This blog is for the open exchange of ideas relating to storage and storage networking hardware, software and services.
Tony Pearson is a Senior Storage Consultant for the IBM System Storage product line, has been working in IBM storage for over 20 years, and is
author of the blook
Inside System Storage: Volume I.
Wednesday October 01, 2008
New BladeCenter Chassis with Storage Inside
Today, IBM announced its latest
[BladeCenter S] with integrated
redundant SAN fabric and disk storage inside the chassis. The tag line is "Data Center Capability, without the Data Center!"
I've gotten a few calls on this today, so I thought it would be good to blog about. To understand what is new,
you need to understand what we had in other BladeCenter chassis. In those other chassis, there were up to 14 blade
servers on the front, and switch modules for FCP and Ethernet on the back. The entire chassis was rack-mounted
to be connected to external devices.
The BladeCenter S was announced a year ago.
With the new "BladeCenter S" chassis, the storage can be included inside the chassis, as well as connecting to
the outside world. It is designed to be stand-alone, rather than rack-mounted,
plugs into a standard 100v-240v office power outlet,
and includes a dust filter in case
you keep it close to the floor, under your desk for example.
Click graphic at left for 4-minute video introduction.
(Here's also a more detailed
[7-minute video] with fellow IBM colleague Alex Yost.)
Here's what you can get with the BladeCenter S:
Up to six(6) server blades that can do the work of 25-45 traditional servers.
Up to two(2) storage blades, each can have six(6) SAS or SATA disk drive modules (DDMs)
Up to four(4) switch modules, with a variety to choose from
Shared KVM, DVD/CD burner, and USB port. You can designate which blade has access to these, useful for
installing software, attaching external devices, and so on.
The blades use either Intel, AMD or POWER processors, so you can run Windows, Linux, AIX, and
[IBM i] (the new
name for i5/OS V6R1).
Back 20 years ago, I worked with people with System/36 and System/38 systems. They loved it. Everything in
one package. This grew into the AS/400 server. Having everything in one package was such an advantage that
IBM extended this to include a few "x86 blades" to run Windows applications but share the storage and network
resources.
Now IBM has taken this one step further. The older models assumed the majority of applications run under
IBM's OS/400 or i5/OS operating system, but this new BladeCenter S does not make that assumption. You can
mix and match different blade servers as needed, and run the operating systems you need.
This is an ideal packaging for Small and Medium sized Business (SMB), remote branch offices, and retail stores.
In fact, more than 4,000 retail stores plan to run their operations using BladeCenter S this holiday season! For more
on this announcement, see the
[IBM Press Release].
IBM Tivoli Advanced Backup and Recovery for z/OS V2.1
Well, it's Tuesday again, which means IBM announcement day. With our
[big launches] we had this year, there might be some confusion on IBM terminology on how announcements are handled.
Basically, there are three levels:
Technology Demonstration
Technology demonstrations show IBM's leadership, innovation and investment direction, without having to detail a specific
product offering.
Last month's
[Project Quicksilver], for example, demonstrated the ability to handle over 1 million IOPS with Solid State Disk.
IBM is committed to develop solid state storage to create real-world uses across a broad range of applications, middleware, and systems offerings.
Preview Announcement
A preview announcement does entail a specific product offering, but may not necessarily include pricing, packaging
or specific availability dates.
Announcement
An announcement also entails a specific product offering, and does include pricing, packaging and specific
availability dates.
With our September 8 launch of the IBM Information Infrastructure strategic initiative, there were a mix of all three of these. Many of the preview announcements will be followed up with full announcements later this year. Today, the IBM Tivoli Advanced Backup and
Recovery for z/OS v2.1 was announced.
Note: If you don't use z/OS on a System z mainframe, you can stop reading now.
As many of my loyal readers know, I was lead architect for DFSMS until 2001, and so functions related to
DFSMS and z/OS are very near and dear to my heart. For Business Continuity, IBM created Aggregate Backup and
Recovery Support (ABARS) as part of the DFSMShsm component. This feature created a self-contained backup
image from data that could be either on disk or tape, including migrated data. In the event of a disaster,
an ABARS backup image can be used to bring back just the exact programs and data needed for a specific
application, speeding up the recovery process, and allowing BC/DR plans to prioritize what is most important.
To help manage ABARS, IBM has partnered with [Mainstar Software Corporation]
to offer a product that helps before, during and after the ABARS processing.
