Behind the Scenes, SANta Claus Global Cloud Story

There is a ton of discussion, stories, articles, videos, conferences and blogs about the benefits and value proposition of cloud computing. Not to mention, discussion or debates about what is or what is not a cloud or cloud product, service or architecture including some perspectives and polls from me.

Now SANta does not really care about these and other similar debates I have learned. However he is concerned with who has been naughty and nice as well watching out for impersonators or members of his crew who misbehave.

In the spirit of the holidays, how about a quick look at how SANta leverages cloud technologies to support his global operations.

Many in IT think that SANta bases his operations out of the North Pole as it is convenient for him to cool all of his servers, storage, networks and telecom equipment (which it is). However its also centrally located (See chart) for the northern hemisphere (folks down under may get serviced via SANtas secret Antarctica base of operations). Just like ANC (Anchorage International Airport) is a popular cargo transient, transload and refueling base for cargo carriers, SANta also leverages the north and South Pole regions to his advantage.

Great Circle Mapper
SANtas Global Reach via Great Circle Mapper

Now do not worry if you have never heard about SANta dual redundant South Pole operations, its one of his better kept secrets. Many organizations including SANtas partners such as Microsoft that have global mega IT operations and logistics centers have followed SANtas lead of leveraging various locations outside of the pacific northwest. Granted like some of his partners and managed service providers, he does maintain a presence in Washington Columbia river basin which provides a nice PR among other benefits.

Likewise, many in business as well as those in IT think that SANta leverages cloud technologies for cost savings or avoidance which is partially the case. However he also leverages cloud, hosting, managed service provider (MSP), virtual data centers, virtual operations centers, Xaas, SaaS or SOA technologies, services, protocols and products that are transparent and complimentary to his own in house resources addressing various business and service requirement needs.

What this has to do with the holidays and clouds is that you may not realize how Santa or St. Nick if you prefer (feel free to plug in whoever you like if Santa or St. Nick does not turn your crank) extensively relies on flexible and scalable resilient technologies for boosting productivity in a cost effective manner. Some of it is IT related, some of it is not. For example, from the GPS and Radar along with recently added RNP and RNAV enhanced capabilities to his increasingly high tech bio fueled powered sleigh, not to mention his information technology (IT) that powers his global operations, old St Nick has got it together when it comes to technology.

The heart or brains of the SANta operation is his global system operations center (SOC) or network operation center (NOC) that rivals those seen at NASA among others with multiple data feeds. The SOC is a 24×365 operations function that covers all aspects from transportation, logistics, distribution, assembly or packaging, financials back office, CRM, IT and communications among other functions.

Naturally, like the Apollo moon shots whose Grumman built LEM Lunar lander had to have 100% availability in that to get off of the moon, their engines only had to fire once, however it had to work 100% of the time! This thought process is said to have had leveraged principles from SANtas operations guide where he has one night a year to accomplish the impossible.

I should mention, while I cannot disclose (due to NDA) the exact locations of the SOCs, data or logistics centers, not to mention the vendors or the technology being used, I can tell you that they are all around you! The fully redundant SOCs, data and call centers as well as logistics sites (including staff, facilities, technology) leverage different time zones for efficiency.

SANtas staff have also found that the redundant SOCs, part of an approach across Santa entire vast organization has helped to guard against global epidemics and pandemics including SARs and H1N1 among others by isolating workers while providing appropriate coverage and availability, something many large organizations have since followed.

Carrying through on the philosophy of redundant SOCs, all other aspects of SANtas operations are distributed yet with centralized coordinated management, leveraging real-time situation awareness, event and activity correlation (what we used to call or refer to as AI), cross technology domain management, proactive monitoring and planning yet with ability for on the spot decision making.

What this means is that the various locations have ability to make localized decisions on the spot. However coordinated with primary operations or mission control to streamline global operations focus on strategic activity along with exceptions handling to be more effective. Thus it is not fully distributed nor fully centralized, rather a hybrid in terms of management, technologies and the way they work.

For example, to handle the diverse applications, there are some primary large processing and data retention facilities that backup, replicate information to other peer sites as well as smaller regional remote office branch offices close to where information services are needed. To say the environment is highly virtualized would be an understatement.

Likewise, optimization is key not just to keep costs low or avoid overheating some of SANtas facilities that are located in the Arctic and Antarctic regions that could melt the ice cap; they are also optimized to keep response time as low as possible while boosting productivity.

Thus, SANta has to rely on very robust and diverse communications networking leveraging LAN, SAN, MAN, WAN, POTS and PANs among other technologies. For example, his communications portfolio is said to involves landlines (copper and optical), RF including microwave and other radio based commutations supporting or using 3G, 4G, MPLS, SONET/SCH, xWDM, Microwave and Free space optics among others.

SANtas networking and communications elves are also said to be working with 5G and 100GbE multiplexed on 256 lambda WDM trunk circuits in non core trunk applications. Of course given the airborne operations, satellite and ACARS are a must to avoid over flying a destination while remaining in positive control during low visibility. Note that Santa routinely makes more CAT 3+ low visibility landings than most of the worlds airlines, air freight companies combined.

My sources also tell me that SANta has virtual desktop capability leveraging PCoIP and other optimizations on his primary and backup sleighs enabling rapid reconfiguration for changing workload conditions. He also is fully equipped with onboard social media capabilities for updates via twitter, Face book and Linked In among others designed by his chief social networking elf.

Consequently, given the vast amount of information needed to support his operations from CRM, shipping, tracking not to mention historical and profiling needs, transactional volumes both on the data as well as voice and social media networks dwarf the stock market trading volume.

Feeding SANtas vast organizations are online highly available robust databases for transactions purposes, reference unstructured data material including videos, websites and more. Some of which look hauntingly familiar given those that are part of SANtas eWorld Helpers initiative including: Sears, Amazon, NetFlix, Target, Albertsons, Staples, EMC, Wall mart, Overstock, RadioShack, Landsend, Dell, HP, eBay, Lowes, Publix, emusic, Riteaid and Supervalu among others (Im just sayin…).

The actual size of SANta information repository is a closely regarded secret as is the exact topology, schema and content structure. However it is understood that on peak days SANtas highly distributed high performance, low latency data warehouse sees upwards of 1,225PBytes of data added, one that is rumored to make Larry Ellison gush with excitement over its growth possibilities.

How does SANta pull this all off is by leveraging virtualization, automation, efficient and enabling technologies that allow him and elves (excuse me, associates or team members) to be more productivity in their areas of focus that is the envy of the universe.

Some of their efficiency is measured in terms of:

  • How many packages can be processed per elf with minimum or no mistakes
  • Number of calls, requests, inquiries per day per elf in a friendly and understandable manner
  • Knowing who has been naughty or nice in the blink of an eye including historical profiles
  • Virtual machines (VM) or physical machine (PM) servers managed per team member
  • Databases and applications, local and remote, logical and physical per team member
  • Storage in terms of PByte and Exabyte managed to given service level per team member
  • Network circuits and bandwidth with fewest dropped packets (or packages) per member
  • Fewest misdirected packages as well as aborted landings per crew
  • Fewest pounds gained from consumption of most milk and cookies per crew

From how many packages can be processed per hour, to the number of virtual servers per person, PBytes of data managed per person, network connections and circuits per person, databases and applications per person to takes and landings (SANta has the top of the list for this one), they are all highly efficient and effective.

