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 a Master Inventor and Senior IT Specialist for the IBM System Storage product line at the
IBM Executive Briefing Center in Tucson Arizona, and featured contributor
to IBM's developerWorks. In 2011, Tony celebrated his 25th year anniversary with IBM Storage on the same day as the IBM's Centennial. 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. You can also follow him on Twitter @az990tony.
(Short URL for this blog: ibm.co/Pearson
For those in the US, a comedian named Carlos Mencia has a great TV show, Mind of Menciaand one of my favorite segments is "Why the @#$% is this news!" where he goes about showingblatantly obvious things that were reported in various channels.
So, when I saw that IBM once again, for the third year in a row, has the fastest disk system,the IBM System Storage SAN Volume Controller (SVC), based on widely-accepted industry benchmarksrepresenting typical business workloads, I thought, "Do I really want to blog about this,and sound like a broken record, repeating my various statements of the past of how great SVC is?" It's like reminding people that IBM hashad the most US patents than any other company, every year, for the past 14 years.
(Last year, I received comments fromWoody Hutsell, VP of Texas Memory Systems,because I pointed out that their "World's Fastest Storage"® cache-only system, was not as fast as IBM's SVC.You can ready my opinions, and the various comments that ensued, hereand here. )
That all changed when EMC uber-blogger Chuck Hollis forgot his own Lessons in Marketingwhen heposted his rantDoes Anyone Take The SPC Seriously?That's like asking "Does anyone take book and movie reviews seriously?" Of course they do!In fact, if a movie doesn't make a big deal of its "Two thumbs up!" rating, you know it did not sitwill with the reviewers. It's even more critical for books. I guess this latest news from SPC reallygot under EMC's skin.
For medium and large size businesses, storage is expensive, and customers want to do as much research as possible ahead of time to make informed decisions. A lot of money is at stake, and often, once you choose a product, you are stuckwith that vendor for many years to come, sometimes paying software renewals after only 90 days, and hardware maintenance renewals after only a year when the warranty runs out.
Customers shopping for storage like the idea of a standardized test that is representative, so they can compare one vendor's claims with another. The Storage Performance Council (SPC), much like the Transaction Processing Performance Council (TPC-C) for servers, requires full disclosure of the test environment so people can see what was measured and make their own judgement on whether or not it reflects their workloads. Chuck pours scorn on SPC but I think we should point to TPC-C as a great success story and ask why he thinks the same can't happen for storage? Server performance is also a complicatedsubject, but people compare TPC-C and TPC-H benchmarks all the time.
Note:This blog post has been updated. I am retracting comments that were unfair generalizations. The next two paragraphs are different than originally posted.
Chuck states that "Anyone is free, however, to download the SPC code, lash it up to their CLARiiON, and have at it." I encourage every customer to do this with whatever disk systems they already have installed. Judge for yourself how each benchmark compares to your experience with your application workload, and consider publishing the results for the benefit of others, or at least send me the results, so that I can understand better all of these"use cases" that Chuck talks about so often. I agree that real-world performance measurements using real applications and real data are always going to be more accurate and more relevant to that particular customer. Unfortunately, there are little or no such results made public. They are noticeably absent. With thousands of customers running with storage from all the major storage vendors, as well as storage from smaller start-up companies, I would expect more performance comparison data to be readily available.
In my opinion, customers would benefit by seeing the performance results obtained by others. SPC benchmarks help to fill this void, to provide customers who have not yet purchased the equipment, and are looking for guidance of which vendors to work with, and which products to put into their consideration set.
Truth is, benchmarks are just one of the many ways to evaluate storage vendors and their products. There are also customer references, industry awards, and corporate statements of a company's financial health, strategy and vision.Like anything, it is information to weigh against other factors when making expensive decisions. And I am sure the SPC would be glad to hear of any suggestions for a third SPC-3 benchmark, if the first two don't provide you enough guidance.
So, if you are not delighted with the performance you are getting from your storage now, or would benefit by having even faster I/O, consider improving its performance by adding SAN Volume Controller. SVC is like salt or soy sauce, it makes everything taste better. IBM would be glad to help you with a try-and-buy or proof-of-concept approach, and even help you compare the performance, before and after, with whatever gear you have now. You might just be surprised how much better life is with SVC. And if, for some reason, the performance boost you experience for your unique workload is only 10-30% better with SVC, you are free to tell the world about your disappointment.
I'm glad to be back home in Tucson for a few weeks. All of these conferences kept mefrom reading up with what was going on in the blogosphere.
A few of us at IBM found it odd that EMC would announce their new Geographically Dispersed Disaster Restart (GDDR) the weekBEFORE their "EMC World" conference. Why not announce all of the stuff all at once instead at the conference?Were they worried that the admission that "Maui" software is still many months awaythat much of a negative stigma? The decision probably went something like this:
EMCer #1: GDDR is finally ready, should we announce now, or wait ONE week to make it part of the thingswe announce at EMC World?
EMCer #2: We are not announcing much at EMC World and what people really want us to talk about, Maui, wearen't delivering for a while. Why can't people understand we are company of hardware engineers, not software programmers! So, better not be associated with that quagmire at all.
EMCer #1: Yes, boss, I see your point. We'll announce this week then.
My fellow blogger and intellectual sparring partner, Barry Burke, on his Storage Anarchist blog, posted [are you wasting money on your mainframe dr solution?"] to bringup the GDDR announcement. The key difference is that IBM GDPS works withIBM, EMC and HDS equipment, being the fair-and-balanced folks that IBM clientshave come to expect, but it appears EMC GDDR works only with EMC equipment.Because GDDR does less, it also costs less. I can accept that. You get whatyou pay for. Of course, IBM does have a variety of protection levels, one probably will meet your budget and your business continuity needs.
To correct Barry's misperception, companies that buy IBM mainframe servers do have a choice.They can purchase their operating system from IBM, get their Linux or OpenSolarisfrom someone else like Red Hat or Novell, or build their own OS distribution fromreadily available open source. And unlike other servers that might require at leastone OS partition from the vendor, IBM mainframes can run 100 percent Linux.GDPS supports a mix of OS data. z/OS and Linux data can all be managed by GDPS.Companies that own mainframes know this. I can forgive the misperception from Barry,as EMC is focused on distributed servers instead, and many in their company may not have muchexposure to mainframe technology, or have ever spoken to mainframe customers.
But what almost had me fall out of my chair was this little nugget from his post:
"If you're an IBM mainframe customer, you are - by definition - IBM's profit stream."
Honestly, is there anyone out there that does not realize that IBM is a for-profitcorporation? In contrast, Barry would like his readers to believe that EMC is selling GDDR at cost, andthat EMC is a non-profit organization. While IBM has been delivering actual solutions thatour clients want, EMC continues to rumor that someday they might get around to offering something worthwhile.In the last six months, the shareholders have interpreted both strategies for what they really are,and the stock prices reflect that:
(Disclosure: I own IBM stock. I do not own EMC stock. Stock price comparisonsby Yahoo were based on publicly reported information. The colors blue and red to represent IBM and EMC, respectively, were selected by Yahoo graph-making facility. The color red does not necessarily imply EMC is losing money or having financial troubles.)
Of course, I for one would love to help Barry's dream of EMC non-profitability come true. If anyone has any suggestions how we can help EMC approach this goal, please post a comment below.
He feels I was unfair to accuse EMC of "proprietary interfaces" without spelling out what I was referring to. Here arejust two, along with the whines we hear from customers that relate to them.
EMC Powerpath multipathing driver
Typical whine: "I just paid a gazillion dollars to renew my annual EMC Powerpath license, so you will have to come back in 12 months with your SVC proposal. I just can't see explaining to my boss that an SVC eliminates the need for EMC Powerpath, throwing away all the good money we just spent on it, or to explain that EMC chooses not to support SVC as one of Powerpath's many supported devices."
EMC SRDF command line interface
Typical whine: "My storage admins have written tons of scripts that all invoke EMC SRDF command line interfacesto manage my disk mirroring environment, and I would hate for them to re-write this to use IBM's (also proprietary) command line interfaces instead."
Certainly BarryB is correct that IBM still has a few remaining "proprietary" items of its own. IBM has been in business over 80 years, but it was only the last 10-15 years that IBM made a strategic shift away from proprietary and over to open standards and interfaces. The transformation to "openness" is not yet complete, but we have made great progress. Take these examples:
The System z mainframe - IBM had opened the interfaces so that both Amdahl and Fujitsu made compatible machines.Unlike Apple which forbids cloning of this nature, IBM is now the single source for mainframes because the other twocompetitors could not keep up with IBM's progress and advancements in technology.
Update: Due to legal reasons, the statements referring to Hercules and other S/390 emulators havebeen removed.
The z/OS operating system - While it is possible to run Linux on the mainframe, most people associate the z/OSoperating system with the mainframe. This was opened up with UNIX System Services to satisfy requests from variousgovernments. It is now a full-fledged UNIX operating system, recognized by the [Open Group] that certifies it as such.
As BarryB alludes, the unique interfaces for disk attachment to System z known as Count-Key-Data (CKD) was published so that both EMC and HDS can offer disk systems to compete with IBM's high-end disk offerings. Linux on System zsupports standard Fibre Channel, allowing you to attach an IBM SVC and anyone's storage. Both z/OS and Linux on System z support NAS storage, so IBM N series, NetApp, even EMC Celerra could be used in that case.
The System i itself is still proprietary, but recently IBM announced that it will now support standard block size (512 bytes) instead of the awkward 528 byte blocks that only IBM and EMC support today. That means that any storage vendor will be ableto sell disk to the System i environment.
Advanced copy services, like FlashCopy and Metro Mirror, are as proprietary as the similar offerings from EMCand HDS, with the exception that IBM has licensed them to both EMC and HDS. Thanks to cross-licensing, you can do [FlashCopy on EMC] equipment. Getting all the storage vendors to agree to open standards for these copy services is still workin progress under [SNIA], but at least people who have coded z/OS JCL batchjobs that invoke FlashCopy utilities can work the same between IBM and EMC equipment.
So for those out there who thought that my comment about EMC's proprietary interfaces in any way implied thatIBM did not have any of its own, the proverbial ["pot calling the kettle black"] so to speak, I apologize.
BarryB shows off his [PhotoShop skills] with the graphic below. I take it as a compliment to be compared to anAll-American icon of business success.
TonyP and Monopoly's Mr. Pennybags Separated at Birth?
However, BarryB meant it as a reference back to long time ago when IBMwas a monopoly of the IT industry, which according to [IBM's History], ended in 1973. In other words, IBMstopped being a monopoly before EMC ever existed as a company, and long before I started working for IBM myself.
The anti-trust lawsuit that BarryB mentions happened in 1969, which forced IBM to separate some of the software from its hardware offerings, and prevented IBM from making various acquisitions for years to follow, forcing IBM instead into technology partnerships. I'm glad that's all behind us now!
The technology industry is full of trade-offs. Take for example solar cells that convert sunlight to electricity. Every hour, more energy hits the Earth in the form of sunlight than the entire planet consumes in an entire year. The general trade-off is between energy conversion efficiency versus abundance of materials:
Get 9-11 percent efficiency using rare materials like indium (In), gallium (Ga) or cadmium (Cd).
Get only 6.7 percent efficiency using abundant materials like copper (Cu), tin (Sn), zinc (Zn), sulfur (S), and selenium (Se)
A second trade-off is exemplified by EMC's recent GeoProtect announcement. This appears similar to the geographic dispersal method introduced by a company called [CleverSafe]. The trade-off is between the amount of space to store one or more copies of data and the protection of data in the event of disaster. Here's an excerpt from fellow blogger Chuck Hollis (EMC) titled ["Cloud Storage Evolves"]:
"Imagine a average-sized Atmos network of 9 nodes, all in different time zones around the world. And imagine that we were using, say, a 6+3 protection scheme.
The implication is clear: any 3 nodes could be completely lost: failed, destroyed, seized by the government, etc.
-- and the information could be completely recovered from the surviving nodes."
For organizations worried about their information falling into the wrong hands (whether criminal or government sponsored!), any subset of the nodes would yield nothing of value -- not only would the information be presumably encrypted, but only a few slices of a far bigger picture would be lost.
Seized by the government?falling into the wrong hands? Is EMC positioning ATMOS as "Storage for Terrorists"? I can certainly appreciate the value of being able to protect 6PB of data with only 9PB of storage capacity, instead of keeping two copies of 6PB each, the trade-off means that you will be accessing the majority of your data across your intranet, which could impact performance. But, if you are in an illicit or illegal business that could have a third of your facilities "seized by the government", then perhaps you shouldn't house your data centers there in the first place. Having two copies of 6PB each, in two "friendly nations", might make more sense.
(In reality, companies often keep way more than just two copies of data. It is not unheard of for companies to keep three to five copies scattered across two or three locations. Facebook keeps SIX copies of photographs you upload to their website.)
ChuckH argues that the governments that seize the three nodes won't have a complete copy of the data. However, merely having pieces of data is enough for governments to capture terrorists. Even if the striping is done at the smallest 512-byte block level, those 512 bytes of data might contain names, phone numbers, email addresses, credit cards or social security numbers. Hackers and computer forensics professionals take advantage of this.
You might ask yourself, "Why not just encrypt the data instead?" That brings me to the third trade-off, protection versus application performance. Over the past 30 years, companies had a choice, they could encrypt and decrypt the data as needed, using server CPU cycles, but this would slow down application processing. Every time you wanted to read or update a database record, more cycles would be consumed. This forced companies to be very selective on what data they encrypted, which columns or fields within a database, which email attachments, and other documents or spreadsheets.
An initial attempt to address this was to introduce an outboard appliance between the server and the storage device. For example, the server would write to the appliance with data in the clear, the appliance would encrypt the data, and pass it along to the tape drive. When retrieving data, the appliance would read the encrypted data from tape, decrypt it, and pass the data in the clear back to the server. However, this had the unintended consequences of using 2x to 3x more tape cartridges. Why? Because the encrypted data does not compress well, so tape drives with built-in compression capabilities would not be able to shrink down the data onto fewer tapes.
(I covered the importance of compressing data before encryption in my previous blog post
[Sock Sock Shoe Shoe].)
Like the trade-off between energy efficiency and abundant materials, IBM eliminated the trade-off by offering compression and encryption on the tape drive itself. This is standard 256-bit AES encryption implemented on a chip, able to process the data as it arrives at near line speed. So now, instead of having to choose between protecting your data or running your applications with acceptable performance, you can now do both, encrypt all of your data without having to be selective. This approach has been extended over to disk drives, so that disk systems like the IBM System Storage DS8000 and DS5000 can support full-disk-encryption [FDE] drives.
Fellow blogger Chuck Hollis from EMC has a post titled[Whither Frankenstorage] causing quite a stir in the [Stor-o-Sphere]. He is not the firstEMC blogger to use this phrase, I credit [BarryB] for coining the term back in September 2008.Frankenstein serves as the ideal icon for EMC's FUD machine. In the novel, Dr. Frankenstein wasattempting to do something nobody else had ever attempted, to create human life from variousdead body parts, a process full of uncertainty and doubt, with frightful results.
Perhaps it was a coincidence that I discussed IBM's storage strategy in my post[Foundations and Flavorings] on January 28, shortly followed by NetApp's announcing V-series gateway [support of Texas Memory Systems' RamSan-500] on February 3. These two events mighthave been the trigger that pushed ChuckH over the edge to put pen to paper, .. finger to keyboard.
Flinging FUD in all directions was ChuckH's not-so-subtle way to remind the world that EMC is the only major storage vendor to not offer a successful storage virtualization product. Withoutfirst-hand experience with well-designed storage virtualization, ChuckH conjectures that a configuration matching intelligent front-ends to reliable back-ends might be more expensive, might be more difficult to manage, or might be harder to support.
(Note: Rest assured, IBM can demonstrate that a modular approach, combining intelligent front-ends to reliableback-ends can help reduce costs, be easier to manage, and be fully supported. Contact yourlocal IBM Business Partner or storage sales rep for details.)
My favorite was from Nigel Poulton's post on[Ruptured Monkey]. Here's an excerpt:
In fact, I'm fairly certain that EMC don't back away from customers who run HP or IBM servers and say "sorry we cant help you here, an end to end HP or IBM solution would be much better for you when it comes to troubleshooting……. putting our storage in would only add extra layers of complexity and make things messy….."
On most other days, ChuckH has well-written, insightful blog posts that show that EMC brings some value to the industry. I could have made a snarky reference to[Dr Jekyll and Mr Hyde], or indicate this post proves that nobody at EMC is editing or reviewingChuck's thoughts before they get posted. But it's too late, Chuck already got the message, and added the following to bring the discussion back to civility:
When considering the broad range of storage media service levels available today (flash, FC, SATA, spin-down, etc.) what's the best way to offer these media choices in an array? Is the answer (a) combine smaller arrays from different vendors together behind a virtualization head, or (b) invest the time and effort to build arrays that can directly support all of these media types?
Would anyone like to try a cogent response to the question posed, please?
To address ChuckH's question, Nigel's post gave me the idea to use today's 200th year celebration of [Charles Darwin].
Over millions of years, Charles Darwin argued, evolution results in change in the inherited traits of a population of organisms from one generation to the next.A key component of this is a biological process called [mitosis] that allows a single cell to split and become two cells. In some cases, these individual daughter cells can then specialize to specific functions, such as nerve cells, muscle cells or bone cells. Over time, adaptations that work well carry forward, and thosethat don't get left behind.
I find it interesting that before [On the Origin of Species] was published in 1859, works of fiction like Mary Shelley's[Frankenstein] had monsters being"created", and afterward, monsters were the result of mutation or selective adaptation.
Nigel compares EMC's monolithic approach to placing an intelligent front-end with a reliable back-end as "One man band, where one guy is trying playing all the instruments himself" versus the "Philharmonic Orchestra". I would take it one step further, comparing single-cell organisms to multi-cell life forms.
Innovative companies like Google and Amazon can't wait for a completely integrated solution from a major IT vendor to meet their needs. Why should they? There are open standards, and ways to interconnect the best intelligence into a [dynamic infrastructure®.].You don't need to wait another million years to see which way the IT marketplace considers the better approach. Just look at the last 60 years. Back then, computer systems were all integrated, server, storage, and the wires that connected them were all inside a huge container. Then, mitosis happened, and IBM created external tape storage in 1952, and external disk storage in 1956. Open standards for interfaces allowed third party manufacturers like HDS, StorageTek and EMC to offer plug-compatible storage devices.
On the server side, it didn't take long for functionality in mainframes to split off. Mitosis happened again, with front-end UNIX systems processing incoming data, and mainframes handling the back-end data bases and printing. The client-server era replaced dumb terminals with more intelligent desktops and workstations, and these could handle the front-end processing to display information, with the back-end storage and number-crunching being handled by the UNIX and mainframe systems they connected to.Connections between desktops and servers, and from servers to storage, have also evolved. From thousands of direct-attach cables to networks of switches and directors.
Charles Darwin was particularly interested in cases where evolution happened faster or slower than in other cases. While IBM and Microsoft encouraged third-party innovations on the PC side, Apple resisted mitosis, trying to keep its machines pure single-cell, integrated solutions.For the same reasons that you can't fight the laws of nature, Apple ended up having to support I/O ports to external devices. Thanks to open standards like USB and Firewire, you can connect third-party storage to Apple computers. My little Mac Mini at home has more devices hanging off it than any of my Windows or Linux boxes! And Apple's iPod is successful because its iTunes software runs on both Windows and Mac OS operating systems.
Every time mitosis happens in the IT industry, it opens up opportunities to specialize, to innovate, to adapt to a dynamically changing world. When mitosis is suppressed, you get limiting products and frustratedengineers leaving to form their own start-up companies.But when mitosis is encouraged, you get successful products, solutions and partnerships positioned for a smarter planet.
Well, it's Tuesday, and so it is "announcement day" again! Actually, for me it is Wednesday morning herein Mumbai, India, but since I was "press embargoed" until 4pm EDT in talking about these enhancements, I had to wait until Wednesday morning here to talk about them.
World's Fastest 1TB tape drive
IBM announced its new enterprise [TS1130 tape drive]and corresponding [TS3500 tape library support]. This one has a funny back-story. Last week while we were preparing the Press Release, we debated on whether we should compare the 1TB per cartridge capacity as double that of Sun's Enterprise T10000 (500GB), or LTO-4 (800GB). The problem changed when Sun announced on Monday they too had a 1TB tape drive, so now instead ofsaying that we had the "World's First 1TB tape drive", we quickly changed this to the "World's Fastest 1TB tape drive" instead. At 160MB/sec top speed, IBM's TS1130 is 33 percent faster than Sun's latest announcement. Sun was rather vague when they will actually ship their new units, so IBM may still end up being first to deliver as well.
While EMC and other disk-only vendors have stopped claiming that "tape is dead", these recent announcements from IBM and Sun indicate that indeed tape is alive and well. IBM is able to borrow technologies from disk, such as the Giant Magneto Resistive (GMR) head over to its tape offerings, which means much of the R&D for disk applies to tape, keeping both forms ofstorage well invested. Tape continues to be the "greenest" storage option, more energy efficient than disk, optical, film, microfiche and even paper.
On the LTO front, IBM enhanced the reporting capabilities of its[TS3310] midrange tape library. This includes identifying the resource utilization of the drives, reporting on media integrity, and improved diagnostics to support library-managed encryption.
IBM System Storage DR550
As a blended disk-and-tape solution, the [IBM System Storage DR550] easily replaces the EMC Centera to meet compliance storagerequirements. IBM announced that we have greatly expanded its scalability, being able to support both 1TBdisk drives, as well as being able to attach to either IBM or Sun's 1TB tape drives.
Massive Array of Idle Disks (MAID)
IBM now offers a "Sleep Mode" in the firmware of the [IBM System Storage DCS9550], which is often called "Massive Array of Idle Disks" (MAID) or spin-down capability. This can reduce the amount of power consumed during idle times.
That's a lot of exciting stuff. I'm off to breakfast now.
In this case, it is not chess pieces, but FUD being slung around like mud between vendors. EMC blogger Chuck Hollis' post [Products vs. Features] correctly pointsout that IBM has invented most nearly everything useful in IT, and sadly a few things we wish we hadn't.Gene Amdahl, who left IBM to start his own company, is credited for coining the phrase describing IBM'sinnovative sales techniques. Wikipedia has a nice write up on the history of[Fear, Uncertainty and Doubt(FUD)].
Nowadays, when you hear "FUD" most storage administrators immediately think of EMC, who have taken this method to anew level of art-form. Take for example two EMC entries from fellow blogger BarryB, on his Storage Anarchist blog:[Not Dead Yet, andPushing Daisies].The first is a reference to a funny scene from a Monty Python movie, and the second one is referring to a terriblenew television program called "Pushing Daisies". (In this show, the main character can bring a dead personback to life for sixty seconds, just long enough to ask a few questions on behalf of his detective friend. He must touch the person again within 60 seconds, or someone else randomly dies instead. I amnot a fan of this concept, and found it a bit morbid and creepy. But I digress.)
It is true I was on vacation the past two weeks, but this was group travel I booked over six months ago before we had the exact dates lined up for our various announcements, and not a last-minute celebration of my recent new job assignment. I got all my assignments for this announcement turned in before leaving for my trip. I never thought of checking with fellow IBM blogger BarryW to make sure that we don't have overlapping vacation schedules, leaving the "blogosphere" unmanned, so to speak, but it is not a bad idea. Fortunately, our IBM PR team was able to make their rebuttal through other means. You can read the recap on Techworld [Marketing Wars by Proxy].
Several astute readers on my blog, however, requested that I add my two cents. Let's take a look at some of BarryB's comments:
...most DS8300's are to this day most frequently bundled as "free" storage with IBM mainframe and server sales.
We just shipped our 15,000th box, so for this absurd statement to be true, more than half would have to be given away as part of a server-and-storage deal?Actually, about a third of our DS8000 sales are sold with servers in the same bundle, and while we do provide discounts from the official list price, that is not the same as "free". The other two thirds are sold into accounts to be used with the existing servers already deployed. So BarryB, your math doesn't work out. (Perhaps you've been taking Hitachi math lessons???)
It is interesting however, that when we do a 4-year TCO comparison, between a normally-discounted DS8000 versus free EMC DMX4 hardware, IBM still has the lower cost, given that most of the price-gouging from EMC happens after the initial sale, through software features, annual Powerpath renewals and MES upgrades. If you are an EMC customer, and you are planning to add more capacity to your DMX, ask EMC to charge you no more than what you originally paid on a dollar-per-GB basis for the initial capacity. That's only fair, right?
...No thin provisioning, or even a commitment to thin provisioning. Just crickets. (Celerra support since Jan 2006...
EMC DMX does not have thin provisioning available today either, so BarryB brings up Celerra, their NAS box? IBM System Storage N series NAS box also has thin provisioning, so if you want thin provisioning you can buy a NAS box from EMC or IBM. Thin provisioning makes sense using NAS protocols, as there are actual commands to "delete a file" that can then free up the related blocks in a thin-provisioned environment. The only way to do this with block-oriented protocols is to get the OS to notify the storage device that blocks can be freed up. As it turns out, IBM's z/OS has such support, which we developed specifically for our thin-provisioning support in our IBM RAMAC Virtual Array disk systems back in the 1990s.For block-oriented devices on most other operating systems, thin provisioning may not be all that it is cracked up to be.
No SATA drives (only DMX-4 supports native SATA-II drives, since Aug’07)
A few people are confused on this. IBM DS8000 has supported FATA for quite some time now, same slower speeds and higher capacities as SATA, but are technically NOT the same as SATA. FATA are designed to provide better protection against vibrational shock, to improve reliability of the drives. IBM felt that if the data was important enough to put on a high-end system, it should get better-than-SATA treatment. If you really want SATA, try our IBM System Storage N series, DS4000 or DS3000 models.
