Storage – Utilization, efficiency, cost, dedup, TP, virtualization, ZPR, compression or call it Economics

August 3rd, 2010 Devang Panchigar View Comments

..

There are fundamental concepts of storage Economics, which typically include Thin Provisioning, Deduplication, Zero Page Reclaim, Compression, Reclaimation, Efficiency, Utilization, TCO, ROI, CAPEX, OPEX, etc.

Storage Economics is one of those subjects, everyone likes to hear about, but it’s hard to find it implemented in today’s storage environments.

With that said, a lot of vendors are natively trying to add the concepts of Storage Economics into their storage arrays. With some latest discussions we had with our current visit to Hitachi Japan on the topics of Storage Economics and the core concepts that help customer increase utilization & efficiency in storage environments, here is an attempt to shed some more light on the topic.

We use storage to run our business, to store structured and unstructured data. Data means everything these days. But have we thought about the economics associated with storage?

As consumers, we tend to consume more than necessary at times if we want to have enough buffer, or if we anticipate projected growth, business requirements, customer requirements, technology improvements, and the list goes on. Many vendors these days guarantee 20% more efficiency, 50% less storage, 50% less storage using Thin, etc, etc, etc.

There are several aspects one should consider related to Storage Economics, how your shrinking IT budgets can still meet up with your growing business requirements, and what you can do to keep a balance between both.

..

With various aspects of Storage Economics below, some may be applicable in the SMB space, some in the enterprise space, and some really at all levels. These may turn into the building blocks of your Storage Economics practice:

  • It’s important to know what storage you have and where you have it.
  • Try to move away from fat provisioning to thin provisioning.
  • Use the concepts of Storage Virtualization to increase efficiency and utilization
  • Run non-vendor specific SRM (Storage Resource Management) tools for storage optimization and storage management.
  • Having a storage management tool is a must. You can still perform your daily task using various native element managers.
  • Industry standard average storage utilization numbers range between 35 to 45%. If you can push your storage utilization numbers higher, it will help you drive the cost down phenomenally.
  • Implement deduplication; verify your storage array supports deduplication natively. If not, it should be implemented in various parts of your storage like backup, unstructured data, etc.
  • Run a heterogeneous environment with multiple vendors in it to keep balance relating to price structures.
  • Though ILM is a forgotten word these days, make sure you run tiering within your storage environment that can help you move your data from higher SLA tiers to lower SLA tiers for cost containment purposes.
  • Implement storage arrays that natively support Automated Storage Tiering and can automate the movement of data to the required Tiers based on time of the day, policies, spike in usage or business requirements.
  • If there are native compression technologies available on the Storage Arrays for secondary or backup storage, implement those as a means to reduce your footprint.
  • Look at extending the life of your storage arrays from a typical 3 years to 6 or 7 years.
  • Leverage the use of outsourced computing models including Cloud technologies available in the market today. Could be private clouds or public clouds or a mesh of both technologies to reduce the storage footprint and management.
  • Budget for your storage requirements and try to live by those even if you have to take drastic measures to keep it under control.
  • Try to gain more operational efficiencies within the storage environments.
  • Understand the TCO with any new storage purchase, as cost of new storage could include several aspects of implementation including migration, consulting, downtime, missed SLA’s, Training, management, etc.
  • Try to reclaim storage as old host systems / server systems are retired or migrated.
  • Check for inconsistencies in your Storage environment as those could result in missed SLA’s, downtime and penalties.
  • Do not over provision and do not over budget. Its just storage, if you need more you can buy more, but having idle storage doing nothing for years in anticipation of future growth will heavily skew operational storage efficiencies.
  • Do not create unnecessary storage management tasks and processes for your storage environment.
  • Having backups and good working backups is very important, but do not tie down your storage with numerous copies of snaps, clones, mirrors, BCV’s, etc for a rainy day, rather have a DR plan and copy single instance of data remotely for DR purposes.
  • Plot trends for your storage environment. See if trends can help you budget, forecast and provision your storage accurately.
  • Remember the larger storage footprint you have, the larger your backup footprints will be, causing more storage space, more backup time windows, more network traffic, slower response times, more tapes, more offsite backups, more backup management cost and possibly more licensing cost.
  • Get away from managing islands of storage; rather move to a more centralized storage management, long-term effects are amazing.
  • Try to reduce licensing cost around storage software. The less storage you deploy, the less licensing per TB cost that you will pay.

..

There are many other factors you can implement; here are a few different posts from the past talking about this topic.

http://storagenerve.com/deepdive/storage-optimization/

..