Likewise, SANta leverages the partners in his SANtas eWORLD Helpers initiative network to help out where of course he looks for value; however value is not just lowest price per VM, lowest cost per TByte or cost per bandwidth. For SANta it is also very focused on performance, availability, capacity and economic efficiency not to mention quality with an environmentally friendly green supply chain.

By having a green supply chain, SANta leverages from a responsible, global approach that also makes economic sense on where to manufacture and produce or procure products. Contrary to growing popular belief, locally produced may not always be the most environmentally as well as economically favorable approach. For example (read more here), instead of growing flowers and plans in western Europe where they are consumed, a process that would require more energy for heat, lights, not to mention water and other resources. SANta has bucked the trend instead relying on the economics and environmental benefit of leveraging flowers and plants grown in warmer, sunnier climates.

Granted and rest assured, SANta still has an army of elves busily putting things together in his own factories along with managing IT related activities in a economically positive manner.

SANta has also leveraged this thinking to his data and information and communications networks leveraging sites such as in the arctic where solar power can be used during summer months along with cooling economizers to offset the impact of batteries, workload is shifted around the world as needed. This approach is rumored to be the envy of the US EPA Energy Star for Server, Storage and Data Center crew not to mention their followers.

How does SANta make sure all of the data and information is protected and available? Its a combination of best practices, techniques, technologies including hardware, software, data protection management tools, disk, dedupe, compression, tape and cloud among others.

Rest assured, if it is in the technology buzzword bingo book, it is a good bet that it has been tested in one of SANtas facilities, or, partner sites long before you hear about it even under a strict NDA discussion with one of his elves (opps, I mean supplier partners).

When asked of the importance of his information and data networks, resources and cloud enabled highly virtualized efficient operations SANta responded with a simple:

Ho Ho Ho, Merry Christmas to all, and to all, a good night!

As you sit back and relax, reflect, recreate, recoup or recharge, or whatever it is that you do this time of the year, take a moment to think about and thank all of SANtas helpers. They are the ones that work behind the scenes in SANtas facilities as well as his partners or suppliers, some in the clouds, some on or underground to make the worlds largest single event day (excuse me, night) possible! Or, is this SANta and cloud thing all just one big fantasy?

Happy and safe holidays or whatever you want to refer to it as, best wishes and thanks!

BTW: FTC disclosure information can be found here!

Greg on Break

Me on a break during tour SANta site tour

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

The other Green Storage: Efficiency and Optimization

Some believe that green storage is specifically designed to reduce power and cooling costs.

The reality is that there are many ways to reduce environmental impact while enhancing the economics of data storage besides simply booting utilizing.

These include optimizing data storage capacity as well as boosting performance to increase productivity per watt of energy used when work needs to be done.

Some approaches require new hardware or software while others can be accomplished with changes to management including reconfiguration leveraging insight and awareness of resource needs.

Here are some related links:

The Other Green: Storage Efficiency and Optimization (Videocast)

Energy efficient technology sales depend on the pitch

Performance metrics: Evaluating your data storage efficiency

How to reduce your Data Footprint impact (Podcast)

Optimizing enterprise data storage capacity and performance to reduce your data footprint

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Green IT and Virtual Data Centers

Green IT and virtual data centers are no fad nor are they limited to large-scale environments.

Paying attention to how resources are used to deliver information services in a flexible, adaptable, energy-efficient, environmentally, and economically friendly way to boost efficiency and productivity are here to stay.

Read more here in the article I did for the folks over at Enterprise Systems Journal.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

How to win approval for upgrades: Link them to business benefits

Drew Rob has another good article over at Processor.com about various tips and strategies on how to gain approval for hardware (or software) purchases with some comments by yours truly.

My tips and advice that are quoted in the story include to link technology resources to business needs impact which may be common sense, however still a time tested effective technique.

Instead of speaking tech talk such as Performance, capacity, availability, IOPS, bandwidth, GHz, frames or packets per second, VMs to PM or dedupe ratio, map them to business speak, that is things that finance, accountants, MBAs or other management personal understand.

For example, how many transactions at a given response time can be supported by a given type of server, storage or networking device.

Or, put a different way, with a given device, how much work can be done and what is the associated monetary or business benefit.

Likewise, if you do not have a capacity plan for servers, storage, I/O and networking along with software and facilities covering performance, availability, capacity and energy demands now is the time to put one in place.

More on capacity and performance planning later, however for now, if you want to learn more, check Chapter 10 (Performance and Capacity Planning) in my book Resilient Storage Networks: Designing Flexible and Scalable Data Infrastructure: Elsevier).

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

What is the Future of Servers?

Recently I provided some comments and perspectives on the future of servers in an article over at Processor.com.

In general, blade servers will become more ubiquitous, that is they wont go away even with cloud, rather become more common place with even higher density processors with more cores and performance along with faster I/O and larger memory capacity per given footprint.

While the term blade server may fade giving way to some new term or phrase, rest assured their capabilities and functionality will not disappear, rather be further enhanced to support virtualization with VMware vsphere, Microsoft HyperV, Citrix/Zen along with public and private clouds, both for consolidation and in the next wave of virtualization called life beyond consolidation.

The other trend is that not only will servers be able to support more processing and memory per footprint; they will also do that drawing less energy requiring lower cooling demands, hence more Ghz per watt along with energy savings modes when less work needs to be performed.

Another trend is around convergence both in terms of packaging along with technology improvements from a server, I/O networking and storage perspective. For example, enhancements to shared PCIe with I/O virtualization, hypervisor optimization, and integration such as the recently announced EMC, Cisco, Intel and VMware VCE coalition and vblocks.

Read more including my comments in the article here.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Justifying Green IT and Home Hardware Upgrades with EnergyStar

Energy Star

Have you seen the TV commercials or print advertisements where an energy star washer is mentioned as so efficient that the savings from reduced power consumption are enough to pay for the dryer? If not, check out the EPA Energy Star website for information about various programs, savings and efficiency options to learn more

What does this have to do with servers, storage, networking, data centers or other IT equipment?

Simple, if you are not aware, Energy Star for Servers now exits and is being enhanced while good progress is being made on the Energy Star for storage program.

The Energy Star for household appliances has been around a bit longer and more refined, something that I anticipated the server and storage programs to follow-suit with over time.

What really caught my eye with the commercial is the focus on closing the green gap, that is instead of the green environmental impact savings of an appliance that uses less power and subsequent carbon footprint benefits, the message is to the economic hot button. That is, switch to more energy efficient technology that allows more work to done at a lower overall cost and the savings can help self fund the enhancements.

For example, a more energy efficient server that can do more work or GHz per watt of energy when needed, or, to go into lower power modes (intelligent power management: IPM). Low power modes do not necessarily mean turning completely off, rather, drawing less energy and subsequently lower cooling demands during slow periods such as with new Intel Nehalem and other processors.

From a disk storage perspective, energy efficiency is often thought to be avoidance or turning disk drives off boosting capacity and squeezing data footprints.

However energy efficiency and savings can also be achieved by slowing a disk drive down or turning of some of the electronics to reduce energy consumption and heat generation.

Other forms of energy savings include thin provisioning and deduplication however another form of energy efficiency for storage is boosting performance. That is, doing more work per watt of energy for active or time sensitive applications or usage scenarios.