Before
ABARS requires the storage admin to have a "selection list" of data sets to process as an aggregate.
IBM Tivoli Advanced Backup and Recovery for z/OS includes Mainstar® ASAP™ to help identify the appropriate
data sets for specific applications, using information from job schedulers, JCL, and SMF records.
During
ABARS has two simple commands: ABACKUP to produce the backup image, and ARECOVER to recover it. However, if
you have hundreds of aggregates, and each aggregate has several backups, you may need some help identifying
which image to recover from.
IBM Tivoli Advanced Backup and Recovery for z/OS includes Mainstar® ABARS Manager™ to present a list of
information, making it easy to choose from. To help prep the ICF Catalogs, there is a CATSCRUB feature for either
"empty" or "full" catalog recovery at the recovery site.
After
The fact that storage admins may not be intimately familiar with the applications they are backing up is a common
source of human error.
IBM Tivoli Advanced Backup and Recovery for z/OS includes Mainstar® All/Star™ to help validate that the data sets
processed by ABACKUP are complete, to support any regulatory audit or application team verification.
This critical data tracking/inventory reporting not only identifies what isn't backed up, so you can ensure that you are not missing critical data, but also can identify which data sets are being backed up multiple times by more than one utility, so you can reduce the occurrence of redundant backups.
With v2.1 of Tivoli Advanced Backup and Recovery for z/OS, IBM has integrated Tivoli Enterprise Portal (TEP)
support. This allows you to access these functions through IBM Tivoli Monitor v6 GUI on a Linux, UNIX or Windows
workstation. IBM Tivoli Monitor has full support to integrate Web 2.0, multi-media and frames. This means
that any other product that can be rendered in a browser can be embedded and supported with launch-in-context
capability.
(If you have not separately purchased a license to IBM Tivoli Monitoring V6.2, don't worry, you can obtain
the TEP-based function by acquiring a no-charge, limited use license to IBM Tivoli Monitoring
Services on z/OS, V6.2.)
In addition to supporting IBM's many DFSMS backup methods,
from ABARS to IDCAMS to IEBGENER,
IBM Tivoli Advanced Backup and Recovery v2.1 can also support third-party products from Innovation Data Processing and Computer Associates.
As many people re-discover the mainframe as the cost-effective platform that it has always been, migrating
applications back to the mainframe to reduce costs, they need solutions that work across both mainframe and
distributed systems during this transition. IBM Tivoli Advanced Backup and Recovery for z/OS can help.
Wrapping up my week on successful uses of information, I thought I would discuss the visualization of data.
Not just bar charts and pie charts, but how effective visual information can be on multi-variable plots.
IBM's [Many Eyes] recognizes that 70 percent
of our sensory input neurons in our brain our focused on visual inputs, and so we might recognize patterns
if only data was presented in more interesting and visual representations.
In addition to X/Y axis, variables can be presented by size of circle and color.
Here's an example plot of the past US bailouts, with variables representing amount, year, company and
industry.
This plot does not include the current 700 Billion US Dollar bailout currently under discussion.
This is part of IBM's Collaborative User Experience (CUE) research lab. The software is available Web2.0
style at no charge, just upload your data set, and choose one of 16 different presentation styles.
These plots get even more interesting when you animate them over time. In 2006, Hans Rosling presented
data he gathered from the United Nations and other publicly funded sources and presented his findings at
the TED conference. Here is the 20-minute video of that presentation (click on play at right), titled
["Debunking third-world myths with the best stats you've ever seen"], in which he debunks the myth that all
countries fall into two distinct categories: Industrialized and Developing.
Amazingly, the data--as well as the software to analyze it--is available at
[GapMinder.org] Web site.
For more information on how you can deploy an information infrastructure that allows you to search, visualize and leverage the most value from your information, contact your local IBM representative or IBM Business Partner.
Continuing this week's theme on customer references of IBM solutions,
IBM helps companies large and small in the Healthcare and Life Sciences industry. I have two examples today.
First, we have
[Northwest Radiology Network], a small firm with 180 employees, having to deal with ten thousand medical images per month. Here is an excerpt from the
[IBM Press Release]:
"IBM announced that Northwest Radiology Network has gone live with a new virtualized enterprise of IBM servers and storage to support its growing medical imaging needs, giving its four locations an enterprise-class infrastructure which enables its doctors to recover medical image reports faster for analysis and enables remote 24x7 access to its medical image report system.
