Storwize V7000 and the IBM NAS software were married Wednesday, October 12, 2012 at midnight at IBM Storage chapel in San Jose, California. The Reverend Rod Adkins officiated. Following the ceremony, the bride’s parents hosted a reception at the Almaden Research Center.
The bride comes from the NAS family who were in attendance. She also has ties with the Tivoli and GPFS families deep within the storage community. There were family members from the X series family who were at the ceremony.
The groom comes from a long line of storage products. XiV, DS8800 and SVC were all part of the festivities and supported the groom throughout entire day.
The couple will honeymoon Redwood City, California with a visit to the Storage Performance Council.
After long anticipation, IBM is now in the unified storage market with the introduction of the Storwize V7000 Unified (SV7kU?). The system stands as small as 6U of rack space and can flex up to four clustered systems (via RPQ) supporting internal SAS, SATA or virtualized external disk from other vendors.
The V7000 Unified is a midrange disk system that will allow new V7000 or existing V7000 customers the ability to integrate their NAS workload into the system. Using the standard V7000 shelf, IBM has added two 3650m3 servers with the IBM NAS software stack to complete a unified architecture. A new GUI that ingrates the NAS portion of the software is now available that will combine management for both technologies with a few mouse clicks. Setup of the system stays the same with the simplified USB key approach. Customers have reported that between the USB key installation and the wizard driven alerts, the V7000 has been one of the easiest systems to install and configure. IBM decided to keep these features in the enhanced GUI.
Here are some screenshots that show the new integration of the NAS software stack
V7000 Unified will support NFS/CIFS/FTP/HTTPs/SCP protocols in addition to block functions FCP and iSCSI. It will also support file replication and file level snapshots for business continuity in addition to existing block functions.
Another function in the V7000 Unified that will help customers is the introduction of the IBM Active Cloud Engine. What is it? Think of it as a very smart, very fast robot – that never sleeps – keeping your cloud storage neat, tidy and running smoothly. Think Rosie the robot from The Jetsons.
This engine is a policy driven engine that will help improve the storage efficiency by automatically placing, moving and deleting files to the appropriate storage. The efficiency gain comes from storing the files where they should be with out an administrator manually moving them. As data is gets older, the engine can move the file to another location where the price per TB is less and even delete the file if necessary.
The movement is done seamlessly and the end user does not have any idea their data has moved. Another aspect of the engine is identifying files for backups or replication to a DR location. As the data ages, the data continues the life cycle through the data center without storage administrators intervention.
Data can be moved from internal disk to external virtualized disk and even to tape. The diagram below shows the movement from file creation to 180 days old and off to deduped tape.
The policy can be created from a wizard in the V7000 Unified GUI by creating thresholds and start times. Customers can also exclude certain files by different file attributes like size or last accessed. For the more advanced customer, an edit feature of the policy is allowed.
Another question people are asking is about the relationship with Netapp and how will this product effect the N series product line. IBM is expanding the midrange storage portfolio by offering both the new V7000 Unified along with our N series products to focus on different client needs.
N series continues to be IBM’s offering focused on clients who have a primary need for NAS optimized (file) workloads. Existing N series clients with growing data requirements will continue to require additional N series disk drives, expansion units, and new systems to meet their needs.
IBM Storwize V7000 Unified will particularly appeal to clients who have a primary need for storage to support block optimized workloads with additional needs to consolidate file workloads for greater efficiency (unified storage). Storwize V7000 Unified is also targeted to clients that can benefit from the unique capabilities of IBM Active Cloud Engine or to clients that already are using Storwize V7000 or SONAS.
Just like in real life, we have seen other marriages come and go but this one seems to be different. The V7000 Unified is using the best of the storage portfolio and bringing value to the customer. IBM is also leveraging the investments made over 10 years of innovation; Virtualization, Easy Tier, Simplified GUI, Active Cloud Engine and is producing a product that will accomplish the lowering total cost of ownership.
As goes with the tradition of the bride to have good-luck: “Something old, something new, something borrowed, something blue, and a silver sixpence in her shoe." (You can find this poem in Leslie Jones' book "Happy is the Bride the Sun Shines On."). We find the IBM version of this offering good luck with the following: Something Old: 4,500 V7000 systems sold last year Something New: Active Cloud Engine Something Borrowed: Storage Virtualization Something Blue: Storwize V7000 Unified, a true IBM organic product
I am still looking for the sixpence but feel free to mail us one and we will attach it to the bezel of each controller.
The old adage of faster, smaller, cheaper has been revived in the N series product line. This week (officially) IBM released the information around the highly anticipated OEM re-brand of Netapp's FAS 2040; the N3400. This system has a small 2U form factor but delivers higher performance than its beefier brother the N3600. If you want to see a full comparison of the three boxes, click here for more information.