No RAID 6 (DMX-3 has supported multi-dimensional RAID since Q1’07, DMX-4 since Aug'07, ...
IBM N series supports RAID6, but we called it RAID-DP and that confused some people. Same thing, DP stands for Dual Parity, protecting against a double-disk failure. We also just announced RAID6 on our DS4000 series, by the way.
No 4Gb back-end (USP-V since May '07, DMX-4 since Aug’07)
I found this one odd, since BarryB himself in an earlier post explained why 4Gbps back-end made no difference to DMX4 performance in this post [DMX-4 and Oh So Much More], which I will put into a different color so you can tell it is from a different post:
You may have noticed that there weren't any specific performance claims attributed to the new 4Gb FC back-end. This wasn't an oversight, it is in fact intentional. The reality is that when it comes to massive-cache storage architectures, there really isn't that much of a difference between 2Gb/s transfer speeds and 4Gb/s. Transmit times are really only a tiny portion of I/O overhead, and just don't make that much difference when a massively-cached system is pre-fetching reads, buffering/delaying writes and reordering I/O requests to minimize seek times. Not that 4Gb/s won't help some applications, but most people just won't see any noticeable difference.
In this case, BarryB is right. The IBM DS8000's 2Gbps back-end is not a performance bottleneck. The DS8000 with a 2Gbps back-end is faster than DMX4 with a 4Gbps back-end for business application workloads. EMC doesn't publish SPC benchmarks to deny this, so you will just have to take our word on this.
Still only 1024 maximum disk drives (DMX-3 & 4 support up to 2400 drives, USP-V supports 1152)
I would be curious to see how many customers have more than 1024 drives on any high-end disk array.As we learned back in [Day 2 Storage Symposium], the average DS8100 has 17.4 TB, and DS8300 has 41.5 TB capacity. Using 500GB drives,that's only 83 spindles. Even with 73GB drives, that's 568 spindles. Plenty of room for growth, so I am notconvinced that higher theoretical upper architectural limits are worth discussing here.
Still only two HARD LPARs (partitions) ..., and even IBM’s mid-tier products support more than 2 storage partitions (in this same announcement)
IBM's two LPARs are TWICE what EMC DMX offers. I don't even know why anyone from EMC would bring this up? While EMC is enjoying their success with VMware, the lack the experience to carry this over to their storage lines. Until EMC offers MORE THAN TWO of any kind of partitions on their high-end offerings, there just is no credibility here. As for our "storage partitions" on our DS4000 line, that is an unfortunate mis-understanding of the press release. On the DS4000, the term "storage partition" is really "LUN masking", dividing up only which disks can be accessed by which hosts, and not dividing up any processor or cache capacity. So this is not the same as any LPAR concept on any other system. For example, a DS4000 with 64 partitions can be attached to 64 hosts, or 64 host-clusters like a Windows MSCS environment or AIX HACMP.
No native Ethernet replication or iSCSI support (Symmetrix has had since 2002)
Again, I found this one odd. On another EMC post, [Vigorous Debates],Chad Sakac mentions that only 2% of Symmetrix are sold with IP ports, not sure if this is for Ethernet replication, iSCSI attachment, or both (Again, I will use a different color):
On the Symm business (a huge part of EMC’s business – the IP ports are included on 2% of deals. That’s a fact.
Just because engineer can put a feature or function on a box, doesn't mean there is business sense to do so. I would hate for IBM to invest millions of dollars on native iSCSI support, only to have 2% of our DS8000 boxes sold with that feature. Customers who have DS8000 on FC SANs already deployed can easily add iSCSI support either through their SAN switches, or by fronting the DS8000 with an N series gateway. Most customers looking for native iSCSI are the smaller no-SAN-deployed SMB customers, and for them, we have both the DS3300 and the various N series models to choose from.
Well that's my two cents. The DS8000 series remains a strategic part of the IBM System Storage offering matrix, with continued investment in the development, as well as on-going research that we can leverage throughout the IBM company. I would like to read your thoughts on this, post me a comment below.
Last week, I was in Austin, and had dinner at [Rudy's Country Store and BBQ]. They offer their self-proclaimed "Worst BBQ in Austin!" with brisket, sausage and other meats by weight. I got a beer, some potato salad, and creamed corn, all at additional cost, of course. When I went to the cashier to pay, I was offered all the white bread I wanted at no additional charge. Are you kidding me? You are going to charge me for beer, but give me 8 to 12 complimentary slices of white bread (practically half a loaf)? Honestly, I consider bread and beer to be basically the same functional food item, differing only in solid versus liquid form. I chose to have only four slices. The food was awesome!
I am reminded of that from my latest exchange with EMC.It didn't take long after IBM's announcement yesterday of IBM's continued investment in its strategic product set, IBM System Storage DS8000 series, that competitors responded. In particular, fellow blogger BarryB from EMC has a post [DS8000 Finally Gets Thin Provisioning] that pokes fun at the new Thin Provisioning feature.
Interestingly, the attack is not on the technical implementation, which is straightforward and rock-solid, but rather that the feature is charged at a flat rate of $69,000 US dollars (list price) per disk array. BarryB claims that recently EMC Corporate has decided to reduce the price of their own thin provisioning, called Symmetrix Virtual Provisioning (VP) on select subset of models of their storage portfolio, although I have not found an EMC press release to confirm. In other words, EMC will bury the cost of thin provisioning into the total cost for new sales, and stop shafting, er.. over-charging their existing Symmetrix customers that are interesting in licensing this feature.
BarryB claims this was a lucky coincidence that his blog post happened just days before IBM's announcement.
(Update: While the timing appears suspicious, I am not accusing Mr. Burke in anywrongdoing of insider information of IBM's plans, nor am I aware of any investigations on this matter from the SEC or any other government agency, and apologize if my previous attempt at humor suggested otherwise. BarryB claimsthat the reduction in price was motivated to counter publicly announced HDS's "Switch In On" program, that it is not a secret thatEMC reduced VP pricing weeks ago, effective beginning 3Q09, just not widely advertised in any formal EMC press releases.Perhaps this new VP pricing was only disclosed to just EMC's existing Symmetrix customers, Business Partners, and employees. Perhaps EMC's decision not to announce this in a Press Release was to avoid upsetting all the EMC CLARiiON customers that continue to pay for Thin Provisioning, or to avoid a long line of existing VP customers asking for refunds. In any case, people are innocent until proven otherwise, and BarryB rightfully deserves the presumption of innocence in this regard. I'm sorry, BarryB, for any trouble my previous comments may have caused you.)
Instead, let's explore some events over the past year that have led up to this.
Let's start with what EMC previously charged for this feature. Software features like this often follow a common pricing method, based per TB, so larger configurations pay more, but tiered in a manner that larger configurations pay less per TB, combined with a yearly maintenance cost.
(Updated: EMC has asked me nicely not to post their actual list prices,so I will provide rough estimates instead. According to BarryB, these are no longer the current prices, soI present them as historical figures for comparison purposes only.)
Initial List price
Software Maintenance (SWMA) percentage
Software Maintenance per year
Number of years
Software License Cost (4 years)
Holy cow! How did EMC get away charging so much for this? To be fair, these are often deeply discounted, a practice common among the industry. However, it was easy for IBMers to show EMC customers that putting SVC or N series gateways in front of their existing EMC disks was more cost effective. Both SVC and N series, as well as IBM's XIV, provide thin provisioning at no additional charge.
HDS offers their own thin provisioning called Hitachi Dynamic Provisioning.Hitachi also offers an SVC-like capability to virtualize storage behind the USP-V. However, I suspect thatfewer than 10 percent of their install base actually licensed this capability because it cost so much. Under the cost pressure from IBM's thin provisioning capabilities in SVC, XIV and N series, Hitachi launched its ["Switch It On"] marketing campaign to activate virtualization and provide some features at no additional charge, including the first 10TB of Hitachi Dynamic Provisioning.
Last week, Martin Glassborow on his StorageBod blog, argued that EMC and HDS should[Set the Wide Stripes Free]. Here is an excerpt:
HDS and EMC are both extremely guilty in this regard, both Virtual Provisioning and Dynamic Provisioning cost me extra as an end-user to license. But this is the technology upon which all future block-based storage arrays will be built. If you guys want to improve the TCO and show that you are serious about reducing the complexity to manage your arrays, you will license for free. You will encourage the end-user to break free from the shackles of complexity and you will improve the image of Tier-1 storage in the enterprise.
Martin is using the term "free" in two contexts above. In the Linux community, we are careful to clarify "free, as in free speech" or "free, as in free beer". Technically, EMC's virtual provisioning is neither, as one has to purchase the hardware to get the feature, so the term "at no additional charge" is more legally correct.
However, the discussion of "free beer" brings me back to my first paragraph about Rudy's BBQ. Nearly everyone eats bread, with the exception of those with [Celiac Disease] that causesan intolerance for gluten protein in wheat, so burying the cost of white bread in the base cost of the BBQ meat is reasonable. In contrast, not everyone drinks beer, and there are probably several people whowould complain if the cost of beer was included in the cost of the BBQ meat, so charging separately forbeer makes business sense.
The same applies in the storage industry. When all (or most) customers of a product can benefit from a feature, it makes sense to include it at no additional charge. When a significant subset might not want to pay a higher base price because they won't use or benefit from a feature, it makes sense to make it optionally priced.
For the IBM SVC, XIV and N series, all customers can benefit from thin provisioning, so it is included at no additional charge.
For the IBM System Storage DS8000, perhaps some 30 to 40 percent of our clients have only System z and/or System i servers attached, and therefore would not benefit from this new thin provisioning. It may seem unfair to raise the price on everybody. The $69,000 flat rate was competitively priced against the prices EMC, HDS and 3PAR were charging for similar capability, and lower than the cost to add a new SVC cluster in front of the DS8000. IBM also charges an annual maintenance, but far lower than what others charged as well.
(Note: These list prices are approximate, and vary slightly based on whether you are on legacy, ESA, Servicesuite or ServiceElect software and subscription (S&S) service plans, and the machine type/model. The tables were too complicated to include here in this post, so these numbers are rounded for comparison purposes only.)
IBM flat rate
Software Maintenance per year (approx)
Number of years
Software License Cost (4 years)
Pricing is more art than science. Getting the right pricing structure that appears fair to everyone involved can be a complicated process.
Last week, I presented IBM's strategic initiative, the IBM Information Infrastructure, which is part of IBM's New Enterprise Data Center vision. This week, I will try to get around to talking about some of theproducts that support those solutions.
I was going to set the record straight on a variety of misunderstandings, rumors or speculations, but I think most have been taken care of already. IBM blogger BarryW covered the fact that SVC now supports XIV storage systems, in his post[SVC and XIV],and addressed some of the FUD already. Here was my list:
Now that IBM has an IBM-branded model of XIV, IBM will discontinue (insert another product here)
I had seen speculation that XIV meant the demise of the N series, the DS8000 or IBM's partnership with LSI.However, the launch reminded people that IBM announced a new release of DS8000 features, new models of N series N6000,and the new DS5000 disk, so that squashes those rumors.
IBM XIV is a (insert tier level here) product
While there seems to be no industry-standard or agreement for what a tier-1, tier-2 or tier-3 disk system is, there seemed to be a lot of argument over what pigeon-hole category to put IBM XIV in. No question many people want tier-1 performance and functionality at tier-2 prices, and perhaps IBM XIV is a good step at giving them this. In some circles, tier-1 means support for System z mainframes. The XIV does not have traditional z/OS CKD volume support, but Linux on System z partitions or guests can attach to XIV via SAN Volume Controller (SVC), or through NFS protocol as part of the Scale-Out File Services (SoFS) implementation.
Whenever any radicalgame-changing technology comes along, competitors with last century's products and architectures want to frame the discussion that it is just yet another storage system. IBM plans to update its Disk Magic and otherplanning/modeling tools to help people determine which workloads would be a good fit with XIV.
IBM XIV lacks (insert missing feature here) in the current release
I am glad to see that the accusations that XIV had unprotected, unmirrored cache were retracted. XIV mirrors all writes in the cache of two separate modules, with ECC protection. XIV allows concurrent code loadfor bug fixes to the software. XIV offers many of the features that people enjoy in other disksystems, such as thin provisioning, writeable snapshots, remote disk mirroring, and so on.IBM XIV can be part of a bigger solution, either through SVC, SoFS or GMAS that provide thebusiness value customers are looking for.
IBM XIV uses (insert block mirroring here) and is not as efficient for capacity utilization
It is interesting that this came from a competitor that still recommends RAID-1 or RAID-10 for itsCLARiiON and DMX products.On the IBM XIV, each 1MB chunk is written on two different disks in different modules. When disks wereexpensive, how much usable space for a given set of HDD was worthy of argument. Today, we sell you abig black box, with 79TB usable, for (insert dollar figure here). For those who feel 79TB istoo big to swallow all at once, IBM offers "capacity on demand" pricing, where you can pay initially for as littleas 22TB, but get all the performance, usability, functionality and advanced availability of the full box.
IBM XIV consumes (insert number of Watts here) of energy
For every disk system, a portion of the energy is consumed by the number of hard disk drives (HDD) andthe remainder to UPS, power conversion, processors and cache memory consumption. Again, the XIV is a bigblack box, and you can compare the 8.4 KW of this high-performance, low-cost storage one-frame system with thewattage consumed by competitive two-frame (sometimes called two-bay) systems, if you are willing to take some trade-offs. To getcomparable performance and hot-spot avoidance, competitors may need to over-provision or use faster, energy-consuming FC drives, and offer additional software to monitor and re-balance workloads across RAID ranks.To get comparable availability, competitors may need to drop from RAID-5 down to either RAID-1 or RAID-6.To get comparable usability, competitors may need more storage infrastructure management software to hide theinherent complexity of their multi-RAID design.
Of course, if energy consumption is a major concern for you, XIV can be part of IBM's many blended disk-and-tapesolutions. When it comes to being green, you can't get any greener storage than tape! Blended disk-and-tapesolutions help get the best of both worlds.
Well, I am glad I could help set the record straight. Let me know what other products people you would like me to focus on next.
(Note: The following paragraphs have been updated to clarify the performance tests involved.)
This time, IBM breaks the 1 million IOPS barrier, achieved by running a test workload consisting of a 70/30 mix of random 4K requests. That is 70 percent reads, 30 percent writes, with 4KB blocks. The throughput achieved was 3.5x times that obtained by running the identical workload on the fastest IBM storage system today (IBM System Storage SAN Volume Controller 4.3),
and an estimated EIGHT* times the performance of EMC DMX. With an average response time under 1 millisecond, this solution would be ideal for online transaction processing (OLTP) such as financial recordings or airline reservations.
(*)Note: EMC has not yet published ANY benchmarks of their EMC DMX box with SSD enterprise flash drives (EFD). However, I believe that the performance bottleneck is in their controller and not the back-end SSD or FC HDD media, so I have givenEMC the benefit of the doubt and estimated that their latest EMC DMX4 is as fast as an[IBMDS8300 Turbo] with Fibre Channel drives. If or when EMC publishes benchmarks, the marketplace can make more accurate comparisons. Your mileage may vary.
IBM used 4 TB of Solid State Disk (SSD) behind its IBM SAN Volume Controller (SVC) technology to achieve this amazing result. Not only does this represent a significantly smaller footprint, but it uses only 55 percent of the power and cooling.
The SSD drives are made by [Fusion IO] and are different than those used by EMC made by STEC.
The SVC addresses the one key problem clients face today with competitive disk systems that support SSD enterprise flash drives: choosing what data to park on those expensive drives? How do you decide which LUNs, which databases, or which files should be permanently resident on SSD? With SVC's industry-leading storage virtualization capability, you are not forced to decide. You can move data into SSD and back out again non-disruptively, as needed to meet performance requirements. This could be handy for quarter-end or year-end processing, for example.
Continuing my catch-up on past posts, Jon Toigo on his DrunkenData blog, posted a ["bleg"] for information aboutdeduplication. The responses come from the "who's who" of the storage industry, so I will provide IBM'sview. (Jon, as always, you have my permission to post this on your blog!)
Please provide the name of your company and the de-dupe product(s) you sell. Please summarize what you think are the key values and differentiators of your wares.
IBM offers two different forms of deduplication. The first is IBM System Storage N series disk system with Advanced Single Instance Storage (A-SIS), and the second is IBM Diligent ProtecTier software. Larry Freeman from NetApp already explains A-SIS in the [comments on Jon's post], so I will focus on the Diligent offering in this post. The key differentiators for Diligent are:
Data agnostic. Diligent does not require content-awareness, format-awareness nor identification of backup software used to send the data. No special client or agent software is required on servers sending data to an IBM Diligent deployment.
Inline processing. Diligent does not require temporarily storing data on back-end disk to post-process later.
Scalability. Up to 1PB of back-end disk managed with an in-memory dictionary.
Data Integrity. All data is diff-compared for full 100 percent integrity. No data is accidentally discarded based on assumptions about the rarity of hash collisions.
InfoPro has said that de-dupe is the number one technology that companies are seeking today — well ahead of even server or storage virtualization. Is there any appeal beyond squeezing more undifferentiated data into the storage junk drawer?
Diligent is focused on backup workloads, which has the best opportunity for deduplication benefits. The two main benefits are:
Keeping more backup data available online for fast recovery.
Mirroring the backup data to another remote location for added protection. With inline processing, only the deduplicated data is sent to the back-end disk, and this greatly reduces the amount of data sent over the wire to the remote location.
Every vendor seems to have its own secret sauce de-dupe algorithm and implementation. One, Diligent Technologies (just acquired by IBM), claims that their’s is best because it collapses two functions — de-dupe then ingest — into one inline function, achieving great throughput in the process. What should be the gating factors in selecting the right de-dupe technology?
As with any storage offering, the three gating factors are typically:
Will this meet my current business requirements?
Will this meet my future requirements for the next 3-5 years that I plan to use this solution?
What is the Total Cost of Ownership (TCO) for the next 3-5 years?
Assuming you already have backup software operational in your existing environment, it is possible to determine thenecessary ingest rate. How many "Terabytes per Hour" (TB/h) must be received, processed and stored from the backup software during the backup window. IBM intends to document its performance test results of specific software/hardwarecombinations to provide guidance to clients' purchase and planning decisions.
For post-process deployments, such as the IBM N series A-SIS feature, the "ingest rate" during the backup only has to receive and store the data, and the rest of the 24-hour period can be spent doing the post-processing to find duplicates. This might be fine now, but as your data grows, you might find your backup window growing, and that leaves less time for post-processing to catch up. IBM Diligent does the processing inline, so is unaffected by an expansion of the backup window.
IBM Diligent can scale up to 1PB of back-end data, and the ingest rate does not suffer as more data is managed.
As for TCO, post-process solutions must have additional back-end storage to temporarily hold the data until the duplicates can be found. With IBM Diligent's inline methodology, only deduplicated data is stored, so less disk space is required for the same workloads.
Despite the nuances, it seems that all block level de-dupe technology does the same thing: removes bit string patterns and substitutes a stub. Is this technically accurate or does your product do things differently?
IBM Diligent emulates a tape library, so the incoming data appears as files to be written sequentially to tape. A file is a string of bytes. Unlike block-level algorithms that divide files up into fixed chunks, IBM Diligent performs diff-compares of incoming data with existing data, and identifies ranges of bytes that duplicate what already is stored on the back-end disk. The file is then a sequence of "extents" representing either unique data or existing data. The file is represented as a sequence of pointers to these extents. An extent can vary from2KB to 16MB in size.
De-dupe is changing data. To return data to its original state (pre-de-dupe) seems to require access to the original algorithm plus stubs/pointers to bit patterns that have been removed to deflate data. If I am correct in this assumption, please explain how data recovery is accomplished if there is a disaster. Do I need to backup your wares and store them off site, or do I need another copy of your appliance or software at a recovery center?
For IBM Diligent, all of the data needed to reconstitute the data is stored on back-end disks. Assuming that all of your back-end disks are available after the disaster, either the original or mirrored copy, then you only need the IBM Diligent software to make sense of the bytes written to reconstitute the data. If the data was written by backup software, you would also need compatible backup software to recover the original data.
De-dupe changes data. Is there any possibility that this will get me into trouble with the regulators or legal eagles when I respond to a subpoena or discovery request? Does de-dupe conflict with the non-repudiation requirements of certain laws?
I am not a lawyer, and certainly there are aspects of[non-repudiation] that may or may not apply to specific cases.
What I can say is that storage is expected to return back a "bit-perfect" copy of the data that was written. Thereare laws against changing the format. For example, an original document was in Microsoft Word format, but is converted and saved instead as an Adobe PDF file. In many conversions, it would be difficult to recreate the bit-perfect copy. Certainly, it would be difficult to recreate the bit-perfect MS Word format from a PDF file. Laws in France and Germany specifically require that the original bit-perfect format be kept.
Based on that, IBM Diligent is able to return a bit-perfect copy of what was written, same as if it were written to regular disk or tape storage, because all data is diff-compared byte-for-byte with existing data.
In contrast, other solutions based on hash codes have collisions that result in presenting a completely different set of data on retrieval. If the data you are trying to store happens to have the same hash code calculation as completely different data already stored on a solution, then it might just discard the new data as "duplicate". The chance for collisions might be rare, but could be enough to put doubt in the minds of a jury. For this reason, IBM N series A-SIS, that does perform hash code calculations, will do a full byte-for-byte comparison of data to ensure that data is indeed a duplicate of an existing block stored.
Some say that de-dupe obviates the need for encryption. What do you think?
I disagree. I've been to enough [Black Hat] conferences to know that it would be possible to read thedata off the back-end disk, using a variety of forensic tools, and piece together strings of personal information,such as names, social security numbers, or bank account codes.
Currently, IBM provides encryption on real tape (both TS1120 and LTO-4 generation drives), and is working withopen industry standards bodies and disk drive module suppliers to bring similar technology to disk-based storage systems.Until then, clients concerned about encryption should consider OS-based or application-based encryption from thebackup software. IBM Tivoli Storage Manager (TSM), for example, can encrypt the data before sending it to the IBMDiligent offering, but this might reduce the number of duplicates found if different encryption keys are used.
Some say that de-duped data is inappropriate for tape backup, that data should be re-inflated prior to write to tape. Yet, one vendor is planning to enable an “NDMP-like” tape backup around his de-dupe system at the request of his customers. Is this smart?
Re-constituting the data back to the original format on tape allows the original backup software to interpret the tape data directly to recover individual files. For example, IBM TSM software can write its primary backup copies to an IBM Diligent offering onsite, and have a "copy pool" on physical tape stored at a remote location. The physical tapes can be used for recovery without any IBM Diligent software in the event of a disaster. If the IBM Diligent back-end disk images are lost, corrupted, or destroyed, IBM TSM software can point to the "copy pool" and be fully operational. Individual files or servers could be restored from just a few of these tapes.
An NDMP-like tape backup of a deduplicated back-end disk would require that all the tapes are in-tact, available, and fully restored to new back-end disk before the deduplication software could do anything. If a single cartridge fromthis set was unreadable or misplaced, it might impact the access to many TBs of data, or render the entire systemunusable.
In the case of a 1PB of back-end disk for IBM Diligent, you would be having to recover over a thousand tapes back to disk before you could recover any individual data from your backup software. Even with dozens of tape drives in parallel, could take you several days for the complete process.This represents a longer "Recovery Time Objective" (RTO) than most people are willing to accept.
Some vendors are claiming de-dupe is “green” — do you see it as such?
Certainly, "deduplicated disk" is greener than "non-deduplicated" disk, but I have argued in past posts, supportedby Analyst reports, that it is not as green as storing the same data on "non-deduplicated" physical tape.
De-dupe and VTL seem to be joined at the hip in a lot of vendor discussions: Use de-dupe to store a lot of archival data on line in less space for fast retrieval in the event of the accidental loss of files or data sets on primary storage. Are there other applications for de-duplication besides compressing data in a nearline storage repository?
Deduplication can be applied to primary data, as in the case of the IBM System Storage N series A-SIS. As Larrysuggests, MS Exchange and SharePoint could be good use cases that represent the possible savings for squeezing outduplicates. On the mainframe, many master-in/master-out tape applications could also benefit from deduplication.
I do not believe that deduplication products will run efficiently with “update in place” applications, that is high levels of random writes for non-appending updates. OLTP and Database workloads would not benefit from deduplication.
Just suggested by a reader: What do you see as the advantages/disadvantages of software based deduplication vs. hardware (chip-based) deduplication? Will this be a differentiating feature in the future… especially now that Hifn is pushing their Compression/DeDupe card to OEMs?
In general, new technologies are introduced on software first, and then as implementations mature, get hardware-based to improve performance. The same was true for RAID, compression, encryption, etc. The Hifn card does "hash code" calculations that do not benefit the current IBM Diligent implementation. Currently, IBM Diligent performsLZH compression through software, but certainly IBM could provide hardware-based compression with an integrated hardware/software offering in the future. Since IBM Diligent's inline process is so efficient, the bottleneck in performance is often the speed of the back-end disk. IBM Diligent can get improved "ingest rate" using FC instead of SATA disk.
Sorry, Jon, that it took so long to get back to you on this, but since IBM had just acquired Diligent when you posted, it took me a while to investigate and research all the answers.
Yesterday, I started this week's topic discussing the various areas of exploration to helpunderstand our recent press release of the IBM System Storage SAN Volume Controller and itsimpressive SPC-1 and SPC-2 benchmark results that ranks it the fastest disk system in the industry.
Some have suggested that since the SVC has a unique design, it should be placed in its own category,and not compared to other disk systems. To address this, I would like to define what IBM meansby "disk system" and how it is comparable to other disk systems.
When I say "disk system", I am going to focus specifically on block-oriented direct-access storage systems, which I will define as:
One or more IT components, connected together, that function as a whole, to serve as a target forread and write requests for specific blocks of data.