A Google search on Storage Economics yields

http://www.google.com/search?q=storage+economics&btnG=Search&hl=en&sa=2

..

There are numerous areas of storage management that customers can try to bring in efficiencies that will help them better manage storage, reduce footprint, and reduce CAPEX and OPEX. It starts as a small practice within organizations and the value it creates grips the rest of the IT management teams.

In large organizations, there are Storage Architecture teams, Deployment teams, Provisioning teams and Operational Support teams, but seldom do we see a Storage Economics Team that helps drive utilization and efficiency through best economic practices within storage environments.

..

So take this opportunity and plant the seeds for your Storage Economics practice now.

..

Cheers
@storagenerve

Japan, a country of cultures and so seems Hitachi

..

We were invited to go to Japan last week to attend Hitachi’s uValue convention in Tokyo for 4 days.

..

..

The Japanese culture is different, very different, but very interesting. No handshakes, you have to bow to people, respected people are called with –San or –Sama after their last names, delicacy food, hot & humid weather, the workplace pride, the dedication to their job, a very hardworking society, very modest, humble and honestly one of the best hosts, these were just some observations.

Things are different, very different…………..…and in middle of that you got a company called HDS, a wholly owned subsidiary of Hitachi Japan that is located in the US. All HDS executives are from the US, while practically everyone on Hitachi’s Executive team is from Japan.

Does it mean, A clash of cultures? Absolutely not……. we rather felt the other way around. The new Executive team within HDS is establishing great relations with their counterparts in Hitachi Japan, enabling a lot of HDS decisions being made locally.

Hitachi CEO, Nakanishi-San went through an hour of speech to the attendees at the uValue convention, there were 50K attendees, out of which 10K were at his speech. He went through the last 100 years of Hitachi innovation and set the stage for the next 10 years of focus.

Hitachi is truly a part of the Japanese culture, as you land at Narita Airport in Tokyo and go through escalators and elevators, you will notice the Hitachi brand. From making the first battery in Japan to making fans, turbines, refrigerators, trains, televisions, they made it all and they still make it all. Talk about IT floors in datacenters, Hitachi is always found in form of Symphony Servers or USPV Storage or Hitachi networking. Every major place you walk into, you will atleast see a thing or two made by Hitachi.

.

First Hitachi Product Ever

.

A Battery

.

A Turbine?

.

FAN

.

Telegraph

.

Disk Drive

.

So far I thought Hitachi Japan made great storage technology and its US wing HDS marketed it. But after seeing the interaction last week, my opinions about the whole relationship between Hitachi Japan and HDS have now changed. HDS seems to help Hitachi Japan with a lot of strategic direction in terms of products and services.

..

Some More details

Both Hitachi and HDS have been great hosts to the bloggers and the analyst invited to this event. All the way from making sure the logistics of the trip including flights, food, travel, events and local trips were very well organized.

Attendees included (Bloggers): (FRONT – Left to Right) Myself, Robin Harris, Nigel Poulton, (BACK – Left to Right) Chris Evans, Greg Knieriemen, Rick Vanover.

.

..

Some activities included

Sunday – Monday: Flying for the better part of the day and losing another 13 hours going there….. pretty much left with only Monday evening for dinner with HDS folks.

Tuesday: Visited Hitachi RSD facilities in Odawara (a suburb of Tokyo). Took the Bullet Train to cover this 70 mile trip, in about 15/20 mins. This train was amazing, the top speed varies upto 200 miles/hour.

The Bullet Train, made by Hitachi

.

Spend the entire day talking about some NDA stuff. It was very interesting, very interesting guys that work on these sophisticated projects. Went out to dinner with Hitachi executives that night and enjoyed some of the finest food in the world with a 7 course dinner and 6 different wines and sake.

Wednesday: Spend pretty much half a day talking to HDS about some strategy, some really creative discussions about technology and marketing.

Spend the rest of the day in Akihabara, which is the electronics district of Tokyo. Imagine a geek store, here there were hundred’s of them, from small shops to mega stores selling just electronic items.

..

Nigel Poulton

.

Rick Vanover, Chris Evans

.

Met up with some other HDS folks (Professional Services and Managed Services) that evening who were visiting Hitachi Japan from the US. It was great to connect with them.

Thursday: Early morning left for the #uValue convention. Great Place, you can catch some of those pictures on the Facebook page, here.

.

.

