Category: I/O Networking

Posted on

Does IBM Power7 processor announcement signal storage upgrades?

IBM recently announced the Power7 as the latest generation of processors that the company uses in some of its mid range and high end compute servers including the iSeries and pSeries.


IBM Power7 processor wafers (chips)

 

What is the Power7 processor?
The Power7 is the latest generation of IBM processors (chips) that are used as the CPUs in IBM mid range and high end open systems (pSeries) for Unix (AIX) and Linux as well as for the iSeries (aka AS400 successor). Building on previous Power series processors, the Power7 increases the performance per core (CPU) along with the number of cores per socket (chip) footprint. For example, each Power7 chip that plugs into a socket on a processor card in a server can have up to 8 cores or CPUs. Note that sometimes cores are also known as micro CPUs as well as virtual CPUs not to be confused with their presented via Hypervisor abstraction.

Sometimes you may also here the term or phrase 2 way, 4 way (not to be confused with a Cincinnati style 4 way chili) or 8 way among others that refers to the number of cores on a chip. Hence, a dual 2 way would be a pair of processor chips each with 2 cores while a quad 8 way would be 4 processors chips each with 8 cores and so on.


IBM Power7 with up to eight cores per processor (chip)

In addition to faster and more cores in a denser footprint, there are also energy efficiency enhancements including Energy Star for enterprise servers qualification along with intelligent power management (IPM also see here) implementation. IPM is implanted in what IBM refers to as Intelligent Energy technology for turning on or off various parts of the system along with varying processor clock speeds. The benefit is when there is work to be done, get it down quickly or if there is less work, turn some cores off or slow clock speed down. This is similar to what other industry leaders including Intel have deployed with their Nehalem series of processors that also support IPM.

Additional features of the Power7 include (varies by system solutions):

  • Energy Star for server qualified providing enhanced performance and efficiency.

  • IBM Systems Director Express, Standard and Enterprise Editions for simplified management including virtualization capabilities across pools of Power servers as a single entity.

  • PowerVM (Hypervisor) virtualization for AIX, iSeries and Linux operating systems.

  • ActiveMemory enables effective memory capacity to be larger than physical memory, similar to how virtual memory works within many operating systems. The benefit is to enable a partition to have access to more memory which is important for virtual machines along with the ability to support more partitions in a given physical memory footprint.

  • TurboCore and Intelligent Threads enable workload optimization by selecting the applicable mode for the work to be done. For example, single thread per core along with simultaneous threads (2 or 4) modes per core. The trade off is to have more threads per core for concurrent processing, or, fewer threads to boost single stream performance.

IBM has announced several Power7 enabled or based server system models with various numbers of processors and cores along with standalone and clustered configurations including:

IBM Power7 family of server systems

  • Power 750 Express, 4U server with one to four socket server supporting up to 32 cores (3.0 to 3.5 GHz) and 128 threads (4 threads per core), PowerVM (Hypervisor) along with main memory capacity of 512GB or 1TByte of virtual memory using Active Memory Expansion.
  • Power 755, 32 3.3Ghz Power7 cores (8 cores per processor) with memory up to 256GB along with AltiVec and VSX SIMD instruction set support. Up to 64 755 nodes each with 32 cores can be clustered together for high performance applications.
  • Power 770, Up to 64 Power7 cores providing more performance while consuming less energy per core compared to previous Power6 generations. Support for up to 2TB of main memory or RAM using 32GB DIMM when available later in 2010.
  • Power 780, 64 Power7 cores with TurboCore workload optimization providing performance boost per core. With TurboCore, 64 cores can operate at 3.8 GHz, or, enable up to 32 cores at 4.1 GHz and twice the amount of cache when more speed per thread is needed. Support for up to 2TB of main memory or RAM using 32GB DIMM when available later in 2010.

Additional Power7 specifications and details can be found here.

 

What is the DS8000?
The DS8000 is the latest generation of a family of high end enterprise class storage systems supporting IBM mainframe (zSeries), Open systems along with mixed workloads. Being high end open systems or mainframe, the DS8000 competes with similar systems from EMC (Symmetrix/DMX/VMAX), Fujitsu (Eternus DX8000), HDS (Hitachi) and HP (XP series OEM from Hitachi). Previous generations of the DS8000 (aka predecessors) include the ESS (Enterprise Storage System) Model 2105 (aka Shark) and VSS (Versatile Storage Server). Current generation family members include the Power5 based DS8100 and DS8300 along with the Power6 based DS8700.