IBM has three systems that round out the entry level or departmental storage platform. The N3600, the N3300 and now the N3400. All three are based on internal drives with some expansion to a few shelves as needed. The N3600 comes with 20 internal drives and the smaller N3300 and N3400 comes with only 12 internal disks and can expand to a maximum capacity of 136TB. There are two controllers that allow administrators to have a high availability solution for low cost. This makes the system more attractive as it also supports FCP, iSCSI, CIFS and NFS all from one platform.
The N3400 does have a few things I want to point out:
8GB of RAM (2x the amount in the N3600 and 4x the amount of the N3300)
512 mb NVRAM
2 integrated SAS ports and 8 total 1GBPS Ethernet port
PCI-e port for expansion
All of these help set this box up for an important role within your datacenter. If you compare this system with other storage systems in the market, you find the new N3400 is well stacked and can compete even with larger mid-tier systems. This box is ideal for our SMB clients who really need the all in one system with the horsepower to keep up with a growing company. The system is a long way from the first entry level system IBM decided to roll out, the N3700. If the two were to be compared the N3700 would be a 'Happy Meal' and the N3400 would be a super sized 2lb Angus burger with fries and shake, maybe even an apple pie.
This new system is considered ideal for both Windows consolidation and virtual environments alike. With the additional ports the system does leverage a larger life span as the new EXN 3000 SAS shelves are becoming more of the standard for the N series product line. The system on the other hand does not support 10GBPS cards or FCoE as the N3600 does. But as all N series systems support the same Data Ontap code, the robust system uses the same commands, interface and is built on the same technology as the other N60x0 and N7X000 lines.
Overall, this is an enhanced refresh of the exisitng N3300 with more ability to scale with currently technologies. The performance will be more than the N3600 which begs the question of the need for the N3300/N3600 systems. I suspect as Data Ontap 8 becomes general available from Netapp, there will be more entry level storage devices released.
For more information on the N3400 and all other N series related information, follow this link or contact your local IBM Storage Rep.
If you haven't heard (get from under that rock) IBM is turning 100 this year and the company is having an awesome time celebrating our longevity. From technical advances, the Apollo program to blazing trails through race and gender equality, IBM has and IS doing the job for all of the world. The company has changed in so many ways and has to adapt in ways only IBMers can but we have survived and thrived.
Find more information about our centennial celebration here.
Here is a great 100 second video of all the cool and great things IBM has done over the last 100 years.
When I first started working at IBM, we had a couple of NAS storage devices: NAS 100, NAS 300(G) and the NAS 500. The NAS 100 was a 1U server appliance that used Windows 2000 and so did the NAS 200 device, all built on IBM hardware. The NAS 500 was on an AIX system also from the IBM stock. They were traditional NAS type systems and IBM sold them as let us build the system for you so you don't have to. Somewhat limited in functionality but did the job they were designed to do, serve NAS data.
That same year, IBM decided to partner with a company that was doing some things in the storage market that looked really interesting. Network Appliance had just started gaining steam with their Data Ontap code (6.something if I remember correctly) and had broken the barrier that IBM systems lacked. Unified protocols from a single architecture and integration into other products like Exchange and SQL using their cool snapshot technology. It took some time to get up to speed on the new Netapp technology with snap this and snap that, but soon we were all talking about waffles and aggrs.
Through out the years, the product set grew and so did the hardware offering. We kept up with the releases and for the most part a 20-60 day lag in release of new software was ok for most IBM customers. We partnered with the sales teams and support teams to help grow the N series customers base and to keep them happy. As with any partnership there are bumps along the way and there seemed to be two parents telling each other they agree to disagree. All in all the N series system has been very successful at IBM.
But as the years progressed, new technology like XiV, Real Time Compression, TSM Flash Copy Manager etc, have filled some of those voids previously filled by N series in the IBM portfolio. As with many companies there are products that overlap and N series does overlap over half of the product line at IBM Storage. Positioning became harder as sales teams questioned when to sale N series and when to sell something "blue". We quickly learned that customers really liked what N series brought to the table and how the solution could be so flexible.
Now with the news of Netapp purchasing Engenio I wonder how the relationship between IBM and Netapp will survive. IBM also rebrands the Engenio products as the IBM DS 3k, 4k and 5k. I guess the bigger question is now what will Netapp do with that product line? If history is any indicator, they will simple keep things like they are for some time and slowly move the customers over to a Data OnTap product. The other question is how long will IBM keep sending money over to Netapp for products that we sale and support?
Labor day has come and gone and so has all of the holidays
between now and Thanksgiving. This is
only augmented with the hope that your favorite football team (both American football
and what we call Soccer) has a great weekend match and you get to celebrate
with the beverage of your choice.
During your work-week, which can and sometimes does include
weekends, all you hear is no more money to do the things you have to do to keep
the business running. If you have kept
up with squeezing more out your systems with virtualization that’s great but
your network is now overtaxed. The staff
that used to take care of certain aspects of the day to day running of your
data center has been let go and their job has been ‘given’ to you with no
thought of compensating you for the extra tasks.