Hearing the CEO of Hitachi and then Iwata-San in a private meeting with the Press, Bloggers and Analyst, topics were around Hitachi’s strategy about IT and Telecommunications. Attended the Michael Hay session on Hitachi Research Strategy and then headed out for dinner. It was absolutely impressive to see the Convention floor with Hitachi Technologies and then hear about some of the strategy behind it.

.

Hitachi CEO - Nakanishi-San

.

Hitachi Executive for IT, Telecommunications, Iwata-San

.

Hitachi Robot at uValue Convention: EMIEW from storagenerve on Vimeo.

.

Then was dinner that night in Roppongi, a suburb of Tokyo (it’s the night life district of Tokyo). Had a great time with Hitachi executives from Communication and Engineering both joining with us for dinner.

Then we were given a tour of the 10th tallest building in Japan called the Roppongi Hills, at the 52nd floor lobby overlooking Tokyo. We had a great time there. After a long and tiring day, sit at the 52nd floor overlooking Tokyo and having a glass of beer, a great feeling.

.

The Gang: Bloggers and Hitachi (Meade-San and Cecilia)

.

Another interesting fact: The Dinner table every night had a sitting scheme, where every person was assigned a chair/seat and that created a nice mix of environments where on each table there would be a blogger, analyst, HDS and Hitachi person. Quite enjoyable to hear different perspective of things.

Friday: It was the day we were all leaving. Finished up some early AM shopping and headed to the airport for a long 24 hour bus, plane, train, plane and car journey back home via Houston.

Uneventful trip back home….

I will end with this; the Japanese know how to take care of their guest. Culturally Japan seems to be a very strong country, Hitachi is a large part of that culture. Syyonara for now….

Thanks Hitachi and HDS for inviting and making us feel part of the family..

.

Cheers
@storagenerve

..

Disclaimer: The 4 day trip to Hitachi Japan to attend the uValue Convention is sponsored by HDS. They paid for all travel, boarding and lodging expenses for these days. The attendees / bloggers are not required to Blog about this event. This is my attempt to share what we learned there.

Storage Federation

..

VPLEX and USPV

EMC’s latest addition to the concept of storage federation is the VPLEX announcement that happened at EMC World 2010. VPLEX comes in two forms today, VPLEX Local and VPLEX Metro. Important features of VPLEX include cache coherency, distributed data and active-active clusters at metro distances. In the works are VPLEX Geo and VPLEX Global enabling inter-continental distances.

VPLEX contains no drives today, it is based on a version of Linux Open Source and runs on the same hardware as a VMAX engine. But said that, what prevents EMC from including VPLEX as part of every VMAX and Clariion sold today or may be just run it as a Virtual Appliance within the VMAX (Enginuity) or Clariion (Flare).

While HDS has a slightly different approach yielding almost the same result using Storage Virtualization, HDS approaches storage federation in its USPV platform. The USPV scales upto synchronous distances, I believe 100 kms max distance today.

USPV natively uses a combination of Universal Volume Manager (UVM), High Availability Manager (HAM), Dynamic Replicator, Hitachi TrueCopy Remote Replication and Hitachi Replication Manager to do synchronous distance (100 kms) replication with distributed data in an active-active clustered environment.

VPLEX local and VPLEX metro has been recent announcements, while the USPV has been offering similar features since the past few years now.

..

Use-Case

Service providers will be largest customers while the VPLEX is still being developed in the Geo and Global modes.

I would think, government customers like DISA, DoD and other cloud providers in the federal space may find VPLEX and USPV very interesting as well.

Migrations using both the VPLEX Local and USPV are a piece of cake, because of its underlying features.

And many more…

..

Future

Will the future of all storage subsystems have federation in it as a core component? It is most likely with virtualization technologies being designed and pushed today, that we will natively see some of these features into backend storage that can typically hold data in containers and these containers move based on requirements. Look at a VM as a container of information or application.

With a Front-end storage controller, call it a VPLEX or a USPV which doesn’t care what sort of disks are sitting behind it, natively add all storage features to it like snaps, clones, RAID, replication, high availability, virtualization and it doesn’t matter if you use the cheapest storage disk behind it.

Typically with a single storage subsystem, you are looking at scaling your storage to 600 drives or 2400 drives or 4096 drives or 8192 drives or 16384 drives max or does it even matter at this point.

Storage federation will allow a system to scale upto 100’s of PB of storage, for example a EMC VPLEX scales upto 8192 Volumes today, while a USPV scales upto 247PB’s of storage, in essence that is 1 TB x 592,000 disk drives in a single system (federated).