Clarification: One could argue, and several do in various comments below, that there are other typesof storage systems that contain disks, some that emulate sequential access tape libraries, some that emulate file-systems through CIFS or NFS protocols, and some that support thestorage of archive objects and other fixed content. At the risk of looking like I may be including or excluding such to fit my purposes, I wanted to avoid apples-to-orangescomparisons between very different access methods. I will limit this exploration to block-oriented, direct-access devices. We can explore these other types of storage systems in later posts.
People who have been working a long time in the storage industry might be satisfied by this definition, thinkingof all the disk systems that would be included by this definition, and recognize that other types of storage liketape systems that are appropriately excluded.
Others might be scratching their heads, thinking to themselves "Huh?" So, I will provide some background, history, and additional explanation. Let's break up the definition into different phrases, and handle each separately.
read and write requests
Let's start with "read and write requests", which we often lump together generically as input/output request, or just I/O request. Typically an I/O request is initiated by a host, over a cable or network, to a target. The target responds with acknowledgment, data, or failure indication. A host can be a server, workstation, personal computer, laptop or other IT device that is capable of initiating such requests, and a target is a device or system designed to receive and respond to such requests.
(An analogy might help. A woman calls the local public library. She picks up the phone, and dials the phone number of the one down the street. A man working at the library hears the phone ring, answers it with "Welcome to the Public Library! How can I help you?" She asks "What is the capital city of Ethiopia?" and replies "Addis Ababa." and hangs up. Satisfied with this response, she hangs up. In this example, the query for information was the I/O request, initiated by the lady, to the public library target)
Today, there are three popular ways I/O requests are made:
CCW commands over OEMI, ESCON or FICON cables
SCSI commands over SCSI, Fibre Channel or SAS cables
SCSI commands over Ethernet cables, wireless or other IP communication methods
specific blocks of data
In 1956, IBM was the first to deliver a disk system. It was different from tape because it was a "direct access storage device" (the acronym DASD is still used today by some mainframe programmers). Tape was a sequential media, so it could handle commands like "read the next block" or "write the next block", it could not directly read without having to read past other blocks to get to it, nor could it write over an existing block without risking overwriting the contents of blocks past it.
The nature of a "block" of data varies. It is represented by a sequence of bytes of specific length. The length is determined in a variety of ways.
CCW commands assume a Count-Key-Data (CKD) format for disk, meaning that tracks are fixed in size, but that a track can consist of one or more blocks, and can be fixed or variable in length. Some blocks can span off the end of one track, and over to another track. Typical block sizes in this case are 8000 to 22000 bytes.
SCSI commands assume a Fixed-Block-Architecture (FBA) format for disk, where all blocks are the same size, almost always a power of two, such as 512 or 4096 bytes. A few operating systems, however, such as i5/OS on IBM System i machines, use a block size that doesn't follow this power-of-two rule.
one or more IT components
You may find one or more of the following IT components in a disk system:
motorized platter(s) covered in magnetic coating with a read/write head to move over its surface. These are often referred to as Hard Disk Drive (HDD) or Disk Drive Modules (DDM), and are manufacturedby companies like Seagate or Hitachi Global Storage Technologies.
A set of HDD can be accessed individually, affectionately known as JBOD for Just-a-bunch-of-disk, or collectively in a RAID configuration.
Memory can act as the high-speed cache in front of slower storage, or as the storage itself. For example, the solid state disk that IBM announced last week is entirely memory storage, using Flash technology.
Lately, there are two popular packaging methods for disk systems:
Monolithic -- all the components you need connected together inside a big refrigerator-sized unit, with options to attach additional frames. The IBM System Storage DS8000, EMC Symmetrix DMX-4 and HDS TagmaStore USP-V all fit this category.
Modular -- components that fit into standard 19-inch racks, often the size of the vegetable drawer inside a refrigerator, that can be connected externally with other components, if necessary, to make a complete disk system. The IBM System Storage DS6000, DS4000, and DS3000 series, as well as our SVC and N series, fall into this category.
Regardless of packaging, the general design is that a "controller" receives a request from its host attachment port, and uses its processors and cache storage to either satisfy the request, or pass the request to the appropriate HDD,and the results are sent back through the host attachment port.
In all of the monolithic systems, as well as some of the modular ones, the controller and HDD storage are contained in the same unit. On other modular systems, the controller is one system, and the HDD storage is in a separate system, and they are cabled together.
serve as a target
The last part is that a disk system must be able to satisfy some or all requests that come to it.
(Using the same analogy used above, when the lady asked her question, the guy at the public library knew the answer from memory, and replied immediately. However, for other questions, he might need to look up the answer in a book, do a search on the internet, or call another library on her behalf.)
Some disk systems are cache-only controllers. For these, either the I/O request is satisfied as a read-hit or write-hit in cache, or it is not, and has to go to the HDD. The IBM DS4800 and N series gateways are examples of this type of controller.
Other systems may have controller and disk, but support additional disk attachment. In this case, either the I/O request is handled by the cache or internal disk, or it has to go out to external HDD to satisfy the request. IBM DS3000 series, DS4100, DS4700, and our N series appliance models, all fall into this category.
So, the SAN Volume Controller is a disk system comprising of one to four node-pairs. Each node is a piece of IT equipment that have processors and cache. These node-pairs are connected to a pair of UPS power supplies to protect the cache memory holding writes that have not yet been de-staged. The combination of node-pairs and UPS acting as a whole, is able to serve as a target to SCSI commands sent over Fibre Channel cables on a Storage Area Network (SAN). To read some blocks of data, it uses its internal cache storage to satisfy the request, and for others, it goes out to external disk systems that contain the data required. All writes are satisfied immediately in cache on the SVC, and later de-staged to external disk when appropriate.
As of end of 2Q07, having reached our four-year anniversary for this product, IBM has sold over 9000 SVC nodes, which are part of more than 3100 SVC disk systems. These things are flying off the shelves, clocking in a 100% YTY growth over the amount we sold twelve months ago. Congratulations go to the SVC development team for their impressive feat of engineering that is starting to catch the attention of many customers and return astounding results!
So, now that I have explained why the SVC is considered a disk system, tomorrow I'll discuss metrics to measure performance.
"The murals in restaurants are on par with the food in museums." --- Peter De Vries
The quote above applies to blogs as well. Those about competitive products of which the blogger has little to no hands-on experience tend to be terribly misleading or technically inaccurate. We saw this last month as Sun Microsystems' Jeff Savit tried to discuss the IBM System z10 EC mainframe.
This time, it comes from EMC bloggers discussing NetApp equipment, and by association, IBM System Storage N series gear.I was going to comment on the ridiculous posts by fellow bloggers from EMC about SnapLock compliance feature on the NetApp, but my buddies at NetApp had already done this for me, saving me the trouble.
The hysterical nature of writing from EMC, and the calm responses from NetApp, speak volumes about the culturesof both companies.
The key point is that none of the "Non-erasable, Non-Rewriteable" (NENR) storage out there are certified as compliant by any government agency on the planet. Governments just aren't in the business of certifying such things. The best you can get is a third-party consultant, such as [Cohasset Associates], to help make decisions that are best for each particular situation.
In addition to SnapLock on N series, IBM offers the [IBM System Storage DR550], WORM tape and optical systems, all of which have been deemed compliant to the U.S. Securities and Exchange Commission [SEC 17a-4] federal regulations by Cohasset Associates. For medical patient records and images like X-rays, IBM offers the Grid Medical Archive Solution [GMAS]designed to meet the requirements of the U.S. Health Insurance Portability and Accountability Act[HIPAA].For other government or industry regulations, consult with your legal counsel.
While EMC bloggers garnered media attention last year pointing out the faulty mathematics from HDS, an astute reader pointed me to EMC's own [DMX-4 specification sheet],updated for its 1TB SATA disk.I've chosen just the minimum and maximum number of drives RAID-6 data points for non-mainframe platforms:
In the first two rows, the numbers appear as expected. For example, 96 drives would be 12 sets of 6+2 RAID ranks, meaning 72 drives' worth of data, so nearly 36TB for 500GB drives, and nearly 72TB for 1TB drives. With 14+2 RAID-6, thenyou would have 84 drives' worth of data, so 42TB and 84TB respectively match expectations.
Where EMC appears miscalculating is having 20x more drives, as the numbers don't match up. For 1920 drives inRAID-6, you would expect 20x more usable capacity than the 96 drive configurations. For 6+2 configurations, one would expect 720TB and 1440TB respectively. For 14+2 configurations, one wouldexpect 840TB and 1680TB, respectively.
Perhaps EMC DMX-4 can't address more than 600TB for the entire system? Does EMC purposely limit the benefitsof these larger drives? It does question why someone might go from 500GB to 1TB drives, if the maximum configuration only gives about 40TB more capacity.Fellow IBM blogger Barry Whyte questioned the use of SATA in an expensive DMX-4 system, in his post[One Box Fits All - Or Does It], and now perhaps there are good reasons to question 1TB from a capacityperspective as well.
While most of the post is accurate and well-stated, two opinions particular caught my eye. I'll be nice and call them opinions, since these are blogs, and always subject to interpretation. I'll put quotes around them so that people will correctly relate these to Hu, and not me.
"Storage virtualization can only be done in a storage controller. Currently Hitachi is the only vendor to provide this." -- Hu Yoshida
Hu, I enjoy all of your blog entries, but you should know better. HDS is fairly new-comer to the storage virtualization arena, so since IBM has been doing this for decades, I will bring you and the rest of the readers up to speed. I am not starting a blog-fight, just want to provide some additional information for clients to consider when making choices in the marketplace.
First, let's clarify the terminology. I will use 'storage' in the broad sense, including anything that can hold 1's and 0's, including memory, spinning disk media, and plastic tape media. These all have different mechanisms and access methods, based on their physical geometry and characteristics. The concept of 'virtualization' is any technology that makes one set of resources look like another set of resources with more preferable characteristics, and this applies to storage as well as servers and networks. Finally, 'storage controller' is any device with the intelligence to talk to a server and handle its read and write requests.
Second, let's take a look at all the different flavors of storage virtualization that IBM has developed over the past 30 years.
IBM introduces the S/370 with the OS/VS1 operating system. "VS" here refers to virtual storage, and in this case internal server memory was swapped out to physical disk. Using a table mapping, disk was made to look like an extension of main memory.
IBM introduces the IBM 3850 Mass Storage System (MSS). Until this time, programs that ran on mainframes had to be acutely aware of the device types being written, as each device type had different block, track and cylinder sizes, so a program written for one device type would have to be modified to work with a different device type. The MSS was able to take four 3350 disks, and a lot of tapes, and make them look like older 3330 disks, since most programs were still written for the 3330 format. The MSS was a way to deliver new 3350 disk to a 3330-oriented ecosystem, and greatly reduce the cost by handling tape on the back end. The table mapping was one virtual 3330 disk (100 MB) to two physical tapes (50 MB each). Back then, all of the mainframe disk systems had separate controllers. The 3850 used a 3831 controller that talked to the servers.
IBM invents Redundant Array of Independent Disk (RAID) technology. The table mapping is one or more virtual "Logical Units" (or "LUNs") to two or more physical disks. Data is striped, mirrored and paritied across the physical drives, making the LUNs look and feel like disks, but with faster performance and higher reliability than the physical drives they were mapped to. RAID could be implemented in the server as software, on top or embedded into the operating system, in the host bus adapter, or on the controller itself. The vendor that provided the RAID software or HBA did not have to be the same as the vendor that provided the disk, so in a sense, this avoided "vendor lock-in".Today, RAID is almost always done in the external storage controller.
IBM introduces the Personal Computer. One of the features of DOS is the ability to make a "RAM drive". This is technology that runs in the operating system to make internal memory look and feel like an external drive letter. Applications that already knew how to read and write to drive letters could work unmodified with these new RAM drives. This had the advantage that the files would be erased when the system was turned off, so it was perfect for temporary files. Of course, other operating systems today have this feature, UNIX has a /tmp directory in memory, and z/OS uses VIO storage pools.
This is important, as memory would be made to look like disk externally, as "cache", in the 1990s.
IBM AIX v3 introduces Logical Volume Manager (LVM). LVM maps the LUNs from external RAID controllers into virtual disks inside the UNIX server. The mapping can combine the capacity of multiple physical LUNs into a large internal volume. This was all done by software within the server, completely independent of the storage vendor, so again no lock-in.
IBM introduces the Virtual Tape Server (VTS). This was a disk array that emulated a tape library. A mapping of virtual tapes to physical tapes was done to allow full utilization of larger and larger tape cartridges. While many people today mistakenly equate "storage virtualization" with "disk virtualization", in reality it can be implemented on other forms of storage. The disk array was referred to as the "Tape Volume Cache". By using disk, the VTS could mount an empty "scratch" tape instantaneously, since no physical tape had to be mounted for this purpose.
Contradicting its "tape is dead" mantra, EMC later developed its CLARiiON disk library that emulates a virtual tape library (VTL).
IBM introduces the SAN Volume Controller. It involves mapping virtual disks to manage disks that could be from different frames from different vendors. Like other controllers, the SVC has multiple processors and cache memory, with the intelligence to talk to servers, and is similar in functionality to the controller components you might find inside monolithic "controller+disk" configurations like the IBM DS8300, EMC Symmetrix, or HDS TagmaStore USP. SVC can map the virtual disk to physical disk one-for-one in "image mode", as HDS does, or can also map virtual disks across physical managed disks, using a similar mapping table, to provide advantages like performance improvement through striping. You can take any virtual disk out of the SVC system simply by migrating it back to "image mode" and disconnecting the LUN from management. Again, no vendor lock-in.
The HDS USP and NSC can run as regular disk systems without virtualization, or the virtualization can be enabled to allow external disks from other vendors. HDS usually counts all USP and NSC sold, but never mention what percentage these have external disks attached in virtualization mode. Either they don't track this, or too embarrassed to publish the number. (My guess: single digit percentage).
Few people remember that IBM also introduced virtualization in both controller+disk and SAN switch form factors. The controller+disk version was called "SAN Integration Server", but people didn't like the "vendor lock-in" having to buy the internal disk from IBM. They preferred having it all external disk, with plenty of vendor choices. This is perhaps why Hitachi now offers a disk-less version of the NSC 55, in an attempt to be more like IBM's SVC.
IBM also had introduced the IBM SVC for Cisco 9000 blade. Our clients didn't want to upgrade their SAN switch networking gear just to get the benefits of disk virtualization. Perhaps this is the same reason EMC has done so poorly with its "Invista" offering.
So, bottom line, storage virtualization can, and has, been delivered in the operating system software, in the server's host bus adapter, inside SAN switches, and in storage controllers. It can be delivered anywhere in the path between application and physical media. Today, the two major vendors that provide disk virtualization "in the storage controller" are IBM and HDS, and the three major vendors that provide tape virtualization "in the storage controller" are IBM, Sun/STK, and EMC. All of these involve a mapping of logical to physical resources. Hitachi uses a one-for-one mapping, whereas IBM additionally offers more sophisticated mappings as well.
You may not be the right person to ask but I am asking everyone so "How do you see hybrid disk drives?"
(For the record, I am not immediately related to Robert. At onepoint, "Pearson" was the 12th most common surname in the USA, but now doesn't even make the Top 100.)
Robert, I would like to encourage you and everyone else to ask questions, don't worry if I am the wrong person to ask, asprobably I know the right person within IBM. Some people have called me the "Kevin Bacon" of Storage,as I am often less than six degrees away from the right person, having worked in IBM Storage for over 20 years.
For those not familiar with hybrid drives, there is a good write-up in Wikipedia.
Unfortunately, most of the people I would consult on this question, such as those from Market Intelligence or Research, are on vacation for the holidays, so, Robert, I will have to rely on my trusted 78-card Tarot deck and answer you with a five-card throw.
Your first card, Robert, is the Hermit. This card represents "introspection". The best I/O is no I/O, which means that if applications can keep the information they need inside server memory, you can avoid the bus bandwidth limitations to going to external storage devices. Where external storage makes sense is when data is shared between servers, or when the single server is limited to a set amount of internal memory. So, consider maxing out the memory in your server first (IBM would be glad to sell you more internal memory!!!), then consider outside solid-state or hybrid devices. Windows for example has an architectural limit of 4GB.
Your second card, Robert, is the Four of Cups, representing "apathy".On the card, you see three cups together, with the fourth cup being delivered from a cloud. This reminds me thatwe have three storage tiers already (memory,disk,tape), and introducing a fourth tier into the mix may not garnermuch excitement. For the mainframe, IBM introduced a Solid-State Device, call the Coupling Facility, which can be accessed from multipleSystem z servers. It is used heavily by DFSMS and DB2 to hold shared information. However, given some customer's apathytowards Information Lifecycle Management which includes "tiered storage", introducing yet another tier that forcespeople to decide what data goes where may be another challenge.
Your third card, Robert, is the Chariot, which represents "Speed, Determination,and Will". In some cases, solid state disk are faster for reading, but can be slower for writing. In the case of ahybrid drive, where the memory acts as a front-end cache, read-hits would be faster, but read-misses might be slower.While the idea of stopping the drives during inactivity will reduce power consumption, spinning up and slowing downthe disk may incur additional performance penalties. At the time of this post, the fastest disk system remains the IBM SAN Volume Controller, based on SPC-1 and SPC-2 benchmarks in excess of those published for other devices.
Your fourth card, Robert, is the Eight of Pentacles, which represents"Diligence, Hard work". The pentacles are coins with five-sided stars on them, and this often represents money.Our research team has projected that spinning disk will continue to be a viable and profitable storage media for at least anothereight years.
Your fifth and last card, Robert, is the World, which normallyrepresents "Accomplishment", but since it is turned upside down, the meaning is reversed to "Limitation". Some Hybriddisks, and some types of solid state memory in general, do have limitations in the number of write cycles they can handle. For thoseunhappy with the frequency and slowness for rebuilds on SATA disk may find similar problems with hybrid drives.For that reason, businesses may not trust using hybrid drives for their busiest, mission-critical applications, but certainlymight use it for archive data with lower write-cycle requirements.
The tarot cards are never wrong, but certainly interpretations of the cards can be.
(Note: IBM [Guidelines] prevent me from picking blogfights, so this post is only to set the record straight on some misunderstandings, point to some positive press about IBM's leadership in this area, and for me to provide a different point of view.)
First, let's set the record straight on a few things. The [RedPaper is still in draft form] under review, and so some information has not yet been updated to reflect the current situation.
You can have 16 or 32 SSD per DA pair. However, you can only have a maximum of 128 SSD drives total in any DS8100 or DS8300. In the case of the IBM DS8300 with 8 DA pairs, it makes more senseto spread the SSD out across all 8 pairs, and perhaps this is what confused BarryB.
Yes, you can order an all-SSD model of the IBM DS8000 disk system. I don't see anywhere in the RedPaper that suggests otherwise, and I have confirmed with our offering manager that this is the case.
The 73GB and 146GB are freshly manufactured from STEC. The 146GB drive and 200GB drives are actually the same drive but just formatted differently. The 200GB format does not offer as much spare capacity for wear-leveling, and are therefore intended only for read-intensive workloads. (Perhaps EMC wants you to find this out the hard way so that you replace them more often???) These reduced-spare-capacity formats may not be appropriate with some write-intensive workloads. Don't let anyone from EMC try to misrepresent the 73GB or 146GB drives from STEC as older, obsolete, collecting dust in a warehouse, or otherwise no longer manufactured by STEC.
You can relocate data from HDD to SSD using "Data Set FlashCopy", a feature that does not involve host-based copy services, does not consume any MIPS on your System z mainframe, and is performed inside the DS8000 disk system. You can also use host-based copy services as well, but it is not the only way.
You can use any supported level of z/OS with SSD in the IBM DS8000. There is ENHANCED support mentioned in the RedPaper that you get only with z/OS 1.8 and above, allowing you to create automation policies that place data sets onto SSD or non-SSD storage pools. This synergy makes SSD with IBM DS8000 superior to the initial offerings that EMC had offered without this OS support.
I find it amusing that BarryB's basic argument is that IBM's initial release of SSD disk on DS8000 is less than what the potential architecture could be extended to support much more. Actually, if you look at EMC's November release of Atmos, as well as their most recent announcement of V-Max, they basically say the same thing "Stay Tuned, this is just our initial release, with various restrictions and limitations, but more will follow." Architecturally, IBM DS8000 could support a mix of SSD and non-SSD on the same DA pairs, could support RAID6 and RAID10 as well, and could support larger capacity drives or use higher-capacity read-intensive formats. These could all be done via RPQ if needed, or in a follow-on release.
BarryB's second argument is that IBM is somehow "throwing cold water" on SSD technology. That somehow IBM is trying to discourage people from using SSD by offering disk systems with this technology. IBM offered SSD storage on BladeCenter servers LONG BEFORE any EMC disk system offering, and IBM continues to innovate in ways that allow the best business value of this new technology. Take for example this 24-page IBM Technical Brief:[IBM System z® and System Storage DS8000:Accelerating the SAP® Deposits Management Workload With Solid State Drives]. It is full of example configurations that show that SSD on IBM DS8000 can help in practical business applications. IBM takes a solution view, and worked with DB2, DFSMS, z/OS, High Performance FICON (zHPF), and down the stack to optimize performance to provide real business value innovation. Thanks to this synergy,IBM can provide 90 percent of the performance improvement with only 10 percent of the SSD disk capacity as EMC offerings. Now that's innovative!
The price and performance differences between FC and SATA (what EMC was mostly used to) is only 30-50 percent. But the price and performance differences between SSD and HDD is more than an order of magnitude in some cases 10-30x, similar to the differences between HDD and tape. Of course, if you want hybrid solutions that take best advantage of SSD+HDD, it makes more sense to go to IBM, the leading storage vendor that has been doing HDD+Tape hybrid solutions for the past 30 years. IBM understands this better, and has more experience dealing with these orders of magnitude than EMC.
But don't just take my word for it. Here is an excerpt from Jim Handy, from [Objective Analysis] market research firm, in a recent Weekly Review from [Pund-IT] (Volume 5, Issue 23--May 6, 2009):
"What about IBM? One thing that we are finding is that IBM really “Gets It” in the area offlash in the data center. Readers of the Pund-IT Review will not only recall that IBM Researchpushed its SSD-based “Quicksilver” storage system to one million IOPS using Fusion-ioflash-based storage, but they also may have noticed that the recent MySQL and mem-cachedappliances recently introduced by Schooner Information Technology are both flash-enableddevices introduced in partnership with IBM. Ironically, while other OEMs are takingthe cautious approach of introducing a standard SSD option to their systems first, IBM appearsto have been working on several approaches simultaneously to bring flash to thedata center not only in SSDs, but in innovative ways as well."
As for why STEC put out a press release on their own this week without a corresponding IBM press release, I can only say that IBM already announced all of this support back in February, and I blogged about it in my post [Dynamic Infrastructure - Disk Announcements 1Q09]. This is not the first time one of IBM's suppliers has tried to drum up business in this manner. Intel often funds promotions for IBM System x servers (the leading Intel-based servers in the industry) to help drive more business for their Xeon processor.
So, BarryB, perhaps its time for you to take out your green pen and work up another one of your all-too-common retraction and corrections.[Read More]
Well, it's Tuesday again, and that means more IBM announcements!
Today, IBM announced the enhanced IBM System Storage DS3200 disk system.It is in our DS3000 series, the DS3200 is SAS-attach, DS3300 is iSCSI-attach, and DS3400 is FC-attach. All of them support up to 48 drives, which can be a mix of SAS and SATA drives.
The DS3200 supports the following operating environments (see IBM's [Interop Matrix] for details):
Linux (both Linux-x86 and Linux on POWER)
With today's announcements, the DS3200 can be used to boot from, as well as contain data. This is ideal to combine with IBM BladeCenter. With the IBM BladeCenter you can have 14 blades, either x86 or POWER based processors, attached to a DS3200 via SAS switch modules in the back of the chassis.
Let's take an example of how this can be used for a Scale-Out File Services[SoFS] deployment.
First, we start with servers. We can have either three [IBM System x3650] servers, but this would use up all six of the direct-attach ports. Instead, we'll choose the [BladeCenter H chassis], with three HS21 blades for SoFS, and that leaves us with eleven empty blade slots we could put in a management node, or other blades to run applications.
SAS connectivity modules
The IBM BladeCenter [SAS Connectivity Module] allows the blade servers to connect to a DS3200. Two of them fit right in the back of the BladeCenter chassis, providing full redundancy without consuming additional rack space.
DS3200 and EXP3000 expansion drawers
We'll have one DS3200 controller with twelve internal drives, and three expansion EXP3000 drawers with twelve drives each, for a total of 48 drives. Using 1TB SATA, this would be 48 TB raw capacity.
The end result? You get a 48TB NAS scalable storage solution, supporting up to 7500 concurrent CIFS and NFS users, with up to 700 MB/sec with large block transfers. By using BladeCenter, you can expand performance by adding more blades to the Chassis, or have some blades running SAP or Oracle RAC have direct read/write access to the SoFS data.
Just another example on how IBM can bring together all the components of a solution to provide customer value!
Storage Networking World conference is over, and the buzz from the analysts appears to be focused onXiotech's low-cost RAID brick (LCRB) called Intelligent Storage Element, or ISE.
(Full disclosure: I work for IBM, not Xiotech, in case there weren't enough IBM references on this blog page to remindyou of that. I am writing this piece entirely from publicly available sources of information, and notfrom any internal working relationships between IBM and Xiotech. Xiotech is a member of the IBM BladeCenteralliance and our two companies collaborate together in that regard.)
