 operational availability, redundancy or business continuity. LAN administrators consider SAN administrators as "Luddites" afraid or unwilling to accept FCoE, iSCSI or NAS approaches.
Driving Innovation through Innovation
Mr. Shannon Poulin from Intel presented their advancements in Cloud Computing. Let's start with some facts and predictions:
There are over 2.5 billion photos on Facebook, which runs on 30,000 servers
30 billion videos viewed every month
Nearly all Internet-connected devices are either computers or phones
An additional billion people on the Internet
Cars, televisions, and households will also be connected to the Internet
The world will need 8x more network bandwidth, 12x more storage, and 20x more compute power
To avoid confusion between on-premise and off-premise deployments, Intel defines "private cloud" as "single tenant" and "public cloud" as "multi-tenant". Clouds should be
automated, efficient, simple, secure, and interoperable enough to allow federation of resources across providers. He also felt that Clouds should be "client-aware" so that it know what devices it is talking to, and optimizes the results accordingly. For example, if watching video on a small 320x240 smartphone screen, it makes no sense for the Cloud server to push out 1080p. All devices are going through a connected/disconnected dichotomy. They can do some things while disconnected, but other things only while connected to the Internet or Cloud provider.
An internal Intel task force investigated what it would take to beat MIPS and IBM POWER processors and found that their own Intel chips lacked key functionality. Intel plans to address some of their shortcomings with a new chip called "Sandbridge" sometime next year. They also plan a series of specialized chips that support graphics processing (GPU), network processing (NPU) and so on. He also mentioned Intel released "Tukwilla" earlier this year, the latest version of Itanium chip. HP is the last major company to still use Itanium for their servers.
Shannon wrapped up the talk with a discussion of two Cloud Computing initiatives. The first is [Intel® Cloud Builders], a cross-industry effort to build Cloud infrastructures based on the Intel Xeon chipset. The second is the [Open Data Center Alliance], comprised of leading global IT managers who are working together to define and promote data center requirements for the cloud and beyond.
The analysts feel that we need to switch from thinking about "boxes" (servers, storage, networks) to "resources". To this end, they envision a future datacenter where resources are connected to an any-to-any fabric that connects compute, memory, storage, and networking resources as commodities. They feel the current trend towards integrated system stacks is just a marketing ploy by vendors to fatten their wallets. (Ouch!)
A new concept to "disaggregate" caught my attention. When you make cookies, you disaggregate a cup of sugar from the sugar bag, a teaspoon of baking soda from the box, and so on. When you carve a LUN from a disk array, you are disaggregating the storage resources you need for a project. The analysts feel we should be able to do this with servers and network resources as well, so that when you want to deploy a new workload you just disaggregate the bits and pieces in the amounts you actually plan to use and combine them accordingly. IBM calls these combinations "ensembles" of Cloud computing.
Very few workloads require "best-of-breed" technologies. Rather, this new fabric-based infrastructure recognizes the reality that most workloads do not. One thing that IT Data Center operations can learn from Cloud Service Providers is their focus on "good enough" deployment.
This means however that IT professionals will need new skill sets. IT administrators will need to learn a bit of application development, systems integration, and runbook automation. Network adminis need to enter into 12-step programs to stop using Command Line Interfaces (CLI). Server admins need to put down their screwdrivers and focus instead on policy templates.
Whether you deploy private, public or hybrid cloud computing, the benefits are real and worth the changes needed in skill sets and organizational structure.
Continuing my post-week coverage of the [Data Center 2010 conference], we had receptions on the Show floor. This started at the Monday evening reception and went on through a dessert reception Wednesday after lunch. I worked the IBM booth, and also walked around to make friends at other booths.
Here are my colleagues at the IBM booth. David Ayd, on the left, focuses on servers, everything from IBM System z mainframes, to POWER Systems that run IBM's AIX version of UNIX, and of course the System x servers for the x86 crowd. Greg Hintermeister, on the right, focuses on software, including IBM Systems Director and IBM Tivoli software. I covered all things storage, from disk to tape. For attendees that stopped by the booth expressing interest in IBM offerings, we gave out Starbucks gift cards for coffee, laptop bags, 4GB USB memory sticks and copies of my latest book: "Inside System Storage: Volume II".
Across the aisle were our cohorts from IBM Facilities and Data Center services. They had the big blue Portable Modular Data Center (PMDC). Last year, there were three vendors that offered these: IBM, SGI, and HP. Apparently, IBM won the smack-down, as IBM has returned victorious, as SGI only had the cooling portion of their "Ice Cube" and HP had no container whatsoever.
IBM's PMDC is fully insulated so that you can use it in cold weather below 50 degrees F like Alaska, to the hot climates up to 150 degrees F like Iraq or Afghanistan, and everything in between. They come in three lengths, 20, 40 and 53 feet, and can be combined and stacked as needed into bigger configurations. The systems include their own power generators, cooling, water chillers, fans, closed circuit surveillance, and fire suppression. Unlike the HP approach, IBM allows all the equipment to be serviced from the comfort inside.
This is Mary, one of the 200 employees secunded to the new VCE. Michael Capellas, the CEO of VCE, offered to give a hundred dollars to the [Boys and Girls Club of America], a charity we both support, if I agreed to take this picture. The Boys and Girls Club inspires and enables young people to realize their full potential as productive, responsible, and caring citizens, so it was for a good cause.
The show floor offers attendees a chance to see not just the major players in each space, but also all the new up-and-coming start-ups.
Continuing my post-week coverage of the [Data Center 2010 conference], Wednesday morning started with another keynote session, followed by some break-out sessions.