Founded in 1967, Northwest Radiology (NWR) is ranked as one of the largest physician groups in the Indianapolis, Indiana area. With 180 employees who offer the Central Indiana community comprehensive inpatient and outpatient imaging services such as mammography, ultrasonography, CT scans, PET-CT scans, bone density scans and MRIs – the Network had a dramatic need to develop a centralized infrastructure where large amounts of data could be stored and shared. A new data center would benefit the company’s clientele; which includes area hospitals and doctor’s offices serving thousands of patients each year.
Storing more than ten thousand medical imaging reports and radiographic images each month for doctors to analyze, the Network realized it had single points of failure and at one point a critical report server failed. Northwest Radiology turned to IBM and IBM Business Partner Software Information Systems (SIS) for a more efficient solution to prevent any possible downtime in the future.
SIS recommended and installed a virtualized infrastructure with IBM servers and storage as the heart of Northwest Radiology’s Indianapolis data center. By April 2007, Northwest Radiology replaced eight servers and direct attached storage with just two IBM System x3650 servers connected to an IBM System Storage DS3400. Today, the new servers run 15 virtual servers to ensure the availability of their services 24x7. When the business needs it, a new server can be provisioned in just minutes. With a Fibre Channel on the SAN Disk, the DS3400 not only increased performance but also met NWR’s requirement to not have one single point of failure. With three TB of storage capacity, they can meet the demands of increased business well into the future. The systems are also now easily managed from a remote site."
“Uptime is paramount in our business. We selected IBM based on the reliability and flexibility of IBM System x servers and the IBM System Storage DS3400,” said Marty Buening, IT Director, Northwest Radiology Network. “The virtualized infrastructure and the SAN storage array that SIS and IBM brought to the table is improving our service and giving our doctors and staff piece of mind knowing each patient’s medical imaging reports are always available.”
Second, we have
[Iowa Health System], a large enterprise with over 19,000 employees, managing four million patients and hundreds of TBs of data.
Here is a 4-minute video on IBM TV from the good folks at Iowa Health System discussing the
IBM Grid Medical Archive Solution (GMAS) as part of their information infrastructure for their
Picture Archiving and Communication Systems (PACS) application.
For more details about Iowa Health System's deployment of GMAS, see Paul Shread's GridComputing article
[Putting Medical Data on the Grid].
In both cases, IBM technology was able to provide remote access to medical information, making images and patient records available to more doctors, specialists and radiologists. Last January, in my post
[Five in Five], IBM had predicted that remote access to healthcare would have an impact over the next five years.
Whether you are a small company or a large one, IBM probably has the right solution for you.
No post today. I will be joining the majority of IBMers in Tucson for "Days of Caring" held annually by
the [United Way of Tucson and Southern Arizona].
IBM has been doing this for years, and we are joined by volunteers from other local businesses, including
HealthNet, Wells Fargo bank, Texas Instruments, KVOA local NBC affiliate, 94.9 MixFM radio, and others.
The "days" involve a kick-off last week (Sep 19) and two days of helping local charities (Sep 24 and 27).
We are split into teams and are assigned out to help fix up old buildings, clean out gutters, re-paint
walls. My team will be sorting canned goods at the local
[Community Food Bank], and assembling boxes of items to be
given out to needy families.
Continuing this week's theme on customer references of IBM's solutions, today I will discuss
the success at Kantana Animation Studios.
Here is a 3-minute video from the good folks at Kantana Animation Studios,
part of the [Kantana Group].
They produced the animated movie [Khan Kluay]
using IBM Scale-out File Services (SoFS), a product IBM announced last November 2007.
As a film-maker myself (see this sample [Highlights clip])
and active member of the Tucson Film Society,
I am pleased to see IBM so greatly involved in the film industry. I've had the pleasure to visit some of these
animation studios myself and meet with other film-makers at various conferences.
For more details on Kantana's implementation, see the
[Case Study]
When Factual Observations Mislead and Misrepresent
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 could
pose 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 putting
a 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 been
retracted] (Update: has now been corrected). Other bloggers borrow the false statement
[for their own blog], perhaps not realizing the
retractions were made elsewhere. Newspapers are unable to fix a previous edition, so are forced to publish
retractions 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 with
chimpanzees, 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 fictitious
Mr. 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 between
different 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 other
software to help re-locate and re-separate the data to re-balance the I/Os. Instead, you just enjoy consistent
performance.