Fellow blogger Jon Toigo in his DrunkenData blog posted [I’m Humming “ISE ISE Baby” this Week] and then a follow-up post[ISE Launches]. I looked up Xiotech's SPC-1benchmark numbers for the Emprise 5000 with both 73GB and 146GB drives, and at 8,202 IOPS per TB, does not seem to be as fast as IBM SAN VolumeControllers 11,354 IOPS per TB. Xiotech offers an impressive 5 year warranty (by comparison, IBM offers up to 4 years, and EMC I think is stillonly 90 days).Jon also wrote a review in [Enterprise Systems]that goes into more detail about the ISE.
Fellow blogger Robin Harris in his StorageMojo blog posted [SNW update - Xiotech’s ISE and the dilithium solution], feeling that Xiotech should win the "Best Announcement at SNW" prize. He points to the cool video on the[Xiotech website]. In that video, they claim 91,000 IOPS.Given that it took forty(40) 73GB drives (or 4 datapacs) in the previous example to get 8,202 IOPS for 1TB usable, I am guessing the 91,000 IOPS is probably 44 datapacs (440 drives) glommed together, representing 11TB usable.The ISE design appears very similar to the "data modules" used in IBM's XIV Nextra system.
Fellow blogger Mark Twomey from EMC in his StorageZilla blog posted[Xiotech: Industry second]correctly points out that Xiotech's 520-byte block (512 bytes plus extra for added integrity) was not the firstin the industry. Mark explains that EMC CLARiiON had this since the early 1990's, and implies in the title that this must have been the first in the industry, making Xiotech an industry second. Sorry Mark, both EMC and Xiotech were late to the game. IBM had been using 520-byte blocksize on its disk since 1980 with the System/38. This system morphed to the AS/400, and the blocksize was bumped up to 522 bytes in 1990, and is now called the System i, where the blocksize was bumped up yet again to 528 bytes in 2007.
While IBM was clever to do this, it actually means fewer choices for our System i clients, being only able to chooseexternal disk systems that explicitly support these non-standard blocksize values, such as the IBM System Storage DS8000and DS6000 series. (Yes, BarryB, IBM still sells the DS6000!) The DS6000 was specifically designed with the System i and smaller System z mainframes in mind, and in that niche does very well. Fortunately, as I mentioned in my February post [Getting off the island - the new i5/OS V6R1], IBM has now used virtualization, in the form of the VIOS logical partition, to allow i5/OS systems to attach to standard 512-byte block devices, greatly expanding the storage choices for our clients.
(Side note: SNW happens twice per year, so the challenge is having something new and fresh to talk about each time. While Andy Monshaw, General Manager of IBM System Storage, highlighted some of the many emerging technologies in his keynote address, IBM shipped on many of them prior to his last appearance in October 2007: thin provisioning in the IBM System Storage N series, deduplication in the IBM System Storage N series Advanced Single Instance Storage (A-SIS) feature, and Solid State Disk (SSD) drives in the IBM BladeCenter HS21-XM models. Of course, not everyone buys IBM gear the first day it is available, and IBM is not the only vendor to offer these technologies. My point is that for many people, these are still not yet deployed in their own data center, and so they are still in the future for them. However, since these IBM deliveries happened more than six months ago, they're old news in the eyes of the SNW attendees. While those who follow IBM closely would know that, others like[Britney Spears] may not.)
Back in the 1990s, when IBM was developing the IBM SAN Volume Controller (SVC), we generically called the managed disk arrays that were being virtualized by the SVC as "low-cost RAID brick" or LCRB. The IBM DS3400 is a good example of this. However, as we learned, SVC is not just for LCRB, it adds value in front of all kinds of disk systems, including the not-so-low-cost EMC DMX and IBM DS8000 disk systems. ISE might make a reasonable back-end managed disk device for IBM SVC to virtualize. This gives you the new cool features of Xiotech's ISE, with IBM SVC's faster performance, more robust functionality and advanced copy services.
Next week, I'll be in South America in meetings with IBM Business Partners and storage sales reps.
EMC Corporation (NYSE:EMC) today announced it has been positioned as a leader in the Forrester Wave™: Enterprise Open Systems Virtual Tape Library (VTL), Q1 2008 by Forrester Research, Inc. (January 31, 2008), an independent market and technology research firm. EMC achieved a position as a leader in the Forrester Wave report on virtual tape libraries based on the largest installed base of the EMC® Disk Library family of systems, its broad ecosystem interoperability. Virtual tape libraries emulate tape drives and work in conjunction with existing backup software applications, enabling fast backup and restoration of data by using high-capacity, low-cost disk drives.
EMC was the first major vendor in the open systems virtual tape library market as it introduced the EMC Disk Library in April 2004 and today is a leading provider of open systems virtual tape solutions, with systems that are designed for businesses and organizations of all sizes.
While the press release implies that "EDL equals VTL", Chuck tries to explain they are in fact very different. Here is an excerpt from his blog post:
Virtual Tape Libraries vs. Disk Libraries
As many of you know, VTLs have been around for a while. They use disk as a cache -- they buffer the incoming backup streams, do some housekeeping and stacking, then turn around and write tape efficiently. When you go to restore, you're usually coming back off of tape, unless the backup image in question is sitting in the disk cache.
Now, there is nothing wrong with the VTL approach, but it was conceived in a time when disks were horribly expensive. It was also pretty clear to many of us that disks were going to be a whole lot cheaper in the near future, and this fundamental assumption wouldn't be valid for much longer.
I kept thinking in terms of disk as a direct target for a backup application. No modifications to the backup application. Native speed of sequential disks for both backup and restore. Tape positioned as a backup to the backup. Use the strengths of the underlying array (e.g. CLARiiON) for performance, availability, management, etc.
We ended up calling the concept a "disk library" to differentiate from the VTLs that had come before it. It was a different value proposition and offering, based on the emergence of lower-cost disk media.
... It's nice to see we're at 1,100+ customers, and still going strong.
For those new to the blogosphere, there is a difference between "Press Releases" as formalcorporate communications versus "Blog Posts" which are informal opinions of the individual blogger, whichmay or may not match exactly the views of their respective employer.As we've learned many times before, one should not treat termslike "first" or "leader" in corporate press releases literally! Let's explore each.
Was EDL the first "open systems" Virtual Tape Library?
This is implied by the Forrester report. Chuck mentions the "VTLs that had came before it" in his blog, and many people are aware that IBM and StorageTek had introduced mainframe-attached VTLs in the 1990s. But what about VTL for "open systems"?
(Hold aside for the moment that IBM System zmainframe is an open system itself, with z/OS certified as a bona fide UNIX operating system by the [the Open Group] standards body. Most analysts and research firms usually refer only to the non-mainframe versions of UNIX and Windows. Alternative definitions for "open systems" can be foundin [Web definitions or Wikipedia]. I will assume Forrester meantnon-mainframe servers.)
IBM announced AIX non-mainframe attachment via SCSI connectivity to the IBM 3494 Virtual Tape Server (VTS) on Feb 16, 1999, with general availability in May 28, 1999. That's nearly FIVE YEARS before the April 2004 introduction of EDL. IBM VTS support for Sun Solaris and Microsoft Windows came shortly thereafter in November 2000, and support for HP-UX a bit later in June 2001. One of my 17 patents is for the software inside the IBM 3494 VTS, so like Chuck, I can takesome pride in the success of a successful product.
(I don't remember if StorageTek, which was subsequently acquired by Sun, had ever supported non-mainframe operating systems with their Virtual Storage Manager[VSM] offering, but if they did, I am sure it was also before EMC.)
Last week, another EMC blogger, BarryB (aka [the Storage Anarchist]),took me to task in comments on my post [IBM now supports 1TB SATA drives]. He felt that IBM should not claim support, given that the software inside the IBM System Storage N series is developed by NetApp. He compared this to the situation of HP and Sun re-badging the HDS USP-V disk system. If someone else wrote the software, BarryB opines, IBM should not claim credit for it. I tried to explain how IBM provides added value and has full-time employees dedicated to N series development and support, butdoubt I have changed his mind.
Why do I bring that up? Because the EMC Disk Library runs OEM software from FalconStor. Basically EMC is assembling a hardware/software solution with components provided from OEM suppliers. Hmmm? Sound familiar? Who is calling the kettle black?
If there is a clear winner here, it is FalconStor itself.Perhaps one of the worst kept industry secrets is that FalconStor software is also used in VTL offerings from Sun, Copan, and IBM, the latter embodied as the [IBM TS7520 Virtualization Engine] offering. If you like the concept of an EDL,but prefer instead one-stop shopping from an "information infrastructure" vendor, IBM can offer the TS7520 along with servers, software and services for a complete end-to-end solution.
Can EMC claim to be "a leader" in Virtual Tape Libraries?
During the measured quarter, IBM shipped its 10 millionth LTO-4 tape drive cartridge to Getty Images, the world's leading creator and distributor of still imagery, footage and multi-media products, as well as a recognized provider of other forms of premium digital content, including music. Getty Images is using the LTO-4 drives as part of a tiered infrastructure of IBM disk and tape solutions that help support the backup needs of their digital imagery;
IBM shipped more than 1,500 Petabytes of tape storage in Q3'07 alone;
During Q3'07, IBM shipped the 10,000th IBM System Storage TS3500 Tape Library. The TS3500 is a highly scalable tape library with support from 1 to 192 tape drives and up to 6,400 cartridge slots for open system, mainframe and virtual tape system attachment.
Let's take a look at the numbers. IBM has sold over 5,400 virtual tape libraries. Sun/STK has sold over 4,000 virtual tape libraries. Both are drastically more than the 1,100 mentioned in Chuck's post. Does IDC recognize EMC in third place? No, EMC chooses instead to declare EDL as disk arrays (probably toprop up their IDC "Disk Tracker" numbers), so they don't even earn an honorable mention under the virtual tape librarycategory. This of course includes the number of mainframe-attached models from IBM and Sun/STK. So, if EMC did call these tape systems instead, they might showup in third place, and as such EMC could claim to be "a leader" in much the same way an athlete can claim to be an "Olympic medalist" winning the bronze for third place. (If you limit thecount to just the FalconStor-based models from IBM, EMC, Sun and Copan, then EMC moves up to first or second, but then press release titles like "EMC a Leader in FalconStor-based non-mainframe Virtual Tape Libraries" can get too confusing.)
Chuck, if you are reading this, I feel you have every right to celebrate your involvement with the EDL. Despite having common software and hardware components, both IBM and EMC can rightfully declare their own unique value-add through their respective VTL offerings. Like the IBM N series, the EMC Disk Library is not diminished by the fact the software was written by someone else. BarryB might disagree.
Fellow Blogger BarryB mentions "chunk size" in his post [Blinded by the light],as it relates to Symmetrix Virtual Provisioning capability. Here is an excerpt:
I mean, seriously, who else but someone who's already implemented thin provisioning would really understand the implications of "chunk" size enough to care?
For those of you who don't know what the heck "chunk size" means (now listen up you folks over at IBM who have yet to implement thin provisioning on your own storage products), a "chunk" is the term used (and I think even trademarked by 3PAR) to refer to the unit of actual storage capacity that is assigned to a thin device when it receives a write to a previously unallocated region of the device.
For reference, Hitachi USP-V uses I think a 42MB chunk, XIV NEXTRA is definitely 1MB, and 3PAR uses 16K or 256K (depending upon how you look at it).
Thin Provisioning currently offered in IBM System Storage N serieswas technically "implemented" by NetApp, and that the Thin Provisioning that will be offered in our IBM XIV Nextrasystems will have been acquired from XIV. Lest I remind you that many of EMC's products were developed by other companies first, then later acquired by EMC, so no need for you to throw rocks from your glass houses in Hopkington.
"Thin provisioning" was first introduced by StorageTek in the 1990's and sold by IBM under the name of RAMAC Virtual Array (RVA). An alternative approach is "Dynamic Volume Expansion" (DVE). Rather than giving the host application a huge 2TB LUN but actually only use 50GB for data, DVE was based on the idea that you only give out 50GB they need now, but could expand in place as more space was required. This was specifically designed to avoid the biggest problem with "Thin Provisioning" which back then was called "Net Capacity Load" on the IBM RVA, but today is now referred to as "over-subscription". It gave Storage Administrators greater control over their environment with no surprises.
In the same manner as Thin Provisioning, DVE requires a "chunk size" to work with. Let's take a look:
On the DS4000 series, we use the term "segment size", and indicate that the choice of a segment size can have some influence on performance in both IOPS and throughput. Smaller segment sizes increase the request rate (IOPS) by allowing multiple disk drives to respond to multiple requests. Large segment sizes increase the data transfer rate(Mbps) by allowing multiple disk drives to participate in one I/O request. The segment size does not actually change what is stored in cache, just what is stored on the disk itself.It turns out in practice there is no advantage in using smaller sizes with RAID 1; only in a few instances does this help with RAID-5 if you can writea full stripe at once to calculate parity on outgoing data. For most business workloads, 64KB or 128KB are recommended. DVE expands by the same number of segments across all disks in the RAID rank, so for example in a 12+P rank using 128KB segment sizes, the chunk size would be thirteen segments, about 1.6MB in size.
SAN Volume Controller
On the SAN Volume Controller, we call this "extent size" and allow it to be various values 64MB to 512MB. Initially,IBM only managed four million extents, so this table was used to explain the maximum amount that could be managedby an SVC system (up to 8 nodes) depending on extent size selected.
IBM thought that since we externalized "segment size" on the DS4000, we should do the same for the SANVolume Controller. As it turned out, SVC is so fast up in the cache, that we could not measure any noticeable performance difference based on extent size. We did have a few problems. First, clients who chose 16MB andthen grew beyond the 64TB maximum addressable discovered that perhaps they should have chosen something larger.Second, clients called in our help desk to ask what size to choose and how to determine the size that was rightfor them. Third, we allowed people to choose different extent sizes per managed disk group, but that preventsmovement or copies between groups. You can only copy between groups that use the same extent size. The generalrecommendation now is to specify 256MB size, and use that for all managed disk groups across the data center.
The latest SVC expanded maximum addressability to 8PB, still more than most people have today in their shops.
Getting smarter each time we introduce new function, we chose 1GB chunks for the DS8000. Based on a mainframebackground, most CKD volumes are 3GB, 9GB, or 27GB in size, and so 1GB chunks simplified this approach. Spreadingthese 1GB chunks across multiple RAID ranks greatly reduced hot-spots that afflict other RAID-based systems.(Rather than fix the problem by re-designing the architecture, EMC will offer to sell you software to help you manually move data around inside the Symmetrix after the hot-spot is identified)
Unlike EMC's virtual positioning, IBM DS8000 dynamic volume expansion does work on CKD volumes for our System z mainframe customers.
The trade-off in each case was between granularity and table space. Smaller chunks allow finer control on the exact amount allocated for a LUN or volume, but larger chunks reduced the number of chunks managed. With our advanced caching algorithms, changes in chunk size did not noticeably impact performance. It is best just to come up with a convenient size, and either configure it as fixed in the architecture, or externalize it as a parameter with a good default value.
Meanwhile, back at EMC, BarryB indicates that they haven't determined the "optimal" chunk size for their newfunction. They plan to run tests and experiments to determine which size offers the best performance, and thenmake that a fixed value configured into the DMX-4. I find this funny coming from the same EMC that won't participate in [standardized SPC benchmarks] because they feel that performance is a personal and private matter between a customer and their trusted storage vendor, that all workloads are different, and you get the idea. Here's another excerpt:
Back at the office, they've taking to calling these "chunks" Thin Device Extents (note the linkage back to EMC's mainframe roots), and the big secret about the actual Extent size is...(wait for it...w.a.i.t...for....it...)...the engineers haven't decided yet!
That's right...being the smart bunch they are, they have implemented Symmetrix Virtual Provisioning in a manner that allows the Extent size to be configured so that they can test the impact on performance and utilization of different sizes with different applications, file systems and databases. Of course, they will choose the optimal setting before the product ships, but until then, there will be a lot of modeling, simulation, and real-world testing to ensure the setting is "optimal."
Finally, BarryB wraps up this section poking fun at the chunk sizes chosen by other disk manufacturers. I don't knowwhy HDS chose 42MB for their chunk size, but it has a great[Hitchiker's Guide to the Galaxy]sound to it, answering the ultimate question to life, the universe and everything. Hitachi probably went to theirDeep Thought computer and asked how big should their "chunk size" be for their USP-V, and the computer said: 42.Makes sense to me.
I have to agree that anything smaller than 1MB is probably too small. Here's the last excerpt:
Now, many customers and analysts I've spoken to have in fact noted that Hitachi's "chunk" size is almost ridiculously large; others have suggested that 3PAR's chunks are so small as to create performance problems (I've seen data that supports that theory, by the way).
Well, here's the thing: the "right" chunk size is extremely dependent upon the internal architecture of the implementation, and the intersection of that ideal with the actual write distribution pattern of the host/application/file system/database.
So my suggestion to EMC is, please, please, please take as much time as you need to come up with the perfect"chunk size" for this, one that handles all workloads across a variety of operating systems and applications, from solid-state Flash drives to 1TB SATA disk. Take months or years, as long as it takes. The rest of the world is in no hurry, as thin provisioning or dynamic volume expansion is readily available on most other disk systems today.
Maybe if you ask HDS nicely, they might let you ask their computer.
Well, it's 2008, which could mark the end to RAID5 and mark the beginnings of a new disk storagearchitecture. IBM starts the year with exciting news, acquiring new disk technology from a smallstart-up called XIV, led by former-EMCer Moshe Yanai. Moshe was ousted publicly in 2001 from hisposition as EMC's VP of engineering, and formed his own company. It didn't take long for EMC bloggersto poke fun at this already. Mark Twomey, in his StorageZilla blog, had mentioned XIV before back in August,[XIV], and again todayin [IBM Buys XIV].
To address the new requirements associated with next generation digital content, IBM chose XIV and its NEXTRA™ architecture for its ability to scale dynamically, heal itself in the event of failure, and self-tune for optimum performance, all while eliminating the significant management burden typically associated with rapid growth environments. The architecture also is designed to automatically optimize resource utilization of all the components within the system, which can allow for easier management and configuration and improved performance and data availability.
"We are pleased to become a significant part of the IBM family, allowing for our unique storage architecture, our engineers and our storage industry experience to be part of IBM's overall storage business," said Moshe Yanai, chairman, XIV. "We believe the level of technological innovation achieved by our development team is unparalleled in the storage industry. Combining our storage architectural advancements with IBM's world-wide research, sales, service, manufacturing, and distribution capabilities will provide us with the ability to have these technologies tackle the emerging Web 2.0 technology needs and reach every corner of the world."
The NEXTRA architecture has been in production for more than two years, with more than four petabytes of capacity being used by customers today.
Current disk arrays were designed for online transaction processing (OLTP) databases. The focus was onusing fastest most expensive 10K and 15K RPM Fibre Channel drives, with clever caching algorithmsfor quick small updates of large relational databases. However, the world is changing, and peoplenow are looking for storage designed for digital media, archives, and other Web 2.0 applications.
One problem that NEXTRA architecture addresses is RAID rebuild. In a standard RAID5 6+P+S configuration of 146GB 10K RPM drives, the loss of one disk drive module (DDM) was recovered by reconstructing the data from parity of the other drives onto the spare drive. The process took46 minutes or longer, depending on how busy the system was doing other things. During this time,if a second drive in the same rank fails, all 876GB of data are lost. Double-drive failures are rare,but unpleasant when they happen, and hopefully you have a backup on tape to recover the data from.Moving to slower, less expensive SATA drives made this situation worse. The drives have highercapacity, but run at slower speeds. When a SATA drive fails in a RAID5 array, it could take severalhours to rebuild, and that is more time exposure for a second drive failure. A rebuild for a 750GBSATA drive would take five hours or more,with 4.5 TB of data at risk during the process if a second drive failure occurs.
The Nextra architecture doesn't use traditional RAID ranks or spare DDMs. Instead, data is carved up into 1MBobjects, and each object is stored on two physically-separate drives. In the event of a DDM loss, allthe data is readable from the second copies that are spread across hundreds of drives. New copies aremade on the empty disk space of the remaining system. This process can be done for a lost 750GB drive in under20 minutes. A double-drive failure would only lose those few objects that were on both drives, so perhaps1 to 2 percent of the total data stored on that logical volume.
Losing 1 to 2 percent of data might be devastating to a large relational database, as this could impactthe entire access to the internal structure. However, this box was designed for unstructuredcontent, like medical images, music, videos, Web pages, and other discrete files. In the event of a double-drivefailure, individual files would be recovered, such as with IBM Tivoli Storage Manager backup software.
IBM will continue to offer high-speed disk arrays like the IBM System Storage DS8000 and DS4800 for OLTP applications, and offer NEXTRA for this new surge in digital content of unstructured data. Recognizing this trend, diskdrive module manufacturers will phase out 10K RPM drives, and focus on 15K RPM for OLTP, and low-speedSATA for everything else.
Update: This blog post was focused on the version of XIV box available as of January 2008 that was built by XIV prior to the IBM acquisition. IBM has since made a major revision, made available August 2008 thataddresses a variety of workloads, including database, OLTP, email, as well as digital content and unstructuredfiles. Contact your IBM or IBM Business Partner for the latest details!
Bottom line, IBM continues to celebrate the new year, while the EMC folks in Hopkington, MA will continue to nurse their hangovers. Now that's a good way to start the new year!
Array-based replication does have drawbacks; all externalised storage becomes dependent on the virtualising array. This makes replacement potentially complex. To date, HDS have not provided tools to seamlessly migrate away from one USP to another (as far as I am aware). In addition, there's the problem of "all your eggs in one basket"; any issue with the array (e.g. physical intervention like fire, loss of power, microcode bug etc) could result in loss of access to all of your data. Consider the upgrade scenario of moving to a higher level of code; if all data was virtualised through one array, you would want to be darn sure that both the upgrade process and the new code are going to work seamlessly...
The final option is to use fabric-based virtualisation and at the moment this means Invista and SVC. SVC is an interesting one as it isn't an array and it isn't a fabric switch, but it does effectively provide switching capabilities. Although I think SVC is a good product, there are inevitably going to be some drawbacks, most notably those similar issues to array-based virtualisation (Barry/Tony, feel free to correct me if SVC has a non-disruptive replacement path).
I would argue that the IBM System Storage SAN Volume Controller (SVC) is more like the HDS USP, and less like the Invista. Both SVC and USP provide a common look and feel to the application server, both provide additional cache to external disk, both are able to provide a consistent set of copy services.
IBM designed the SVC so that upgrades can occur non-disruptively. You can replace the hardware nodes, one node at a time, while the SVC system is up and running, without disruption to reading and writing data on virtual disk. You can upgrade the software, one node at a time, while the SVC system is up and running, without disruption to reading and writing data on virtual disk. You can upgrade the firmware on the managed disk arrays behind the SVC, again, without disruption to reading and writing data on virtual disk.
More importantly, SVC has the ultimate "un-do" feature. It is called "image mode". If for any reason you want to take a virtual disk out of SVC management, you migrate over to an "image mode" LUN, and then disconnect it from SVC. The "image mode" LUN can then be used directly, with all the file system data in tact.
I define "virtualization" as technology that makes one set of resources look and feel like a different set of resources with more desirable characteristics. For SVC, the more desirable characteristics include choice of multi-pathing driver, consistent copy services, improved performance, etc. For EMC Invista, the question is "more desirable for whom?" EMC Invista seems more designed to meet EMC's needs, not its customers. EMC profits greatly from its EMC PowerPath multi-pathing driver, and from its SRDF copy services, so it appears to have designed a virtualization offering that:
Continuesthe use of EMC Powerpath as a multi-pathing driver. SVC supports driversthat are provided at no charge to the customer, as well as those built-in to each operating system like MPIO.
and, continuesthe use of Array-based copy services like SRDF of the underlying disk. SVC providesconsistent copy services regardless of storage vendor being managed.
A post from Dan over at Architectures of Control explains the anti-social nature of public benches. City planners, in an effort to discourage homeless people from sleeping on benches in parks or sidewalks, design benches that are so uncomfortableto use, that nobody uses them. These included benches made of metal that are too hot or too cold during certainmonths, benches slanted at an angle that dump you on the ground if you lay down, or benches that have dividers sothat you must be in an upright seated position to use.
This is not a disparagement of split-path switch-based designs. Rather, EMC's specific implementation appears to be designed for it to continuevendor lock-in for its multi-pathing driver, continuevendor lock-in for its copy services when used with EMC disk, and only provide slightly improved data migration capability for heterogeneous storage environments. Other switch-based solutions, such as those from Incipient or StoreAge, had different goals in mind.
Sadly, my IBM colleague BarryW and I have probably spent more words discussing Invista than all eleven EMC bloggers combined this year. While everyone in the industry is impressed how often EMC can sell "me, too" products with an incredibly large marketing budget, EMC appears not to have set aside funds for the Invista.
If a customer could design the ideal "storage virtualization" solution that would provide them the characteristics they desire the most from storage resources, it would not be anything like an Invista. While there are pros and cons between IBM's SVC and HDS's TagmaStore offerings, the reason both IBM and HDS are the market leaders in storage virtualization is because both companies are trying to provide value to the customer, just in different ways, and with different implementations.
When new technologies are introduced to the marketplace, it is normal for customers to be skeptical.
My sister is a mechanical engineer, so when she needs to configure a part or component, she candesign it on the computer, and then use a "Rapid Prototyping Machine"that acts like a 3D printer, to generate a plastic part that matches the specifications. Some machinesdo this by taking a hunk of plastic and cutting it down to the appropriate shape, and others use glue andpowder to assemble the piece.
But not everything is that simple. Harry Beckwith deals with the issue of selling services and software featuresin his book "Selling the Invisible". How do you sell a service before it is performed? How do you sell a softwarefeature based on new technology that the customer is not familiar with?
Our good friends over at NetApp, our technology partners for the IBM System Storage N series, developed a"storage savings estimator" tool that can provide good insight into the benefits of Advanced Single InstanceStorage (A-SIS) deduplication feature.
