I'm back. Thanks for all the comments.
For those who participated in Clark Hodge's "Where's Tony" contest,I was in Croatia, Bosnia and Herzogovina. There were optional side-tours to Montenegro and Slovenia, but I decided not to incur the added time and expense with those.
For those wondering where to go this Summer for vacation, I recommend Croatia. It is a beautiful country, with clean cities, good road conditions, and a calm Adriatic sea as we went from island to island.
And if you get to Mostar, don't let them talk you into jumping off the "old bridge". The water is terribly cold down there![Read More]
Continuing this week's theme on virtual worlds, I saw thatGartner predicts 80% of the online community will be using virtual worlds like Second Life by 2011.ComputerWorld ranks the top 8 corporations present in Second Life, IBM ranks #1.
Well, I'm off on another business trip.
My friends over at Appcessories sent me an awesome infographic on the Internet of Things. If you happen to receive any gifts this holiday related to any of these categories, mention them in the comments below!
Enjoy your time off with friends and family!
Happy [Thanksgiving], everyone! Yes, I mean everyone. Even if you are not an American from United States eating turkey and stuffing this week, it wouldn't hurt to take stock in what you are thankful for.
And before I forget, I want to thank all of you, my readers, for making this blog the #1 most read blog at IBM developerWorks, and one of the top blogs in the IT storage industry!
A few years ago, I was stuck in Venice, Italy for the holiday. Not by choice, but because I was the victim of a car accident on my business trip. My neck in a brace, I was unable to fly home in time to celebrate Thanksgiving.
The local IBMers directed me to a wonderful restaurant where I would dine alone, on Thanksgiving, and insisted that I ask the waiter to have some butter for my bread. The joke was on me! A collection of waiters came out, banging on pot lids, with a huge six-pound "cube" of butter on a tray, with a fork and knife stuck into the top. They do like to make fun of the tourists in Vencie, don't they?
In other years past, I have found myself spending the holiday working at client locations, baby-sitting their datacenter. Why? Since Thanksgiving always lands on a Thursday in the USA, the day after is known as "Black Friday", the official kick-off of consumerism craziness.
The next day is "Small Business Saturday", to give small local businesses a chance to compete for some revenue. Two days after that is "Cyber Monday", where many people shop online from their office, rather than fight all the crowds in the traditional brick-and-mortar stores. My job was to make sure the systems ran smoothly, from Thursday to Monday, for our largest clients in the retail industry.
(Note: This is not the first time I have mentioned [Cyber Monday] on my blog. For the past few years, I remind people that the perfect holiday gift is one or more of my books from the Inside System Storage series, volumes I through V, are available in hardcover, paperback and eBook formats from my [Spotlight page on Lulu.com].)
This year, I am thankful that I will be in Tucson with my friends and family. The weather here is expected to be a beautiful 72 degrees Fahrenheit.
Last year, I hosted my friends and family in my home for the big meal. It went so well that I invited everyone back again this year. In August, I started the contractual process to remodel my kitchen, and the company I hired assured me repeatedly it would be ready by Thanksgiving.
Unfortunately, due to a combination of sloppy project management of the company that I hired to do the work and a few unforseen circumstances that caused some delays, I have no kichen.
I have an empty room where my kitchen used to be, the floor partially tiled, the walls clean and freshly panelled and painted. My new cabinets and sink are stacked up inside cardboard boxes in my garage.
So, instead, I am taking everyone out. I am thankful there are restaurants open tomorrow, and I was able to make a last-minute reservation for the six of us. Construction will resume on Friday.
This week, I was in beautiful Melbourne, Australia for IBM Systems Technical University. On Wednesday evening, we had a poster session.
(I have so many photos that I will split this post up into topics. This post will focus on IBM Z systems, see my other posts for storage and IBM Power systems.)
Topics can be anything that is of interest to your peers and colleagues. It can be research-related, a specific solution you implemented or an interesting customer case you want to share.
Linux Scalability at a Small Scale (or, An Adventure In Minimalist Multitudinousness)
Vic Cross, IBM Senior Systems Engineer, used the Ganglia Monitor System to generate traffic and measure 1,680 Linux guests on a single IBM Z mainframe LPAR with only 16GB of memory! His poster consisted of 18 pages of material, a mix of traditional presentation slides, screen shots of web pages, and densely detailed performance results.