IBM DS8000 Storage System

Learn more about the DS8000 here, here, here and here.

 

What is the association between the Power7 and DS8000?
Disclosure: Before I go any further, lets be clear on something, what I am about to post on is based entirely on researching, analyzing, correlating (connecting the dots) of what is publicly and freely available from IBM on the Web (e.g. there is no NDA material being disclosed here that I am aware of) along with prior trends and tendency of IBM and their solutions. In other words, you can call it speculation, a prediction, industry analysis perspective, looking into the proverbial crystal ball or educated guess and thus should not be taken as an indicator of what IBM may actually do or be working on. As to what may actually be done or not done, for that you will need to contact one of the IBM truth squad members.

As to what is the linkage between Power7 and the DS8000?

The linkage between the Power7 and the DS8000 is just that, the Power processors!

At the heart of the DS8000 are Power series processors coupled or clustered together in pairs for performance and availability that run IBM developed storage systems software. While the spin doctors may not agree, essentially the DS8000 and its predecessors are based on and around Power series processors clustered together with a high speed interconnect that combine to host an operating system and IBM developed storage system application software.

Thus IBM has been able to for over a decade leverage technology improvement curve advantages with faster processors, increased memory and I/O connectivity in denser footprints while enhancing their storage system application software.

Given that the current DS8000 family members utilize 2 way (2 core) or 4 way (4 core) Power5 and Power6 processors, similar to how their predecessors utilized previous generation Power4, Power3 and so forth processors, it only makes sense that IBM might possibly use a Power7 processor in a future DS8000 (or derivative perhaps even with a different name or model number). Again, this is just based all on historical trends and patterns of IBM storage systems group leveraging the latest generation of Power processors; after all, they are a large customer of the Power systems group.

Consequently it would make sense for IBM storage folks to leverage the new Power7 processors and features similar to how EMC is leveraging Intel processor enhances along with what other vendors are doing.

There is certainly room in the DS8000 architecture for growth in terms of supporting additional nodes or complexes or controllers (or whatever your term preference of choice is for describing a server) each equipped with multiple processors (chips or sockets) that have multiple cores. While IBM has only commercially released two complex or dual server versions of the DS8000 with various numbers of cores per server, they have come nowhere close to their architecture limit of nodes. In fact with this release of Power7, as an example, the model 755 can be clustered via InfiniBand with up to 64 nodes, with each node having 4 sockets (e.g. 4 way) with up to 8 cores each. That means on paper, 64 x 4 x 8 = 2048 cores and each core could have up to 4 threads for concurrency, or half as many cores for more cache performance. Now will IBM ever come out with a 64 node DS8000 on steroids?

Tough to say, maybe possibly some day to play specmanship vs EMC VMAX 256 node architectural limit, however Im not holding my breath just yet. Thus with more and faster cores per processor, ability to increase number of processors per server or node, along with architectural capabilities to boost the number of nodes in an instance or cluster, on paper alone, there is lots of head room for the DS8000 or a future derivative.

What about software and functionality, sure IBM could in theory simply turn the crank and use a new hardware platform that is faster, more capacity, denser, better energy efficiency, however what about new features?

Can IBM enhance its storage systems application software that it evolved from the ESS with new features to leverage underlying hardware capabilities including TurboCore, PowerVM, device and I/O sharing, Intelligent Energy efficiency along with threads enhancements?

Can IBM leverage those and other features to support not only scaling of performance, availability, capacity and energy efficiency in an economical manner, however also add features for advanced automated tiering or data movement plus other popular industry buzzword functionality?

 

Additional thoughts and perspectives
One of the things I find interesting is that some IBM folks along with their channel partners will go to great lengths to explain why and how the DS8000 is not just a pair of Power enabled based servers tightly coupled together. Yet, on the other hand, some of those folks will go to great lengths touting the advantages of leveraging off the shelf or commercial enabled servers based on Intel or AMD based systems such as IBMs own XIV storage solution.

I can understand in the past when the likes of EMC, Hitachi and Fujitsu were all competing with IBM building bigger and more function rich monolithic systems, however that trend is shifting. The trend now as is being seen with EMC and VMAX is to decouple and leverage more off the shelf commercially available technology combined with custom ASICs where and when needed.

