After the general session today, I wanted to update everyone. What a great release session!
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
Well the last two days have been crazy with really good sessions, lots of networking with tons of people and great discussions throughout the entire conference. The sessions have been well attended and people are really asking great questions. For the most part, I hear that everyone is learning from the sessions, which I hope they dont get overloaded with so much information.
Today I presented on PAM II technology for the N series system. We disussed the need for large Read Cache systems and how its not only the size of the disks that are driving this need, but also the business requesting for lower return times on data. During this session, the question was brought up about the new acquisition of StorWize and how that would effect the NAS solutions at IBM.
Here is IBM VP of Storage, Doug Balog, talking about the product.
I think its going to be a good product to put in front of our NAS systems and it will drive the heavy read cache systems like PAM II and the huge amounts of cache in the SONAS systems. Speaking of StorWize, I wanted to give everyone a little more information about this product and maybe why IBM purchased them. They provide real time compression technology that will reduce the storage need by compressing the data into images. They have an engine called Random Access Compression Engine (RACE) which is just a compression algorithm that does the conversion with no overhead. The Storwize appliance will work with popular NAS systems, including IBM N series and SONAS, as well as non-IBM NAS systems from EMC, HP, NetApp and others. Storwize real-time compression can provide added value to clients already using data deduplication, thin provisioning and other storage efficiency technologies.
For more information on the StorWize acquisition, go here for the press release.
I am at the IBM Storage University this week with the hope to spread the good word about NAS technology at IBM. The opening session was awesome and SONAS was mentioned a couple of times as part of the IBM Storage strategy. Listen below to a few remarks (short clip) from IBM VP Storage Doug Balog.
My session on NAS technology was well attended and people asked thoughtful questions. We talked about the N series and a couple of new features we have been adding through out the year. Then we talked about the SONAS platform which I think is one of the hottest topics being discussed here this week. I also worked in the solution center where all of the vendors setup booths even Netapp, who is a platinum sponser came with a very large booth this year, right at the door. I didn't get a chance to talk to that team afterward but I hope they were able to speak to alot of people here about N series.
I had a ton of people coming by and asking about SONAS, and not just what is it, but how can it help them.
Today there are some great sessions that I am hoping to attend. One is a N series client from IBM talking about Managing the Largest AGFA PACS solution in the Americas. Then there is my session on ILM/HSM in the SONAS system. I am hoping we will have a great turnout for that ! There are so many sessions that I want to attend, I need to clone myself so that I can get them all.
Just a quick note on two new Solution Briefs that were posted to the IBM SONAS front page. These briefs have important information on using Symantec's EndPoint and NetBackup to protect data on the SONAS system. As always, the devil is in the details but this gives SONAS clients a look into how we can utilize these two solutions with the very powerful SONAS system.
SONAS with Symantec EndPoint
SONAS with Symantec NetBackup
I am also headed up to the IBM Storage University to present on NAS technology at IBM. If you get a chance to stop by and see one of my sessions, please come up and give me feedback on the blog (and other things). I will also be in the Solution Center at the SONAS booth.
Here is a You Tube video of Windows Explorer VSS and IBM SoNAS snapshot demonstration by Roshan Ratnayak..
RichardSwain 060000VQ8G 1,315 Views
Move that File! You know that show were people are moved out of their old house, an army of contractors come in and build a new house, then the people come back and are astonished at their new home. I was watching an older episode the other night and released how much this improves a family's mobility, productiveness and state of mind. While, their old house was ok, it provided some what of a shelter, the new house was 100x better.
I think of SONAS in the same way. There are many ways to do NAS technologies. Some take time to develop and build, but others are just as effective with little to no planning. I was talking to a client the other day and his response to NAS was to put NFS servers in all of their locations. It's cheap and something they can repeat like a cookie cutter many times over. What he was not taking in to his planning was administrating all of these islands of storage and how much he was spending on data sitting on expensive disk. If he was able to consolidate these servers and have a way of moving data around and eventually off to the greenest storage media out there, tape, then how much more money and time would that save him? He didn't have an answer but we are working on plan for him today.
IBM announced yesterday that SONAS version 1.1.1 will now support ILM tiering with GPFS and then moving data off to tape using Tivoli's Storage Manger HSM. These two work in concert with the policy manager on the SONAS system to move data on and out of pools based on the meta data properties. As discussed in previous posts, SONAS separates the meta data which allows the scan engine to pass the needed data on to the ILM or TSM agents. These agents then move data between the pools and allows the client to free up space on valuable spinning disks.
If you are one of the people that says tape and tiering is not needed, then think about the idea of putting data that hasn't been touched on a disk that costs $0.03 per GB. Its not that your storage isn't cool and you may not need tiers for your high performance, but what if the only data that was on the system was data that was actively being used and not my old spreadsheet from 2009.
Along with the ILM announcement, IBM released the following with version 1.1.1
If you want more information on the IBM Storage release announcements click here.
