The Storage Tank

Yes, IBM is at it again with it’s storage innovation receiving 12 new patents for tape systems. What? You thought tape was a dead? Again? Tape is very much alive and kicking and while you may be jaded one way or another, tape is still the cheapest most reliable long term storage platform out there.

IBM is known for it’s innovation and the patents it is awarded every year. For the last 23 years, it has been awarded more patents in the US than any other company. Just in 2015, IBM was awarded 7355 patents compared to 7852 patents for Google, Microsoft GE and HP combined. Roughly 40% of the 18172 patents awarded went to IBM.

When you look at the 12 storage patents (listed here), you notice they are all from 2010- to 2014/15. They range from how the data is written to abrasion check. The people behind these technologies are brilliant to say the least and it shows in the details of the filing. While they are sometimes hard to read, the technology being introduced will save IBM customers time and money down the road.

IBM also uses its patents as a revenue source. Just in the last year, IBM sold patents to both Pure Storage and Western Digital. Since Pure and IBM compete in the all flash array environment, IBM must of gotten a huge sum of money for those patents to offset the ability to crush your competitor. None the less, IBM utilizes its investment of R&D buy selling the technology to others who may be spending their money elsewhere (like marketing and selling).

If you want to learn more about the IBM Storage Patents, click over here to read about them in detail.

We have been getting this question about clustering the storage controllers on the V7000 Unified (V7kU) more and more as people start expanding their systems beyond their initial controllers. But let’s step back a few steps and understand what we are working with first.

1. V7kU is a mixed protocol storage platform. It uses Spectrum Scale as the file system and Storwize as the operating system. This is important as people get interested in how they can adopt a high speed, parallel file system with grace and ease. The V7kU comes preloaded so no need to understand the knobs and switches of installing and configuring Spectrum Scale (formerly known as GPFS). The V7kU supports SMB (CIFS), NFS, FC, FCoE, iSCSI and can be used with other building blocks like Openstack to support Object Storage too.
2. V7kU can scale up to 20 disk enclosures per controller. This platform can cluster up to four controllers giving customers a chance to max out around 7.5 PBs of storage. The best part is you can mix and match drives types and sizes. You can have flash drives in the same enclosure as SAS and NLSAS drives.
3. Single interface is the best part of this solution. You can provision both block and file access from the same gui/cli. Data protection like snapshot s and flash copies, replication and remote cache copies.
4. Policy based data management. One of my favorite parts of the solution is I can create policies to manage the data on the box. For example, I can create a policy that says if my flash pool becomes 75% full start moving the oldest data to the NLSAS pool. Not only does this make my job easier not having to manage the data move, but it frees up the flash pool and extends the buying power of the flash. Since flash is the most expensive part of the storage, I want the best bang for the buck there.

Now comes the part of can we cluster these V7000s to make a bigger pool, yes we can. Not only can we cluster the systems (multiple IO groups) we can mix the file and block independently. The best part as you add IO groups you add more performance, capacity all the while managing it from the same single interface.

This was taken from the V7000 Infocenter:

1. Issue this CLI command to list the node candidates:

   lsnodecandidate

   This output is an example of what you might see after you issue the lsnodecandidate command:

   id               panel_name        UPS_serial_number     UPS_unique_id     hardware
   50050768010037DA 104615            10004BC047            20400001124C0107  8G4
   id               panel_name        UPS_serial_number     UPS_unique_id     hardware
   5005076801000149 106075            10004BC031            20400001124C00C1  8G4

2. Issue this CLI command to add the node:

   addnode -panelname panel_name -name new_name_arg -iogrp iogroup_name

   where panel_name is the name that is noted in step 1 (in this example, the panel name is 000279). The number is printed on the front panel of the node that you are adding back into the system. The new_name_arg is optional to specify a name for the new node; iogroup_name is the I/O group that was noted when the previous node was deleted from the system.

   Note: In a service situation, add a node back into a clustered system using the original node name. As long as the partner node in the I/O group has not been deleted too, the default name is used if -name is not specified.

   This example shows the command that you might issue:

   addnode -panelname 000279 -name newnode -iogrp io_grp1

   This output is an example of what you might see:

   Node, id [newnode], successfully added

   Attention: If more than one candidate node exists, ensure that the node that you add into an I/O group is the same node that was deleted from that I/O group. Failure to do so might result in data corruption. If you are uncertain about which candidate node belongs to the I/O group, shut down all host systems that access this clustered system before you proceed. Reboot each system when you have added all the nodes back into the clustered system.
3. Issue this CLI command to ensure that the node was added successfully:

   lsnode

   This output is an example of what you might see when you issue the lsnode command:

id name   UPS_serial_number WWNN             status  IO_group_id IO_group_name config_node UPS_unique_id    hardware
1  node1  1000877059        5005076801000EAA online  0           io_grp0       yes         20400002071C0149 8F2
2  node2  1000871053        500507680100275D online  0           io_grp0       no          2040000207040143 8F2

I had a customer recently upgrade their XIVs to the 11.6.1 code and wanted to know more about the real time compression that is now built into the code. IBM purchased the compression technology from a company named “Storwize” and adopted the name for their mid-range product family. One of the cool things that came out of that acquisition is the RACE engine that runs the compression algorithm.

Basically the compression is your standard LZ compression with some cool technology that keeps meta data about what you are writing. For XIV, this happens before the data is written to cache and turns all of those random writes into a sequential write. If you want to dig into the way RTC works check out this link.

The XIV team took the compression technology and integrated it into the XIV. The GUI even will show you an estimate on which volume will get better compression savings in order to fine tune your workloads. 