Ganglia is a scalable distributed monitoring system for high-performance computing systems such as clusters and Grids. It is based on a hierarchical design targeted at federations of clusters. It leverages widely used technologies such as XML for data representation, XDR for compact, portable data transport, and RRDtool for data storage and visualization. It uses carefully engineered data structures and algorithms to achieve very low per-node overheads and high concurrency. The implementation is robust, has been ported to an extensive set of operating systems and processor architectures, and is currently in use on thousands of clusters around the world. It has been used to link clusters across university campuses and around the world and can scale to handle clusters with 2000 nodes. Learn more at [htt
Spectrum Scale 2 site cluster
Antony Steel, IBM Senior Consulting IT Specialist, presents an option to configure a 2 site GPFS (Spectrum Scale) "almost active-active" cluster when a 3rd site is not available. This option will require simple administrative tasks to make DR filesystem available should Production site fail. Spectrum Scale runs on IBM Z, IBM Power and x86 servers.
The poster used 13 traditional landscape slides, printed on what appears to be A4 paper. A4 is 297 mm wide, so three side by side exceeds the 841 mm width of the poster foam board. These were arranged with a title slide on top, and then 12 content slides in four rows of three.
While I was glad that someone else had a QR code on their poster, the placement was way at the top, and difficult for anyone to actually scan it. I thought of this, and had mine at waist level in the middle right side of my poster.
Life is better with Linux
I couldn't resist taking a photo of the back of this guy's tee-shirt, which says "Life is better with Linux"
In effect, tee-shirts can also be "posters", although that would make for an awkward "poster session" if everyone wore them? Pointing at your chest would be weird, and pointing to your back would be near impossible!
In 1999-2001, I helped the port of Linux to IBM S/390 mainframe chip-set architecture by testing and debugging the disk and tape device drivers. I was the first to install Linux on an IBM mainframe in Tucson, AZ!
I would then go on to work with SAN Volume Controller, Tivoli Storage Manager (now called Spectrum Protect), Tivoli Storage Productivity Center (now called Spectrum Control), and the General Parallel File System (GPFS, now called Spectrum Scale). All of these run on Linux!
I would become the "Linux storage expert" at conferences like SHARE and GUIDE. While my co-workers in DFSMS and z/OS felt Linux was just a fad, I predicted that Linux was going to be a major force in the IT industry. I was right, not only does Linux run on all of our IBM Z and Power servers, it is the underlying operating system for nearly all of IBM storage devices.
Today, I run Linux directly on my laptop, using a Windows KVM guest image as needed for specific projects or applications.
Erina Araki poses for a photo with one of the attendees, Marco. Erina was the organizer for this poster event, and was my primary contact to answer all of my questions. I think the poster session was a big success!
technorati tags: IBM, #IBMtechU, #IBMstu2017, Ganglia Monitor System, Vic Cross, Anthony Steel, GPFS, QR Code, Linux, S/390, SAN Volume Controller, SVC, Tivoli Storage Manager, TSM, Spectrum Protect,Tivoli Storage Productivity Center, TPC, Spectrum Control, GPFS, Spectrum Scale, DFSMS, z/OS, SHARE Conference, GUIDE Conference, Linux KVM, Erina Araki
I got an interesting email from a new blogger asking me for advice on how frequently to post entries.I am probably not the right person to ask, as I blog whenever a thought comes to mind that I think otherswould enjoy reading, and sometimes that means several times a day, and other times only a few per month.I actually have a day job, busy doing other things, and blogging is just now part of my general set of activities.My focus is quality not quantity.
With that in mind, I was delightfully surprised that this blog was ranked among theTop 10 Storage Blogs by Network World, which explains my recent spike in traffic.
I shared the news with my 72-year-old father, and he exclaimed "There are actually 10 or more blogsto cover the IT storage industry?" He couldn't understand why the world would read more than two or three. I personally track thirty-five of them, and I suspect there are hundredsothers out there. Of these, some blog quite regularly, while others do not, so I am in good company. Deni Connor, the author who selected these top 10, gave a nice general complement tothe entire list of blogs:
The blogs written by storage company executives can be surprisingly vendor-agnostic, though the analysts and consultants still tend to pull fewer punches.
And this was my goal as well, to enlighten and entertain, in a fair and balanced manner, that adds value to the blogosphere, rather than just repeat the IBM press releases of each day. If you are just looking for "announcements" there is an RSS feed for IBM System Storage you cansubscribe to.
Not surprisingly, two of the blog entries that Deni mentions are the ones I get the most comments on:
The blogosphere has quieted down a bit over the two papers on MTBF estimates for Disk Drive Modules (DDM).One article on SearchStorage.com by Arun Taneja asksIs RAID passé? Disk capacity is growing at a faster rate than DDM reliability. During the hours to rebuild a DDM, companies are at risk of additional failures that could require recovery from a copy, or result in data loss, depending on how well your Business Continuity (BC) plan is written and followed.
I'll discuss two comments in particular.
Both are fair comments. Disk arrays do run microcode to assist or perform the RAID function, detect failures and start the rebuild process, and so clever designs to support spare disks, process the rebuild quickly, and so on, can differentiate one vendor's offering from another.