Thus at a time where more attention and discussion is around clustered, grid, scalable storage systems, will we see or hear the IBM folks change their tune about the architectural scale up and out capabilities of the Power enabled DS8000 family?

There had been some industry speculation that the DS8000 would be the end of the line if the Power7 had not been released which will now (assuming that IBM leverages the Power7 for storage) shift to if there will be a Power8 or Power9 and so forth.

From a storage perspective, is the DS8K still relevant?

I say yes given its installed base and need for IBM to have an enterprise solution (sorry, IMHO XIV does not fit that bill just yet) of their own, lest they cut an OEM deal with the likes of Hitachi or Fujitsu which while possible, I do not see it as likely near term. Another soft point on its relevance is to gauge reaction from their competitors including EMC and HDS.

From a server perspective, what is the benefit of the new Power7 enabled servers from IBM?

Simple, increase scale of performance for single thread as well as concurrent or parallel application workloads.

In other words, supporting more web sites, partitions for virtual machines and guest operating system instances, databases, compute and other applications that demand performance and economy of scale.

This also means that IBM has a platform to aggressively go after Sun Solaris server customers with a lifeline during the Oracle transition, not to mention being a platform for running Oracle in addition to its own UDB/DB2 database. In addition to being a platform for Unix AIX as well as Linux, the Power7 series also are at the heart of current generation iSeries (the server formerly known as the AS400).

Additional links and resources:

Closing comments (for now):
Given IBMs history of following a Power chip enhancement with a new upgraded version of the DS8000 (or ESS/2105 aka Shark/VSS) and its predecessors by a reasonable amount of time, I would be surprised if we do not see a new DS8000 (perhaps even renamed or renumbered) within the year.

This is similar to how other vendors leverage new processor chip technology evolution to pace their systems upgrades for example how many vendors who leverage Intel processes have done announcements over the past year since the Nehalem series rolled out including EMC among others.

Lets see what the IBM truth squads have to say, or, not have to say :)

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

Posted on

Technology Tiering, Servers Storage and Snow Removal

Granted it is winter in the northern hemisphere and thus snow storms should not be a surprise.

However between December 2009 and early 2010, there has been plenty of record activity from in the U.K. (or here), to the U.S. east coast including New York, Boston and Washington DC, across the midwest and out to California, it made for a white christmas and SANta fun along with snow fun in general in the new year.

2010 Snow Storm via www.star-telegram.com

What does this have to do with Information Factories aka IT resources including public or private clouds, facilities, server, storage, networking along with data management let alone tiering?

What does this have to do with tiered snow removal, or even snow fun?

Simple, different tools are needed for addressing various types of snow from wet and heavy to light powdery or dustings to deep downfalls. Likewise, there are different types of servers, storage, data networks along with operating systems, management tools and even hyper visors to deal with various application needs or requirements.

First, lets look at tiered IT resources (servers, storage, networks, facilities, data protection and hyper visors) to meet various efficiency, optimization and service level needs.

Do you have tiered IT resources?

Let me rephrase that question to do you have different types of servers with various performance, availability, connectivity and software that support various applications and cost levels?

Thus the whole notion of tiered IT resources is to be abe to have different resources that can be aligned to the task at hand in order to meet performance, availability, capacity, energy along with economic along with service level agreement (SLA) requirements.

Computers or servers are targeted for different markets including Small Office Home Office (SOHO), Small Medium Business (SMB), Small Medium Enterprise (SME) and ultra large scale or extreme scaling, including high performance super computing. Servers are also positioned for different price bands and deployment scenarios.

General categories of tiered servers and computers include:

  • Laptops, desktops and workstations
  • Small floor standing towers or rack mounted 1U and 2U servers
  • Medium sizes floor standing towers or larger rack mounted servers
  • Blade Centers and Blade Servers
  • Large size floor standing servers, including mainframes
  • Specialized fault tolerant, rugged and embedded processing or real time servers

Servers have different names email server, database server, application server, web server, and video or file server, network server, security server, backup server or storage server associated with them depending on their use. In each of the previous examples, what defines the type of server is the type of software is being used to deliver a type of service. Sometimes the term appliance will be used for a server; this is indicative of the type of service the combined hardware and software solution are providing. For example, the same physical server running different software could be a general purpose applications server, a database server running for example Oracle, IBM, Microsoft or Teradata among other databases, an email server or a storage server.