The IBM XIV offers thin provisioning, allowing LUNs to grow as needed to accommodate business needs. You don't
have to estimate or over-allocate space for planned future projects. You don't have to monitor if a LUN is reaching
80 or 90 percent full. You don't have to carve larger and larger LUNs and schedule time on the weekends to move the
data over to these new bigger spaces. Instead, you just write to the disk, monitoring the box as a whole, rather
than 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 problem
is that many failures happen 3-5 years out, and disk manufacturers move on to bigger capacities and different
form factors, making it sometimes difficult to find an exact replacement or forcing customers to keep their own stock
of 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.
Fellow blogger from EMC Mark Twomey on his StorageZilla blog, posted about
[
Steinhardt's Rule of Customer Beliefs] with his own Twomey Corollary. Here is an excerpt:
In priority order, customers believe:
Their own experience
The experiences of other customers
Objective third-party sources
Everybody else
Vendors
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 bloggers
presenting 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 is
trying to capture. Certainly, I can't argue with the top two: a customer's own experience and the experiences
of 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 folks
at [NaviSite], one of our many
customer references for the IBM XIV Storage System.
Well, this has been an interesting two weeks. On week 1, I focused on IBM's strategy and four key
solutions areas: Information Availability, Information Security, Information Retention, and Information
Compliance. On week 2, I focused on individual products, their attributes, features and functions.
Which week drew more blog traffic? You guessed it--week 1. Apparently, people want to know more about
solutions to their challenges and problems, and not just see what piece part components are available.
While IBM had switched over to solution-selling a while ago, some of our competitors are still in
product-selling mode, and try to frame all competitive comparisons on a product-by-product basis.
In my post
[Supermarkets and Specialty Shops], I drew the analogy that the IT supermarkets (IBM, HP, Sun and Dell) are focused
on selling solutions, but the IT specialty shops (HDS, EMC, and others) are still focused on
products.
Certainly, the transition from product-focused to solution-focused is not an easy one.
As the IT industry matures, more and more clients are looking to buy solutions from their
vendors. What does it take to change behaviour of newly acquired employees, recently hired sales reps, and business partners, many of whom come from product-centric cultures, to match this dramatic shift in the marketplace? Let's take a look at change in other areas of the world.
On the
[Freakonomics blog], Stephen Dubner discusses how clever people in Israel have figured out a
way to get people to clean up after their pets in public places. This is a problem in many countries.
Here we see an old idea, the
[carrot-and-stick] approach, combined with new
information technology. Here's an excerpt:
"In order to keep a city’s streets clean of dog poop, require dog owners to submit DNA samples from their pets when they get licenses; then use that DNA database to trace any left-behind poop and send the dogs’ owners stiff fines.
Well, it took three years but the Israeli city of Petah Tikva has actually put this plan to work:
The city will use the DNA database it is building to match feces to a registered dog and identify its owner.
Owners who scoop up their dogs’ droppings and place them in specially marked bins on Petah Tikva’s streets will be eligible for rewards of pet food coupons and dog toys.
But droppings found underfoot in the street and matched through the DNA database to a registered pet could earn its owner a municipal fine."
Sometimes, if enough people change, then changing behaviours of the few remaining becomes much easier. Dan
Lockton on his Architectures of Control blog posts about the
[London Design
Festival - Greengaged].
This year, the festival focused on behavior changes for a greener environment, ecodesign and sustainable issues in design.
Here's an excerpt and corresponding 5-minute YouTube video:
"Lea Simpson started with
[this great Candid Camera clip] from 1960s demonstrating how easily social proof can be used to influence behaviour.
Lea argued three important points relevant to behaviour change:
Behaviour change requires behaviour (i.e. the behaviour of others: social effects are critical, as we respond to others’ behaviour which in turn affects our own; targeting the ‘right’ people allows behaviour to spread)
Behaviour and motivation are two different things: To change behaviour, you need to understand and work with people’s motivations - which may be very different for different people.
Desire is not enough: lots of people desire to behave differently, but it needs to be very easy for them to do it before it actually happens."
Of course, tax and government regulations can heavily influence behaviour and decisions. Since today is
[International Talk Like a Pirate Day], I thought I would finish this post off with this interesting piece on Google barges.
Some companies, like IBM and Google, seem more adaptable to changing behaviour and trying out fresh new ideas.