I decided to run the tool to analyze my own IBM Thinkpad C: drive (Windows operating system and programs) and D: drive ("My Documents" folder containing all my data files) to see how much storage savings thetool would estimate. Here are my results:
WINXP-C-07G (C: drive)Total Number of Directories: 1272Total Number of Files: 56265Total Number of Symbolic Links: 0Total Number of Hard Links: 41996Total Number of 4k Blocks: 2395884Total Number of 512b Blocks: 18944730Total Number of Blocks: 2395884Total Number of Hole Blocks: 290258Total Number of Unique Blocks: 1611792Percentage of Space Savings: 20.61Scan Start Time: Wed Sep 5 14:37:06 2007Scan End Time: Wed Sep 5 14:53:51 2007
WINXP-D-07H (D: drive)Total Number of Directories: 507Total Number of Files: 7242Total Number of Symbolic Links: 0Total Number of Hard Links: 11744Total Number of 4k Blocks: 3954712Total Number of 512b Blocks: 31610595Total Number of Blocks: 3954712Total Number of Hole Blocks: 3204Total Number of Unique Blocks: 3524605Percentage of Space Savings: 10.79Scan Start Time: Wed Sep 5 14:21:16 2007Scan End Time: Wed Sep 5 14:34:30 2007
I am impressed with the results, and have a better understanding of the way A-SIS works. A-SIS looks at every4kB block of data, and creates a "fingerprint", a type of hash code of the contents. If two blocks have different "fingerprints", then the contents are known to be different. If two blocks have the same fingerprint, it is mathematically possible for them to be unique in content, so A-SIS schedules a byte-for-byte comparison to be sure they are indeed the same. This might happen hours after the block is initially written to disk, but is a much safer implementation, and does not slow down the applications writing data.
(In an effort to provide support "real time" as data was being written, earlier versions of deduplication
had to either assume that a hash collision was a match, or take time to perform the byte-for-byte comparisonrequired during the write process. Doing this byte-for-byte comparison when the device is the busiest doingwrite activities causes excessive undesirable load on the CPU.)
The estimator tool runs on any x86-based Laptop, personal computer or server, and can scan direct-attached, SAN-attached, or NAS-attached file systems. If you are a customer shopping around for deduplication, ask your IBM pre-sales technical support, storage sales rep, or IBM Business Partner to analyze your data. Tools like this can help make a simple cost-benefit analysis: the cost of licensing the A-SIS software feature versus the amount of storage savings.
Wrapping up my week's theme of "diversity", with posts on a diverse set of topics,today I will suggest ways to spendyour time while you are walking 10,000 steps per day, as recommended by the authorsof the book "You: On a Diet".
(If you thought this was about the 10,000 steps it might take to implement a storage solution, you should switch over to IBM as your storage vendor. For example, the DS3200 and DS3400 can beimplemented in as little as SIX steps. That's pretty cool.)
Blogs like Lifehacker are an excellent resource for neat littletips and tricks to help you throughout your day, like how to use your iPod, cell phone or computer better, for example. These suggestions are based on the idea that you can walk your 10,000 steps with access to an iPod and cell phone.
Learning a language
... or refreshing yourself on a language you might not have spoken in a while. In addition to formal audio-based lessons from Pimsleur, there are podcasts you can get for various languages. In preparation for my upcoming trip to Japan and China, I have been listening to JapanesePod101.com and ChinesePod.com which have quick lessons that complement the formal training.This Lifehacker postindicates there are similar ones for French, Spanish, Italian, and Brazillian Portuguese.
Practicing your presentation
Walking while practicing your 30-60 minute presentation would be good exercise.MicroPersuasion explains how to turn your iPod into the ultimate PowerPoint accessory, and this article in PlayListmag.com providesthe steps to get a PowerPoint presentation onto your iPod. I did this, and the slides are found underPhotos->Photo Library. The images are small, but heck, they are your charts and you should recognize themwell enough to remind yourself what to say on each slide.Also, I am able to record my practice sessions using MP3 Recorder and listen as I page through each slide. (In theory, you can use your iPod to present your slides to your audience, plugging the iPod directly into the laptop projector, instead of a laptop, using cables available at your local Apple store, and use the iPod controls as your forward/backward remote.)
Working your To-Do list
You can download your to-do list to your iPod. I use BackPackIt from 37 Signals. You can sign up for a free account, or upgrade to a paid account, and have anamazingly simple browser-based tool to develop your to-do lists, one for each project or aspect of your life. Oncedone, the list can be emailed to you as plain text. Enable your iPod as an "external disk drive" and copy this text file to your NOTES directory on the iPod drive. Voila! You can now read your to-do list! (I could also send it to my cell phone, using firstname.lastname@example.org, but I find the iPod easier to read and navigate)
Think of something to add? Send an email from your cell phone. With BackPackit, I can send an email that will directly add my text as a note or todo list item. On my phone, this is simply sending a text message to "500" with text like:
"email@example.com todo # buy bread".
The hash mark (#) separates the subject line from the body of the email, and this is how Backpackit knows its a todo item or a note. If you pre-program the huge email address in advance on your phone, then it isn't as bad as it looks. It will be on your packpackit page the next time you log in.
Well, that's three suggestions. The next time you complain that there is no time to walk, you now have no excuse.
In general, people agree that IBM, HP and EMC are the top three vendors in storage,with HDS, Sun and Dell rounding out the top six.
The fun begins when a respected analyst like IDC Corp. publishes their calculations,and individual vendors re-swizzle the results because they are not happy with theirfindings.
I thought it would be helpful to illustrate how this all works. First, you need to comeup with a defintion of what you are going to count. You could count units sold, revenue dollars, or capacity Terabytes, or some other generally accepted metric.
Next, you need to define what's in and what's out. For example, you can say "storage"which would include both disk drives and tape drives, both internal to servers, orexternal to servers, or you can choose a more narrow definition, say external disksystems, which might suit you better if you aren't in the tape business, and don't sell servers.
By some definitions, my Apple iPod, Motorolla cell phone, and Canon digital camera,could all be counted as external disk systems, as they all connect via USB cableto my IBM laptop, and act like a disk drive to my Windows operating system, allowingme to read and write data back and forth. It is necessary to define exactly what you plan to include,and what to exclude, based on the reported numbers available.
The last rule is that nothing gets double-counted. In our complicated industry ofmanufacturers and vendors, sometimes storage is manufactured by one company, but soldby another, typically under the vendor's brand, not the manufacturer's brand. Youcan either count manufactured units, or vendor units, but you can't mix and match.
IBM is both manufacturer and vendor. However, IDC only counts vendor units, so storagemanufactured by someone else, but sold by IBM is counted as IBM, and storage manufacturedby IBM but branded by someone else goes to that other vendor. Likewise, HP and Sun re-brandHitachi storage, and Dell re-brands EMC storage.
EMC would like to treat all EMC-manufactured storage re-branded by Dell as EMC vended storage,so that it can move up in the ratings. But Dell wants to count it too, so that it can appearin the top six. You can't have it both ways.
But are these ratings just "bragging rights"? Not always. When big purchases are planned fornew projects, or a client decides its time to throw out the current vendor and shop for a newone, the ratings could influence that decision. In that regard, IDC 4Q05 Storage Tracker reportedIBM as number one over all in storage hardware at the end of 2005, which includes both internal and external disk systems, as well as tape drives sold under the IBM brand, based on dollar revenues. By this method of counting, HP came in at number 2, EMC at number 3, and the rest round out thetop six as before.
In the end, this is just one factor when deciding which brand to choose for your storage needs.
This month (September, 2006) marks our 50th anniversary of the disk system. The first disk system was the 350 Disk Storage Unit, designed to attach to the IBM 305 RAMAC mainframe computer, both introduced to the world in September, 1956.
Tonight PBS plans to air Season 38, Episode 6 of NOVA, titled [Smartest Machine On Earth]. Here is an excerpt from the station listing:
"What's so special about human intelligence and will scientists ever build a computer that rivals the flexibility and power of a human brain? In "Artificial Intelligence," NOVA takes viewers inside an IBM lab where a crack team has been working for nearly three years to perfect a machine that can answer any question. The scientists hope their machine will be able to beat expert contestants in one of the USA's most challenging TV quiz shows -- Jeopardy, which has entertained viewers for over four decades. "Artificial Intelligence" presents the exclusive inside story of how the IBM team developed the world's smartest computer from scratch. Now they're racing to finish it for a special Jeopardy airdate in February 2011. They've built an exact replica of the studio at its research lab near New York and invited past champions to compete against the machine, a big black box code -- named Watson after IBM's founder, Thomas J. Watson. But will Watson be able to beat out its human competition?"
Like most supercomputers, Watson runs the Linux operating system. The system runs 2,880 cores (90 IBM Power 750 servers, four sockets each, eight cores per socket) to achieve 80 [TeraFlops]. TeraFlops is the unit of measure for supercomputers, representing a trillion floating point operations. By comparison, Hans Morvec, principal research scientist at the Robotics Institute of Carnegie Mellon University (CMU) estimates that the [human brain is about 100 TeraFlops]. So, in the three seconds that Watson gets to calculate its response, it would have processed 240 trillion operations.
Several readers of my blog have asked for details on the storage aspects of Watson. Basically, it is a modified version of IBM Scale-Out NAS [SONAS] that IBM offers commercially, but running Linux on POWER instead of Linux-x86. System p expansion drawers of SAS 15K RPM 450GB drives, 12 drives each, are dual-connected to two storage nodes, for a total of 21.6TB of raw disk capacity. The storage nodes use IBM's General Parallel File System (GPFS) to provide clustered NFS access to the rest of the system. Each Power 750 has minimal internal storage mostly to hold the Linux operating system and programs.
When Watson is booted up, the 15TB of total RAM are loaded up, and thereafter the DeepQA processing is all done from memory. According to IBM Research, "The actual size of the data (analyzed and indexed text, knowledge bases, etc.) used for candidate answer generation and evidence evaluation is under 1TB." For performance reasons, various subsets of the data are replicated in RAM on different functional groups of cluster nodes. The entire system is self-contained, Watson is NOT going to the internet searching for answers.
Continuing my quest to "set the record straight" about [IBM XIV Storage System] and IBM's other products, I find myself amused at some of the FUD out there. Some are almost as absurd as the following analogy:
Humans share over 50 percent of DNA with bananas. [source]
If you peel a banana, and put the slippery skin down on the sidewalk outside your office building, it couldpose a risk to your employees
If you peel a human, the human skin placed on the sidewalk in a similar manner might also pose similar risks.
Mr. Jones, who applied for the opening in your storage administration team, is a human being.
You wouldn't hire a banana to manage your storage, would you? This might be too risky!
The conclusion we are led to believe is that hiring Mr. Jones, a human being, is as risky as puttinga banana peel down on the sidewalk. Some bloggers argue that they are merely making a series of factual observations,and letting their readers form their own conclusions. For example, the IBM XIV storage system has ECC-protected mirrored cache writes. Some false claims about this were [properly retracted]using strike out font to show the correction made, other times the same statement appears in another post from the same blogger that[have not yet beenretracted] (Update: has now been corrected). Other bloggers borrow the false statement [for their own blog], perhaps not realizing theretractions were made elsewhere. Newspapers are unable to fix a previous edition, so are forced to publishretractions in future papers. With blogs, you can edit the original and post the changed version, annotated accordingly, so mistakes can be corrected quickly.
While it is possible to compare bananas and humans on a variety of metrics--weight, height, and dare I say it,caloric value--it misses the finer differences of what makes them different. Humans might share 98 percent withchimpanzees, but having an opposable thumb allows humans to do things that chimpanzeesother animals cannot.
Full Disclosure: I am neither vegetarian nor cannibal, and harbor no ill will toward bananas nor chimpanzees.No bananas or chimpanzees were harmed in the writing of this blog post. Any similarity between the fictitiousMr. Jones in the above analogy and actual persons, living or dead, is purely coincidental.
So let's take a look at some of IBM XIV Storage System's "opposable thumbs".
The IBM XIV system comes pre-formatted and ready to use. You don't have to spend weeks in meetings deciding betweendifferent RAID levels and then formatting different RAID ranks to match those decisions. Instead, you can start using the storage on the IBM XIV Storage System right away.
The IBM XIV offers consistent performance, balancing I/O evenly across all disk drive modules, even when performing SnapShot processing, or recovering from component failure. You don't have to try to separate data to prevent one workload from stealing bandwidth from another. You don't have to purchase extra software to determine where the "hot spots" are on the disk. You don't have to buy othersoftware to help re-locate and re-separate the data to re-balance the I/Os. Instead, you just enjoy consistentperformance.
The IBM XIV offers thin provisioning, allowing LUNs to grow as needed to accommodate business needs. You don'thave to estimate or over-allocate space for planned future projects. You don't have to monitor if a LUN is reaching80 or 90 percent full. You don't have to carve larger and larger LUNs and schedule time on the weekends to move thedata over to these new bigger spaces. Instead, you just write to the disk, monitoring the box as a whole, ratherthan individual LUNs.
The IBM XIV Storage System's innovative RAID-X design allows drives to be replaced with drives of any larger or smaller capacity. You don't have to find the exact same 73GB 10K RPM drive to match the existing 73GB 10K RPM drive that failed. Some RAID systems allow "larger than original" substitutions, for example a 146GB drive to replace a 73GB drive, but the added capacity is wasted, because of the way most RAID levels work. The problemis that many failures happen 3-5 years out, and disk manufacturers move on to bigger capacities and differentform factors, making it sometimes difficult to find an exact replacement or forcing customers to keep their own stockof spare drives. Instead, with the IBM XIV architecture, you sleep well at night, knowing it allows future drive capacities to act as replacements, and getting the full value and usage of that capacity.
In the case of IBM XIV Storage System, it is not clear whether
"Vendors" are those from IBM and IBM Business Partners, including bloggers like me employed by IBM,and "everybody else" includes IBM's immediate competitors, including bloggers employed by them.
-- or --
"Vendors" includes IBM and its competitors including any bloggers, so that "everybody else" refers instead to anyone not selling storage systems, but opinionated enough to not qualify as "objective third-party sources".
-- or --
"Vendors" includes official statements from IBM and its competitors, and "everybody else" refers to bloggerspresenting their own personal or professional opinions, that may or may not correspond to their employers.
That said, feel free to comment below on which of these you think the last two points of Steinhardt's rule istrying to capture. Certainly, I can't argue with the top two: a customer's own experience and the experiencesof other customers, which I mentioned previously in my post[Deceptively Delicious].
In that light, here is a 5-minute video on IBM TV with a customer testimonial from the good folksat [NaviSite], one of our manycustomer references for the IBM XIV Storage System.
Last July, IBM and EMC traded blog postings over SPC-1 benchmark results. Fellow EMC bloggerChuck Hollis wrote his post [Does Anyone Take The SPC Seriously?]. Here is an excerpt:
I think most storage users have figured this out. We've never done an SPC test, and probably will never do one. Anyone is free, however, to download the SPC code, lash it up to their CLARiiON, and have at it.
I responded with [Getting Under EMC Skin], and then followed up with a series explaining IBM SVC and SPC benchmarks here:
So what is the good news?Yesterday, our friends at NetApp took up Chuck's challenge and posted results on their FAS3040 as well as their EMC CLARiiON devices. IBM sells the FAS3040 under the name IBM System Storage N5300 disk system. Knowing that NetApp maintains excellent performance when it is doing point-in-time copies, NetApp ran both with and without on both boxes. I include DS4700 and DS4800 as well for comparison purposes, but only have them without FlashCopy running.
NetApp FAS3040 (IBM N5300)
NetApp FAS3040 (IBM N5300)
EMC CLARiiON CX3-40
IBM DS4700 Express
EMC CLARiiON CX3-40
One would expect some performance degradation with a box running point-in-time copies at the same time it is reading and writing data, but NetApp/IBM N5300 does not degrade by much, but EMC's drops a significant amount.
So what is the bad news? Last October, I welcomed HDS USP-V to the [Super High-End Club], but now we need to invite Texas Memory Systems as well.In 2006, I posted [Hybrid, Solid State and the future of RAID], and poked fun at Texas Memory Systems using the slogan "World's Fastest Storage", which at the time that honor belonged to IBM SAN Volume Controller instead.The VP of Texas Memory Systems, Woody Hutsell, explained the only reason their solid-state disk system, RAMSAN-320, didn't have faster results is that they didn't have the fastest IBM server to run against it. It may not surprise you that nearly everyone's SPC benchmarks use IBM servers because IBM has the fastest servers as well. I didn't have a million-dollar System p UNIX server to send Woody for this, but it looks like they have finally gotten one, and a new RAMSAN-400 device, as they have posted their latest results.
Texas Memory Systems RAMSAN-400
IBM SAN Volume Controller 4.2
EMC doesn't publish numbers for their Symmetrix box, despite their announcement of faster SSD drives. They claim that SSD drives make their overall disk system performance faster, but without SPC benchmarks, we will never know. If you have a Symmetrix, this YouTube video may help you decide where it belongs:
IBM doesn't publicly report subset numbers on individual product lines, but we are growing, albeit single-digit growth, on the high-end with our IBM System Storage DS8000 and DS6000 series products. Single digit growth is not "booming", but it is what we expected in this space, so it is not like we are"feeling the chill" as Robin stated.Obviously, if the U.S. market overall is doing poorly, then it must be from something else. IBM's success appears to be from organic growth in our Asia and Europe markets, and taking marketshare away from the top two contenders, EMC and HDS. Here are my thoughts why:
EMC is remodeling its kitchen
Not happy with its status as #1 disk hardware specialty shop, EMC is admirably trying to redefine itself as an ["information infrastructure"] company, buying up software companies and introducing new storage services. [Byte and Switch] reports onEMC's recent acquisitions:
EMC is the latest vendor to pin its colors to the SaaS mast, revealing its plan to offer SaaS-based archiving services during its recent Innovation Day in Boston.
EMC gave another clear indication of its SaaS intentions last month, when it spent $76 million to acquire online backup specialist Mozy.
IBM has offered[Managed Storage Services] foryears through our Global Technology Services (GTS) division. Gartner recognized IBM as the #1 leader in storageservices, with three times more revenues than EMC in this space.
As with a restaurant that is remodeling its kitchen, it can expect a temporary drop inrevenue. If it is done right, customers will come back to a bigger brighter restaurant. If not, the restaurant re-opens as a much smaller lesser version of itself. Recent events this year might incent EMC to get that kitchen done quickly:
A recent [class-action lawsuit]might result in having EMC's "86 percent male" sales force goes to sexual harassment sensitivity training, takingtime away from selling high-end storage arrays in the field. Analysts consider "high-end" boxes as those costingover $300,000 US dollars. Because of the money involved, there is a lot of competition for high-end storage, so face-to-face time with prospective customers is crucial to making the sale.Anytime any vendor is mentioned in a lawsuit (andcertainly IBM has had its share in the past, as Chuck Hollis correctly points out in the comment below), priorities get shifted, and there is potential dip in revenues.
Dell acquires EMC's rival EqualLogic. Dell resold EMC midrange storage, like CLARiiON, so this should notimpact their high-end storage sales. While Dell will be allowed to sell EMC until 2011, this new acquisition mightmean Dell leads with the EqualLogic offerings, and that could potentially reduce EMC revenues in the midrange space.
IBM went through a similar phase in the 1990's, redefining itself from an "IT Technology" company, intoa "Systems, Software and Services" company. These transitions can't be done in a quarter, or even a year, theytake several years. IBM lost business to EMC in the 1990s, but is back with a stronger portfolio in the 2000's, and so IBM's kitchen remodeling effort appears to be paying off. We will see what happens with EMC in a few years.
HDS puts on the white lab coats
Meanwhile, HDS appears interested in taking over as #1 disk hardware specialty shop.For years, Hitachi was the stereotypical JCM (Japanese IBM-compatible manufacturer) that made well-engineered"me, too" storage arrays. They would see what innovators like IBM and EMC were doing, and copy them. Recently,however, they seemed to have changed strategy, introducing new featuresand functions on their high-end USP-V device, like[Dynamic Provisioning].
The problem is that customers don't want to feel like [Guinea pigs] in an experimental lab, especially withmission-critical data that they trust to their most-available, most-reliable high-end disk storage systems.Like IBM and EMC and the rest of the major storage vendors, Hitachi has top-notch engineers making quality products, but new features scare people, and so there is a lag in the adoption of new technologies.
In our youth, we might have preferred beer with recent born-on dates, and tequila aged less than 90 days. But as weget older, we switch to drinks like wine and whiskey, aged years, not weeks. The same is true for themarketplace. New start-ups and other "early adopters"might be willing to try fresh new features and functions on their storage systems, but more established enterprises prefer storage with more mature and stable microcode.Storage admins want to leave at the end of the day, knowing that the data will still be there the next morning. In tough financial times, many established companies want the technological equivalent to ["comfort food"], nothing spicy or exotic, but simplehearty fare that fills the belly and keeps you satisfied.
Recognizing this, IBM often introduces new features and functions on its midrange lines first, and position them accordingly. Once customers are comfortable with the concepts, IBM then can consider moving them into the high-end lines. For example, dynamic volume expansion was introduced on the DS4000 and SAN Volume Controller first, and once proven safe and effective, brought over to the DS8000 series. This strategy has served us well.
Well those are my theories. If you have a different explanation of why storage vendors are not doing well in thehigh-end, drop me a comment!
It's official! My "blook" Inside System Storage - Volume I is now available.
This blog-based book, or “blook”, comprises the first twelve months of posts from this Inside System Storage blog,165 posts in all, from September 1, 2006 to August 31, 2007. Foreword by Jennifer Jones. 404 pages.
IT storage and storage networking concepts
IBM strategy, hardware, software and services
Disk systems, Tape systems, and storage networking
Storage and infrastructure management software
Second Life, Facebook, and other Web 2.0 platforms
IBM’s many alliances, partners and competitors
How IT storage impacts society and industry
You can choose between hardcover (with dust jacket) or paperback versions:
This is not the first time I've been published. I have authored articles for storage industry magazines, written large sections of IBM publications and manuals, submitted presentations and whitepapers to conference proceedings, and even had a short story published with illustrations by the famous cartoon writer[Ted Rall].
But I can say this is my first blook, and as far as I can tell, the first blook from IBM's many bloggers on DeveloperWorks, and the first blook about the IT storage industry.I got the idea when I saw [Lulu Publishing] run a "blook" contest. The Lulu Blooker Prize is the world's first literary prize devoted to "blooks"--books based on blogs or other websites, including webcomics. The [Lulu Blooker Blog] lists past year winners. Lulu is one of the new innovative "print-on-demand" publishers. Rather than printing hundredsor thousands of books in advance, as other publishers require, Lulu doesn't print them until you order them.
I considered cute titles like A Year of Living Dangerously, orAn Engineer in Marketing La-La land, or Around the World in 165 Posts, but settled on a title that matched closely the name of the blog.
In addition to my blog posts, I provide additional insights and behind-the-scenes commentary. If you go to the Luluwebsite above, you can preview an entire chapter in its entirety before purchase. I have added a hefty 56-page Glossary of Acronyms and Terms (GOAT) with over 900 storage-related terms defined, which also doubles as an index back to the post (or posts) that use or further explain each term.
So who might be interested in this blook?
Business Partners and Sales Reps looking to give a nice gift to their best clients and colleagues
Managers looking to reward early-tenure employees and retain the best talent
IT specialists and technicians wanting a marketing perspective of the storage industry
Mentors interested in providing motivation and encouragement to their proteges
Educators looking to provide books for their classroom or library collection
Authors looking to write a blook themselves, to see how to format and structure a finished product
Marketing personnel that want to better understand Web 2.0, Second Life and social networking
Analysts and journalists looking to understand how storage impacts the IT industry, and society overall
College graduates and others interested in a career as a storage administrator
And yes, according to Lulu, if you order soon, you can have it by December 25.
In North America, today marks the start of the "Give 1 Get 1" program.
Children using the XO laptop
I first learned from this when I was reading about Timothy Ferriss' [LitLiberation project] on his [Four Hour Work Week] blog, and was surfing around for related ideas, and chanced upon this. I registered for a reminder, and it came today(the reminder, not the laptop itself).
Here's how the program works. You give $399 US dollars to the "One Laptop per Child" (OLPC)[laptop.org] organization for two laptops: One goes to a deserving child ina developing country, the second goes to you, for your own child, or to donate to a localcharity that helps children. This counts as a $199 purchase plus a $200 tax-deductible donation.For Americans, this is a [US 501(c)(3)] donation, and for Canadians and Mexicans, take advantage of the low-value of the US dollar!
If your employer matches donations, like IBM does, get them to match the $200donation for a third laptop, which goes to another child in a developing country. As for shipping, you pay only for the shipping of the one to you, each receiving country covers their own shipping. In my case, the shipping was another $24 US dollars for Arizona.No guarantees that it will arrive in time for the holidays this December, but it might.
To sweeten the deal, T-mobile throws in a year's worth of "Wi-Fi Hot Spot"that you can use for yourself, either with the XO laptop itself, or your regular laptop, iPhone, or otherWi-Fi enabled handheld device.
National Public Radio did a story last week on this:[The $100 Laptop Heads for Uganda]where they interview actor [Masi Oka], best known from the TV show ["Heroes"], who has agreed to be their spokesman.At the risk of sounding like their other spokesman, I thought I would cover the technology itself, inside the XO,and how this laptop represents IBM's concept of "Innovation that matters"!
The project was started by [Nicholas Negroponte] from [MIT University] as the "$100 laptop project". Once the final designwas worked out, it turns out it costs $188 US dollars to make, so they rounded it up to $200. This is stillan impressive price, and requires that hundreds of thousands of them be manufactured to justify ramping upthe assembly line.