Thus there is another Green IT, one that provides both economic and environmental benefits!

Here are some related links:

Saving Money with Green IT: Time To Invest In Information Factories

EPA Energy Star for Data Center Storage Update

Green Storage is Alive and Well: ENERGY STAR Enterprise Storage Stakeholder Meeting Details

Shifting from energy avoidance to energy efficiency

U.S. EPA Energy Star for Server Update

U.S. EPA Looking for Industry Input on Energy Star for Storage

Update: EnergyStar for Server Workshop

US EPA EnergyStar for Servers Wants To Hear From YOU!

Optimize Data Storage for Performance and Capacity Efficiency

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Did HP respond to EMC and Cisco VCE with Microsoft HyperV bundle?

Last week EMC and Cisco along with Intel and VMware created the VCE collation along with a consumption model based service joint venture called Acadia.

In other activity last week, HP made several announcements including:

  • Improvements in sensing technologies
  • StorageWorks enhancements (SVSP, IBRIX, EVA and HyperV, X9000 and others)

EMC and Cisco were relatively quiet this week on announcement front, however HP unleashed another round of announcements that among others included:

  • Quarterly financial results
  • SMB server, storage, network and virtualization enhancements (here, here, here and here)
  • Acquisitions of 3COM (see related blog post here)

The reason I bring up all of this HP activity is not to simply re-cap all of the news and announcements which you can find on many other blogs or news sites, rather I see as a trend.

That trend appears to be one of a company on the move, not ready to sit back on its laurels, rather a company that continues to innovate in-house and via acquisitions.

Some of those acquisitions including IBRIX were relatively small, some like EDS last year and the one this week of 3COM to some would be large while to others perhaps as being seen as medium sized. Either way, HP has been busy expanding its portfolio of technology solution and services offerings along with its comprehensive IT stack.

Cisco, EMC and HP are examples of companies looking to expand their IT stacks and footprint in terms of diversifying current product focus and reach, along with extending into new or further into existing customer and market sector areas. Last weeks EMC and Cisco signaled two large players combing their resources to make virtualization and private clouds easy to acquire and deploy for mid to large size environments with a theme around VMware.

This week buried in all of the HP announcements was one that caught my eye which is a virtualization solution bundle designed for small business (that is something smaller than a vblock0), something that was missing in the Cisco and EMC news of last week however one that Im sure will be addressed sooner versus later.

In the case of HP, the other thing with their virtualization bundle was the focus on the mid to small business that fall into the broad and diverse SMB category, not to mention including Microsoft.

Yes, that is right, while a VMware based solution from HP would be a no-brainer given all of the activity the two companies are involved  in as joint partners, Microsoft HyperV was front and center.

Is this a reaction to last weeks Cisco and EMC salvo?

Perhaps and some will jump to that conclusion. However I will also offer this alternative scenario, 85-90 percent of servers consolidated into virtual machines (VMs) on VMware or other hypervisors including Microsoft HyperV are Windows based.

Likewise as one of the largest if not largest server vendors (pick your favorite server category or price band) who also happens to be one of the largest Microsoft Windows partners, I would have been more surprised if HP had not done a HyperV bundle.

While Cisco and EMC may stay the course or at least talk the talk with a VMware affinity in the Acadia and VCE coalition for the time being, I would expect HP to flex its wings a bit and show diversity of support for multiple Hypervisors, Operating Systems across its various server, network, storage and services platforms.

I would not be surprised to see some VMware based bundles appear over time building on previous announced HP blade systems matrix solution bundles.

Welcome back my friends to the show that never ends, that is the on-going server, storage, networking, virtualization, hardware, software and services solutions game for enabling the adaptive, dynamic, flexible, scalable, resilient, service oriented, public or private cloud, infrastructure as a service green and virtual data center.

Stay tuned, there is much more to come!

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Poll: EMC and Cisco Acadia VCE, what does it mean?

EMC and Cisco recently announced their new Acadia VCE coalition along with Intel and VMware.

As part of the VCE the collation or joint venture is also providing to market pre-acted vblocks that include Cisco servers power by Intel and network switches, EMC storage and management tools (Inonx and RSA for security), VMware vsphere virtualization along with pre-post sales services.

How does this move from a technology, packaging, integration as well as business or alliance perspective change the server, storage, networking, hardware, software and services game?

Whats your take?

Cheers gs

Greg Schulz – StorageIO, Author “The Green and Virtual Data Center” (CRC)

Acadia VCE: VMware + Cisco + EMC = Virtual Computing Environment

Was today the day the music died? (click here or here if you are not familar with the expression)

Add another three letter acronym (TLA) to your IT vocabulary if you are involved with server, storage, networking, virtualization, security and related infrastructure resource management (IRM) topics.

That new TLA is Virtual Computing Environment (VCE), a coalition formed by EMC and Cisco along with partner Intel called Acadia that was announced today. Of course, EMC who also happens to own VMware for virtualization and RSA for security software tools bring those to the coalition (read press release here).

For some quick fun, twittervile and the blogosphere have come up with other meanings such as:

VCE = Virtualization Communications Endpoint
VCE = VMware Cisco EMC
VCE = Very Cash Efficient
VCE = VMware Controls Everything
VCE = Virtualization Causes Enthusiasm
VCE = VMware Cisco Exclusive

Ok, so much for some fun, at least for now.

With Cisco, EMC and VMware announcing their new VCE coalition, has this signaled the end of servers, storage, networking, hardware and software for physical, virtual and clouding computing as we know it?

Does this mean all other vendors not in this announcement should pack it up, game over and go home?

The answer in my perspective is NO!

No, the music did not end today!

NO, servers, storage and networking for virtual or cloud environments has not ended.

Also, NO, other vendors do not have to go home today, the game is not over!

However a new game is on, one that some have seen before, for others it is something new, exciting perhaps revolutionary or an industry first.

What was announced?
Figure 1 shows a general vision or positioning from the three major players involved along with four tenants or topic areas of focus. Here is a link to a press release where you can read more.

CiscoVirtualizationCoalition.png
Figure 1: Source: Cisco, EMC, VMware

General points include:

  • A new coalition (e.g. VCE) focused on virtual compute for cloud and non cloud environments
  • A new company Acadia owned by EMC and Cisco (1/3 each) along with Intel and VMware
  • A new go to market pre-sales, service and support cross technology domain skill set team
  • Solution bundles or vblocks with technology from Cisco, EMC, Intel and VMware

What are the vblocks and components?
Pre-configured (see this link for a 3D model), tested, and supported with a single throat to choke model for streamlined end to end management and acquisition. There are three vblocks or virtual building blocks that include server, storage, I/O networking, and virtualization hypervisor software along with associated IRM software tools.

Cisco is bringing to the game their Unified Compute Solution (UCS) server along with Nexus 1000v and Multilayer Director (MDS) switches, EMC is bringing storage (Symmetrix VMax, CLARiiON and unified storage) along with their RSA security and Ionix IRM tools. VMware is providing their vSphere hypervisors running on Intel based services (via Cisco).