Will Runyon over on the
Raised Floor blog, has a post about Google's patent for
[Data center barges on the sea]:
"The idea is to use waves to power the data centers, ocean water to cool them, and a moored distance of seven miles or more to avoid paying taxes."
Arrr! Now that's what I call a new way of looking at things!
Continuing this week's theme on products that were part of last week's
IBM Information Infrastructure launch, today I'll cover the TS2900.
IBM System Storage TS2900 Tape Autoloader
This little baby is SWEET! At 1U high, it holds a single drive and up to 9 cartridges,
up to a total of 14.4 TB at 2:1 compression. The
drive can be a Half-Height (HH) LTO-3 or LTO-4 drive. (It is called an autoloader because there is
only a single drive. Automation with multiple drives are called libraries).
This can be rack-mounted, or sit on your desktop. There is an I/O station for inserting
or removing individual cartridges, as well as a removable tape magazine to populate or
remove the tapes in a more efficient manner.
Both LTO3 and LTO4 support a mix of regular and "Write Once, Read Many" (WORM) media to
help comply with regulations demanding "Non-erasable, Non-rewriteable" storage. The
LTO4 can also support on-drive encryption, managed by the IBM Encryption Key Manager (EKM).
To learn more, see the IBM System Storage
[TS2900 page].
Continuing this week's theme about the products that were part of last week's IBM Information Infrastructure
launch, I will cover today the IBM System Storage TS7650G ProtecTIER deduplication gateway.
Before acquisition, Diligent offered only software. The task of putting this software on an appropriate x86 server with sufficient
memory and processor capability was left as an exercise for the storage admin. With the TS7650G, IBM installs the
ProtectTIER software on the fastest servers in the industry, the IBM System x3850 M2 and x3950 M2. This eliminates
having the storage admins pretend that they have hardware engineering degrees.
Before acquisition, the software worked only on a single system. IBM was able to offer multiple configurations of the TS7650G, including a single-controller model as well as a clustered dual-controller model. The clustered dual-controller model can ingest data at an impressive 900 MB/sec, which is up to nine times faster than some of the
competitive deduplication offerings.
Before acquisition, ProtecTIER emulated DLT tape technology. This limited its viability, as the market share
for DLT has dropped dramatically, and continues to dwindle. Most of the major backup software support DLT as an
option, but going forward this may not be true much longer for new tape applications.
IBM was able to extend support by adding LTO emulation on the
TS7650G gateway, future-proofing this into the 21st Century.
At last week's launch, covering so many products with so few slides, this announcement was shrunken down to a
single line "Store 25 TB of backups onto 1 TB of disk, in 8 hours" and perhaps a few people missed that this was
actually covering two key features.
With deduplication, the TS7650G might get up to 25 times reduction on disk. If you back up a 1 TB data base
that changes only slightly from one day to the next, once a day for 25 days, it might only take 1 TB, or so, of disk to
hold all the unique versions, as most of the blocks would be identical, rather than 25 TB on traditional disk or tape
storage systems. The TS7650G can manage up to 1 PB of disk,
which could represent in theory up to 25 PB of backup data.
With an ingest rate of 900 MB/sec, the TS7650G could ingest 25 TB of backups during a typical 8 hour backup window.
The 25 TB of the first may not necessarily be the 25 TB of the second, but the wording was convenient for marketing
purposes, and a comma was used to ensure no misunderstandings.
Of course, depending on the type of application, the frequency of daily change, and the backup software employed, your mileage may vary.
Continuing this week's theme about new products that were mentioned in last week's launch, today I will
cover the new
[S24 and S54 frames].
Before these new frames, customers had two choices for their tape cartridges: keep them in an automated
tape library, or on an external shelf. Most of the critics of tape focus almost entirely on the problems
related to the latter. When tapes are placed outside of automation, you need human intervention to find
and fetch the tapes, tapes can be misplaced or misfiled, tapes can be dropped, tapes can get liquids spilled
on them, and so on. These problems just don't happen when stored in automated tape libraries.
Until now, the number of cartridges were limited to the surface area of the wall accessible by the robotic
picker. Whether the robot rotates in a circle picking from dodecagon walls, or back and forth from long
rectangular walls, the problem was the same.