Two of IBM's technology partners are behind this project. First is Advanced Micro Devices (AMD) that providesthe 433Mhz x86 processor, which is 75 percent slower than Thinkpad T60. Second is Red Hat,as this runs lean Fedora 6 version of Linux. Obviously, you couldn't have Microsoft Windows or Apple OS X, as both require significantly more resources.
The laptop is "child size", and would be considered in the [subnotebook] category. At 10" x 9" x 1.25", it is about the size of class textbook,can be carried easily in a child's backpack, or carried by itself with the integrated handle. When closed, it is sealedenough to be protected when carried in rain or dust storms. It weighs about 3.5 pounds, less than the 5.2 pounds of myThinkpad T60.
The XO is "green", not just in color, but also in energy consumption.This laptop can be powered by AC, or human power hand-crank, with workin place to get options for car-battery or solar power charging. Compared to the 20W normally consumed bytraditional laptops, the XO consumes 90 percent less, running at 2W or less. To accomplish this, there is no spinning disk inside. Instead, a 1GB FLASH drive holds 700MB of Linux, and gives you 300MB to hold your files. There isa slot for an MMC/SD flash card, and three USB 2.0 ports to connect to USB keys, printers or other remote I/O peripherals.
The XO flips around into three positions:
Standard laptop position has screen and keyboard. The water-tight keyboard comes in ten languages:International/English, Thai, Arabic, Spanish, Portuguese, West African, Urdu, Mongolian, Cyrillic, and Amharic.(I learned some Amharic, having lived five years with Ethiopians.)There does not appear be a VGA port, so don't be thinking this could be used as an alternative to project Powerpoint presentations onto a big screen.
Built-in 640x480 webcam, microphone and speakers allow the XO to be used as a communication device. Voice-over-IP (VOIP) client software, similar to Skype or [IBM Lotus Sametime], is pre-installed for this purpose.
The basic built-in communication are 802.1g (54Mbs) that you can use to surf the web usingthe Wi-Fi at your local Starbucks; and 802.1s which forms a "mesh network" with other XO laptops, and can surf theweb finding the one laptop nearby that is connected to the internet to share bandwidth. This eliminates the need to build a separate Wi-Fi hub at the school. There are USB-to-Ethernet and USB-to-Cellular converters, so that might be an alternative option.
Flipped vertically, the device can be read like a book.The screen can be changed between full-color and black-white, 200 dpi, with decent 1200x900 pixel resolution. The full-color is back-lit, and can be read in low-lighting. The black-white is not back-lit, consumes much less power, andcan be read in bright sunlight. In that regards, it is comparable to other [e-book devices], like a Cybook or Sony Reader.
Software includes a web-browser, document reader, word processor and RSS feed reader to read blogs.The OLPC identifies all of the software, libraries and interfaces they use, so that anyone that wants to developchildren software for this platform can do so.
With the keyboard flipped back, the 6" x 4.5" screen has directional controls and X/Y/A/B buttons to run games. This would make it comparable to a Nintendo DS or Playstation Portable (PSP). Again, the choice between back-lit color,or sunlight black-white screen modes apply. Some games are pre-installed.
So for $399, you could buy a Wi-Fi enabled[16GB iPod Touch] for yourself, which does much the same thing, or you can make a difference in the world.I made my donation this morning, and suggest you--my dear readers in the US, Canada and Mexico--consider doing the same.Go to [www.laptopgiving.org] for details.
Miles per Gallon measures an effeciency ratio (amount of work done with a fixed amount of energy), not a speed ratio (distance traveled in a unit of time).
Given that IOPs and MB/s are the unit of "work" a storage array does, wouldn't the MPG equivalent for storage be more like IOPs per Watt or MB/s per Watt? Or maybe just simply Megabytes Stored per Watt (a typical "green" measurement)?
You appear to be intentionally avoiding the comparison of I/Os per Second and Megabytes per Second to Miles Per Hour?
May I ask why?
This is a fair question, Barry, so I will try to address it here.
It was not a typo, I did mean MPG (miles per gallon) and not MPH (miles per hour). It is always challenging to find an analogy that everyone can relate to explain concepts in Information Technology that might be harder to grasp. I chose MPG because it was closely related to IOPS and MB/s in four ways:
MPG applies to all instances of a particular make and model. Before Henry Ford and the assembly line, cars were made one at a time, by a small team of craftsmen, and so there could be variety from one instance to another. Today, vehicles and storage systems are mass-produced in a manner that provides consistent quality. You can test one vehicle, and safely assume that all similar instances of the same make and model will have the similar mileage. The same is true for disk systems, test one disk system and you can assume that all others of the same make and model will have similar performance.
MPG has a standardized measurement benchmark that is publicly available. The US Environmental Protection Agency (EPA) is an easy analogy for the Storage Performance Council, providing the results of various offerings to chose from.
MPG has usage-specific benchmarks to reflect real-world conditions.The EPA offers City MPG for the type of driving you do to get to work, and Highway MPG, to reflect the type ofdriving on a cross-country trip. These serve as a direct analogy to SPC having SPC-1 for Online transaction processing (OLTP) and SPC-2 for large file transfers, database queries and video streaming.
MPG can be used for cost/benefit analysis.For example, one could estimate the amount of business value (miles travelled) for the amount of dollar investment (cost to purchase gallons of gasoline, at an assumed gas price). The EPA does this as part of their analysis. This is similar to the way IOPS and MB/s can be divided by the cost of the storage system being tested on SPC benchmark results. The business value of IOPS or MB/s depends on the application, but could relate to the number of transactions processed per hour, the number of music downloads per hour, or number of customer queries handled per hour, all of which can be assigned a specific dollar amount for analysis.
It seemed that if I was going to explain why standardized benchmarks were relevant, I should find an analogy that has similar features to compare to. I thought about MPH, since it is based on time units like IOPS and MB/s, butdecided against it based on an earlier comment you made, Barry, about NASCAR:
Let's imagine that a Dodge Charger wins the overwhelming majority of NASCAR races. Would that prove that a stock Charger is the best car for driving to work, or for a cross-country trip?
Your comparison, Barry, to car-racing brings up three reasons why I felt MPH is a bad metric to use for an analogy:
Increasing MPH, and driving anywhere near the maximum rated MPH for a vehicle, can be reckless and dangerous,risking loss of human life and property damage. Even professional race car drivers will agree there are dangers involved. By contrast, processing I/O requests at maximum speed poses no additional risk to the data, nor possibledamage to any of the IT equipment involved.
While most vehicles have top speeds in excess of 100 miles per hour, most Federal, State and Local speed limits prevent anyone from taking advantage of those maximums. Race-car drivers in NASCAR may be able to take advantage of maximum MPH of a vehicle, the rest of us can't. The government limits speed of vehicles precisely because of the dangers mentioned in the previous bullet. In contrast, processing I/O requests at faster speeds poses no such dangers, so the government poses no limits.
Neither IOPS nor MB/s match MPH exactly.Earlier this week,I related IOPS to "Questions handled per hour" at the local public library, and MB/s to "Spoken words per minute" in those replies. If I tried to find a metric based on unit type to match the "per second" in IOPS and MB/s, then I would need to find a unit that equated to "I/O requests" or "MB transferred" rather than something related to "distance travelled".
In terms of time-based units, the closest I could come up with for IOPS was acceleration rate of zero-to-sixty MPH in a certain number of seconds. Speeding up to 60MPH, then slamming the breaks, and then back up to 60MPH, start-stop, start-stop, and so on, would reflect what IOPS is doing on a requestby request basis, but nobody drives like this (except maybe the taxi cab drivers here in Malaysia!)
Since vehicles are limited to speed limits in normal road conditions, the closest I could come up with for MB/s would be "passenger-miles per hour", such that high-occupancy vehicles like school buses could deliver more passengers than low-occupancy vehicles with only a few passengers.
Neither start-stops nor passenger-miles per hour have standardized benchmarks, so they don't work well for comparisonbetween vehicles.If you or anyone can come up with a metric that will help explain the relevance of standardized benchmarks better than the MPG that I already used, I would be interested in it.
You also mention, Barry, the term "efficiency" but mileage is about "fuel economy".Wikipedia is quick to point out that the fuel efficiency of petroleum engines has improved markedly in recent decades, this does not necessarily translate into fuel economy of cars. The same can be said about the performance of internal bandwidth ofthe backplane between controllers and faster HDD does not necessarily translate to external performance of the disk system as a whole. You correctly point this out in your blog about the DMX-4:
Complementing the 4Gb FC and FICON front-end support added to the DMX-3 at the end of 2006, the new 4Gb back-end allows the DMX-4 to support the latest in 4Gb FC disk drives.
You may have noticed that there weren't any specific performance claims attributed to the new 4Gb FC back-end. This wasn't an oversight, it is in fact intentional. The reality is that when it comes to massive-cache storage architectures, there really isn't that much of a difference between 2Gb/s transfer speeds and 4Gb/s.
Oh, and yes, it's true - the DMX-4 is not the first high-end storage array to ship a 4Gb/s FC back-end. The USP-V, announced way back in May, has that honor (but only if it meets the promised first shipments in July 2007). DMX-4 will be in August '07, so I guess that leaves the DS8000 a distant 3rd.
This also explains why the IBM DS8000, with its clever "Adaptive Replacement Cache" algorithm, has such highSPC-1 benchmarks despite the fact that it still uses 2Gbps drives inside. Given that it doesn't matter between2Gbps and 4Gbps on the back-end, why would it matter which vendor came first, second or third, and why call it a "distant 3rd" for IBM? How soon would IBM need to announce similar back-end support for it to be a "close 3rd" in your mind?
I'll wrap up with you're excellent comment that Watts per GB is a typical "green" metric. I strongly support the whole"green initiative" and I used "Watts per GB" last month to explain about how tape is less energy-consumptive than paper.I see on your blog you have used it yourself here:
The DMX-3 requires less Watts/GB in an apples-to-apples comparison of capacity and ports against both the USP and the DS8000, using the same exact disk drives
It is not clear if "requires less" means "slightly less" or "substantially less" in this context, and have no facts from my own folks within IBM to confirm or deny it. Given that tape is orders of magnitude less energy-consumptive than anything EMC manufacturers today, the point is probably moot.
I find it refreshing, nonetheless, to have agreed-upon "energy consumption" metrics to make such apples-to-apples comparisons between products from different storage vendors. This is exactly what customers want to do with performance as well, without necessarily having to run their own benchmarks or work with specific storage vendors. Of course, Watts/GB consumption varies by workload, so to make such comparisons truly apples-to-apples, you would need to run the same workload against both systems. Why not use the SPC-1 or SPC-2 benchmarks to measure the Watts/GB consumption? That way, EMC can publish the DMX performance numbers at the same time as the energy consumption numbers, and then HDS can follow suit for its USP-V.
I'm on my way back to the USA soon, but wanted to post this now so I can relax on the plane.
Wrapping up this week's exploration on disk system performance, today I willcover the Storage Performance Council (SPC) benchmarks, and why I feel they are relevant to help customers make purchase decisions. This all started to address a comment from EMC blogger Chuck Hollis, who expressed his disappointment in IBM as follows:
You've made representations that SPC testing is somehow relevant to customers' environments, but offered nothing more than platitudes in support of that statement.
Apparently, while everyone else in the blogosphere merely states their opinions and moves on,IBM is held to a higher standard. Fair enough, we're used to that.Let's recap what we covered so far this week:
Monday, I explained how seemingly simple questions like "Which is the tallestbuilding?" or "Which is the fastest disk system?" can be steeped in controversy.
Tuesday, I explored what constitutes a disk system. While there are special storage systemsthat include HDD that offer tape-emulation, file-oriented access, or non-erasable non-rewriteable protection,it is difficult to get apples-to-apples comparisions with storage systems that don't offer these special features.I focused on the majority of general-purpose disk systems, those that are block-oriented, direct-access.
Today, I will explore ways to apply these metrics to measure and compare storageperformance.
Let's take, for example, an IBM System Storage DS8000 disk system. This has a controller thatsupports various RAID configurations, cache memory, and HDD inside one or more frames.Engineers who are testing individual components of this system might run specifictypes of I/O requests to test out the performance or validate certain processing.
100% read-hit, this means that all the I/O requests are to read data expectedto be in the cache.
100% read-miss, this means that all the I/O requests are to read data expectedNOT to be in the cache, and must go fetch the data from HDD.
100% write-hit, this means that all the I/O requests are to write data into cache.
100% write-miss, this means that all the I/O requests are to bypass the cache,and are immediately de-staged to HDD. Depending on the RAID configuration, this can result in actually reading or writing several blocks of data on HDD to satisfy thisI/O request.
Known affectionately in the industry as the "four corners" test, because you can show them on a box, with writes on the left, reads on the right,hits on the top, and misses on the bottom.Engineers are proud of these results, but these workloads do notreflect any practical production workload. At best, since all I/O requests are oneof these four types, the four corners provide an expectation range from the worst performance (most often write-missin the lower left corner)and the best performance (most often read-hit in the upper right corner) you might get with a real workload.
To understand what is needed to design a test that is more reflective of real business conditions,let's go back to yesterday's discussion of fuel economy of vehicles, with mileage measured in miles per gallon.The How Stuff Works websiteoffers the following description for the two measurements taken by the EPA:
The "city" program is designed to replicate an urban rush-hour driving experience in which the vehicle is started with the engine cold and is driven in stop-and-go traffic with frequent idling. The car or truck is driven for 11 miles and makes 23 stops over the course of 31 minutes, with an average speed of 20 mph and a top speed of 56 mph.
The "highway" program, on the other hand, is created to emulate rural and interstate freeway driving with a warmed-up engine, making no stops (both of which ensure maximum fuel economy). The vehicle is driven for 10 miles over a period of 12.5 minutes with an average speed of 48 mph and a top speed of 60 mph.
Why two different measurements? Not everyone drives in a city in stop-and-go traffic. Having only one measurement may not reflect the reality that you may travel long distances on the highway. Offering both city and highway measurements allows the consumers to decide which metric relates closer to their actual usage.
Should you expect your actual mileage to be the exact same as the standardized test?Of course not. Nobody drives exactly 11 miles in the city every morning with 23 stops along the way,or 10 miles on the highway at the exact speeds listed.The EPA's famous phrase "your mileage may vary" has been quickly adopted into popular culture's lexicon. All kinds of factors, like weather, distance, anddriving style can cause people to get better or worse mileage than thestandardized tests would estimate.
Want more accurate results that reflect your driving pattern, in specific conditions that you are most likely to drive in? You could rentdifferent vehicles for a week and drive them around yourself, keeping track of whereyou go, and how fast you drove, and how many gallons of gas you purchased, so thatyou can then repeat the process with another rental, and so on, and then use yourown findings to base your comparisons. Perhaps you find that your results are always20% worse than EPA estimates when you drive in the city, and 10% worse when you driveon the highway. Perhaps you have many mountains and hills where you drive, you drive too fast, you run the Air Conditioner too cold, or whatever.
If you did this with five or more vehicles, and ranked them best to worstfrom your own findings, and also ranked them best to worst based on the standardizedresults from the EPA, you likely will find the order to be the same. The vehiclewith the best standardized result will likely also have the best result from your ownexperience with the rental cars. The vehicle with the worst standardized result willlikely match the worst result from your rental cars.
(This will be one of my main points, that standardized estimates don't have to be accurate to beuseful in making comparisons. The comparisons and decisions you would make with estimatesare the same as you would have made with actual results, or customized estimates based on current workloads. Because the rankings are in the same order, they are relevant and useful for making decisions based on those comparisons.)
Most people shopping around for a new vehicle do not have the time or patience to do this with rental cars. Theycan use the EPA-certified standardized results to make a "ball-park" estimate on how much they will spendin gasoline per year, decide only on cars that might go a certain distancebetween two cities on a single tank of gas, or merely to provide ranking of thevehicles being considered. While mileage may not be the only metric used in making a purchase decision, it can certainly be used to help reduce your consideration setand factor in with other attributes, like number of cup-holders, or leather seats.
In this regard, the Storage Performance Council has developed two benchmarks that attempt to reflect normal business usage, similar to "City" and "Highway" driving measurements.
SPC-1 consists of a single workload designed to demonstrate the performance of a storage subsystem while performing the typical functions of business critical applications. Those applications are characterized by predominately random I/O operations and require both queries as well as update operations. Examples of those types of applications include OLTP, database operations, and mail server implementations.
SPC-2 consists of three distinct workloads designed to demonstrate the performance of a storage subsystem during the execution of business critical applications that require the large-scale, sequential movement of data. Those applications are characterized predominately by large I/Os organized into one or more concurrent sequential patterns. A description of each of the three SPC-2 workloads is listed below as well as examples of applications characterized by each workload.
Large File Processing: Applications in a wide range of fields, which require simple sequential process of one or more large files such as scientific computing and large-scale financial processing.
Large Database Queries: Applications that involve scans or joins of large relational tables, such as those performed for data mining or business intelligence.
Video on Demand: Applications that provide individualized video entertainment to a community of subscribers by drawing from a digital film library.
The SPC-2 benchmark was added when people suggested that not everyone runs OLTP anddatabase transactional update workloads, just as the "Highway" measurement was addedto address the fact that not everyone drives in the City.
If you are one of the customers out there willing to spend the time and resources to do your own performance benchmarking, either at your own data center, or with theassistance of a storage provider, I suspect most, if not all, the major vendors(including IBM, EMC and others), and perhaps even some of the smaller start-ups, would be glad to work with you.
If you want to gather performance data of your actual workloads, and use this to estimate how your performance might be with a new or different storage configuration, IBMhas tools to make these estimates, and I suspect (again) that most, if not all, of theother storage vendors have developed similar tools.
For the rest of you who are just looking to decide which storage vendors to invite on your next RFP, and which products you might like to investigate that matchthe level of performance you need for your next project or application deployment,than the SPC benchmarks might help you with this decision. If performance is importantto you, factor these benchmark comparisons with the rest of the attributes you arelooking for in a storage vendor and a storage system.
In my opinion, I feel that for some people, the SPC benchmarks provide some value in this decision making process. They are proportionally correct, in that even ifyour workload gets only a portion of the SPC estimate, that storage systems withfaster benchmarks will provide you better performance than storage systems with lower benchmark results. That is why I feel they can be relevant in makingvalid comparisons for purchase decisions.
Hopefully, I have provided enough "food for thought"on this subject to support why IBM participates in the Storage Performance Council, why the performance of the SAN Volume Controller can be compared to the performanceof other disk systems, and why we at IBM are proud of the recent benchmark results in our recent press release.
Well, this week I am in Maryland, just outside of Washington DC. It's a bit cold here.
Robin Harris over at StorageMojo put out this Open Letter to Seagate, Hitachi GST, EMC, HP, NetApp, IBM and Sun about the results of two academic papers, one from Google, and another from Carnegie Mellon University (CMU). The papers imply that the disk drive module (DDM) manufacturers have perhaps misrepresented their reliability estimates, and asks major vendors to respond. So far, NetAppand EMC have responded.
I will not bother to re-iterate or repeat what others have said already, but make just a few points. Robin, you are free to consider this "my" official response if you like to post it on your blog, or point to mine, whatever is easier for you. Given that IBM no longer manufacturers the DDMs we use inside our disk systems, there may not be any reason for a more formal response.
Coke and Pepsi buy sugar, Nutrasweet and Splenda from the same sources
Somehow, this doesn't surprise anyone. Coke and Pepsi don't own their own sugar cane fields, and even their bottlers are separate companies. Their job is to assemble the components using super-secret recipes to make something that tastes good.
IBM, EMC and NetApp don't make DDMs that are mentioned in either academic study. Different IBM storage systems uses one or more of the following DDM suppliers:
Seagate (including Maxstor they acquired)
Hitachi Global Storage Technologies, HGST (former IBM division sold off to Hitachi)
In the past, corporations like IBM was very "vertically-integrated", making every component of every system delivered.IBM was the first to bring disk systems to market, and led the major enhancements that exist in nearly all disk drives manufactured today. Today, however, our value-add is to take standard components, and use our super-secret recipe to make something that provides unique value to the marketplace. Not surprisingly, EMC, HP, Sun and NetApp also don't make their own DDMs. Hitachi is perhaps the last major disk systems vendor that also has a DDM manufacturing division.
So, my point is that disk systems are the next layer up. Everyone knows that individual components fail. Unlike CPUs or Memory, disks actually have moving parts, so you would expect them to fail more often compared to just "chips".
If you don't feel the MTBF or AFR estimates posted by these suppliers are valid, go after them, not the disk systems vendors that use their supplies. While IBM does qualify DDM suppliers for each purpose, we are basically purchasing them from the same major vendors as all of our competitors. I suspect you won't get much more than the responses you posted from Seagate and HGST.
American car owners replace their cars every 59 months
According to a frequently cited auto market research firm, the average time before the original owner transfers their vehicle -- purchased or leased -- is currently 59 months.Both studies mention that customers have a different "definition" of failure than manufacturers, and often replace the drives before they are completely kaput. The same is true for cars. Americans give various reasons why they trade in their less-than-five-year cars for newer models. Disk technologies advance at a faster pace, so it makes sense to change drives for other business reasons, for speed and capacity improvements, lower power consumption, and so on.
The CMU study indicated that 43 percent of drives were replaced before they were completely dead.So, if General Motors estimated their cars lasted 9 years, and Toyota estimated 11 years, people still replace them sooner, for other reasons.
At IBM, we remind people that "data outlives the media". True for disk, and true for tape. Neither is "permanent storage", but rather a temporary resting point until the data is transferred to the next media. For this reason, IBM is focused on solutions and disk systems that plan for this inevitable migration process. IBM System Storage SAN Volume Controller is able to move active data from one disk system to another; IBM Tivoli Storage Manager is able to move backup copies from one tape to another; and IBM System Storage DR550 is able to move archive copies from disk and tape to newer disk and tape.
If you had only one car, then having that one and only vehicle die could be quite disrupting. However, companies that have fleet cars, like Hertz Car Rentals, don't wait for their cars to completely stop running either, they replace them well before that happens. For a large company with a large fleet of cars, regularly scheduled replacement is just part of doing business.
This brings us to the subject of RAID. No question that RAID 5 provides better reliability than having just a bunch of disks (JBOD). Certainly, three copies of data across separate disks, a variation of RAID 1, will provide even more protection, but for a price.
Robin mentions the "Auto-correlation" effect. Disk failures bunch up, so one recent failure might mean another DDM, somewhere in the environment, will probably fail soon also. For it to make a difference, it would (a) have to be a DDM in the same RAID 5 rank, and (b) have to occur during the time the first drive is being rebuilt to a spare volume.
The human body replaces skin cells every day
So there are individual DDMs, manufactured by the suppliers above; disk systems, manufactured by IBM and others, and then your entire IT infrastructure. Beyond the disk system, you probably have redundant fabrics, clustered servers and multiple data paths, because eventually hardware fails.
People might realize that the human body replaces skin cells every day. Other cells are replaced frequently, within seven days, and others less frequently, taking a year or so to be replaced. I'm over 40 years old, but most of my cells are less than 9 years old. This is possible because information, data in the form of DNA, is moved from old cells to new cells, keeping the infrastructure (my body) alive.
Our clients should approach this in a more holistic view. You will replace disks in less than 3-5 years. While tape cartridges can retain their data for 20 years, most people change their tape drives every 7-9 years, and so tape data needs to be moved from old to new cartridges. Focus on your information, not individual DDMs.
What does this mean for DDM failures. When it happens, the disk system re-routes requests to a spare disk, rebuilding the data from RAID 5 parity, giving storage admins time to replace the failed unit. During the few hours this process takes place, you are either taking a backup, or crossing your fingers.Note: for RAID5 the time to rebuild is proportional to the number of disks in the rank, so smaller ranks can be rebuilt faster than larger ranks. To make matters worse, the slower RPM speeds and higher capacities of ATA disks means that the rebuild process could take longer than smaller capacity, higher speed FC/SCSI disk.
According to the Google study, a large portion of the DDM replacements had no SMART errors to warn that it was going to happen. To protect your infrastructure, you need to make sure you have current backups of all your data. IBM TotalStorage Productivity Center can help identify all the data that is "at risk", those files that have no backup, no copy, and no current backup since the file was most recently changed. A well-run shop keeps their "at risk" files below 3 percent.
So, where does that leave us?
ATA drives are probably as reliable as FC/SCSI disk. Customers should chose which to use based on performance and workload characteristics. FC/SCSI drives are more expensive because they are designed to run at faster speeds, required by some enterprises for some workloads. IBM offers both, and has tools to help estimate which products are the best match to your requirements.
RAID 5 is just one of the many choices of trade-offs between cost and protection of data. For some data, JBOD might be enough. For other data that is more mission critical, you might choose keeping two or three copies. Data protection is more than just using RAID, you need to also consider point-in-time copies, synchronous or asynchronous disk mirroring, continuous data protection (CDP), and backup to tape media. IBM can help show you how.
Disk systems, and IT environments in general, are higher-level concepts to transcend the failures of individual components. DDM components will fail. Cache memory will fail. CPUs will fail. Choose a disk systems vendor that combines technologies in unique and innovative ways that take these possibilities into account, designed for no single point of failure, and no single point of repair.
So, Robin, from IBM's perspective, our hands are clean. Thank you for bringing this to our attention and for giving me the opportunity to highlight IBM's superiority at the systems level.
Continuing my week in Chicago, for the IBM Storage Symposium 2008, we had sessions that focused on individual products. IBM System Storage SAN Volume Controller (SVC) was a popular topic.
SVC - Everything you wanted to know, but were afraid to ask!
Bill Wiegand, IBM ATS, who has been working with SAN Volume Controller since it was first introduced in 2003. answered some frequently asked questions about IBM System Storage SAN Volume Controller.
Do you have to upgrade all of your HBAs, switches and disk arrays to the recommended firmware levels before upgrading SVC? No. These are recommended levels, but not required. If you do plan to update firmware levels, focus on the host end first, switches next, and disk arrays last.