The components include:

  • EMC Ionix management tools and framework – The IRM tools
  • EMC RSA security framework software – The security tools
  • EMC VMware vSphere hypervisor virtualization software – The virtualization layer
  • EMC VMax, CLARiiON and unified storage systems – The storage
  • Cisco Nexus 1000v and MDS switches – The Network and connectivity
  • Cisco Unified Compute Solution (UCS) – The physical servers
  • Services and support – Cross technology domain presales, delivery and professional services

CiscoEMCVMwarevblock.jpg
Figure 2: Source: Cisco vblock (Server, Storage, Networking and Virtualization Software) via Cisco

The three vblock models are:
Vblock0: entry level system due out in 2010 supporting 300 to 800 VMs for initial customer consolidation, private clouds or other diverse applications in small or medium sized business. You can think of this as a SAN in a CAN or Data Center in a box with Cisco UCS and Nexus 1000v, EMC unified storage secured by RSA and VMware vSphere.

Vblock1: mid sized building block supporting 800 to 3000 VMs for consolidation and other optimization initiatives using Cisco UCS, Nexus and MDS switches along with EMC CLARiiON storage secured with RSA software hosting VMware hypervisors.

Vblock2 high end supporting up 3000 to 6000 VMs for large scale data center transformation or new virtualization efforts combing Cisco Unified Computing System (UCS), Nexus 1000v and MDS switches and EMC VMax Symmetix storage with RSA security software hosting VMware vSpshere hypervisor.

What does this all mean?
With this move, for some it will add fuel to the campfire that Cisco is moving closer to EMC and or VMware with a pre-nuptial via Acadia. For others, this will be seen as fragmentation for virtualization particularly if other vendors such as Dell, Fujitsu, HP, IBM and Microsoft among others are kept out of the game, not to mention their channels of vars or IT customers barriers.

Acadia is a new company or more precisely, a joint venture being created by major backers EMC and Cisco with minority backers being VMware and Intel.

Like any other joint ventures, for examples those commonly seen in the airline industry (e.g. transportation utility) where carriers pool resources such as SkyTeam whose members include Delta who had a JV with Airframe owner of KLM who had a antitrust immunity JV with northwest (now being digested by Delta).

These joint ventures can range from simple marketing alliances like you see with EMC programs such as their Select program to more formal OEM to ownership as is the case with VMware and RSA to this new model for Acadia.

An airline analogy may not be the most appropriate, yet there are some interesting similarities, least of which that air carriers rely on information systems and technologies provided by members of this collation among others. There is also a correlation in that joint ventures are about streamlining and creating a seamless end to end customer experience. That is, give them enough choice and options, keep them happy, take out the complexities and hopefully some cost, and with customer control come revenue and margin or profits.

Certainly there are opportunities to streamline and not just simply cut corners, perhaps that’s another area or analogy with the airlines where there is a current focus on cutting, nickel and dimming for services. Hopefully the Acadia and VCE are not just another example of vendors getting together around the campfire to sing Kumbaya in the name of increasing customer adoption, cost cutting or putting a marketing spin on how to sell more to customers for account control.

Now with all due respect to the individual companies and personal, at least in this iteration, it is not as much about the technology or packaging. Likewise, while important, it is also not just about bundling, integration and testing (they are important) as we have seen similar solutions before.

Rather, I think this has the potential for changing the way server, storage and networking hardware along with IRM and virtualization software are sold into organizations, for the better or worse.

What Im watching is how Acadia and their principal backers can navigate the channel maze and ultimately the customer maze to sell a cross technology domain solution. For example, will a sales call require six to fourteen legs (e.g. one person is a two legged call for those not up on sales or vendor lingo) with a storage, server, networking, VMware, RSA, Ionix and services representative?

Or, can a model to drive down the number of people or product specialist involved in a given sales call be achieved leveraging people with cross technology domain skills (e.g. someone who can speak server and storage hardware and software along with networking)?

Assuming Acadia and VCE vblocks address product integration issues, I see the bigger issue as being streamlining the sales process (including compensation plans) along with how partners are dealt with not to mention customers.

How will the sales pitch be to the Cisco network people at VARs or customer sites, or too the storage or server or VMware teams, or, all of the above?

What about the others?
Cisco has relationships with Dell, HP, IBM, Microsoft and Oracle/Sun among others that they will be stepping even more on the partner toes than when they launched the UCS earlier this year. EMC for its part if fairly diversified and is not as subservient to IBM however has a history of partnering with Dell, Oracle and Microsoft among others.

VMware has a smaller investment and thus more in the wings as is Intel given that both have large partnership with Dell, HP, IBM and Microsoft. Microsoft is of interest here because on one front the bulk of all servers virtualized into VMware VMs are Windows based.

On the other hand, Microsoft has their own virtualization hypervisor HyperV that depending upon how you look at it, could be a competitor of VMware or simply a nuisance. Im of the mindset that its still to early and don’t judge this game on the first round which VMware has won. Keep in mind the history such as desktop and browser wars that Microsoft lost in the first round only to come back strong later. This move could very well invigorate Microsoft, or perhaps Oracle, Citrix among others.

Now this is far from the first time that we have seen alliances, coalitions, marketing or sales promotion cross technology vendor clubs in the industry let alone from the specific vendors involved in this announcement.

One that comes to mind was 3COMs failed attempt in the late 90s to become the first traditional networking vendor to get into SANs, that was many years before Cisco could spell SAN let alone their Andiamo startup incubated. The 3COM initiative which was cancelled due to financial issues literally on the eve of rollout was to include the likes of STK (pre-sun), Qlogic, Anchor (People were still learning how to spell Brocade), Crossroads (FC to SCSI routers for tape), Legato (pre-EMC), DG CLARiiON (Pre-EMC), MTI (sold their patents to EMC, became a reseller, now defunct) along with some others slated to jump on the bandwagon.

Lets also not forget that while among the traditional networking market vendors Cisco is the $32B giant and all of the others including 3Com, Brocade, Broadcom, Ciena, Emulex, Juniper and Qlogic are the seven plus dwarfs. However, keep the $23B USD Huawei networking vendor that is growing at a 45% annual rate in mind.

I would keep an eye on AMD, Brocade, Citrix, Dell, Fujitsu, HP, Huawei, Juniper, Microsoft, NetApp, Oracle/Sun, Rackable and Symantec among many others for similar joint venture or marketing alliances.

Some of these have already surfaced with Brocade and Oracle sharing hugs and chugs (another sales term referring to alliance meetings over beers or shots).

Also keep in mind that VMware has a large software (customer business) footprint deployed on HP with Intel (and AMD) servers.

Oh, and those VMware based VMs running on HP servers also just happen to be hosting in their neighbor of 80% or more Windows based guests operating systems, I would say its game on time.

When I say its game on time, I dont think VMware is brash enough to cut HP (or others) off forcing them to move to Microsoft for virtualization. However the game is about control, control of technology stacks and partnerships, control of vars, integrators and the channel, as well as control of customers.

If you cannot tell, I find this topic fun and interesting.

For those who only know me from servers they often ask when did I learn about networking to which I say check out one of my books (Resilient Storage Networks-Elsevier). Meanwhile for others who know me from storage I get asked when did I learn about or get into servers to which I respond about 28 years ago when I worked in IT as the customer.

Bottom line on Acadia, vblocks and VCE for now, I like the idea of a unified and bundled solution as long as they are open and flexible.

On the other hand, I have many questions and even skeptical in some areas including of how this plays out for Cisco and EMC in terms of if it can be a unifier or polarized causing market fragmentation.