On the issue of what does IBM provide to help its clients make the right decisions for their environments, Jon William Toigo at DrunkenData points his readers to IBM's Business Continuity Self-Assessment tool. In normal data center conditions, DDMs will fail, and a Business Continuity plan shouldbe written and developed to handle this fact. Using 2-site and 3-site mirroring, complemented with versions of tape backups, can help address some of these concerns and mitigate some of the risks involved with using disk systems.
For those who want a more technical answer, IBM has just published a series of IBM Redbooks.
Continuing my coverage of the IBM Systems Technical University in Orlando, here are the sessions that I presented or attended on Day 3 (Wednesday).
The day ended with a trip to Universal Studios. Dinner on the City Walk offered entertainment with Dueling Pianos. This was then followed by a trip to Hogsmeade, the Harry Potter themed portion of the resort.
technorati tags: IBM, #ibmtechu, big data, analytics, BigInsights, BigSQl, Spectrum Scale, Hadoop, John Wilkinson, SVC, Storwize, Stretch Cluster, HyperSwap, Dave Willoughby, Thin Provisioning, Space-Efficient Snapshot, Deduplication, Real-time Compression, Spectrum Virtualize, FlashSystem V9000
Comments (2) Visits (6325)
I have been blogging for more than 10 years now, so I am no stranger to commenting on competitive comparisons. In some cases, I am setting the record straight, and other times, poking fun at competitor results, claims or conclusions. This comparison from Brian Carmody was too juicy to ignore.
(FCC Disclosure: I work for IBM. I have no financial interest in Infinidat, Dell EMC, nor Pure Storage, mentioned in this post. I do have friends and former co-workers who now work for Infinidat. This blog post can be considered a "paid celebrity endorsement" for IBM FlashSystem products.)
Fellow blogger Brian Carmody, formerly with IBM but now Chief Technology Officer at a startup called Infinidat, wrote [Flash is not Fast, and the Sky is Falling].
Here is an excerpt, I have added (Infinidat) wherever Brian says "we" just so there is no confusion:
"... So last week we (Infinidat) finally got around to running the same profiles against an INFINIDAT F6230 in our Waltham Solution Center, configured with 1.1TB of DDR-4 DRAM, 200TB TLC NAND, and 480 3TB Nearline HDDs.
In summary, we (Infinidat) wrecked the Pure and EMC systems. Here are the results side by side with EMC's data:<<
By the way, we (Infinidat) took the liberty of running the test with a 200TB data set instead of Pure and EMC's 50TB because modern workloads require performance at scale, and we ran it with in-line compression enabled because our compression algorithm doesn't hurt performance.
This was an interesting test to run, and we (Infinidat) hope it helps the storage industry move away from media type wars and benchmarks (you will lose every time on performance if INFINIDAT is in the mix) ..."
Notice anything wrong here? anything missing?
The Tortoise beat "Hare 1" and "Hare 2", but did not invite the Cheetah to the race?
Brian was smart enough not to compare their product to anything from IBM. IBM has a wide variety of All-Flash Arrays, including the DS8880F models, the Storwize V7000F and V5030F models, and Elastic Storage Server models. However, for this workload, IBM would probably recommend the FlashSystem V9000, A9000 or A9000R.
Any All-Flash Array with a steady-state latency of 2 milliseconds or greater is embarassing, but then Infinibox is not really an All-Flash Array.
The architecture of their Infinibox appears much like the original XIV. It has a mix of DRAM memory and SSD cache, combined with spinning drives. It offers only compression, not data deduplication. Unlike the IBM XIV powered by six to 15 servers, the Infinibox appears under-powered with just three servers.
The Infinibox uses software-based in-line compression, which must put a huge tax on the few CPUs they have in those three servers. Infinidat chose not to compress the data in their cache, probably to reduce the additional overhead on their over-taxed CPUs.
The IBM FlashSystem V9000 has an innovative design, based on IBM Spectrum Virtualize, the mature software that you also find in the IBM SAN Volume Controller and Storwize family of products.
The FlashSystem V9000 offers hard
IBM compresses its cache, using a two-tier approach. The "upper cache" receives the data uncompressed, so that it can then tell the application to continue, for fastest turn-around time. Then the data is compressed, and stored in the "lower cache", optimizing the value and benefits of DRAM memory. Many databases get up to 80 percent savings, resulting in a 5-to-1 benefit in DRAM cache memory.
The IBM FlashSystem A9000 and A9000R also have an innovative, based on IBM Spectrum Accelerate, the code originally developed for IBM XIV storage system.
(Fun fact: Infinidat's founder, [Moshe Yanai], was formerly the founder and designer of XIV, and it appears that Infinidat is just a re-design of old XIV technology architecture, re-packaged with a few differences. Since Moshe left, IBM has drastically enhanced the IBM XIV.)