How do we request special support for stuff not yet listed on the Interop Matrix?
Submit an RPQ/SCORE, same as for any other IBM hardware.
How do we sign up for SVC hints and tips? Go to the IBM
[SVC Support Site] and select the "My Notifications" under the "Stay Informed" box on the right panel.
When we call IBM for SVC support, do we select "Hardware" or "Software"?
While the SVC is a piece of hardware, there are very few mechanical parts involved. Unless there are sparks,
smoke, or front bezel buttons dangling from springs, select "Software". Most of the questions are
related to the software components of SVC.
When we have SVC virtualizing non-IBM disk arrays, who should we call first?
IBM has world-renown service, with some of IT's smartest people working the queues. All of the major storage vendors play nice
as part of the [TSAnet Agreement when a mutual customer is impacted.
When in doubt, call IBM first, and if necessary, IBM will contact other vendors on your behalf to resolve.
What is the difference between livedump and a Full System Dump?
Most problems can be resolved with a livedump. While not complete information, it is generally enough,
and is completely non-disruptive. Other times, the full state of the machine is required, so a Full System Dump
is requested. This involves rebooting one of the two nodes, so virtual disks may temporarily run slower on that
What does "svc_snap -c" do?The "svc_snap" command on the CLI generates a snap file, which includes the cluster error log and trace files from all nodes. The "-c" parameter includes the configuration and virtual-to-physical mapping that can be useful for
disaster recovery and problem determination.
I just sent IBM a check to upgrade my TB-based license on my SVC, how long should I wait for IBM to send me a software license key?
IBM trusts its clients. No software license key will be sent. Once the check clears, you are good to go.
During migration from old disk arrays to new disk arrays, I will temporarily have 79TB more disk under SVC management, do I need to get a temporary TB-based license upgrade during the brief migration period?
Nope. Again, we trust you. However, if you are concerned about this at all, contact IBM and they will print out
a nice "Conformance Letter" in case you need to show your boss.
How should I maintain my Windows-based SVC Master Console or SSPC server?
Treat this like any other Windows-based server in your shop, install Microsoft-recommended Windows updates,
run Anti-virus scans, and so on.
Where can I find useful "How To" information on SVC?
Specify "SAN Volume Controller" in the search field of the
[IBM Redbooks vast library of helpful books.
I just added more managed disks to my managed disk group (MDG), can I get help writing a script to redistribute the extents to improve wide-striping performance?
Yes, IBM has scripting tools available for download on
[AlphaWorks]. For example, svctools will take
the output of the "lsinfo" command, and generate the appropriate SVC CLI to re-migrate the disks around to optimize
performance. Of course, if you prefer, you can use IBM Tivoli Storage Productivity Center instead for a more
Any rules of thumb for sizing SVC deployments?
IBM's Disk Magic tool includes support for SVC deployments. Plan for 250 IOPS/TB for light workloads,
500 IOPS/TB for average workloads, and 750 IOPS/TB for heavy workloads.
Can I migrate virtual disks from one manage disk group (MDG) to another of different extent size?
Yes, the new Vdisk Mirroring capability can be used to do this. Create the mirror for your Vdisk between the
two MDGs, wait for the copy to complete, and then split the mirror.
Can I add or replace SVC nodes non-disruptively? Absolutely, see the Technotes
[SVC Node Replacement page.
Can I really order an SVC EE in Flamingo Pink? Yes. While my blog post that started all
this [Pink It and Shrink It] was initially just some Photoshop humor, the IBM product manager for SVC accepted this color choice as an RPQ option.
The default color remains Raven Black.
Continuing my ongoing discussion on Solid State Disk (SSD), fellow blogger BarryB (EMC) points out in his [latest post]:
Oh – and for the record TonyP, I don't think I ever said EMC was using a newer or different EFDs than IBM. I just asserted that EMC knows more than IBM about these EFDs and how they actually work a storage array under real-world workloads.
(Here "EFD" is refers to "Enterprise Flash Drive", EMC's marketing term for Single Layer Cell (SLC) NAND Flash non-volatile solid-state storage devices. Both IBM and EMC have been selling solid-state storage for quite some time now, but EMC felt that a new term was required to distinguish the SLC NAND Flash devices sold in their disk systems from solid-state devices sold in laptops or blade servers. The rest of the industry, including IBM, continues to use the term SSD to refer to these same SLC NAND Flash devices that EMC is referring to.)
Although STEC asserts that IBM is using the latest ZeusIOPS drives, IBM is only offering the 73GB and 146GB STEC drives (EMC is shipping the latest ZeusIOPS drives in 200GB and 400GB capacities for DMX4 and V-Max, affording customers a lower $/GB, higher density and lower power/footprint per usable GB.)
Here is where I enjoy the subtleties between marketing and engineering. Does the above seem like he is saying EMC is using newer or different drives? What are typical readers expected to infer from the statement above?
That there are four different drives from STEC, in four different capacities. In the HDD world, drives of different capacities are often different, and larger capacities are often newer than those of smaller capacities.
That the 200GB and 400GB are the latest drives, and that 73GB and 146GB drives are not the latest.
That STEC press release is making false or misleading claims.
Uncontested, some readers might infer the above and come to the wrong conclusions. I made an effort to set the record straight. I'll summarize with a simple table:
Usable (conservative format)
Usable (aggressive format)
So, we all agree now that the 256GB drives that are formatted as 146GB or 200GB are in fact the same drives, that IBM and EMC both sell the latest drives offered by STEC, and that the STEC press release was in fact correct in its claims.
I also wanted to emphasize that IBM chose the more conservative format on purpose. BarryB [did the math himself] and proved my key points:
Under some write-intensive workloads, an aggressive format may not last the full five years. (But don't worry, BarryB assures us that EMC monitors these drives and replaces them when they fail within the five years under their warranty program.)
Conservative formats with double the spare capacity happen to have roughly double the life expectancy.
I agree with BarryB that an aggressive format can offer a lower $/GB than the conservative format. Cost-conscious consumers often look for less-expensive alternatives, and are often willing to accept less-reliable or shorter life expectancy as a trade-off. However, "cost-conscious" is not the typical EMC targeted customer, who often pay a premiumfor the EMC label. To compensate, EMC offers RAID-6 and RAID-10 configurations to provide added protection. With a conservative format, RAID-5 provides sufficient protection.
(Just so BarryB won't accuse me of not doing my own math, a 7+P RAID-5 using conservative format 146GB drives would provide 1022GB of capacity, versus 4+4 RAID-10 configuration using aggressive format 200GB drives only 800GB total.)
In an ideal world, you the consumer would know exactly how many IOPS your application will generate over the next five years, exactly how much capacity you will require, be offered all three drives in either format to choose from, and make a smart business decision. Nothing, however, is ever this simple in IT.
My post last week [Solid State Disk on DS8000 Disk Systems] kicked up some dust in the comment section.Fellow blogger BarryB (a member of the elite [Anti-Social Media gang from EMC]) tried to imply that 200GB solid state disk (SSD) drives were different or better than the 146GB drives used in IBM System Storage DS8000 disk systems. I pointed out that they are the actual same physical drive, just formatted differently.
To explain the difference, I will first have to go back to regular spinning Hard Disk Drives (HDD). There are variances in manufacturing, so how do you make sure that a spinning disk has AT LEAST the amount of space you are selling it as? The solution is to include extra. This is the same way that rice, flour, and a variety of other commodities are sold. Legally, if it says you are buying a pound or kilo of flour, then it must be AT LEAST that much to be legal labeling. Including some extra is a safe way to comply with the law. In the case of disk capacity, having some spare capacity and the means to use it follows the same general concept.
(Disk capacity is measured in multiples of 1000, in this case a Gigabyte (GB) = 1,000,000,000 bytes, not to be confused with [Gibibyte (GiB)] = 1,073,741,824 bytes, based on multiples of 1024.)
Let's say a manufacturer plans to sell 146GB HDD. We know that in some cases there might be bad sectors on the disk that won't accept written data on day 1, and there are other marginally-bad sectors that might fail to accept written data a few years later, after wear and tear. A manufacturer might design a 156GB drive with 10GB of spare capacity and format this with a defective-sector table that redirects reads/writes of known bad sectors to good ones. When a bad sector is discovered, it is added to the table, and a new sector is assigned out of the spare capacity.Over time, the amount of space that a drive can store diminishes year after year, and once it drops below its rated capacity, it fails to meet its legal requirements. Based on averages of manufacturing runs and material variances, these could then be sold as 146GB drives, with a life expectancy of 3-5 years.
With Solid State Disk, the technology requires a lot of tricks and techniques to stay above the rated capacity. For example, you can format a 256GB drive as a conservative 146GB usable, with an additional 110GB (75 percent) spare capacity to handle all of the wear-leveling. You could lose up to 22GB of cells per year, and still have the rated capacity for the full five-year life expectancy.
Alternatively, you could take a more aggressive format, say 200GB usable, with only 56GB (28 percent) of spare capacity. If you lost 22GB of cells per year, then sometime during the third year, hopefully under warranty, your vendor could replace the drive with a fresh new one, and it should last the rest of the five year time frame. The failed drive, having 190GB or so usable capacity, could then be re-issued legally as a refurbished 146GB drive to someone else.
The wear and tear on SSD happens mostly during erase-write cycles, so for read-intensive workloads, such as boot disks for operating system images, the aggressive 200GB format might be fine, and might last the full five years.For traditional business applications (70 percent read, 30 percent write) or more write-intensive workloads, IBM feels the more conservative 146GB format is a safer bet.
This should be of no surprise to anyone. When it comes to the safety, security and integrity of our client's data, IBM has always emphasized the conservative approach.[Read More]
Well, it's Tuesday, which means IBM makes its announcements!
This week, IBM announces that it now supports 50GB Solid State Disk (SSD) in its [IBM System Storage EXP3000] disk systems.IBM has already made announcements about SSD enablement in the DS8000 and SAN Volume Controller (SVC), but now the EXP3000 brings SSD technology down to smaller System x server deployments.
Adoption of this new exciting technology is still in the early stages, despite the fact that IBM and other vendors have been touting this technology for a while. (For a quick blast to the past, here was my first post on the subject back from December 20, 2006: [Hybrid, Solid State and the future of RAID])Recently, fellow blogger BarryB admitted that EMC have only sold SSD to [hundreds of their customers], and to be fair, I suspect IBM's sales of SSD in its BladeCenter servers [available since July 2007] have been in similar single-digit percentage territory as well.
The advantage of today's announcement is that you can mix and match SSD drives with SAS and SATA drives in the EXP3000. You won't have to buy the entire drawer of SSD, you can start with just a few, depending on your business needs. On the other extreme, you can have up to two drawers, with 12 SSD drives each, for a total of 24 drives directly attached to System x servers via the ServeRAID MR10M SAS/SATA controller adapter.
Perhaps the recent financial meltdown is making storage vendors nervous.Both IBM and EMC gained market share in 3Q08, but EMC is acting strangelyat IBM's latest series of plays and announcements. Almost contradictory!
Benchmarks bad, rely on your own in-house evaluations instead
Let's start with fellow blogger Barry Burke from EMC, who offers his latest post[Benchmarketing Badly] with commentaryabout Enterprise Strategy Group's [DS5300 Lab Validation Report]. The IBM System Storage DS5300 is one of IBM's latest midrange disk systems recently announced. Take for example this excerpt from BarryB's blog post:
"I was pleasantly surprised to learn that both IBM and ESG agree with me about the relevance and importance of the Storage Performance Council benchmarks.
That is, SPC's are a meaningless tool by which to measure or compare enterprise storage arrays."
Nowhere in the ESG report says this, nor have I found any public statements from either IBM nor ESG that makes this claim. Instead, the ESG report explains that traditional benchmarks from the Storage Performance Council [SPC] focus on a single, specific workload, and ESG has chosen to complement this with a variety of other benchmarks to perform their product validation, including VMware's "VMmark", Oracle's Orion Utility, and Microsoft's JetStress.
Benchmarks provide prospective clients additional information to make purchasedecisions. IBM understands this, ESG understands this, and other well-respected companies like VMware, Oracle and Microsoft understand this. EMC is afraid that benchmarks mightencourage a client to "mistakenly" purchase a faster IBM product than a slower EMC product. Sunshine makes a great disinfectant, but EMC (and vampires) prefer their respective "prospects" remain in the dark.
Perhaps stranger still is BarryB's postscript. Here's an excerpt:
"... a customer here asked me if EMC would be willing to participate in an initiative to get multiple storage vendors to collaborate on truly representative real-world "enterprise-class" benchmarks, and I reassured him that I would personally sponsor active and objective participation in such an effort - IF he could get the others to join in with similar intent."
As I understand it, EMC was once part of the Storage Performance Council a long time ago, then chose to drop out of it. Why re-invent the wheel by creating yet another storage industry benchmark group? EMC is welcome to come back to SPC anytime! In addition to the SCP-1 and SPC-2 workloads, there is work underway for an SPC-3 benchmark. Each SPC workload provides additional insight for product comparisons to help with purchase decisions. If EMC can suggest an SPC-4 benchmark that it feels is more representative of real-world conditions, they are welcome to join the SPC party and make that a reality.
The old adage applies: ["It's better to light a candle than curse the darkness"]. EMC has been cursing the lack of what it considers to be acceptable benchmarks but has yet to offer anything more realistic or representative than SPC.What does EMC suggest you do instead? Get an evaluation box and run your own workloads and see for yourself! EMC has in the past offered evaluation units specifically for this purpose.
In-house evaluations bad, it's a trap!
Certainly, if you have the time and staff to run your own evaluation, with your own applications in your own environment, then I agree with EMC that this can provide better insight for your particular situation than standardized benchmarks.
In fact, that is exactly what IBM is doing for IBM XIV storage units, which are designed for Web 2.0 and Digital Archive workloads that current SPC benchmarks don't focus on. Fellow blogger Chuck Hollis from EMC opines in his post[Get yer free XIV!]. Here's an excerpt:
"Now that I think about it, this could get ugly. Imagine a customer who puts one on the floor to evaluate it, and -- in a moment of desperation or inattention -- puts production data on the device.
Nobody was paying attention, and there you are. Now IBM comes calling for their box back, and you've got a choice as to whether to go ahead and sign the P.O., or migrate all your data off the thing. Maybe they'll sell you an SVC to do this?
Yuck. I bet that happens more than once. And I can't believe that IBM (or the folks at XIV) aren't aware of this potentially happening."
Perhaps Chuck is speaking from experience here, as this may have happened with customers with EMC evaluation boxes, and is afraid this could happen with IBM XIV. I don't see anything unique about IBM XIV in the above concern. Typical evaluations involve copying test data onto the box, test it out with some particular application or workload, and then delete the data no longer required. Repeat as needed. Moving data off an IBM XIV is aseasy as moving data off an EMC DMX, EMC CLARiiON or EMC Celerra, and I am sure IBM wouldgladly demonstrate this on any EMC gear you now have.
Thanks to its clever RAID-X implementation, losing data on an IBM XIV is less likely thanlosing data on any RAID-5 based disk array from any storage vendor. Of course, there will always be skeptics about new technology that will want to try the box out for themselves.
If EMC thought the IBM XIV had nothing unique to offer, that its performance was just "OK",and is not as easy to manage as IBM says it is, then you would think EMC would gladly encourage such evaluations and comparisons, right?
No, I think EMC is afraid that companies will discover what they already know, that IBM has quality products that would stand a fair chance of side-by-side comparisons with their own offerings.We have enough fear, uncertainty and doubt from our current meltdown of the global financial markets, don't let EMC add any more.
Have a safe and fun Halloween! If you need to add some light to your otherwise dark surroundings, consider some of these ideas for [Jack-O-Lanterns]!
In my post yesterday [Spreading out the Re-Replication process], fellow blogger BarryB [aka The Storage Anarchist]raises some interesting points and questions in the comments section about the new IBM XIV Nextra architecture.I answer these below not just for the benefit of my friends at EMC, but also for my own colleagues within IBM,IBM Business Partners, Analysts and clients that might have similar questions.
If RAID 5/6 makes sense on every other platform, why not so on the Web 2.0 platform?
Your attempt to justify the expense of Mirrored vs. RAID 5 makes no sense to me. Buying two drives for every one drive's worth of usable capacity is expensive, even with SATA drives. Isn't that why you offer RAID 5 and RAID 6 on the storage arrays that you sell with SATA drives?
And if RAID 5/6 makes sense on every other platform, why not so on the (extremely cost-sensitive) Web 2.0 platform? Is faster rebuild really worth the cost of 40+% more spindles? Or is the overhead of RAID 6 really too much for those low-cost commodity servers to handle.
Let's take a look at various disk configurations, for example 3TB on 750GB SATA drives:
JBOD: 4 drives
JBOD here is industry slang for "Just a Bunch of Disks" and was invented as the term for "non-RAID".Each drive would be accessible independently, at native single-drive speed, with no data protection. Puttingfour drives in a single cabinet like this provides simplicity and convenience only over four separate drivesin their own enclosures.
RAID-10: 8 drives
RAID-10 is a combination of RAID-1 (mirroring) and RAID-0 (striping). In a 4x2 configuration, data is striped across disks 1-4,then these are mirrored across to disks 5-8. You get performance improvement and protection against a singledrive failure.
RAID-5: 5 drives
This would be a 4+P configuration, where there would be four drives' worth of data scattered across fivedrives. This gives you almost the same performance improvement as RAID-10, similar protection againstsingle drive failure, but with fewer drives per usable TB capacity.
RAID-6: 6 drives
This would be a 4+2P configuration, where the first P represents linear parity, and the second represents a diagonal parity. Similar in performance improvement as RAID-5, but protects against single and double drive failures, and still better than RAID-10 in terms of drives per TB usable capacity.
For all the RAID configurations, rebuild would require a spare drive, but often spares are shared among multiple RAID ranks, not dedicated to a single rank. To this end, you often have to have several spares per I/O loop, and a different set of spares for each kind of speed and capacity. If you had a mix of 15K/73GB, 10K/146GB, and 7200/500GB drives, then you would have three sets of spares to match.
In contrast, IBM XIV's innovative RAID-X approach doesn't requireany spare drives, just spare capacity on existing drives being used to hold data. The objects can be mirroredbetween any two types of drives, so no need to match one with another.
All of these RAID levels represent some trade-off between cost, protection and performance, and IBM offers each of theseon various disk systems platforms. Calculating parity is more complicated than just mirrored copies, but this can be done with specialized chips in cache memory to minimize performance impact.IBM generally recommends RAID-5 for high-performance FC disk, and RAID-6 for slower, large capacity SATA disk.
However, the questionassumes that the drive cost is a large portion of the overall "disk system" cost. It isn't. For example,Jon Toigo discusses the cost of EMC's new AX4 disk system in his post [National Storage Rip-Off Day]:
EMC is releasing its low end Clariion AX4 SAS/SATA array with 3TB capacity for $8600. It ships with four 750GB SATA drives (which you and I could buy at list for $239 per unit). So, if the disk drives cost $956 (presumably far less for EMC), that means buyers of the EMC wares are paying about $7700 for a tin case, a controller/backplane, and a 4Gbps iSCSI or FC connector. Hmm.
Dell is offering EMC’s AX4-5 with same configuration for $13,000 adding a 24/7 warranty.
(Note: I checked these numbers. $8599 is the list price that EMC has on its own website. External 750GB drivesavailable at my local Circuit City ranged from $189 to $329 list price. I could not find anything on Dell'sown website, but found [The Register] to confirm the $13,000 with 24x7 warranty figure.)
Disk capacity is a shrinking portion of the total cost of ownership (TCO). In addition to capacity, you are paying forcache, microcode and electronics of the system itself, along with software and services that are included in the mix,and your own storage administrators to deal with configuration and management. For more on this, see [XIV storage - Low Total Cost of Ownership].
EMC Centera has been doing this exact type of blob striping and protection since 2002
As I've noted before, there's nothing "magic" about it - Centera has been employing the same type of object-level replication for years. Only EMC's engineers have figured out how to do RAID protection instead of mirroring to keep the hardware costs low while not sacrificing availability.
I agree that IBM XIV was not the first to do an object-level architecture, but it was one of the first to apply object-level technologies to the particular "use case" and "intended workload" of Web 2.0 applications.
RAID-5 based EMC Centera was designed insteadto hold fixed-content data that needed to be protected for a specific period of time, such as to meet government regulatory compliance requirements. This is data that you most likelywill never look at again unless you are hit with a lawsuit or investigation. For this reason, it is important to get it on the cheapest storage configuration as possible. Before EMC Centera, customers stored this data on WORM tape and optical media, so EMC came up with a disk-only alternative offering.IBM System Storage DR550 offers disk-level access for themost recent archives, with the ability to migrate to much less expensive tape for the long term retention. The end result is that storing on a blended disk-plus-tape solution can help reduce the cost by a factor of 5x to 7x, making RAID level discussion meaningless in this environment. For moreon this, see my post [OptimizingData Retention and Archiving].
While both the Centera and DR550 are based on SATA, neither are designed for Web 2.0 platforms.When EMC comes out with their own "me, too" version, they will probably make a similar argument.
IBM XIV Nextra is not a DS8000 replacement
Nextra is anything but Enterprise-class storage, much less a DS8000 replacement. How silly of all those folks to suggest such a thing.
I did searches on the Web and could not find anybody, other than EMC employees, who suggested that IBM XIV Nextra architecture represented a replacement for IBM System Storage DS8000. The IBM XIV press release does not mentionor imply this, and certainly nobody I know at IBM has suggested this.
The DS8000 is designed for a different "use case" andset of "intended workloads" than what the IBM XIV was designed for. The DS8000 is the most popular disk systemfor our IBM System z mainframe platform, for activities like Online Transaction Processing (OLTP) and large databases, supporting ESCON and FICON attachment to high-speed 15K RPM FC drives. Web 2.0 customers that might chooseIBM XIV Nextra for their digital content might run their financial operations or metadata search indexes on DS8000.Different storage for different purposes.
As for the opinion that this is not "enterprise class", there are a variety of definitions that refer to this phrase.Some analysts look at "price band" of units that cost over $300,000 US dollars. Other analysts define this as beingattachable to mainframe servers via ESCON or FICON. Others use the term to refer to five-nines reliability, havingless than 5 minutes downtime per year. In this regard, based on the past two years experience at 40 customer locations,I would argue that it meets this last definition, with non-disruptive upgrades, microcode updates and hot-swappable components.
By comparison, when EMC introduced its object-level Centera architecture, nobody suggested it was the replacement for their Symmetrix or CLARiiON devices. Was it supposed to be?
Given drive growth rates have slowed, improving utilization is mandatory to keep up with 60-70 percent CAGR
Look around you, Tony- all of your competitors are implementing thin provisioning specifically to drive physical utilization upwards towards 60-80%, and that's on top of RAID 5/RAID 6 storage and not RAID 1. Given that disk drive growth rates and $/GB cost savings have slowed significantly, improving utilization is mandatory just to keep up with the 60-70% CAGR of information growth.
Disk drive capacities have slowed for FC disk because much of the attention and investment has been re-directed to ATA technology. Dollar-per-GB price reduction is slowing for disks in general, as researchers are hitting physicallimitations to the amount of bits they can pack per square inch of disk media, and is now around 25 percent per year.The 60-70 percent Compound Annual Growth Rate (CAGR) is real, and can be even growing faster for Web 2.0providers. While hardware costs drop, the big ticket items to watch will be software, services and storage administrator labor costs.
To this end, IBM XIV Nextra offers thin provisioning and differential space-efficient snapshots. It is designed for 60-90 percent utilization, and can be expanded to larger capacities non-disruptively in a very scalable manner.
On his The Storage Architect blog, Chris Evans wrote [Twofor the Price of One]. He asks: why use RAID-1 compared to say a 14+2 RAID-6 configuration which would be much cheaper in terms of the disk cost? Perhpaps without realizing it, answers itwith his post today [XIV part II]:
So, as a drive fails, all drives could be copying to all drives in an attempt to ensure the recreated lost mirrors are well distributed across the subsystem. If this is true, all drives would become busy for read/writes for the rebuild time, rather than rebuild overhead being isolated to just one RAID group.
Let me try to explain. (Note: This is an oversimplification of the actual algorithm in an effortto make it more accessible to most readers, based on written materials I have been provided as partof the acquisition.)
In a typical RAID environment, say 7+P RAID-5, you might have to read 7 drives to rebuild one drive, and in the case of a 14+2 RAID-6, reading 15 drives to rebuild one drive. It turns out the performance bottleneck is the one driveto write, and today's systems can rebuild faster Fibre Channel (FC) drives at about 50-55 MB/sec, and slower ATA disk at around 40-42 MB/sec. At these rates, a 750GB SATA rebuild would take at least 5 hours.
In the IBM XIV Nextra architecture, let's say we have 100 drives. We lose drive 13, and we need to re-replicate any at-risk 1MB objects.An object is at-risk if it is the last and only remaining copy on the system. A 750GB that is 90 percent full wouldhave 700,000 or so at-risk object re-replications to manage. These can be sorted by drive. Drive 1 might have about 7000 objects that need re-replication, drive 2might have slightly more, slightly less, and so on, up to drive 100. The re-replication of objects on these other 99 drives goes through three waves.
Select 49 drives as "source volumes", and pair each randomly with a "destination volume". For example, drive 1 mapped todrive 87, drive 2 to drive 59, and so on. Initiate 49 tasks in parallel, each will re-replicate the blocks thatneed to be copied from the source volume to the destination volume.
50 volumes left.Select another 49 drives as "source volumes", and pair each with a "destination volume". For example, drive 87 mapped todrive 15, drive 59 to drive 42, and so on. Initiate 49 tasks in parallel, each will re-replicate the blocks thatneed to be copied from the source volume to the destination volume.
Only one drive left. We select the last volume as the source volume, pair it off with a random destination volume,and complete the process.