For some this is or will be dejavu, back to the future, while for others it is a new, exciting and revolutionary approach while for others it will be new fodder for smack talk!

More to follow soon.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Saving Money with Green IT: Time To Invest In Information Factories

There is a good and timely article titled Green IT Can Save Money, Too over at Business Week that has a familiar topic and theme for those who read this blog or other content, articles, reports, books, white papers, videos, podcasts or in-person speaking and keynote sessions that I have done..

I posted a short version of this over there, here is the full version that would not fit in their comment section.

Short of calling it Green IT 2.0 or the perfect storm, there is a resurgence and more importantly IMHO a growing awareness of the many facets of Green IT along with Green in general having an economic business sustainability aspect.

While the Green Gap and confusion still exists, that is, the difference between what people think or perceive and actual opportunities or issues; with growing awareness, it will close or at least narrow. For example, when I regularly talk with IT professionals from various sized, different focused industries across the globe in diverse geographies and ask them about having to go green, the response is in the 7-15% range (these are changing) with most believing that Green is only about carbon footprint.

On the other hand, when I ask them if they have power, cooling, floor space or other footprint constraints including frozen or reduced budgets, recycling along with ewaste disposition or RoHS requirements, not to mention sustaining business growth without negatively impacting quality of service or customer experience, the response jumps up to 65-75% (these are changing) if not higher.

That is the essence of the green gap or disconnect!

Granted carbon dioxide or CO2 reduction is important along with NO2, water vapors and other related issues, however there is also the need to do more with what is available, stretch resources and footprints do be more productive in a shrinking footprint. Keep in mind that there is no such thing as an information, data or processing recession with all indicators pointing towards the need to move, manage and store larger amounts of data on a go forward basis. Thus, the need to do more in a given footprint or constraint, maximizing resources, energy, productivity and available budgets.

Innovation is the ability to do more with less at a lower cost without compromise on quality of service or negatively impacting customer experience. Regardless of if you are a manufacturer, or a service provider including in IT, by innovating with a diverse Green IT focus to become more efficient and optimized, the result is that your customers become more enabled and competitive.

By shifting from an avoidance model where cost cutting or containment are the near-term tactical focus to an efficiency and productivity model via optimization, net unit costs should be lowered while overall service experience increase in a positive manner. This means treating IT as an information factory, one that needs investment in the people, processes and technologies (hardware, software, services) along with management metric indicator tools.

The net result is that environmental or perceived Green issues are addressed and self-funded via the investment in Green IT technology that boosts productivity (e.g. closing or narrowing the Green Gap). Thus, the environmental concerns that organizations have or need to address for different reasons yet that lack funding get addressed via funding to boost business productivity which have tangible ROI characteristics similar to other lean manufacturing approaches.

Here are some additional links to learn more about these and other related themes:

Have a read over at Business Week about how Green IT Can Save Money, Too while thinking about how investing in IT infrastructure productivity (Information Factories) by becoming more efficient and optimized helps the business top and bottom line, not to mention the environment as well.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Poll: Whats Your Take on Windows 7


Microsoft finally officially released Windows 7 recently, whats your take?

Have you already taken the jump to be the first on the block or neighbored to be on Windows 7, getting ready to make the leap, have it on the back burner for next year, no plans, or perhaps already dumped Windows for Mac or Linux or getting ready to pull the plug?

Cheers – gs

Greg Schulz – StorageIO, Author “The Green and Virtual Data Center” (CRC)

Optimize Data Storage for Performance and Capacity Efficiency

This post builds on a recent article I did that can be read here.

Even with tough economic times, there is no such thing as a data recession! Thus the importance of optimizing data storage efficiency addressing both performance and capacity without impacting availability in a cost effective way to do more with what you have.

What this means is that even though budgets are tight or have been cut resulting in reduced spending, overall net storage capacity is up year over year by double digits if not higher in some environments.

Consequently, there is continued focus on stretching available IT and storage related resources or footprints further while eliminating barriers or constraints. IT footprint constraints can be physical in a cabinet or rack as well as floorspace, power or cooling thresholds and budget among others.

Constraints can be due to lack of performance (bandwidth, IOPS or transactions), poor response time or lack of availability for some environments. Yet for other environments, constraints can be lack of capacity, limited primary or standby power or cooling constraints. Other constraints include budget, staffing or lack of infrastructure resource management (IRM) tools and time for routine tasks.

Look before you leap
Before jumping into an optimization effort, gain insight if you do not already have it as to where the bottlenecks exist, along with the cause and effect of moving or reconfiguring storage resources. For example, boosting capacity use to more fully use storage resources can result in a performance issue or data center bottlenecks for other environments.

An alternative scenario is that in the quest to boost performance, storage is seen as being under-utilized, yet when capacity use is increased, low and behold, response time deteriorates. The result can be a vicious cycle hence the need to address the issue as opposed to moving problems by using tools to gain insight on resource usage, both space and activity or performance.

Gaining insight means looking at capacity use along with performance and availability activity and how they use power, cooling and floor-space. Consequently an important tool is to gain insight and knowledge of how your resources are being used to deliver various levels of service.

Tools include storage or system resource management (SRM) tools that report on storage space capacity usage, performance and availability with some tools now adding energy usage metrics along with storage or system resource analysis (SRA) tools.

Cooling Off
Power and cooling are commonly talked about as constraints, either from a cost standpoint, or availability of primary or secondary (e.g. standby) energy and cooling capacity to support growth. Electricity is essential for powering IT equipment including storage enabling devices to do their specific tasks of storing data, moving data, processing data or a combination of these attributes.

Thus, power gets consumed, some work or effort to move and store data takes place and the by product is heat that needs to be removed. In a typical IT data center, cooling on average can account for about 50% of energy used with some sites using less.

With cooling being a large consumer of electricity, a small percentage change to how cooling consumes energy can yield large results. Addressing cooling energy consumption can be to discuss budget or cost issues, or to enable cooling capacity to be freed up to support installation of extra storage or other IT equipment.

Keep in mind that effective cooling relies on removing heat from as close to the source as possible to avoid over cooling which requires more energy. If you have not done so, have a facilities review or assessment performed that can range from a quick walk around, to a more in-depth review and thermal airflow analysis. A means of removing heat close to the sort are techniques such as intelligent, precision or smart cooling also known by other marketing names.

Powering Up, or, Powering Down
Speaking of energy or power, in addition to addressing cooling, there are a couple of ways of addressing power consumption by storage equipment (Figure 1). The most popular discussed approach towards efficiency is energy avoidance involving powering down storage when not used such as first generation MAID at the cost of performance.

For off-line storage, tape and other removable media give low-cost capacity per watt with low to no energy needed when not in use. Second generation (e.g. MAID 2.0) solutions with intelligent power management (IPM) capabilities have become more prevalent enabling performance or energy savings on a more granular or selective basis often as a standard feature in common storage systems.

GreenOptionsBalance
Figure 1:  How various RAID levels and configuration impact or benefit footprint constraints

Another approach to energy efficiency is seen in figure 1 which is doing more work for active applications per watt of energy to boost productivity. This can be done by using same amount of energy however doing more work, or, same amount of work with less energy.

For example instead of using larger capacity disks to improve capacity per watt metrics, active or performance sensitive storage should be looked at on an activity basis such as IOP, transactions, videos, emails or throughput per watt. Hence, a fast disk drive doing work can be more energy-efficient in terms of productivity than a higher capacity slower disk drive for active workloads, where for idle or inactive, the inverse should hold true.