Realities of IT Investment
Tighter budgets mean more business decisions. Future investments will come from cost savings. The analysts report that 77 percent of IT decisions are made by CFOs. Most organizations are spending less now than back in 2008 before the recession.
How we innovate through IT is changing. In bad times, risk trumps return, but only 21 percent of the audience have a formal "risk calculation" as part of their purchase plans.
Divestment matters as much as investment. Reductions in complexity have the greatest long-term cost savings. Try to retire at least 20 percent of your applications next year. With the advent of Cloud Computing, companies might just retire it and go entirely with public cloud offerings. Note that this graph the years are different than the ones above, in groups of half-decade increments.
It is important to identify functional dependencies and link your IT risks to business outcomes. Focus on making costs visible, and re-think how you communicate IT performance measurements and their impact to business. Try to change the culture and mind-set so that projects are not referred to as "IT projects" focused on technology, but rather they are "business projects" focused on business results.
Moving to the Cloud
Richard Whitehead from Novell presented challenges in moving to Cloud Computing. There are risks and challenges managing multiple OS environments. Users should have full access to all IT resources they need to do their jobs. Computing should be secure, compliant, and portable. Here is the shift he sees from physical servers to virtual and cloud deployments, years 2010 to 2015:
Richard considers a "workload" as being the combination of the operating system, middleware, and application. He then defines "Business Service" as an appropriate combination of these workloads. For example, a business service that provides a particular report might involve a front-end application, talking through business logic workload server, talking to a back-end database workload server.
To address this challenge, Novell introduces "Intelligent Workload Management", called WorkloadIQ. This manages the lifecycle to build, secure, deploy, manage and measure each workload. Their motto was to take the mix of physical, virtual and cloud workloads all "make it work as one". IBM is a business partner with Novell, and I am a big fan of Novell's open-source solutions including SUSE Linux.
A Funny Thing Happened on the Way to the Cloud....
Bud Albers, CTO of Disney, shared their success in deploying their hybrid cloud infrastructure. Everyone recognizes the Disney brand for movies and theme parks, but may not aware that they also own ABC News and ESPN television, Travel cruises, virtual worlds, mobile sites, and deploy applications like Fantasy Football and Fantasy Fishing.
Two years ago, each Line of Business (LOB) owned their own servers, they were continually out of space, power and HVAC issues forced tactical build-outs of their datacenters. But in 2008, the answer to all questions was Cloud Computing, it slices and dices like something invented by [Ron Popeill], with no investment or IT staff required. However, continuing to ask the CFO for CAPEX to purchase assets that were only 1/7th used was not working out either. That's right, over 75 percent of their servers were running less than 15 percent CPU utilization.
The compromise was named "D*Cloud". Internal IT infrastructure would be positioned for Cloud Computing, by adopting server virtualization, implementing REST/SOAP interfaces, and replicating the success across their various Content Distribution Networks (CDN). Disney is no stranger to Open Source software, using Linux and PHP. Their [Open Source] web page shows tools available from Disney Animation studios.
At the half-way point, they had half their applications running virtualized on just 4 percent of their servers. Today, they run over 20 VMs per host and have 65 percent of their apps virtualized. Their target is 80 percent of their apps virtualized by 2014.
Bud used the analogy that public clouds will be the "gas stations" of the IT industry. People will choose the cheapest gas among nearby gas stations. By focusing on "Application management" rather than "VM instance management", Disney is able to seamlessly move applications as needed from private to public cloud platforms.
Their results? Disney is now averaging 40 percent CPU utilization across all servers. Bud feels they have achieved better scalability, better quality of service, and increased speed, all while saving money. Disney is spending less on IT now than in 2008,
UPMC Maximizes Storage Efficiency with IBM
Kevin Muha, UPMC Enterprise Architect & Technology Manager for Storage and Data Protection Services, was unable to present this in person, so Norm Protsman (IBM) presented Kevin's charts on the success at the University of Pittsburgh Medical Center [UPMC]. UPMC is Western Pennsylvania's largest employer, with roughly 50,000 employees across 20 hospitals, 400 doctors' offices and outpatient sites. They have frequently been rated one of the best hospitals in the US.
Their challenge was storage growth. Their storage environment had grown 328 percent over the past three years, to 1.6PB of disk and nearly 7 PB of physical tape. To address this, UPMC deployed four IBM TS7650G ProtecTIER gateways (2 clusters) and three XIV storage systems for their existing IBM Tivoli Storage Manager (TSM) environment. Since they were already using TSM over a Fibre Channel SAN, the implementation took only three days.
UPMC was backing up nearly 60TB per day, in a 15-hour back window. Their primary data is roughly 60 percent Oracle, with the rest being a mix of Microsoft Exchange, SQL Server, and unstructured data such as files and images.
Their results? TSM reclamation is 30 percent faster. Hardware footprint reduced from 9 tiles to 5. Over 50 percent reduction in recovery time for Oracle DB, and 20 percent reduction in recovery of SQL Server, Microsoft Exchange, and Epic Cache. They average 24:1 deduplication overall, which can be broken down by data category as follows:
29:1 Cerner Oracle
18:1 EPIC Cache
10:1 Microsoft SQL Server
8:1 Unstructured files
6:1 Microsoft Exchange
UPMC still has lots of LTO-4 tapes onsite and offsite from before the change-over, so the next phase planned is to implement "IP-based remote replication" between ProtecTIER gateways to a third data center at extended distance. The plan is to only replicate the backups of production data, and not replicate the backups of test/dev data.