Like the IBM Spectrum Virtualize family, the IBM FlashSystem A9000 and A9000R have hard
The IBM FlashSystem A9000 and A9000R also offer in-line data deduplication. Modern workloads are virtualized, and Virtual Machine (VM) and Virtual Desktop Infrastructure (VDI) get significant benefits from data deduplication. Infinidat does not play here. For the FlashSystem A9000, most of the metadata related to data deduplication is in cache, minimizing the overhead.
IBM FlashSystem A9000 and A9000R have full performance that blows these published Infinibox results away WITH compression and deduplication turned on.
Brian ran a workload that used the DRAM and SSD cache exclusively, eliminating the reality that any REAL WORLD workload would have to tap into those much slower spinning drives. This is not really a side-to-side benchmark. He is comparing his live run on Infinibox to published numbers from a previous comparison run on a completely different set of data.
This raises the question, why pay for all those spinning drives at all, if you plan to only use the DRAM and Flash storage for your workloads?
A week later, Brian followed up with another post [The INFINIDAT Challenge], acknowledging his comparison was bogus. Here's an excerpt. Again, I have added (Infinidat) wherever Brian is referring to his employer just so there is no confusion:
"... It's not likely that a room full of storage engineers will ever agree on parameters for a synthetic benchmark since storage evaluations are competitive and control of test parameters will invariably predetermine the 'winner'. However, I hope we can all agree that synthetic benchmarks are a waste of time, and that real world performance is what matters in the data center.
So, what can we (Infinidat) do about it?
We (Infinidat) cordially invite every enterprise storage customer who wants lower latency and lower storage cost to visit [Fas
Thanks again to all who participated in the dialog over the past week. I know the post generated some controversy. Traditional storage companies are fighting for their lives trying to keep enterprise storage expensive; indeed their business models are predicated upon maintaining price levels from a bygone era...."
As consolidation play doing full range of data services, I do not see this Infinibox working out. Talking to clients who have the Infinibox, the performance deteriorates in REAL WORLD workloads as you add more data to the unit.
The Infinibox seems fine for workloads that do not demand high performance, so I was surprised Brian compared it to All-Flash arrays. The Infinibox is out of its league!
(To be fair, Pure Storage and EMC XtremeIO aren't really in the same league as IBM FlashSystem, either, given that both of those products are based on commodity SSD. IBM FlashSystem models are consistently 4 to 10 times lower latency than these Commodity-SSD based competitors.)
The Infinibox also lacks features many people expect in an Enterprise-class storage array, like Call-Home capability to identify problems quickly, and Synchronous remote mirroring for disaster recovery. It is often common for startups like Infinidat to deliver a [Minimum Viable Product] as their first offering.
To paraphrase Brian himself, your applications will lose every time on performance if INFINIDAT is in your datacenter.
technorati tags: IBM, FlashSystem, A9000, A9000R, Brian Carmody, Infinidat, Infinibox, Pure Storage, EMC, EMC Unity, Infinidat F6230, Infinibox F6230, IBM XIV, Moshe Yanai, SSD, VDI, All-Flash Array, AFA, Call-Home, Synchronous Mirror, Disaster Recovery, Minimum Viable Product, Spectrum Virtualize, Intel QuickAssist, American Cancer Society
In the 2004 comedy ["A Day Without a Mexican"], the director envisions how disruptive life would be in California if all the Mexicans suddenly disappeared. The point is that sometimes you take things in the background for granted.
I was reminded of this when I saw Mark Underwood's blog post [Mainframe: Still Not Crazy After All These Years]. The article reminds us how critical IBM z Systems mainframes (and related storage like the IBM DS8880 disk systems) are in our lives. Here's an excerpt:
What would a comparable film depicting "A Day without a Mainframe" be like? I would imagine it somewhere between a disaster movie like  and an end-of-the-world zombie horror movie like [28 Days Later]. I would gladly take a million dollars to write the screenplay!
(FCC Disclosure: I work for IBM and am a filmmaker as well. Earlier in my career, I was chief architect of IBM's Data Facility Storage Management Subsystem (DFSMS) which manages around 80 percent of the world's corporate data. This blog post can be considered a "paid celebrity endorsement" for IBM's z13 System mainframes and DS8880 Disk Systems. I have personal experience with both and highly recommend them. I am neither a Mexican nor resident of California, but work regularly with both in my job responsibilities. Like Warren Buffett, I also own stock in both IBM and Berkshire Hathaway companies. I had no involvement in the making of any of the major motion pictures mentioned in this blog post, have no financial interest in their distribution, and have not been provided any compensation for mentioning them in this blog post. They are all great movies worth watching!)
What do you think the movie would be like? Enter your comments below!