On a go forward basis the trend already being seen with some servers and storage systems is to do both more work, while using less energy. Thus a larger gap between useful work (for active or non idle storage) and amount of energy consumed yields a better efficiency rating, or, take the inverse if that is your preference for smaller numbers.

Reducing Data Footprint Impact
Data footprint impact reduction tools or techniques for both on-line as well as off-line storage include archiving, data management, compression, deduplication, space-saving snapshots, thin provisioning along with different RAID levels among other approaches. From a storage access standpoint, you can also include bandwidth optimization, data replication optimization, protocol optimizers along with other network technologies including WAFS/WAAS/WADM to help improve efficiency of data movement or access.

Thin provisioning for capacity centric environments can be used to achieving a higher effective storage use level by essentially over booking storage similar to how airlines oversell seats on a flight. If you have good historical information and insight into how storage capacity is used and over allocated, thin provisioning enables improved effective storage use to occur for some applications.

However, with thin provisioning, avoid introducing performance bottlenecks by leveraging solutions that work closely with tools that providing historical trending information (capacity and performance).

For a technology that some have tried to declare as being dead to prop other new or emerging solutions, RAID remains relevant given its widespread deployment and transparent reliance in organizations of all size. RAID also plays a role in storage performance, availability, capacity and energy constraints as well as a relief tool.

The trick is to align the applicable RAID configuration to the task at hand meeting specific performance, availability, capacity or energy along with economic requirements. For some environments a one size fits all approach may be used while others may configure storage using different RAID levels along with number of drives in RAID sets to meet specific requirements.


Figure 2:  How various RAID levels and configuration impact or benefit footprint constraints

Figure 2 shows a summary and tradeoffs of various RAID levels. In addition to the RAID levels, how many disks can also have an impact on performance or capacity, such as, by creating a larger RAID 5 or RAID 6 group, the parity overhead can be spread out, however there is a tradeoff. Tradeoffs can be performance bottlenecks on writes or during drive rebuilds along with potential exposure to drive failures.

All of this comes back to a balancing act to align to your specific needs as some will go with a RAID 10 stripe and mirror to avoid risks, even going so far as to do triple mirroring along with replication. On the other hand, some will go with RAID 5 or RAID 6 to meet cost or availability requirements, or, some I have talked with even run RAID 0 for data and applications that need the raw speed, yet can be restored rapidly from some other medium.

Lets bring it all together with an example
Figure 3 shows a generic example of a before and after optimization for a mixed workload environment, granted you can increase or decrease the applicable capacity and performance to meet your specific needs. In figure 3, the storage configuration consists of one storage system setup for high performance (left) and another for high-capacity secondary (right), disk to disk backup and other near-line needs, again, you can scale the approach up or down to your specific need.

For the performance side (left), 192 x 146GB 15K RPM (28TB raw) disks provide good performance, however with low capacity use. This translates into a low capacity per watt value however with reasonable IOPs per watt and some performance hot spots.

On the capacity centric side (right), there are 192 x 1TB disks (192TB raw) with good space utilization, however some performance hot spots or bottlenecks, constrained growth not to mention low IOPS per watt with reasonable capacity per watt. In the before scenario, the joint energy use (both arrays) is about 15 kWh or 15,000 watts which translates to about $16,000 annual energy costs (cooling excluded) assuming energy cost of 12 cents per kWh.

Note, your specific performance, availability, capacity and energy mileage will vary based on particular vendor solution, configuration along with your application characteristics.


Figure 3: Baseline before and after storage optimization (raw hardware) example

Building on the example in figure 3, a combination of techniques along with technologies yields a net performance, capacity and perhaps feature functionality (depends on specific solution) increase. In addition, floor-space, power, cooling and associated footprints are also reduced. For example, the resulting solution shown (middle) comprises 4 x 250GB flash SSD devices, along with 32 x 450GB 15.5K RPM and 124 x 2TB 7200RPM enabling an 53TB (raw) capacity increase along with performance boost.

The previous example are based on raw or baseline capacity metrics meaning that further optimization techniques should yield improved benefits. These examples should also help to discuss the question or myth that it costs more to power storage than to buy it which the answer should be it depends.

If you can buy the above solution for say under $50,000 (cost to power), or, let alone, $100,000 (power and cool) for three years which would also be a good acquisition, then the myth of buying is more expensive than powering holds true. However, if a solution as described above costs more, than the story changes along with other variables include energy costs for your particular location re-enforcing the notion that your mileage will vary.

Another tip is that more is not always better.

That is, more disks, ports, processors, controllers or cache do not always equate into better performance. Performance is the sum of how those and other pieces working together in a demonstrable way, ideally your specific application workload compared to what is on a product data sheet.

Additional general tips include:

  • Align the applicable tool, technique or technology to task at hand
  • Look to optimize for both performance and capacity, active and idle storage
  • Consolidated applications and servers need fast servers
  • Fast servers need fast I/O and storage devices to avoid bottlenecks
  • For active storage use an activity per watt metric such as IOP or transaction per watt
  • For in-active or idle storage, a capacity per watt per footprint metric would apply
  • Gain insight and control of how storage resources are used to meet service requirements

It should go without saying, however sometimes what is understood needs to be restated.

In the quest to become more efficient and optimized, avoid introducing performance, quality of service or availability issues by moving problems.

Likewise, look beyond storage space capacity also considering performance as applicable to become efficient.

Finally, it is all relative in that what might be applicable to one environment or application need may not apply to another.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

EPA Energy Star for Data Center Storage Update

EPA Energy Star

Following up on a recent post about Green IT, energy efficiency and optimization for servers, storage and more, here are some additional  thoughts, perspectives along with industry activity around the U.S. Environmental Protection Agency (EPA) Energy Star for Server, Data Center Storage and Data Centers.

First a quick update, Energy Star for Servers is in place with work now underway on expanding and extending beyond the first specification. Second is that Energy Star for Data Center storage definition is well underway including a recent workshop to refine the initial specification along with discussion for follow-on drafts.

Energy Star for Data Centers is also currently undergoing definition which is focused more on macro or facility energy (notice I did not say electricity) efficiency as opposed to productivity or effectiveness, items that the Server and Storage specifications are working towards.

Among all of the different industry trade or special interests groups, at least on the storage front the Storage Networking Industry Association (SNIA) Green Storage Initiative (GSI) and their Technical Work Groups (TWG) have been busily working for the past couple of years on taxonomies, metrics and other items in support of EPA Energy Star for Data Center Storage.

A challenge for SNIA along with others working on related material pertaining to storage and efficiency is the multi-role functionality of storage. That is, some storage simply stores data with little to no performance requirements while other storage is actively used for reading and writing. In addition, there are various categories, architectures not to mention hardware and software feature functionality or vendors with different product focus and interests.

Unlike servers that are either on and doing work, or, off or in low power mode, storage is either doing active work (e.g. moving data), storing in-active or idle data, or a combination of both. Hence for some, energy efficiency is about how much data can be stored in a given footprint with the least amount of power known as in-active or idle measurement.

On the other hand, storage efficiency is also about using the least amount of energy to produce the most amount of work or activity, for example IOPS or bandwidth per watt per footprint.