The Earth is warming, the weather is out of control and the
price of gas is so high that you decide to bike to work to help save the
planet. You spend more time on the road
commuting and look like you need a shower when you get to work after dodging
traffic all morning. Your coffee is
priced higher now because the coffee house wants to use Fair Trade coffee from
farmers in a county you have never been. And your dog is on anti-depressing meds because
you are not home as much and he can’t go out in the yard because of the killer bees
migrating north from Mexico.
Our lives seem to be getting more complicated and it’s nice
when we find things that not only help us but are easy to use.When you
come across these items they make such an impression that you like to tell others
about your great fortunes. I came by a
solution that was very easy to use and the value was so great that at first I
didn’t believe the whole story.
About a year ago, I was asked to help out on the Storewize/Real
Time Compression (RTC) team as it transitioned into the IBM portfolio. I met with the engineers and sales people and
all had wonderful things to say about the technology. I listened but was hesitant
to drink all of the kool aid they were pouring.
A year later I am very much a believer of the RTC technology
and think it really could be a game changer in the market. If you keep up with IDC, Gartner and the other
analyst, they all point to compression of the data as being one of the larger
items for handling future growth.There are a lot of vendors that claim they can
compress data but it’s not all done the same.
One of the things that stood out from day one is the idea of
using LZ compression in real time to compress data instead of deduplication. Coming from a N series (*Netapp) background I
understood how deduplication works and where it was useful. But this was compression which is a different
ball game.Now we are able to shrink the
storage footprint that wasn’t exactly the same as before. Given that Netapp has issues with block size
and offsets, this is exactly what is needed in the market.
The next question I always get and one I had was “That’s
great, you can compress data with the best, but whats the overhead?”. I waited a long time to see what the
performance numbers were going to be and found an astonishing outcome.The RTC appliance made a performance
improvement on the overall solution.It
does help by adding cache and adding processing to the serving of data but it
also improves the performance of the system by having to process less data.
For example, if a system has to save 100GB of data with no
compression, then all of the data has to be laid out on the disk, that sping
for 100GB of data, cache, CPUs, I/O ports all have to work harder to save 100GB
of data.But if we get 2:1 or 3:1 compression ratios,
then all of the components have to work less. No longer are they working to save 100GB of
data but 50GB or 25GB or data. This
allows the system to process more data and have cycles to respond quicker to
I/O requests (IE lower latency).
So the final thing is always the question of how hard is
this to install. Is there a period of
time that you have to wait or have 5 IBM technicians to install it. All I have to say is its easy.So easy that there is a good YouTube video
that goes through the entire process of unpacking to racking to compressing
data. I think the video speaks for
So if you are back at work today and find your life swirling
around you like a hurricane, stop and be reassured there is a few things out
there that still can make your life a little easier. It doesn’t make the killer bees go away but
maybe it will give you peace of mind that your storage doesn’t run out in the
I just read the blogs from Chris Mellor from the Register
and Tom Trainer Network Computing and thought how insightful are these two
outsiders about the inner workings of IBM.
First off, yes IBM is no longer selling the DCS9900, a DDN
OEM rebranded system in the very large IBM storage portfolio. There is no question that this product is no
longer available after the October 15 date.
Second, the DCS 3700 is already part of our portfolio and is
now an OEM box from Netapp/Engenio/LSI. The density of this system is the same as the
DCS 9900 and makes sense to use the DCS 3700 as a replacement for the DCS9900.
Third, Tom’s blog about SONAS being a monolithic NAS storage
is very skewed. SONAS is a very flexible
in the way we can scale both storage and the throughput with out affecting either
variable. Most “scale out” systems you
have to scale both in order to keep up with demand. SONAS uses some of the best technology on the
market with a huge amount of throughput.
His statement about IBM dropping DDN from SONAS is un-true
and goes to show how much research Tom put into writing this blog. I am sure Tom is looking out to write a
non-biased blog for Network Computing but maybe those days at HDS are still
making a big influence in his ability to look at announcement letter and make a
extrapolations about other products.
Finally, If HDS thought BlueArc was so great, why didn’t they
buy them back when they could have gotten the company for a better deal? Has the product changed THAT much since
2006?I wish HDS only the best for
dealing with the transition and getting that product under the HDS umbrella.
If you do your homework and base your assumptions on facts
instead of conjecture, you will find SONAS is a solid platform in the enterprise
NAS market.SONAS has proven it can be
the market leader with a low cost to performance ratio and will only get better
as time goes on.
How does one judge a glass of wine? There are a few tests, how it looks, smells and taste are the basic three. But as the wine is poured you may or may not know that your wine is made up of different varieties of grapes. A producer sits down and experiments with different percentages of grapes and this allows some creativity in making a better glass of wine for the consumer. Of course there are many more factors that play into this process but its by in large the same no matter what wine you enjoy. You enjoy the wine as a whole, a combination of things put together for you with out you having to know or even understand all that went into making that glass of wine.