When you connect two of these VPLEX’s or two of the USPV’s at synchronous distances, you now start taking advantage of active-active clusters (datacenters) with distributed data. (Again I will be the first to say, I am not sure how much of cache coherency is built within the USPV today).

But that brings us to some important questions…

..

Questions

Is storage federation that important?

Is storage federation the future of all storage?

Do you care about active-active datacenters?

What is the use-case for federation outside of service providers?

Will this technology shape the future of how we do computing today by leveraging and pooling storage assets together for a higher availability and efficiency?

How large, a single namespace would you like to have? I believe HP IBRIX brings a similar concept of scaling storage to 16PB’s total in a single name space..

Does federation add latency, which limits its usage to only certain applications?

Is VPLEX the future of all EMC storage controller technology, and will that eliminate the Flare or Enginuity code?

If you add a few disk drives to the VPLEX locally, can it serve high demand IOPS applications?

How large will cache get on these storage controllers to minimize the impact of latency and cache coherency on devices at synchronous distances? Is PAM or Flash Cache that answer?

At that point, does it matter if you can do coupling on your systems to extend it like we initially thought the VMAX would have 16 or 32 engines or may be you can couple Clariion SP’s or AMS or USPV’s?

..

More Questions

Will the future VPLEX look like a USPV with local disk drives attached?

Though the big vision of VPLEX is Global replication creating active – active datacenters, does the next generation VBlocks meant for Service Provider market include a VPLEX natively within it?

Is EMC Virtual Storage just catching upto HDS technology? Or is VPLEX vision a big and unique one that will change the direction of EMC Storage in the future…

Is Storage federation game changing and is EMC ahead of HDS or HDS ahead of EMC…

..

Hitachi Data Systems (HDS), the super secret technology company

..

When was the last time you got into a conversation with an HDS employee on Twitter or an HDS PR person engaged with you or you saw a blog post from anyone outside the HDS executive team or an HDS employee blogging outside the HDS domain name.

When was the last time you saw a HDS executive at a large storage / virtualization show or VMUG? Does HDS host any storage shows (technology forums). When was the last time you engaged in a conversation with an HDS employee about HDS vs competition products.

..

Hitachi uValue Convention 2010, Celebrating 100th year Anniversary of Hitachi

..

Culture

HDS marketing approach has been super secret so far. HDS is quite a bit influenced by its parent company Hitachi Ltd, Japan, where typically marketing seems to be quite conservative. Hitachi Ltd is a 100 Billion dollar company, doing business in most of the world. The Japanese are very modest and focus on engineering and not on product marketing.

Hitachi hardly talks about its own success, when asked a Hitachi executive on how HDS influences IT within Hitachi and how it helps drive more efficiency into Hitachi, the executive was very modest about it.

..

Today

But said that, things are now changing. From what we saw and learnt about HDS a month ago at the HDS Geek Day 0.9 in Santa Clara and this week at Hitachi in Japan at the research labs and the uValue convention, now its pretty apparent that HDS is changing how it does marketing and focuses on product and datacenter strategy.

There is a list put together by HDSCorp on twitter with all twitter users from HDS

http://twitter.com/HDScorp/hdsers/members

A few HDS executives also blog at the HDS Blogs site

http://blogs.hds.com/

..

Tomorrow

We saw some really new focus areas in terms of marketing within HDS. This is the changing side of the company.

A few things HDS should do, allow blogging outside the HDS domain, follow and create some unique marketing efforts to drive the messaging internally within HDS, internally to Hitachi and externally to customers and social media folks. Get more HDS folks on Twitter and other social media channels.

One thing we know, the new executive team within HDS is very aggressive and wants to make a difference. This was very visible at the HDS Geek Day 0.9 and this week in Japan where HDS is really pushing Hitachi engineering with new product innovation and product strategy.

Hitachi has a ton of datacenter products, as Nigel Poulton points out in one of his Blog post about Hitachi Networking, some of these products are so successful in the Japanese market, but never even make it to the rest of the world.

The big vision story is missing. Its not about one datacenter product like storage, its about how every component in the puzzle can help customers drive more efficiency within datacenters.

Its wait and watch, but what we saw over the past month, I can say, HDS is rolling their sleeves ….. and getting ready…..

..

Disclaimer: The 4 day trip to Hitachi Japan to attend the uValue Convention was sponsored by HDS. They paid for all Travel, Boarding and lodging expenses for these days. The attendees / bloggers are not required to Blog about this event. This is my attempt to share what we learned there.