Thus the challenge and need for at least a two dimensional  model looking at, and reflecting different types or categories of storage aligned for active or in-active (e.g. storing) data enabling apples to apples, vs. apples to oranges comparison.

This is not all that different from how EPA looks at motor vehicle categories of economy cars, sport utility, work or heavy utility among others when doing different types of work, or, in idle.

What does this have to do with servers and storage?

Simple, when a server powers down where does its data go? That’s right, to a storage system using disk, ssd (RAM or flash), tape or optical for persistency. Likewise, when there is work to be done, where does the data get read into computer memory from, or written to? That’s right, a storage system. Hence the need to look at storage in a multi-tenant manner.

The storage industry is diverse with some vendors or products focused on performance or activity, while others on long term, low cost persistent storage for archive, backup, not to mention some doing a bit of both. Hence the nomenclature of herding cats towards a common goal when different parties have various interests that may conflict yet support needs of various customer storage usage requirements.

Figure 1 shows a simplified, streamlined storage taxonomy that has been put together by SNIA representing various types, categories and functions of data center storage. The green shaded areas are a good step in the right direction to simplify yet move towards realistic and achievable befits for storage consumers.


Figure 1 Source: EPA Energy Star for Data Center Storage web site document

The importance of the streamlined SNIA taxonomy is to help differentiate or characterize various types and tiers of storage (Figure 2) products facilitating apples to apples comparison instead of apples or oranges. For example, on-line primary storage needs to be looked at in terms of how much work or activity per energy footprint determines efficiency.


Figure 2: Tiered Storage Example

On other hand, storage for retaining large amounts of data that is in-active or idle for long periods of time should be looked at on a capacity per energy footprint basis. While final metrics are still being flushed out, some examples could be active storage gauged by IOPS or work or bandwidth per watt of energy per footprint while other storage for idle or inactive data could be looked at on a capacity per energy footprint basis.

What benchmarks or workloads to be used for simulating or measuring work or activity are still being discussed with proposals coming from various sources. For example SNIA GSI TWG are developing measurements and discussing metrics, as have the storage performance council (SPC) and SPEC among others including use of simulation tools such as IOmeter, VMware VMmark, TPC, Bonnie, or perhaps even Microsoft ESRP.

Tenants of Energy Star for Data Center Storage overtime hopefully will include:

  • Reflective of different types, categories, price-bands and storage usage scenarios
  • Measure storage efficiency for active work along with in-active or idle usage
  • Provide insight for both storage performance efficiency and effective capacity
  • Baseline or raw storage capacity along with effective enhanced optimized capacity
  • Easy to use metrics with more in-depth back ground or disclosure information

Ultimately the specification should help IT storage buyers and decision makers to compare and contrast different storage systems that are best suited and applicable to their usage scenarios.

This means measuring work or activity per energy footprint at a given capacity and data protection level to meet service requirements along with during in-active or idle periods. This also means showing storage that is capacity focused in terms of how much data can be stored in a given energy footprint.

One thing that will be tricky however will be differentiating GBytes per watt in terms of capacity, or, in terms of performance and bandwidth.

Here are some links to learn more:

Stay tuned for more on Energy Star for Data Centers, Servers and Data Center Storage.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

I/O Virtualization (IOV) Revisited

Is I/O Virtualization (IOV) a server topic, a network topic, or a storage topic (See previous post)?

Like server virtualization, IOV involves servers, storage, network, operating system, and other infrastructure resource management areas and disciplines. The business and technology value proposition or benefits of converged I/O networks and I/O virtualization are similar to those for server and storage virtualization.

Additional benefits of IOV include:

    • Doing more with what resources (people and technology) already exist or reduce costs
    • Single (or pair for high availability) interconnect for networking and storage I/O
    • Reduction of power, cooling, floor space, and other green efficiency benefits
    • Simplified cabling and reduced complexity for server network and storage interconnects
    • Boosting servers performance to maximize I/O or mezzanine slots
    • reduce I/O and data center bottlenecks
    • Rapid re-deployment to meet changing workload and I/O profiles of virtual servers
    • Scaling I/O capacity to meet high-performance and clustered application needs
    • Leveraging common cabling infrastructure and physical networking facilities

Before going further, lets take a step backwards for a few moments.

To say that I/O and networking demands and requirements are increasing is an understatement. The amount of data being generated, copied, and retained for longer periods of time is elevating the importance of the role of data storage and infrastructure resource management (IRM). Networking and input/output (I/O) connectivity technologies (figure 1) tie facilities, servers, storage tools for measurement and management, and best practices on a local and wide area basis to enable an environmentally and economically friendly data center.

TIERED ACCESS FOR SERVERS AND STORAGE
There is an old saying that the best I/O, whether local or remote, is an I/O that does not have to occur. I/O is an essential activity for computers of all shapes, sizes, and focus to read and write data in and out of memory (including external storage) and to communicate with other computers and networking devices. This includes communicating on a local and wide area basis for access to or over Internet, cloud, XaaS, or managed services providers such as shown in figure 1.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 1 The Big Picture: Data Center I/O and Networking

The challenge of I/O is that some form of connectivity (logical and physical), along with associated software is required along with time delays while waiting for reads and writes to occur. I/O operations that are closest to the CPU or main processor should be the fastest and occur most frequently for access to main memory using internal local CPU to memory interconnects. In other words, fast servers or processors need fast I/O, either in terms of low latency, I/O operations along with bandwidth capabilities.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 2 Tiered I/O and Networking Access

Moving out and away from the main processor, I/O remains fairly fast with distance but is more flexible and cost effective. An example is the PCIe bus and I/O interconnect shown in Figure 2, which is slower than processor-to-memory interconnects but is still able to support attachment of various device adapters with very good performance in a cost effective manner.

Farther from the main CPU or processor, various networking and I/O adapters can attach to PCIe, PCIx, or PCI interconnects for backward compatibility to support various distances, speeds, types of devices, and cost factors.

In general, the faster a processor or server is, the more prone to a performance impact it will be when it has to wait for slower I/O operations.

Consequently, faster servers need better-performing I/O connectivity and networks. Better performing means lower latency, more IOPS, and improved bandwidth to meet application profiles and types of operations.

Peripheral Component Interconnect (PCI)
Having established that computers need to perform some form of I/O to various devices, at the heart of many I/O and networking connectivity solutions is the Peripheral Component Interconnect (PCI) interface. PCI is an industry standard that specifies the chipsets used to communicate between CPUs and memory and the outside world of I/O and networking device peripherals.

Figure 3 shows an example of multiple servers or blades each with dedicated Fibre Channel (FC) and Ethernet adapters (there could be two or more for redundancy). Simply put the more servers and devices to attach to, the more adapters, cabling and complexity particularly for blade servers and dense rack mount systems.
PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 3 Dedicated PCI adapters for I/O and networking devices

Figure 4 shows an example of a PCI implementation including various components such as bridges, adapter slots, and adapter types. PCIe leverages multiple serial unidirectional point to point links, known as lanes, in contrast to traditional PCI, which used a parallel bus design.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)

Figure 4 PCI IOV Single Root Configuration Example

In traditional PCI, bus width varied from 32 to 64 bits; in PCIe, the number of lanes combined with PCIe version and signaling rate determine performance. PCIe interfaces can have 1, 2, 4, 8, 16, or 32 lanes for data movement, depending on card or adapter format and form factor. For example, PCI and PCIx performance can be up to 528 MB per second with a 64 bit, 66 MHz signaling rate, and PCIe is capable of over 4 GB (e.g., 32 Gbit) in each direction using 16 lanes for high-end servers.