But what about tapes that may not need to be readily accessible, but still automated? With the new
high density frames, you can now stack tapes several cartridges deep, spring loaded deep shelves that
push the tape cartridges up to the front one at a time. The high-density frame design might have been inspired by the
famous [Pez] candy dispenser, but at 70.9 inches, does not beat the
[World's Tallest Pez Dispenser].
(Note: PEZ® is a registered trademark of Pez Candy, Inc.)
In a regular cartridge-only frame, like the D23, you have slots for 200 cartridges on the left, and 200
cartridges on the right, and the robotic picker can pull out and push back cartridges into any of these
slot positions. In the new S24, there are still 200 slots on the left, now referred to as "tier 0",
but up to 800 cartridges on the right. In each slot there are up to four 3592 cartridges, the position
immediately reachable to the picker is referred to as "tier 1", and the ones tucked behind
are "tier 2", "tier 3" and "tier 4".
Tier 0
<- - - S24 frame - - - >
Tier 1
Tier 2
Tier 3
Tier 4
Tape A
Robotic Picker
Tape B
Tape C
Tape D
Tape E
We have fun slow-motion videos we show customers on how these work. For example, in the diagram above, let's
suppose you want to fetch Tape E in the "tier 4" position. The following sequence happens:
Robotic picker pulls "tier 1" tape cartridge B, and pushes it into another shelf slot. Tapes C, D and E get pushed up to be Tiers 1, 2 and 3 now.
Robotic picker pulls "tier 1" tape cartridge C, and puts it in another shelf slot. Tapes D and E get pushed up to be Tiers 1 and 2 now.
Robotic picker pulls "tier 1" tape cartridge D, and puts it in another shelf slot. Tape E gets pushed up to be Tier 1 now.
Robotic picker pulls "tier 1" tape cartridge E, this is the tape we wanted, and can move it to the drive.
The other three cartridges (B, C and D) are then pulled out of the temporary slot, and pushed back into their original order.
In this manner, the most recently referenced tape cartridges will be immediately accessible, and the ones least
referenced will eventually migrate to the deeper tiers. The 3592 cartridges can be used with either TS1120 or
TS1130 drives. Each cartridge can hold up to 3TB of data (1TB raw, at 3:1 compression), so the entire frame
could hold 3PB in just 10 square feet of floor space. Five D23 frames could be consolidated down to two S24 frames.
The S24 frame comes in "Capacity on Demand" pricing options. The base model of the S24 has just tiers 0, 1 and 2, for
a total capacity of 600 cartridges. You can then later license tiers 3 and 4 when needed.
The S54 is basically similar in operation, but for LTO cartridges. It works with any mix of LTO-1, LTO-2, LTO-3 and
LTO-4 cartridges.
The left side holds tier 0 as before, but the right side has up to five LTO cartridges deep. For Capacity on Demand pricing,
the base model supports 660 cartridges (tiers 0,1,2), with options to upgrade for the additional 660 cartridges.
The total 1320 cartridges could hold up to 2.1 PB of data (at 2:1 compression). One S54 frame could replace
three traditional S53 frames that held only 440 LTO cartridges each.
If you have both TS1100 series and LTO drives in your TS3500 tape library, then you can have
both S24 and S54 frames side by side.
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 the
products 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 radical
game-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 other
planning/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 load
for bug fixes to the software. XIV offers many of the features that people enjoy in other disk
systems, 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 the
business 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 its
CLARiiON and DMX products.
On the IBM XIV, each 1MB chunk is written on two different disks in different modules. When disks were
expensive, how much usable space for a given set of HDD was worthy of argument. Today, we sell you a
big black box, with 79TB usable, for (insert dollar figure here). For those who feel 79TB is
too big to swallow all at once, IBM offers "capacity on demand" pricing, where you can pay initially for as little
as 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) and
the remainder to UPS, power conversion, processors and cache memory consumption. Again, the XIV is a big
black box, and you can compare the 8.4 KW of this high-performance, low-cost storage one-frame system with the
wattage consumed by competitive two-frame (sometimes called two-bay) systems, if you are willing to take some trade-offs. To get
comparable 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 the
inherent 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-tape
solutions. When it comes to being green, you can't get any greener storage than tape! Blended disk-and-tape
solutions 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.
In Monday's post,
[IBM Information Infrastructure launches today], I explained how this strategic initiative fit into IBM's New Enterprise
Data Center vision. The launch has been reviewed in the press now all over the world.
This post will focus on Information Compliance, the fourth and final part of the four-part series this week.
I have received a few queries on my choice of sequence for this series: Availability, Security, Retention and
Compliance.
Why not have them in alphabetical order? IBM avoids alphabetizing in one language, because then
it may not be alphabetized when translated to other languages.
Why not have them in a sequence that spells out
an easy to remember mnemonic, like "CARS"? Again, when translated to other languages, those mnemonics no longer
work.
Instead, I worked with our marketing team for a more appropriate sequence, based on psychology and the
cognitive bias of [primacy and recency effects].
Here's another short 2-minute video, on Information Compliance
Full disclosure: I am not a lawyer. The following will delve
into areas related to government and industry regulations. Consult
your risk officer or legal counsel to make sure any IT solution is appropriate
for your country, your industry, or your specific situation.
IBM estimates there are over 20,000 regulations worldwide related to information storage and transmission.
For information availability, some industry regulations mandate a secondary copy a minimum distance away to
protect against regional disasters like hurricanes or tsunamis.
IBM offers Metro Mirror (up to 300km) and Global Mirror (unlimited distance) disk mirroring to support these
requirements.
For information security, some regulations relate to privacy and prevention of unauthorized access. Two
prominent ones in the United States are:
Health Insurance Portability and Accountability Act (HIPAA) of 1996
HIPAA regulates health care providers, health plans, and health care clearinghouses in how they handle the privacy of patient's medical records. These regulations apply whether the information is on film, paper, or stored
electronically. Obviously, electronic medical records are easier to keep private. Here is an excerpt from
an article from [WebMD]:
"There are very good ways to protect data electronically. Although it sounds scary, it makes data more protected than current paper records. For example, think about someone looking at your medical chart in the hospital. It has a record of all that is happening -- lab results, doctor consultations, nursing notes, orders, prescriptions, etc. Anybody who opens it for whatever reason can see all of this information. But if the chart is an electronic record, it's easy to limit access to any of that. So a physical therapist writing physical therapy notes can only see information related to physical therapy. There is an opportunity with electronic records to limit information to those who really need to see it. It could in many ways allow more privacy than current paper records."
GLBA regulates the handling of sensitive customer information by banks, securities firms, insurance companies, and other financial service providers. Financial companies use tape encryption to comply with GLBA when sending tapes from one firm to another. IBM was the first to deliver tape drive encryption with
the TS1120, and then later with LTO-4 and TS1130 tape drives.
For information retention, there are a lot of regulations that deal with how information is stored, in some cases
immutable to protect against unethical tampering, and when it can be discarded. Two prominent regulations in
the United States are:
U.S. Securities and Exchange Commission (SEC) 17a-4 of 1997
In the past, the IT industry
used the acronym "WORM" which stands for the "Write Once, Read Many" nature of certain media, like CDs, DVDs,
optical and tape cartridges. Unfortunately, WORM does not apply to disk-based solutions, so IBM adopted the language
from SEC 17a-4 that calls for storage that is "Non-Erasable, Non-Rewriteable" or NENR. This new umbrella term
applies to disk-based solutions, as well as tape and optical WORM media.
SEC 17a-4 indicates that broker/dealers and exchange members must preserve all electronic communications relating to the business of their firmm a specific period of time. During this time, the information must not be erased or re-written.
Sarbanes-Oxley (SOX) Act of 2002
SOX was born in the wake of
[Enron and other corporate scandals]. It protects the way that financial information is
stored, maintained and presented to investors, as well as disciplines those who break its rules. It applies only
to public companies, i.e. those that offer their securities (stock shares, bonds, liabilities) to be sold to the public
through a listing on a U.S. exchange, such as NASDAQ or NYSE.
SOX focuses on preventing CEOs and other executives from tampering the financial records.
To meet compliance, companies are turning to the
[IBM System Storage DR550] which provides
Non-erasable, Non-rewriteable (NENR) storage for financial records. Unlike competitive products like EMC Centera that
function mostly as space-heaters on the data center floor once they filled up, the DR550 can be
configured as a blended disk-and-tape storage system, so that the most recent, and most likely to be accessed data, remains on disk, but the older, least likely to be accessed data, is moved automatically to less expensive, more environment-friendly "green" tape media.
Did SOX hurt the United States' competitiveness? Critics feared that these new regulations would discourage new
companies from going public. Earnst & Young found these fears did not come true, and published a study
[U.S. Record IPO Activity from 2006 Continues in 2007]. In fact, the improved confidence that SOX has given investors has given rise to similar
legislation in other parts of the world: Euro-Sox for the European Union Investor Protection Act, and J-SOX
Financial Instruments and Exchange Law for Japan.
For those who only read the first and last paragraphs of each post, here is my recap:
Information Compliance is ensuring that information is protected against regional disasters, unauthorized
access, and unethical tampering, as required to meet industry and government regulations. Such regulations
often apply if the information is stored on traditional paper or film media, but can often be handled more cost-effectively when stored electronically. Appropriate IT governance can help maintain investor confidence.
In Monday's post,
[IBM Information Infrastructure launches today], I explained how this strategic initiative fit into IBM's New Enterprise
Data Center vision. The launch was presented at the IBM Storage and Storage Networking Symposium to over 400 attendees
in Montpelier, France, with corresponding standing-room-only crowds in New York and Tokyo.
This post will focus on Information Retention, the third of the four-part series this week.
Here's another short 2-minute video, on Information Retention
Let's start with some interesting statistics.
Fellow blogger Robin Harris on his StorageMojo blog has an interesting post:
[Our changing file workloads],
which discusses the findings of study titled
"Measurement and Analysis of Large-Scale Network File System Workloads"
[14-page PDF]. This paper was a collaboration
between researchers from University of California Santa Cruz and our friends at NetApp.
Here's an excerpt from the study:
Compared to Previous Studies:
Both of our workloads are more write-oriented. Read to write byte ratios have significantly decreased.
Read-write access patterns have increased 30-fold relative to read-only and write-only access patterns.
Most bytes are transferred in longer sequential runs. These runs are an order of magnitude larger.
Most bytes transferred are from larger files. File sizes are up to an order of magnitude larger.
Files live an order of magnitude longer. Fewer than 50 percent are deleted within a day of creation.
New Observations:
Files are rarely re-opened. Over 66 percent are re-opened once and 95% fewer than five times.
Files re-opens are temporally related. Over 60 percent of re-opens occur within a minute of the first.
A small fraction of clients account for a large fraction of file activity. Fewer than 1 percent of clients account for
50 percent of file requests.
Files are infrequently shared by more than one client. Over 76 percent of files are never opened by more than one client.
File sharing is rarely concurrent and sharing is usually read-only. Only 5 percent of files opened by multiple clients are concurrent and 90 percent of sharing is read-only.
Most file types do not have a common access pattern.
Why are files being kept ten times longer than before? Because the information still has value:
Provide historical context
Gain insight to specific situations, market segment demographics, or trends in the greater marketplace
Help innovate new ideas for products and services
Make better, smarter decisions
National Public Radio (NPR) had an interesting piece the other day. By analyzing old photos, a researcher for Cold War Analysis was able to identify an interesting
[pattern for Russian presidents].
(Be sure to listen to the 3-minute audio to hear a hilarious song about the results!)
Which brings me to my own collection of "old photos". I bought my first digital camera in the year 2000,
and have taken over 15,000 pictures since then. Before that,
I used 35mm film camera, getting the negatives developed and prints made.
Some of these date back to my years in High School and College. I have a mix of sizes, from 3x5, 4x6 and 5x7 inches,
and sometimes I got double prints.
Only a small portion are organized into
scrapbooks. The rest are in envelopes, prints and negatives, in boxes taking up half of my linen closet in my house.
Following the success of the
[Library of Congress using flickr],
I decided the best way to organize these was to have them digitized first. There are several ways to do this.
Flat-bed scanner
This method is just too time consuming. Lift the lid place 1 or a few prints face down on the glass, close the lid,
press the button, and then repeat. I estimate 70 percent of my photos are in
[landscape orientation], and 30 percent in
[portrait mode]. I can either spend extra time to
orient each photo correctly on the glass, or rotate the digital image later.
Sheet-feed scanner
I was pleased to learn that my Fujitsu ScanSnap S510 sheet-feed scanner can take in a short stack (dozen or so) photos, and generate JPEG format files for each. I can select 150, 300 or 600dpi, and five levels of JPEG compression.
All the photos feed in portrait mode, which I can then rotate later on the computer once digitized.
A command line tool called
[ImageMagick] can help automate the rotations.
While I highly recommend the ScanSnap scanner, this is still a time-consuming process for thousands of photos.
Inside System Storage -- hosted by Tony Pearson
technorati tags: 