There is always a part of the business that gets over looked and usually its the people that are in the trenches making things work and keeping those machines going. I recently had the pleasure of spending some time with three great IBM CEs here in the Raleigh NC area. I was impressed with their professionalism and thoroughness while working on the SONAS upgrade. They made sure everything was installed, cabled and tabled according to the documentation. It is one thing to have a great product and lots of features, but it is even more important to have people who can service the system and do it with the highest level of craftsmanship. Thanks guys and gals for everything you do to help make our job easier!
Today, I helped our local Client Engineers install a couple of new nodes and some more storage into a local SONAS system. This was exciting for me as I love working with the hardware and software and it keeps up my keyboard skills. This client is bringing online more demand and needs both horsepower (interface nodes) and storage to accommodate a new business line. I was amazed at how easy the system is to upgrade and soon his little starter rack is almost full.
We added two interface nodes, IBM xSeries 3650 m2 and two 60 disk shelves to the unit. Once the disks are online and presented up to the interface modules, they can start creating shares for the new operation. As they need more storage or more interface nodes, another rack will be but in and the same process of pooling these resources together will come together.
The idea of having multiple interface nodes and storage pools is to not have single points of failure. In traditional storage, if a controller goes down, its partner has to pick up the entire work load for the down hardware. Not so in SONAS, if a controller goes down, the work is then evenly spread across all of the other nodes in the system. This is why we do not have a problem of loosing CIFS connections when systems go down.
The addition of new storage is also interesting as we are tripling the amount of storage the base system had originally with two 4 U shelves. These shelves are highly dense, top loading containers using either SAS or SATA disks. In this instance today, we were installing 120 2 TB SATA drives. A total of 240TB in 8 U of space. Not too shabby.
At the end of the day, I was pleased to see that IBM is moving forward with smarter storage systems. If you look at the entire portfolio, you can see that our systems like XiV grid, the auto tiering on DS8700, SVC virtualzation, all of these systems are helping our goal of a Smarter Planet. Look for some more pictures and maybe a video on Monday.
IBM has been working to enhance the way we do business from day one. From clock, to typewriters, mainframes, PCs, software, storage... the idea behind our innovation is to make it easier for our clients to do their business. Now we are taking it one step further to help our clients make the world better.
If you have been watching standard TV, Youtube or Hulu, you probably have seen a commercial for the IBM Smarter Planet initiative. These great adverts keep the tradition of IBM marketing our message to the masses. They describe how IBM is making our world better by using technology through many disciplines; Healthcare, Traffic, Food, etc. If you dig a little deeper than the catchy ads, you see a real movement not only to 'save the planet' but to make our lives better.
One of the ways IBM is making our planet better is by increasing the utilization of our systems. Today's average commodity server rarely uses more than 6% of its available capacity. This hold true for our storage systems as well. We find storage systems are bound by traditional technologies that keep us from keeping up with demand.
Looking at how this relates to my involvement I see how both SONAS and N series fit this mantra. The technologies allow clients to conserve energy by decreasing the amount of storage needed to achieve typical installations.
N series software allows a client to over subscribe a system by cloning the volumes with out adding additional space. This software called FlexClone allows clients to use products like VMWare, Xen or Hyper-V to create zero space copies of the original image. This zero consumption keeps the original blocks locked to the original image and any new changes are added to the free space as a delta. In traditional storage systems, a 10GB image would consume 1 TB for just 100VMs. With FlexClone, the only space needed for all 101 VMs would be just 10GB. Lowering both the OPEX and CAPEX for this system.
The IBM Scale out NAS system (SONAS) is a gaining steam as the private cloud business has increased in the business market. Not only are research universities and high performance computing labs seeing the benefits, so are mid-market to enterprise business leaders. Typical storage systems are not utilized to their full potential because of the purpose of the system or how it was integrated into their data center.
With a SONAS system, we no longer have to think how this system will be provision as all of the equipment can respond to requests from multiple parts of the business. If you have 5 systems that provide storage to your business and one of those systems is struggling to keep up with demand, the only way to keep up with the requests is to move data off by hand to the other systems. This is time consuming and could introduce mistakes and possible data loss. SONAS allows clients to be flexible in a dynamic-on-demand business environment. No longer will you have one system slowing down productivity as all of the storage in a SONAS system can be distributed through out the entire client interface. This will increase your efficiency rates and lower the required amount of systems in your data center, lowering environmental cost, CAP/OPEX.
There are other Storage systems that can increase utilization, Information Archive moves older data off to low cost, slower disk allowing you to store more on primary, faster disks. XiV keeps data spread throughout the entire system in case of a failure with no traditional RAID overhead. We at IBM are constantly looking for ways to increase the utilization of our systems.
IBM is working hard to build a smarter planet that not helps our clients, but helps the human race. Either through smarter storage systems, servers, software or consulting, IBM is working hard to bring this vision to a realization. Take a look at your systems and take stock of their utilization. Can they be doing more for you? Find out more about the IBM Smarter Planet initiative here.