Q. How does the compression work? Is it on all the volumes/pools?

A. Compression can turned on if a pool is set to “thin”. This thin pool then can have both thick and thin volumes in it. Once compression is turned on and licensed you can convert any thin volume to a compressed volume by right clicking on it and choosing compress. You can also tell XIV to compress all of your volumes or de-compress all of your volumes.

Q. Can I turn it off and on based on compression savings?

A. Yes, compression can be turned off on the whole box or just one volume. You get to decide based on the compression savings

Q. What size volumes can it handle?

A. The maximum is 10TB and the minimum is 52GB

Q. What kind of performance hit will it have on the XIV?

A. There are some benchmarks in the redbook with turning on compression that can help you decide on compression. Basically it comes down to two things: the workload and the model of XIV. If you look in the Compression Savings field and it is 30% or less then the you should not compress that data. If you have a new 314 model or 214 model compression can be turned on but 114 models need to be checked to make sure there is enough horsepower.

Q. What type of data does not compress well?

A. I get this question a lot. The basic answer is any time of data that has either already been compressed. Also backups seem to have lower compression savings. The better answer is always look at the compression savings in the gui and base conclusion on that output.

Q. Can I compress volumes that are mirrored?

A. Of course. Mirrored volumes can be compressed on both sides. If the mirror already exists then the mirror has to be broken, data compressed and the mirror copy has to be re-synced. We have seen a major performance improvement with compressed mirrored volumes as the amount of data being transferred is cut into half or less.

If you have questions about running compression on XIV or any other IBM platform leave a comment and I will try to answer them here.

Storage is a wonderful place to work. It seems like every few months someone or something new is coming out with the latest way to make it easy to store more data for less. There seems like about 100 new startups all begging for money and clients all the while trying to build new code bases to fix issues solved by the Big 5 years ago.

The 5 big five of course being IBM, EMC, NTAP, HP and HDS in some sort of order. These companies have spent Billions of dollars researching and engineering ways to store the simple bits of our 1s and 0s. Now in the new age we see these companies struggling for sales and even the market share leader of ~45% is being sold to a PC company because its not making the money it did a few years ago.

If you look at what is happening in the storage industry you can see why. Price per TB is rock bottom thanks to our buddies at Amazon and Google. IT Directors expect these cloud prices of pennies on the TBs in order to keep up with the demand on budgets. Just think 30 years ago gas cost $1.09 and a GB of data cost you $105,000. Now gas is around $2.00 and a GB of data? Well let’s just say it is around $0.03. What other commodity has fallen so quickly as data storage?

Another reason is efficiency. Storage has gotten better at making better use of the disks and better space savings all together. You can see it in the technologies like XIV and VSAN where the disks are dumb and the RAID is software. Also through in Dedupe, compression, clones, etc. and now the system that you bought for 100TBs a couple years ago is compared to a system with the same hardware (drive sizes anyway) that can push 300-500TBs of capacity. So that $100,000 storage array that was pushing 100TB is now the same cost for 500TBs.

And the last reason I see causing companies to squirm is Software Defined Infrastructure. Companies buy what hardware they want and then lay down their preferred software on top to manage and protect their data. And since its a heck of a lot easier to start a software company where you don’t have to worry about all of those pesky firmware versions and interop-ability matrix things, they are sprouting up like dandelions.

Now put it all together, lower cost /TB, better efficiency, and more software sales reps will lead to lower sales and lower potential. There is only one way out. Those who can put all of this together.

I have heard over and over that everyone wants to move out of hardware and move to cloud based or hybrid cloud. I see the value in cloud and I believe it has a place in the data center but for the most part I see it as a low cost storage platform where data is hosted for non mission critical applications. You want to run you email or CRM system there? sure go for it. You want to run distribution system or your surgical system out there when Netflix and Chill is happening? Probably not.

So to the Big 5 as a 2016 word of advice, embrace your hardware. It makes you different. It gives you a chance to walk into customers and give them a choice. Don’t fall for the flashy object of cloud (honestly the margins can’t be that good). Spend time developing integration into applications so things can work better together. Spend time reaching out to other companies and seeing how you can integrate their technologies into your own with out having to acquire them.

In the long run, people are going to make the best choice for their company and one shoe doesn’t fit all. The more you can offer and the better the offerings are, the better the customer will feel about your company. And who knows they might take a look at something else you sell down the road.

It appears IBM has removed the requirement for XIV systems running 11.6 that need to over provision beyond what the box is provide. Before 11.6 a XIV customer had to ask a Technical Advisor (TA) to submit a RPQ and then they would dial into the system to change the total amount of storage that could be provisioned. This was normally done because of thin provisioning but now even more so becuase of compression on XIV. 

Here is the information I see in the release notes:

XIV 11.6 Command Reference: system_soft_capacity_set soft_size=SizeGB

This command is used to set the size of the system soft capacity. The soft capacity size of the system can be set to up to 3 times the size of the hard capacity of the system, and as low as the maximum size between the currently allocated soft capacity and the system’s hard capacity (whichever is greater). The current hard, soft, and/or allocated soft capacity can be retrieved using the system_capacity_list command.

I still would advise any customers wishing to change the soft capacity to speak with either a TA or a support person. 

If you are attending the IBM Inetconnect conference there is a TON of storage related sessions.  Here is the link to the main page where you can find out all the information about general sessions and the Aerosmith concert.

To build your agenda you can go to the portal here: IBM Interconnect Portal

There you will see all sorts of information about the conference and you can sign up for sessions ahead of time. You can look at certain ‘tracks’ for different types of sessions or you can search for them based on the date/time or session topic.  If you are interested in a storage related topic I have listed them below. Do notice that these sessions are at Mandalay Bay.

If you see me in the halls feel free to introduce yourself and I will buy you a coffee/beverage of choice.