When we talk to clients about their data backup strategy, we find a very similar process to that of wine making. The end user rarely knows all that goes in to creating a backup of their data and protecting it for them. They just enjoy the knowledge that their data is safe and will be there if they need to access it. But what we see in the making of the backup is a blend of technologies and a creative element that allows administrators some work around constraints like budget and man power.
As data evolves, we are seeing multiple layers of protection and depending on the severity of the data will determine the recovery point and recovery time as well as retention period. Backup technologies usually mean more than doing a bunch of incrementals and then a full off to disk pools and then tape. There are many different levels of protection that we can use. Snapshots seem to be more common today than 5 years ago. They allow for a clean and consistent recovery point of a database or file system. But snapshots are used for more than just a quick backup, with writable copies we can quickly setup copies for test and dev environments and also rapidly deploy virtual images for desktops or servers. Snapshots are usually set to the same disk set that data is sitting on, and can be moved around via a vault technology or a mirror to another site. This can be used for long term storage if needed but typically snapshots are used for quick recoveries of less than 7 days. Snapshots are also vulnerable to data corruption. If a software bug comes in and corrupts data on the storage system, that can effect the snapshots and mirrors.
Backups are more traditional where the file system is scanned for changes and then those changes are sent off to a device where the data is stored until needed. In the past it has taken more time to backup file systems and as storage has gotten larger, those backup times grow longer. The technology has tried to keep up with adding larger backup servers and more tape drives allowing for more streams coming in. Now with the idea of using spinning disk for tape pools, we can backup a little quicker as the disk can write data faster than tape. There are many things that have evolved out of this technology, for example Long Term File System or Hierarchical Storage Management.
When clients are looking for strategies on protecting their data, they will use a combination of these techniques, and a mixture of both disks and tape to fully protect their environment. Depending o the data type, you may want to just use snapshots as the data changes rapidly and you do not need to restore from a week or a year ago. Snapshots are really useful in the case, and so is mirroring or even metro mirroring if the RTO is small enough. There are other factors such as Sarbanes-Oxley that will require longer term recovery methods like backups.
Just like a great wine, there is fewer rules today and room for creativity in designing data protection. And just like wine, there are many consultants that will help you find a good balance of technology to match levels of protection with data. Spend the time looking at your protection schemes and see if there are any better ways of balancing this equation. Maybe, with the right planning, you will be able to enjoy a glass of wine instead of spending time recovering from a disaster.
One of my favorite TV programs is the BBC show Top Gear. They go through and test cars not only for handling, looks, and cup holders but mainly for power. At the end they run all of the cars through the same test track and get a time. That time then gets recorded on their list of all the cars tested and is celebrated for achievement or scorned at for doing poorly. No matter what the car turns up, they were all treated equally.
Today, IBM is announcing a test done by a certain benchmark called SPECsfs. This has been the yardstick for all NAS vendors wanting to flex their muscles and show how they handle small block I/O. Vendors can bring how ever many drives and tweaks they want but the test itself is very rigid and has to be certified before the results are published. IBM put together a SONAS system consisting of 10 interface nodes and 8 storage pods with all SAS disk. A total of about 900TB of usable disk, and about 1/3 of the maximum SONAS configuration. There was no solid state disk or extra tweaks done just a SONAS system that you could order today. That said, the IBM SONAS set a new world record for performance for a single file system at 403,000 IOPS per second.
Yes you read that right, 403k IOPS in a single file system. If you look at the other vendors they have used multiple file systems to aggregate the performance together in order to achieve a benchmark. Then they tend to use a virtual name space with software that is layered over all of the file systems, but here SONAS is one file system over 900TB with a true global name space. Some issues with multiple file system is they cannot stripe data across the file systems and the load balancing becomes an issue. If you look at the comparison of performance per file system, you can see that IBM is WAY beyond the competitors.
So you maybe asking, "Yeah that's pretty cool but what was the response time?". According to the test, the average response time was 3.23 MS from 0 to 403k IOPs per second. This is extremely good and when you think that was coming from one file system of 900TB, you realize how good that number is compared to other results. There will be tons of vendors trying to debunk how IBM out performed them and how they have better software or better market share but it really boils down to these key points:
An all-spinning SAS disk SONAS configuration, typical of SONAS configurations being installed today
Single file system featuring ease of use, minimum complexity, global load balancing, sharing of resources, proof of scale
903 TB usable capacity is indicative of current real life customer scale out NAS requirements
An environment in which all applications would benefit from the single file system and benefit from the high IOPs and excellent response time
One can clearly correlate the SONAS SPECsfs benchmark with the response time received to a real world application by today’s SONAS
I have included the slide deck for the announcement below. Feel free to check out the information on the SPECsfs website.