The importance of PCIe and its predecessors is a shift from multiple vendors’ different proprietary interconnects for attaching peripherals to servers. For the most part, vendors have shifted to supporting PCIe or early generations of PCI in some form, ranging from native internal on laptops and workstations to I/O, networking, and peripheral slots on larger servers.

The most current version of PCI, as defined by the PCI Special Interest Group (PCISIG), is PCI Express (PCIe). Backwards compatibility exists by bridging previous generations, including PCIx and PCI, off a native PCIe bus or, in the past, bridging a PCIe bus to a PCIx native implementation. Beyond speed and bus width differences for the various generations and implementations, PCI adapters also are available in several form factors and applications.

Traditional PCI was generally limited to a main processor or was internal to a single computer, but current generations of PCI Express (PCIe) include support for PCI Special Interest Group (PCI) I/O virtualization (IOV), enabling the PCI bus to be extended to distances of a few feet. Compared to local area networking, storage interconnects, and other I/O connectivity technologies, a few feet is very short distance, but compared to the previous limit of a few inches, extended PCIe provides the ability for improved sharing of I/O and networking interconnects.

I/O VIRTUALIZATION(IOV)
On a traditional physical server, the operating system sees one or more instances of Fibre Channel and Ethernet adapters even if only a single physical adapter, such as an InfiniBand HCA, is installed in a PCI or PCIe slot. In the case of a virtualized server for example, Microsoft HyperV or VMware ESX/vSphere the hypervisor will be able to see and share a single physical adapter, or multiple adapters, for redundancy and performance to guest operating systems. The guest systems see what appears to be a standard SAS, FC or Ethernet adapter or NIC using standard plug-and-play drivers.

Virtual HBA or virtual network interface cards (NICs) and switches are, as their names imply, virtual representations of a physical HBA or NIC, similar to how a virtual machine emulates a physical machine with a virtual server. With a virtual HBA or NIC, physical NIC resources are carved up and allocated as virtual machines, but instead of hosting a guest operating system like Windows, UNIX, or Linux, a SAS or FC HBA, FCoE converged network adapter (CNA) or Ethernet NIC is presented.

In addition to virtual or software-based NICs, adapters, and switches found in server virtualization implementations, virtual LAN (VLAN), virtual SAN (VSAN), and virtual private network (VPN) are tools for providing abstraction and isolation or segmentation of physical resources. Using emulation and abstraction capabilities, various segments or sub networks can be physically connected yet logically isolated for management, performance, and security purposes. Some form of routing or gateway functionality enables various network segments or virtual networks to communicate with each other when appropriate security is met.

PCI-SIG IOV
PCI SIG IOV consists of a PCIe bridge attached to a PCI root complex along with an attachment to a separate PCI enclosure (Figure 5). Other components and facilities include address translation service (ATS), single-root IOV (SR IOV), and multiroot IOV (MR IOV). ATS enables performance to be optimized between an I/O device and a servers I/O memory management. Single root, SR IOV enables multiple guest operating systems to access a single I/O device simultaneously, without having to rely on a hypervisor for a virtual HBA or NIC.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)

Figure 5 PCI SIG IOV

The benefit is that physical adapter cards, located in a physically separate enclosure, can be shared within a single physical server without having to incur any potential I/O overhead via virtualization software infrastructure. MR IOV is the next step, enabling a PCIe or SR IOV device to be accessed through a shared PCIe fabric across different physically separated servers and PCIe adapter enclosures. The benefit is increased sharing of physical adapters across multiple servers and operating systems not to mention simplified cabling, reduced complexity and resource utilization.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 6 PCI SIG MR IOV

Figure 6 shows an example of a PCIe switched environment, where two physically separate servers or blade servers attach to an external PCIe enclosure or card cage for attachment to PCIe, PCIx, or PCI devices. Instead of the adapter cards physically plugging into each server, a high performance short-distance cable connects the servers PCI root complex via a PCIe bridge port to a PCIe bridge port in the enclosure device.

In figure 6, either SR IOV or MR IOV can take place, depending on specific PCIe firmware, server hardware, operating system, devices, and associated drivers and management software. For a SR IOV example, each server has access to some number of dedicated adapters in the external card cage, for example, InfiniBand, Fibre Channel, Ethernet, or Fibre Channel over Ethernet (FCoE) and converged networking adapters (CNA) also known as HBAs. SR IOV implementations do not allow different physical servers to share adapter cards. MR IOV builds on SR IOV by enabling multiple physical servers to access and share PCI devices such as HBAs and NICs safely with transparency.

The primary benefit of PCI IOV is to improve utilization of PCI devices, including adapters or mezzanine cards, as well as to enable performance and availability for slot-constrained and physical footprint or form factor-challenged servers. Caveats of PCI IOV are distance limitations and the need for hardware, firmware, operating system, and management software support to enable safe and transparent sharing of PCI devices. Examples of PCIe IOV vendors include Aprius, NextIO and Virtensys among others.

InfiniBand IOV
InfiniBand based IOV solutions are an alternative to Ethernet-based solutions. Essentially, InfiniBand approaches are similar, if not identical, to converged Ethernet approaches including FCoE, with the difference being InfiniBand as the network transport. InfiniBand HCAs with special firmware are installed into servers that then see a Fibre Channel HBA and Ethernet NIC from a single physical adapter. The InfiniBand HCA also attaches to a switch or director that in turn attaches to Fibre Channel SAN or Ethernet LAN networks.

The value of InfiniBand converged networks are that they exist today, and they can be used for consolidation as well as to boost performance and availability. InfiniBand IOV also provides an alternative for those who do not choose to deploy Ethernet.

From a power, cooling, floor-space or footprint standpoint, converged networks can be used for consolidation to reduce the total number of adapters and the associated power and cooling. In addition to removing unneeded adapters without loss of functionality, converged networks also free up or allow a reduction in the amount of cabling, which can improve airflow for cooling, resulting in additional energy efficiency. An example of a vendor using InfiniBand as a platform for I/O virtualization is Xsigo.

General takeaway points include the following:

  • Minimize the impact of I/O delays to applications, servers, storage, and networks
  • Do more with what you have, including improving utilization and performance
  • Consider latency, effective bandwidth, and availability in addition to cost
  • Apply the appropriate type and tiered I/O and networking to the task at hand
  • I/O operations and connectivity are being virtualized to simplify management
  • Convergence of networking transports and protocols continues to evolve
  • PCIe IOV is complimentary to converged networking including FCoE

Moving forward, a revolutionary new technology may emerge that finally eliminates the need for I/O operations. However until that time, or at least for the foreseeable future, several things can be done to minimize the impacts of I/O for local and remote networking as well as to simplify connectivity.

PCIe Fundamentals Server Storage I/O Network Essentials

Learn more about IOV, converged networks, LAN, SAN, MAN and WAN related topics in Chapter 9 (Networking with your servers and storage) of The Green and Virtual Data Center (CRC) as well as in Resilient Storage Networks: Designing Flexible Scalable Data Infrastructures (Elsevier).

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved