RichardSwain 060000VQ8G Tags:  tsm tivoli snapshots rto data wine nas sonas rpo hsm ltfs backup recovery ibm protection 10,856 Views
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.
RichardSwain 060000VQ8G Tags:  nseries ibm storage rtc #ibmtechu sonas ibmtechconfs 6,613 Views
Every year IBM puts on a conference for all of our clients, business partners and strategic partners.
RichardSwain 060000VQ8G Tags:  presentation performance specsfs sonas 1 Comment 10,358 Views
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:
I have included the slide deck for the announcement below. Feel free to check out the information on the SPECsfs website.
I was driving into the IBM Almaden Research Center and just enjoying the beautiful scenery of the San Jose area. The campus is on top of a hill and surrounded by farm lands. I would really like to have a corner office here, but I don't think I would get much done. So here is my Vlog for this morning and I am hoping to get some interviews on here from some of the presenters and attendees.
RichardSwain 060000VQ8G Tags:  cloud v7000 storage unified sonas san ace gpfs nas 5 Comments 42,516 Views
Storwize V7000 Unified, A marriage of SAN and NAS
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.
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.
RichardSwain 060000VQ8G Tags:  nas ibm trainer" sonas "tom chris_mellor cloud ddn storage 11,140 Views
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.
RichardSwain 060000VQ8G Tags:  pearson nseries x3650 sonas tony ibm storage r1.2 nas 7,152 Views
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:
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 performance.
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 @az990tony You can also send questions to our IBM Storage feed at @ibmstorage