This can lead to confusion when looking at servers in that a server may be able to support different types of workloads thus it should be considered a server, storage, networking or application platform. It depends on the type of software being used on the server. If, for example, storage software in the form a clustered and parallel file system is installed on a server to create highly scalable network attached storage (NAS) or cloud based storage service solution, then the server is a storage server. If the server has a general purpose operating system such as Microsoft Windows, Linux or UNIX and a database on it, it is a database server.

While not technically a type of server, some manufacturers use the term tin wrapped software in an attempt to not be classified as an appliance, server or hardware vendor but want their software to be positioned more as a turnkey solution. The idea is to avoid being perceived as a software only solution that requires integration with hardware. The solution is to use off the shelf commercially available general purpose servers with the vendors software technology pre integrated and installed ready for use. Thus, tin wrapped software is a turnkey software solution with some tin, or hardware, wrapped around it.

How about the same with tiered storage?

That is different tiers (Figure 1) of fast high performance disk including RAM or flash based SSD, fast Fibre Channel or SAS disk drives, or high capacity SAS and SATA disk drives along with magnetic tape as well as cloud based backup or archive?

Tiered Storage Resources
Figure 1: Tiered Storage resources

Tiered storage is also sometimes thought of in terms large enterprise class solutions or midrange, entry level, primary, secondary, near line and offline. Not to be forgotten, there are also tiered networks that support various speeds, convergence, multi tenancy and other capabilities from IO Virtualization (IOV) to traditional LAN, SAN, MAN and WANs including 1Gb Ethernet (1GbE), 10GbE up to emerging 40GbE and 100GbE not to mention various Fibre Channel speeds supporting various protocols.

The notion around tiered networks is like with servers and storage to enable aligning the right technology to be used for the task at hand economically while meeting service needs.

Two other common IT resource tiering techniques include facilities and data protection. Tiered facilities can indicate size, availability, resiliency among other characteristics. Likewise, tiered data protection is aligning the applicable technology to support different RTO and RPO requirements for example using synchronous replication where applicable vs. asynchronous time delayed for longer distance combined with snapshots. Other forms of tiered data protection include traditional backups either to disk, tape or cloud.

There is a new emerging form of tiering in many IT environments and that is tiered virtualization or specifically tiered server hyper visors in virtual data centers with similar objectives to having different server, storage, network, data protection or facilities tiers. Instead of an environment running all VMware, Microsoft HyperV or Xen among other hyper visors may be deployed to meet different application service class requirements. For example, VMware may be used for premium features and functionality on some applications, where others that do not need those features along with requiring lower operating costs leverage HyperV or Zen based solutions. Taking the tiering approach a step further, one could also declare tiered databases for example Oracle legacy vs. MySQL or Microsoft SQLserver among other examples.

What about IT clouds, are those different types of resources, or, essentially an extension of existing IT capabilities for example cloud storage being another tier of data storage?

There is another form of tiering, particularly during the winter months in the northern hemisphere where there is an abundance of snow this time of the year. That is, tiered snow management, removal or movement technologies.

What about tiered snow removal?

Well lets get back to that then.

Like IT resources, there are different technologies that can be used for moving, removing, melting or managing snow.

For example, I cant do much about getting ready of snow other than pushing it all down the hill and into the river, something that would take time and lots of fuel, or, I can manage where I put snow piles to be prepared for next storm, plus, to help put it where the piles of snow will melt and help avoid spring flood. Some technologies can be used for relocating snow elsewhere, kind of like archiving data onto different tiers of storage.

Regardless of if snowstorm or IT clouds (public or private), virtual, managed service provider (MSP), hosted or traditional IT data centers, all require physical servers, storage, I/O and data networks along with software including management tools.

Granted not all servers, storage or networking technology let alone software are the same as they address different needs. IT resources including servers, storage, networks, operating systems and even hyper visors for virtual machines are often categorized and aligned to different tiers corresponding to needs and characteristics (Figure 2).

Tiered IT Resources
Figure 2: Tiered IT resources

For example, in figure 3 there is a light weight plastic shovel (Shove 1) for moving small amounts of snow in a wide stripe or pass. Then there is a narrow shovel for digging things out, or breaking up snow piles (Shovel 2). Also shown are a light duty snow blower (snow thrower) capable of dealing with powdery or non wet snow, grooming in tight corners or small areas.