Each wave can take as little as 3-5 minutes. The actual algorithm is more complicated than this, as tasks complete early the source and volumes drives are available for re-assignment to another task, but you get the idea. XIV hasdemonstrated the entire process, identifying all at-risk objects, sorting them by drive location, randomly selectingdrive pairs, and then performing most of these tasks in parallel, can be done in 15-20 minutes. Over 40 customershave been using this architecture over the past 2 years, and by now all have probably experienced at least adrive failure to validate this methodology.
In the unlikely event that a second drive fails during this short time, only one of the 99 task fails. The other 98 tasks continue to helpprotect the data. By comparison, in a RAID-5 rebuild, no data is protected until all the blocks are copied.
As for requiring spare capacity on each drive to handle this case, the best disks in production environments aretypically only 85-90 percent full, leaving plenty of spare capacity to handle re-replication process. On average,Linux, UNIX and Windows systems tend to only fill disks 30 to 50 percent full, so the fear there is not enough sparecapacity should not be an issue.
The difference in cost between RAID-1 and RAID-5 becomes minimal as hardware gets cheaper and cheaper. For every $1 dollar you spend on storage hardware, you spend $5-$8 dollars managing the environment. As hardware gets cheaper still, it might even be worth making three copies of every 1MB object, the parallel processto perform re-replications would be the same. This could be done using policy-based management, some data gets triple-copied, and other data gets only double-copied, based on whether the user selected "premium" or "basic" service.
The beauty of this approach is that it works with 100 drives, 1000 drives, or even a million drives. Parallel processingis how supercomputers are able to perform feats of amazing mathematical computations so quickly, and how Web 2.0services like Google and Yahoo can perform web searches so quickly. Spreading the re-replication process acrossmany drives in parallel, rather than performing them serially onto a single drive, is just one of the many uniquefeatures of this new architecture.
Well, we had another successful event in Second Life today.
Unlike our April 26 launch of our System Storage products for IBM Business Partners only, this time we decided this time to make it as a "Meet the Storage Experts" Q&A Panel format, and open up registration to everyone. Thesubject matter experts sat at the front of the room on four stools. We had six rows of chairs arrangedsemi-circularly.
Shown above, from left to right, are the avatars of our four experts:
IBM System Storage N series, focusing on recent N3000 disk system announcements
Harold Pike (holding the microphone while speaking)
IBM System Storage DS3000 and DS4000 series, focusing on recent DS3000 disk system announcements
IBM System Storage TS series, focusing on recent TS2230, TS3400 and TS7700 tape system announcements
IBM storage networking, focusing on recent IBM SAN256B director blade announcements
While Eric was a veteran Second Lifer, having presented at our April event, the other three were trainedon how to raise their hand, speak into the microphone, sit on the stool, and so on. I want to thank allof our experts for putting in this effort!
The event was produced by Katrina H Smith. She did a great job, and made sure we were on top ofall the issues and tasks required to get the job done. Running a Second Life event is every bit ashard as running a real face-to-face event. We had several meetings to discuss venue details, placementof chairs, placement of product demos, audio/video recording, wall decorations, tee-shirt and coffee mug design, logistics, and so on.
I acted as moderator/emcee for the event. That is my back in the picture above. The process wassimple, modeled after the "Birds of a Feather" sessions at events like SHARE and the IBMStorage and Storage Networking Symposium. We threw out a list of topics the experts would cover,and people in the audience would "raise their left hand". I, as the moderator, would then walkover to each person, and hold out the microphone for them to ask the question. I would then repeat the question and ask the appropriate expert to provide an answer. We defined gestures onhow to "raise hand" and "put hand down" that we gave to each registered participant.
We had four dedicated "camera-avatars" in world to capture both video and screenshots.Our video editors are now working to edit "highlight videos" that we can use at future events, for training materials, and for our internal "BlueTube" online video system.
The room was filled with examples of each of our products, made into 3D objects that were dimensionallycorrect, and "textured" with photographs of the actual products. If you click on an object, you get a "notecard" that provided more information. Special thanks to Scott Bissmeyer for making all of theseobjects for us.
We made posters of each expert and placed them in all four corners of the room. On the bottom of each coffee mug was a picture of each of the experts, and if you walked under each of the posters, you were"dispensed" a coffee mug matching the expert shown in the poster.Participants could "Collect all Four!" When you bring the coffee mug up to takea sip, the picture on the bottom of the mug is exposed for all to see.And as a final give-away to the audience, we made a variety of event tee-shirts and polo-shirts.
At the end of the session, we asked everyone to click on the "Survey" kiosk near the exit door. We askedsix simple questions using SurveyMonkey.com that took only a fewminutes to process. We found asking questions immediately at the end of the event was the best way tocapture this feedback.
From a "Green" perspective, we had people registered from the following countries: US, India, Mexico,Australia, United Kingdom, Brazil, Germany, Argentina, Chile, China, Canada, and Venezuela. Second Lifeallows all these people who probably could not travel, or could not afford the time and expense to travel,to participate in a simulated face-to-face meeting without energy consumption of traditional travel methods.
More importantly, we got several leads for business. People often ask "Yes, but is there any businessassociated with this?" This time, there was, based on the answers to the questions, several avatars asked for a real sales call to follow-up on the products and offerings they were discussed.
With such a great success, we have already scheduled our next Second Life event, November 8. Mark your calendars! I'll postmore details on the registration process of the November event when available.
The proof-of-concept that IBM Haifa research center developed back in 1998 became what we now call the iSCSI protocol.The book iSCSI: The Universal Storage Connection introduces the history as follows:
In the fall of 1999 IBM and Cisco met to discuss the possibility of combining their SCSI-over-TCP/IP efforts. After Cisco saw IBM's demonstration of SCSI over TCP/IP, the two companies agreed to develop a proposal that would be taken to the IETF for standardization.
There are three ways to introduce iSCSI into your data center:
Through a gateway, like the IBM System Storage N series gateway, that allows iSCSI-based servers connect to FC-based storage devices
Through a SAN switch or director, a FC-based server can access iSCSI-based storage, an iSCSI-based server accessing FC-based storage, or even iSCSI-based servers attaching to iSCSI-based storage.
Directly through the storage controller.
IBM has been delivering the first method with its successful IBM System Storage N series gateway products, buttoday we have announced additional support for the second and third methods.Here's a quick recap.
New SAN director blades
Supporting the second method, IBM TotalStorage SAN256B Director is enhanced to deliver iSCSI functionality with a new M48 iSCSI Blade, which includes 16 ports (8 Fibre Channel ports; and 8 Ethernet ports for iSCSI connectivity). We also announced a new Fibre Channel M48 Blade which provides 10 Gbps Fibre Channel Inter Switch Link (ISL) connectivity between SAN256B Directors.
With support for Boot-over-iSCSI, diskless rack-optimized and blade servers can boot Windows or Linux over Ethernet,eliminating the management hassles with internal disk.
All of this is part of IBM's overall push into the Small and Medium size Business marketplace, making it easier to shop for and buy from IBM and its many IBM Business Partners, easier to deploy and install storage, and easier tomanage the storage once you have it.
Some people find it surprising that it is often more cost-effective, and power-efficient, to run workloads on mainframe logical partitions (LPARs) than a stack of x86 servers running VMware.
Perhaps they won't be surprised any more. Here is an article in eWeek that explains how IBM isreducing energy costs 80% by consolidating 3,900 rack-optimized servers to 33 IBM System z mainframe servers, running Linux, in its own data centers. Since 1997, IBM has consolidated its 155 strategic worldwide data center locations down to just seven.
I am very pleased that IBM has invested heavily into Linux, with support across servers, storage, software andservices. Linux is allowing IBM to deliver clever, innovative solutions that may not be possible with other operating systems. If you are in storage, you should consider becoming more knowledgeable in Linux.
The older systems won't just end up in a landfill somewhere. Instead, the details are spelled out inthe IBM Press Release:
As part of the effort to protect the environment, IBM Global Asset Recovery Services, the refurbishment and recycling unit of IBM, will process and properly dispose of the 3,900 reclaimed systems. Newer units will be refurbished and resold through IBM's sales force and partner network, while older systems will be harvested for parts or sold for scrap. Prior to disposition, the machines will be scrubbed of all sensitive data. Any unusable e-waste will be properly disposed following environmentally compliant processes perfected over 20 years of leading environmental skill and experience in the area of IT asset disposition.
Whereas other vendors might think that some operational improvements will be enough, such as switching to higher-capacity SATA drives, or virtualizing x86 servers, IBM recognizes that sometimes more fundamental changes are required to effect real changes and real results.
People are confused over various orders of magnitude. News of the economic meltdownoften blurs the distinction between millions (10^6), billions (10^9), and trillions (10^12).To show how different these three numbers are, consider the following:
A million seconds ago - you might have received your last paycheck (12 days)
A billion seconds ago - you were born or just hired on your current job (31 years)
A trillion seconds ago - cavemen were walking around in Asia (31,000 years)
That these numbers confuse the average person is no surprise, but that it confuses marketing people in the storage industry is even more hilarious. I am often correcting people who misunderstandMB (million bytes), GB (billion bytes) and TB (trillion bytes) of information.Take this graph as an example from a recent presentation.
At first, it looks reasonable, back in 2004, black-and-white 2D X-Ray images were only 1MBin size when digitized, but by 2010 there will be fancy 4D images that now take 1TB, representinga 1000x increase. What?When I pointed out this discrepancy, the person who put this chart together didn't know what to fix.Were 4D images only 1GB in size, or was it really a 1000000x increase.
If a 2D image was 1000 by 1000 pixels, each pixel was a byte of information, then a 3D imagemight either be 1000 by 1000 by 1000 [voxels], or 1000 by 1000 at 1000 frames per second (fps). Thefirst being 3D volumetric space, and the latter called 2D+time in the medical field, the rest of us just say "video".4D images are 3D+time, volumetric scans over time, so conceivably these could be quite large in size.
The key point is that advances in medical equipment result in capturing more data, which canhelp provide better healthcare. This would be the place I normally plug an IBM product, like the Grid Medical Archive Solution [GMAS], a blended disk and tape storage solution designed specifically for this purpose.
So, as government agencies look to spend billions of dollars to provide millions of peoplewith proper healthcare, choosing to spend some of this money on a smarter infrastructure can result in creating thousands of jobs and save everyone a lot of money, but more importantly, save lives.
Short 2-minute [video] argues the case for Smarter Healthcare
For more on this, check out Adam Christensen's blog post on[Smarter Planet], which points to a podcast byDr. Russ Robertson, chairman of the Counsel of Medical Education at Northwestern University’s Feinberg School of Medicine, and Dan Pelino, general manager of IBM's Healthcare and Life Sciences Industry.
This week is Thanksgiving holiday in the USA, so I thought a good theme would be things I am thankful for.
I'll start with saying that I am thankful EMC has finally announcedAtmos last week. This was the "Maui" part of the Hulk/Maui rumors we heard over a year ago. To quickly recap, Atmos is EMC's latest storage offeringfor global-scale storage intended for Web 2.0 and Digital Archive workloads. Atmos can be sold as just software, or combined with Infiniflex,EMC's bulk, high-density commodity disk storage systems. Atmos supports traditionalNFS/CIFS file-level access, as well as SOAP/REST object protocols.
I'm thankful for various reasons, here's a quick list:
It's hard to compete against "vaporware"
Back in the 1990s, IBM was trying to sell its actual disk systems against StorageTek's rumored "Iceberg" project. It took StorageTek some four years to get this project out,but in the meantime, we were comparing actual versus possibility. The main feature iswhat we now call "Thin Provisioning". Ironically, StorageTek's offering was not commercially successful until IBM agreed to resell this as the IBM RAMAC Virtual Array (RVA).
Until last week, nobody knew the full extent of what EMC was going to deliver on the many Hulk/Maui theories. Severalhinted as to what it could have been, and I am glad to see that Atmos falls short of those rumored possibilities. This is not to say that Atmos can't reach its potential, and certainly some of the design is clever, such as offering native SOAP/REST access.
Instead, IBM now can compare Atmos/Infiniflex directly to the features and capabilities of IBM's Scale Out File Services [SoFS], which offers a global-scale multi-site namespace with policy-based data movement, IBM System Storage Multilevel Grid Access Manager[GAM] that manages geographical distrubuted information,and IBM [XIV Storage System] that offers high-density bulk storage.
Web 2.0 and Digital Archive workloads justify new storage architectures
When I presented SoFS and XIV earlier this year, I mentioned they were designed forthe fast-growing Web 2.0 and Digital Archive workloads that were unique enough to justify their own storage architectures. One criticism was that SoFS appeared to duplicate what could be achieved with dozens of IBM N series NAS boxes connected with Virtual File Manager (VFM). Why invent a new offering with a new architecture?
With the Atmos announcement, EMC now agrees with IBM that the Web 2.0 and DigitalArchive workloads represent a unique enough "use case" to justify a new approach.
New offerings for new workloads will not impact existing offerings for existing workloads
I find it amusing that EMC is quickly defending that Atmos will not eat into its DMXbusiness, which is exactly the FUD they threw out about IBM XIV versus DS8000 earlier this year. In reality, neither the DS8000 nor the DMX were used much for Web 2.0 andDigital Archive workloads in the past. Companies like Google, Amazon and others hadto either build their own from piece parts, or use low-cost midrange disk systems.
Rather, the DS8000 and DMX can now focus on the workloads they were designed for,such as database applications on mainframe servers.
Cloud-Oriented Storage (COS)
Just when you thought we had enough terminology already, EMC introduces yet another three-letter acronym [TLA]. Kudos to EMC for coining phrases to help move newconcepts forward.
Now, when an RFP asks for Cloud-oriented storage, I am thankful this phrase will help serve as a trigger for IBM to lead with SoFS and XIV storage offerings.
Digital archives are different than Compliance Archives
EMC was also quick to point out that object-storage Atmos was different from theirobject-storage EMC Centera. The former being for "digital archives" and the latter for"compliance archives". Different workloads, Different use cases, different offerings.
Ever since IBM introduced its [IBM System Storage DR550] several years ago, EMC Centera has been playing catch-up to match IBM'smany features and capabilities. I am thankful the Centera team was probably too busy to incorporate Atmos capabilities, so it was easier to make Atmos a separate offering altogether. This allows the IBM DR550 to continue to compete against Centera's existingfeature set.
Micro-RAID arrays, logical file and object-level replication
I am thankful that one of the Atmos policy-based feature is replicating individualobjects, rather than LUN-based replication and protection. SoFS supports this forlogical files regardless of their LUN placement, GAM supports replication of files and medical images across geographical sites in the grid, and the XIV supports this for 1MBchunks regardless of their hard disk drive placement. The 1MB chunk size was basedon the average object size from established Web 2.0 and DigitalArchive workloads.
I tried to explain the RAID-X capability of the XIV back in January, under muchcriticism that replication should only be done at the LUN level. I amthankful that Marc Farley on StorageRap coined the phrase[Micro-RAID array] to helpmove this new concept further. Now, file-level, object-level and chunk-level replication can be considered mainstream.
Much larger minimum capacity increments
The original XIV in January was 51TB capacity per rack, and this went up to 79TB per rack for the most recent IBM XIV Release 2 model. Several complained that nobody would purchase disk systems at such increments. Certainly, small and medium size businessesmay not consider XIV for that reason.
I am thankful Atmos offers 120TB, 240TB and 360TB sizes. The companies that purchasedisk for Web 2.0 and Digital Archive workloads do purchase disk capacity in these large sizes. Service providers add capacity to the "Cloud" to support many of theirend-clients, and so purchasing disk capacity to rent back out represents revenue generating opportunity.
Renewed attention on SOAP and REST protocols
IBM and Microsoft have been pushing SOA and Web Services for quite some time now.REST, which stands for [Representational State Transfer] allows static and dynamic HTML message passing over standard HTTP.SOAP, which was originally [Simple Object Access Protocol], and then later renamed to "Service Oriented Architecture Protocol", takes this one step further, allowingdifferent applications to send "envelopes" containing messages and data betweenapplications using HTTP, RPC, SMTP and a variety of other underlying protocols.Typically, these messages are simple text surrounded by XML tags, easily stored asfiles, or rows in databases, and served up by SOAP nodes as needed.
It's hard to show leadership until there are followers
IBM's leadership sometimes goes unnoticed until followerscreate "me, too!" offerings or establish similar business strategies. IBM's leadership in Cloud and Grid computing is no exception.Atmos is the latest me-too product offering in this space, trying pretty muchto address the same challenges that SoFS and XIV were designed for.
So, perhaps EMC is thankful that IBM has already paved the way, breaking throughthe ice on their behalf. I am thankful that perhaps I won't have to deal with as much FUD about SoFS, GAM and XIV anymore.
Tim Ferris started the festivities with [The Grand Illusion: The Real Tim Ferriss speaks]. He claimed that for the past year, he outsourced the writing of his blog to a writer from India, and an editor from the Philippines. Given that his post was dated March 31, and he writes frequently about the benefits of outsourcing, it appeared like a legitimate post. However, Tim fessed up the following day, claiming that it was April 1 in Japan where he wrote it.
Guy Kawasaki wrote[April Fools' Stories You Shouldn't Believe]including my favorite #12 "Ruby on Rails cited Twitter as the centerpiece of its new 'Rails Can Scale' marketing program." Speaking of Twitter, Fellow IBM blogger Alan Lepofsky from our Lotus Notes team wrote[Great, now there is Twitter Spam]. It looked like a real post, but then I realized, ... everything on Twitter is spam!
Topics like energy consumption and global warming were fodder for posts and pranks.The post[Was Earth Hour a joke again?], argued thatthe preparation of "Earth Hour" last week in effect used up more energy than the hour of this annual "lights-off event" actually saved. This reminded me of John Tierney's piece in the New York Times ["How virtuous is Ed Begley, Jr.?"] where a scientist explains that it is more "green" for the environment to drive a car short distances than to walk:
If you walk 1.5 miles, Mr. Goodall calculates, and replace those calories by drinking about a cup of milk, the greenhouse emissions connected with that milk (like methane from the dairy farm and carbon dioxide from the delivery truck) are just about equal to the emissions from a typical car making the same trip. And if there were two of you making the trip, then the car would definitely be the more planet-friendly way to go.
Wayan Vota, my buddy over at OLPCnews, writes in his post[Windows XO Child Centric Development] that the "Sugar" operating environment on the innovative Linux-based XO laptops will soon be re-named the"Windows XO Operating System", with their new motto "Windows XO: A Child-Centric Operating Platform for Learning, Expression and Exploration." The mocked up photo of an XO laptop with the Windows XO logo was excellent!
The economists from Freakonomics explain in [And While You're at it, Toss the Nickel] that it costs the US Government 1.7 cents to produce each penny. The US government loses $50 million dollars each year making pennies. Each nickel costs 10 cents to produce. This one was dated March 31, so it could actually be true. Sad, but true.
My favorite, however, was EMC blogger Barry Burke's post["5773 > c"] explaining howtheir scientists were able to reduce latency on the EMC SRDF disk replication capability:
What the de-dupe team found is that there is a hidden feature within recent generations of this chip that allow a single bit, under certain circumstances, to represent TWO bits of information.
Still, almost 34% of the total bits transferred were in fact aligned double-zeros, far more than all other bit combinations - and most importantly, these were quite frequently byte-aligned, as required by this new-found capability. Makes sense, if you think about it - most of those 32- and 64-bit integers are used to store numbers that are relatively small (years, months, days, credit charges, account balances, etc.). So that's why the team decided to use this new two-fer bit to represent "00".
Mathematically, if you can transmit 34% of the data using half as many bits, you reduce the number of bits you have to transfer in total by 17%. Which, while not necessarily earth-shattering, is nothing to be ashamed of. On top of the SRDF performance enhancements delivered in 5772 (30% reduction in latency or 2x the distance), this new enhancement adds another 17% latency improvement (or ~1.4x more distance at the same latency). Combined with 5772, SRDF/S customers could see a 50% reduction in latency. And 5773 allows SRDF/A cycle times to be set below 5 seconds (with RPQ) - this new feature adds a little headroom to maximize bandwidth efficiency for the shortest possible RPO.
Again, this looked real, until I did the math. Start with the speed of light in a vacuum of space ("c" in BarryB's title) which is roughly 300,000 kilometers per second, or put into more understandable units, 300 kilometers per millisecond. However, light travels slower through all other materials, and for fiber optic glass it is only 200 kilometers per millisecond. Sending a block of data across 100km, and then getting a response back that it arrived safely, is a total round-trip distance of 200km, so roughly 1 millisecond. However, EMC SRDF often takes two or three round-trips per write, versus IBM Metro Mirror on the IBM System Storage DS8000 which has got this down to a single round-trip. The number of round-trips has a much bigger effect on latency than EMC's double-bit data compression technique. With IBM, you only experience about 1 millisecond latency per write for every 100km distance between locations, the shortest latency in the industry.
It is good that once a year, you should be skeptical of what you read in the blogosphere, and sometimes check the facts!
I got some interesting queries about IBM's Scale-Out File Services [SoFS] that I mentioned in my post yesterday [Area rugs versus Wall-to-Wall carpeting]. I thought I would provide some additional details of the product.
SoFS combines three key features: a global namespace, a clustered file system, and Information LifecycleManagement (ILM). Let's tackle each one.
Global Name Space
A long time ago, IBM acquired a company called Transarc that developed Andrew File System (AFS) and DistributedFile System (DFS). These both provided global namespace capability, meaning that all of your files could beaccessible from a single URL file tree. Imagine if you have data centers in Tucson, Austin, Raleigh and Chicago.Normally, to access files from each city, you would have to mount a unique IP address for that location, and thento get to files in a different city, you'd have to mount a second, and so on. But with a global namespace, you could mount a single drive letter Z: and access files simply by using Z:/Tucson/abc or Z:/Austin/xyz. IBM uses its DFS to make this happen.
Just because you have access to a global namespace doesn't give you read/write authority to every file. IBM SoFS has full NTFS Access Control List (ACL) support, so that only those who can read or write data can access the files. A "hide unreadable" feature provideswhat I like to call "parental controls": you don't even get to see on your directly list any file or subdirectory that you don't have access to. For example, if there is a directory with 50 projects, but you only have authority tothree projects, then you only see the three subdirectories related to those projects, and nothing else.
There are other ways to get a global namespace. IBM also offers the IBM System Storage N series Virtual FileManager, Brocade offers Storage/X, and F5 acquired Acopia. These all work by putting a box in front of a set ofindependent NAS storage units, and giving you a single mount point to represent all of the file systems managedbehind the scenes. This however can sometimes be a bottleneck for performance.
Clustered File System
Often, when you have a lot of data in one place, you are also expected to deliver that data to lots of clientswith relatively good performance. Otherwise, end users revolt and get their own internal direct attach storage.To solve this, you need a clustered architecture that provides access in parallel to the data.
First, we start with a node that is optimized for CIFS and NFS access. We have clocked our node to run CIFS at577 MB/sec, and NFS at 880 MB/sec, through a 10GbE pipe between a single client and a single SoFS node. Comparethat to the 400 MB/sec you get today with 4Gbps FCP, or the 800 MB/sec you will get if you upgrade to 8 GbpsFCP, and quickly you recognize that this is comparable performance for demanding workloads.
Then, you combine multiple nodes together, and have them all be able to read/write any file in the file system, andfront-end that with a load-balancing Virtual IP address (VIPA) that spreads the requests around, and you've gotyourself a lean and mean machine for accessing data.
In 2005, IBM delivered[ASC Purple] with the world's fastest file system. 1536 nodeswere able to access billions of files in the 2 Petabyte of data. The record of 126 GB/sec access to a single filewas set, and has yet to be beaten by any other vendor since.This same file system is used in SoFS, as well as a variety of other IBM storage offerings.
The back-end storage can be SAS or FC-attached, from the DS3200 to our mighty DS8300 Turbo, as well as ourIBM System Storage DCS9550 and SAN Volume Controller (SVC), and a variety of tape libraries.
Information Lifecycle Management
Lastly, we get to ILM. With SoFS, you can have different tiers of storage, high-speed SAS or FC disk, low-speedFATA and SATA disk, and even tape. Policy-based automation allows you to place any file onto any disk tier whencreated, and other policies can migrate or delete the data trigged by certain threshold, age, or other criteria.The advantage is that this is on a file by file basis, so Z:/Tucson/Project could have a bunch of files, some ofthem on my FC disk, some of them on my SATA, and some on tape. The file path doesn't change when they move, anddifferent files in the same directory can be on different tiers.
Data movement is bi-directional. If you know you will be using a set of files for an upcoming job, say perhapsquarter-end or year-end processing, you can pre-fetch those files from tape and move them to your fastest disk pool.
There is also integrated backup support. Typically, a large NAS environment is difficult to backup. Traditionalmethods take days to scan the directory tree looking for files in need of backup. A single SoFS node can scana billion files in 95 minutes, and 8 nodes in a cluster can scan a billion files in under 15 minutes.
Recovery is even more impressive. When you recover, SoFS brings back the entire directory structure first, withall the file names in place. This would make it appear that all the data is restored, but actually it is still on tape.When you access individual files, it will then drive the recovery of that file, so your applications and end usersbasically determine the priority of the recovery. Traditional methods would wait until every file was restoredbefore letting anyone access the system.
SoFS is part of IBM's [Blue Cloud] initiativethat was launched last November 2007. Of course, IBM isn't the only one competing in this space. HDS has partneredwith BlueArc, HP has acquired PolyServe, and Sun acquired CFS for their Lustre file system. Isilon and Exanet arestart-up companies with some offerings. EMC acquired Rainfinity,and have hinted at a Hulk/Maui project that they might deliver later this year or perhaps in 2009, but by thenmight be a dollar-short and a day-late.
But why wait? IBM SoFS is available today and is orders of magnitude more scalable!