Netapp, for some reason, has removed the SVC from their interoperability list of storage subsystems under a V series. The development team at Netapp has for months not kept up the development and testing for support on SVC (and other storage platforms). This was no more evident when the Storwize V7000 was announced last year that runs the same code base as the SVC system and Netapp refused to offer any support for the product. The lack of support probably comes from the V series team feeling threaten by the virtualization power of the SVC code. These two systems do have some similar capabilities but we find them in different parts of the data center. The V series / Gateway is more of a host to another storage system. It treats the luns presented to it as disk and then presents another protocol out to another host or client. SVC is more a virtualization engine for all the storage and allows customers to move data around in pools that can cross storage subsystems with out the end user knowing.
With all this said, IBM has stepped up and is continuing support for the N series and Netapp models in front of the SVC or the Storwize V7000. As my fellow IBM blogger "The Storage Buddhist" the place for support is not Netapp, but IBM. I stole this chart from his blog to show the levels of code and models supported.
Today IBM is releasing two new N6200 systems that will be a huge improvement over the existing N6000 systems. The two new systems will show a bump in capacity and performance and more flexibility. For a very crowded midrange market this new N series product set will bridge the gap between entry level and enterprise class systems
One of the biggest issues with the previous 6000 systems was the limited amount of PCI-e slots. The other issue is the lack of more common hardware onboard like SAS and 10gbps ethernet.
The first thing that stands out to me is the footprint of the new system. The older N6000 has a 6 U requirement for an HA pair. The new N6200 is half the size, only occupying 3U for the two HA pair, or a single node with a I/O expansion module, providing an additional four PCI-e cards. Another configuration is two controllers with two expansion modules in a total space of 6U (equal of the older N6000 systems) but with a total of 12 PCI-e slots (vs 8 on the older N6000).
We will recommend using the two slots built into the controller for high performance 10GbE and / or 8 Gb PC adapters. The additional expansion slots in the expansion module can be used for Flash Cache and other connectivity for disks.
The on-board hardware is getting an face lift as well. While the new system sports a 10GbE port this is used mainly for the interconnect and nothing else. This was one of the disappointments I have with this systems, but understand this is how Netapp will accomplish scale out clustering.
FC ports were kept at 4 Gbps but there is two new SAS ports with matching ACP (alternate control path) ports used for off loading some of the traffic from the data path.
One of the unsung updates was in the NVRAM. Instead of using the same memory in the past, we now see an improvement of the memory by using something called Asynchronous DRAM Refresh (ADR). This is a new self-refresh mode in the Intel chipset that allows a portion of the main memory to be backed by an on-board battery. This gives the NVRAM the same high bandwidth as main memory and also simplifies the design of the motherboard.
This gives the new N6200 systems a bump in performance along with the introduction of the new Intel processors. The SPECsfs benchmark on the highest N6200 system showed 101,183 ops at 1.66ms ORT compared to the N6060 showing 60,507 ops and 1.58ms ORT, an improvement of about 70% in SFS throughput.
IBM is introducing the IBM System Storage N6210 Series and the IBM System Storage N6240 Series These new systems replace the IBM N3600 and N6040 Series respectively. GA date is scheduled for January 28, 2011 (N6240) and February 25, 2011(N6210). Here is the slide deck that is published with the release.
IBM announced the enhancement of compressing not only block data on the V7000
but also now it includes the file data on the V7000 Unified.The V7000 was first set up with compression back
in the summer with a big announcement surrounding “Smarter Storage”.This optimization was the same code and
engine that was purchased from a company named Storwize a few years ago.
initially kept the compression appliance that Storwize was first known for in
the market.Using LZ compression with a
RACE (Random Access Compression Engine) providing an optimized real-time compression
without performance degradation. Thus slowing down data growth and reducing the
amount of storage to be managed, powered and cooled.
compression does not require the compression or decompression of entire files
to access the data block. The engine will compress and decompress the relevant
data blocks “on the fly”. As data is
written the RACE engine compresses the data into a smaller chunk and its 100%
transparent for systems, storage and applications.
The V7000 Unified can now deliver a larger compressed
platform than any other mid-range platform.With compression percentages around 75%, a system that was maxed out at
2.8 PB (960 drives x 3TB each) can now see the system handle up to 5 PB of
Each V7000 Unified with code base 6.4 has the option of
turning on a 45 day trial of the compression software.After setting the license to “45” then you
can add new compressed volumes on the system.You can also compress data on virtualized storage arrays.
Compression has been part of NAS for a very long time.We have seen compression of files from jpeg
to office documents.But the best part
is the end user will never have to worry about which files needed to zipped or
compressed. Everything that comes through the V700 Unified can be compressed in
line before it writes the data to disks.
A couple of other improvements that IBM announced were the
addition of a integrated LDAP server to V7000 Unified.This now allows customers to use both local authentication
and external authentication servers to allow access to data. Another feature was the ability to upgrade a
V7000 to a V7000 Unified in the field.If you currently own a V7000 but need to add file access to the system,
IBM will sell you the two file modules and corresponding software to upgrade
you system. Now mind you there is a list of requirements that will need to be
met so check with your local storage engineer for more information. And finally
we now have support for a 4 way cluster on V7000 unified.This allows for more disks to be provisioned
and can compete with some of the other mid-range storage platforms in the
This all together makes a nice round of improvements that
will make life easier for IBM customers. As the V7000 platform matures it looks like IBM
is putting their money where their mouth is and making storage smarter and more
efficient.More to come on this platform
as I suspect we will see bigger things down the road.
I had the pleasure to present at the IBM Technical conference (aka STG-U) this past week. I was asked to speak about NAS technology basics and how the world is moving to more and more NAS platforms. Typically I get to present on some type of product, SONAS, NSeries, and the like. This was very much different as I got the chance to go deeper into the technology with out talking too much about products. The session name I used was NAS 101: An Introduction into NAS technology. The idea was to help educate our technical teams about the history of NAS, how NAS works, some pitfalls and then NAS at IBM.
There is so much surrounding NAS and to boil all of that down to a 1 hr 15min presentation is pretty difficult. The other challenge is trying to keep the information relative to the amount of knowledge everyone has in the session. I had people who were very skilled storage engineers to people who just getting into the business. I hope the information I presented was relative at all levels.
wanted to post my slide deck here so if you have a need or want me to
come and help teach what NAS is all about feel free to contact me.
I was just thinking the other day that I really need to
write an article for my blog about the upcoming releases. When I opened the page it said I had not
written anything since May of this year. Time really flies when you are having fun, so
IBM just released a new XiV system dubbed the Gen 3.Generation 1 of course was built by the XiV company
before IBM purchased them, then came Gen2 shortly there after. As you expect the system has to keep up with
customer demands and technology refreshes but some thing very unique caught my
eye. The performance with this system
will be heads and shoulders above the competition.
Nehalem micro-architecture now makes up the heart
of the processing power within the grid with tons more cache to boot.There is a change in the inter-connectivity
from Ethernet to Infiband. I can’t wait
to see the new SPC2 numbers when they are published.
I suspect with
the introduction of more cache (via SSD) and the switch over to near-line SAS
drives is only going to help increase performance from gen2 to a gen3 system.The
self tuning/healing, tierless storage is still at the heart of the system and still
redefines how storage is done today.
Last week at the IBM Technical Conference I was able to
spend some time with a couple of friends discussing technology.It is always interesting to hear their take
on where the storage market is going and what lays ahead in the future. As my Netapp pal and I were chatting about the
messaging around unified architecture, we both noted that unified to one
perceptive is disjointed to another.
IBM and Netapp have been using the term unified for its NAS/SAN device for about 5 years now.The
idea is to share a common code base on the same hardware to increase
functionality and usability of that storage. Other vendors have gone similar routes using
multiple code bases and/or hardware but I see that as a NAS gateway in front of
SAN storage system.
This has been very successful in data centers both large and
small. But the idea of how we manage
storage is changing.Virtualization is
changing the idea of how and even where our data may be stored. The term cloud is something of a marketing
term but I like the term Storage Utility better. Utility companies such as electric, water,
sewer and even cable provide a product to its consumers and storage utility
vendors could do the same.
Most people are not concerned about process companies take
to make water drinkable or how electricity is generated as long as it is safe,
reliable and easy for them to consume. Storage
as a Utility is no different, it is only when the storage is offline or hacked
in by outsiders the consumers are concerned. There are laws that govern utilities and the FTC has put some privacy laws together to help consumers but I believe we can
take it a little further (a blog for another time).
As our data is changing from traditional spinning drives in
our data center to a storage utility, we will need some type of bridge that
will ease the pain of transition. The
main reason people do not adapt new technology is because the transition is
often too painful and the benefit of new technology is less than the need to
move. Whether it is a software package
that helps move data or a hardware device, it will have to give access to both file
based data and object based data. This
will allow for users to read the files as needed no matter what their connectivity
or location. It could also be used to
help drive efficiencies up buy allowing data to move from file based (high
cost) to object based (lower cost) environments.
Today there are some vendors who have early versions of this
type of unified solution. They are bridging
the gap between what we have today in private data centers and the future of
public utility storage. This is very
early in the transition but with this type of technology, we will be able to
adapt and provide a better way of storing data. Will it still be called a unified solution?
Only the marketing people can tell us that.
This week, I am at SNW in San Jose, CA. If you have never heard of the conference, its
all about storage and networking and pulls in all of the big vendors to put on
labs, lectures and a vendor hall. People
come from all over the world to this event to learn what is new and how to do
One thing that I love doing at these events is talking to
customers and potential customers about IBM storage technology solutions. Often we find the conversations do not talk
about products as much as the technology in them that fix some sort of issue in
the data center. I think this is best
seen when you come in to the IBM booth. There is no hardware to see blinking lights or
yank cables. We have something better,
people who know the solutions to your issues.
If you ask any of the IBMers that work these events, they
always say it’s a love hate relationship. The hours are long and you stand on feet for
4-8 hrs. The best part is talking about
IBM solutions and finding out what people are doing in the field. This is the best way to help drive innovation,
listening to the customer. IBM has
programs that send our developers into the field to listen to customers and
this is just one example of that program.
Another event at SNW this year was a gathering of the
storage social media moguls. This is a
non-vendor specific event and is open to everyone. It is associated with a certain hash tag of
#storagebeers and they have been going on all over the world. Last night was the largest storagebeers to
date and it was a whos who of this community. But what was better than meeting the people
that you see on twitter or those who write blogs, was the idea of putting all
of the vendor fighting behind us and just a group of people who work in the
storage industry talking about whatever was on their mind. If you find yourself at an event like SNW or
VMWorld, check to see if there is a #storagebeers and go back and meet some
really cool people.
If you are at SNW and want to come by for a chat, you will find me at the IBM Booth today between 11am and 3pm. I would love to spend some time learning about what you are doing in the data center.
IBM released a new Data Ontap version last Friday along with some other minor releases but more about those later. Data Ontap 8 7mode was the first release of a new 64-bit architecture that will allow N series customers to take advantage of larger aggregates. A little history. Back about 8 years ago, Netapp purchased a company named Spinnaker for the use of their 64 bit code, global name space and some other odds and ends. For the most part, Netapp has been re-branding this code as their GX platform allowing customers who want the feature set to purchase it aside from their Data Ontap base. GX was not a heavy seller as it was complicated to install and much more pricey than the other brand and Netapp decided to co-mingle the two code streams into one. At first glance this sounds like a good idea. The Data Ontap code definitely had some limitations (small aggregates sizes, limited growth and no global name space) but the merging of the two streams was harder than Netapp imagined. This was shown by Netapp promising a release of the new merged code for over years and finally a release was available for testing. There were many bugs (as RC code can be) but Netapp worked through the majority of them to produce a stepping stone release of the merged code called 7 mode. The developers used bits and pieces of the GX code to get the 64-bit architecture allowing customers to build larger aggregates, up to 100TB in size. This was really important as the release of the 2 TB Sata drives were coming and the limitation of 16TB in an aggregate would of killed any performance on the system. With only 8 2TB drives in the aggregate, the maximum IOPs throughput would be limited to about 400 IOPS per 16TB of drive space, not a good ratio at all. Therefor having a larger aggregate size allows them to put up to 50 2TB drives achieving a more respectable 2500 IOPS per aggregate. Now that we have the 7 mode available, there are some upsides and some downsides. First, as stated above, the aggregate sizes have increased tremendously. Allowing for more data disks in the aggregate increases the amount of IOPs the filer can pool. On the downside of this news, we see that you can not simply flip a switch and increase an aggregate created in the old 32-bit code to a new 64-bit aggregate. Customers will have to create a new aggregate after upgrading to the 7-mode version of Data Ontap 8 and then migrate with some restore method (think DR restore from backup) on to the new space. You can not mirror the two as SnapMirror can only mirror between like for like aggregates (32-bit to 32-bit and 64-bit to 64-bit). No big deal if you are new customer or if the filer is a new addition to the filer farm, but for those existing customers I believe this will be a lot tougher. If you do not have the drive space to create a new 100TB or less aggregate, you will have to either wait to buy more disks or do a manual backup (not snapshot), destroy the existing aggregate, and build a new aggregate on the 64-bit code, then restore. This is and the fact this is the first release of the new code family, will be why customers will not adopt the new code very quickly. There are also some other gotchas like no support for Performance Accelerator Cards (PAMII), no real interoperability between the two code bases and more. When I was an administrator, I hated having to read the release notes for the 'fine print gotchas' but in this case I encourage everyone to read the notes thoroughly and perhaps engaging your local IBM Storage engineer to help you access if you are a good candidate to upgrade or not. The fact this is a stepping stone to the full code line does help customers that need to move to the 64-bit architecture today without slowing down Netapp's development team. They are working on the next release of Data Ontap 8 called cluster mode. This will be the code that allows customers to cluster more than one pair of systems under one global name space. I suspect this will be a great addition to the Data Ontap code line and will give Netapp more traction in the larger enterprise business. There were also some firmware releases for the EXN3000 shelf on Friday as well. For more information on what was released, visit www.ibm.com support page
First, off I want to say what an awesome year IBM had in storage! We announced several new products and improvements to older ones. SONAS was one of the NAS product of 2010 at IBM. The idea that came from bringing a parallel file system and merging it with commodity parts is brilliant. People have been building these systems for years and having to deal with the issues of interoperability and supportability, can now focus more on making storage work for them. Real Time Compression was also released for the N series product. This was an acquisition that really helps IBM position compression technology in the NAS market. RTC today is an appliance that compresses the data into smaller packages with no performance degrade. I believe we will see more of this technology spread into other aspects of storage line.
The biggest storage announcement was definitely the introduction of a new mid-tier storage device, Storwize V7000. This device is based on the tried and true SVC code base with some new enterprise class features from our DS8000 line. This system has the cool XiV like interface and a very cool form factor and with things like easy-tier and disk virtualzation, the box is going to be hard to beat in 2011.
Second, I want to honor IBM as we celebrate our centennial year of business. The Computing Tabulating Record Company started on June 15, 1911 and while the name has changed and our products and services have changed, but our mission and dedication to our clients remains unchanged. So many of us do not even begin to understand the role IBM has made on our world as it is today. IBM has been well known through most of its recent history as one of the world's largest computer companies and systems integrators. With over 388,000 employees worldwide, IBM is one of the largest and most profitable information technology employers in the world. IBM holds more patents than any other U.S. based technology company and has eight research laboratories worldwide. The company has scientists, engineers, consultants, and sales professionals in over 170 countries. IBM employees have earned Five Nobel Prizes, four Turning Awards, five National Medals of Technology and five National Medals of Science.
Lastly, I want to challenge everyone, IBMers, clients, everyone, to really look at what is going on in the storage space this year. With the explosive growth of data we are seeing people buying unprecedented amounts of storage. Most of the vendors are going to be investing in R & D for storage and coming out with new and time saving features. Clients should challenge their vendors to exceed their requirements not just make them. I also want vendors to look beyond products and start looking the services that help clients make better decisions and support the products they have purchased.
May 9th has been a target on my calendar for some
time now. Inside of IBM, we have been
waiting for this day to come so we could talk about the new things being
released in the storage platform. It
almost feels like Christmas morning with a bunch of new presents under the
tree. Each gift has inside something
that is either really cool or something very useful.The only difference is your Aunt Matilda and
her little dog is not coming over for brunch.
Under the IBM tree today is a slew of presents for almost the
entire storage platform. I will
concentrate on just the IBM NAS ones but if you are interested in knowing what
is going on elsewhere, you can find more information at the main website.
SONAS must have been a good boy because there are plenty of
gifts for him under the tree this morning. Not only did he find presents under the tree
but there were a few little things in his stocking. Here is what Santa brought:
hardware update on the X3650 nodes. Just like before, the SONAS system uses
the impressive workhorse but now it uses the more powerful M3 class with a
six core Xeon Intel 2.66GHz processor. It has 24GB of DDR3 RAM with the option
to increase to a total of 144 GB of DDR3 RAM per interface node. Also new with the X3650 is the option to
include a second processor to double the amount of cores to 12 total per
under the tree is new support for not only XiV but now SONAS supports the
SVC and V7000 as disk subsystems. This
is a huge gift because now SONAS can support tons of other storage under
the awesome virtualization of the SVC code. V7000 support is also interesting as that
platform has the virtualization code from SVC but also support its own
drive architecture including solid state drives.
same category of sweaters, SONAS gets a little smaller rack extender.In the past IBM has used a 16 inch
extender in order to accommodate the large 60 drive disk enclosure.That
has now been trimmed down to only 8 inches and 0 for the gateway model and
RXC rack that houses only interface nodes.
gets a new file system upgrade to GPFS 3.4 PTF4. This will provide a significant performance
improvement over the R1.1.1x release. The updated file system handles small
file and random I/O a lot more efficiently. With this update we now use the role of
manager nodes instead of interface nodes to gain more flexibility in how
we track data in cache.
gifts SONAS received were new support for NDMP, Anti-virus support, use of
both 10GbE ports on the same CNA and some power updates for the EU countries.
And along with all of that, there
is a new performance monitoring package called Perfcol that collects more
information for analysis.
This SONAS release is labeled R1.2 and can be obtained by
contacting the technical advisor assigned to you.
Santa was also at the N series house and dropped off a few
gifts.A new N6270 to replace the
N6070.This new system is in line with
the N6200 series with larger amounts of RAM and processors.Just like the smaller N6240, there is an
expansion controller where customers can add more PCI control cards like HBAs,
10GbE or even FCoE.A new disk shelf was
also released which uses the smaller 2.5 inch drives with improved back end
And over at the Real Time Compression house they got new
support for EMC Celerra.
Over all a very busy time of year for IBM (and Santa) as
these were just a fraction of the Storage announcements today.Also today is the IBM Storage Executive
Summit in New York City.My friend and
fellow blogger Tony Pearson is covering this great event and will be updating
his blog and twitter feed.If you were
not able to make it to NYC for the event, feel free to tweet him your questions
@az990tonyYou can also send questions
to our IBM Storage feed at @ibmstorage