Tiered Snow tools
Figure 3: Tiered Snow management and migration tools

For other light dustings, a yard leaf blower does double duty for migrating or moving snow in small or tight corners such as decks, patios or for cleanup. Larger snowfalls, or, where there is a lot of area to clear involves heavier duty tools such as the Kawasaki mule with 5 foot curtis plow. The mule is a multifunction, multi protocol tool capable of being used for hauling items, towing, pulling or recreational tasks.

When all else fails, there is a pickup truck to get or go out and about, not to mention to pull other vehicles out of ditches or piles of snow when they become stuck!

Snow movement
Figure 4: Sometimes the snow light making for fast, low latency migration

Snow movement
Figure 5: And sometimes even snow migration technology goes off line!

Snow movement

And that is it for now!

Enjoy the northern hemisphere winter and snow while it lasts, make the best of it with the right tools to simplify the tasks of movement and management, similar to IT resources.

Keep in mind, its about the tools and when along with how to use them for various tasks for efficiency and effectiveness, and, a bit of snow fun.

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

Posted on

Infosmack Episode 34, VMware, Microsoft and More

Following on the heals of several guest appearances late in 2009 ( here, here, here and here) on the Storage Monkeys Infosmack weekly pod cast, I was recently asked to join them again for the inaugural 2010 show (Episode 34).

Along with VMguru Rich Brambley and hosts Greg Knieriemen and Marc Farley we discussed several recent industry topics in this first show of the year which can be accessed here or on iTunes.

Heres a link to the pod cast where you can listen to the discussion including VMware Go, VMware buying Zimbra, Vendor Alliances such as HP and Microsoft HyperV and EMC+Cisco+VMware, along with data protection for virtual servers issues options (or opportunities) among other topics.

I have included the following links that pertain to some of the items we discussed during the show.

Enjoy the show.

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

Posted on

2010 and 2011 Trends, Perspectives and Predictions: More of the same?

2011 is not a typo, I figured that since Im getting caught up on some things, why not get a jump as well.

Since 2009 went by so fast, and that Im finally getting around to doing an obligatory 2010 predictions post, lets take a look at both 2010 and 2011.

Actually Im getting around to doing a post here having already done interviews and articles for others soon to be released.

Based on prior trends and looking at forecasts, a simple predictions is that some of the items for 2010 will apply for 2011 as well given some of this years items may have been predicted by some in 2008, 2007, 2006, 2005 or, well ok, you get the picture. :)

Predictions are fun and funny in that for some, they are taken very seriously, while for others, at best they are taken with a grain of salt depending on where you sit. This applies both for the reader as well as who is making the predictions along with various motives or incentives.

Some are serious, some not so much…

For some, predictions are a great way of touting or promoting favorite wares (hard, soft or services) or getting yet another plug (YAP is a TLA BTW) in to meet coverage or exposure quota.

Meanwhile for others, predictions are a chance to brush up on new terms for the upcoming season of buzzword bingo games (did you pick up on YAP).

In honor of the Vancouver winter games, Im expecting some cool Olympic sized buzzword bingo games with a new slippery fast one being federation. Some buzzwords will take a break in 2010 as well as 2011 having been worked pretty hard the past few years, while others that have been on break, will reappear well rested, rejuvenated, and ready for duty.

Lets also clarify something regarding predictions and this is that they can be from at least two different perspectives. One view is that from a trend of what will be talked about or discussed in the industry. The other is in terms of what will actually be bought, deployed and used.

What can be confusing is sometimes the two perspectives are intermixed or assumed to be one and the same and for 2010 I see that trend continuing. In other words, there is adoption in terms of customers asking and investigating technologies vs. deployment where they are buying, installing and using those technologies in primary situations.

It is safe to say that there is still no such thing as an information, data or processing recession. Ok, surprise surprise; my dogs could have probably made that prediction during a nap. However what this means is more data will need to be moved, processed and stored for longer periods of time and at a lower cost without degrading performance or availability.

This means, denser technologies that enable a lower per unit cost of service without negatively impacting performance, availability, capacity or energy efficiency will be needed. In other words, watch for an expanded virtualization discussion around life beyond consolidation for servers, storage, desktops and networks with a theme around productivity and virtualization for agility and management enablement.

Certainly there will be continued merger and acquisitions on both a small as well as large scale ranging from liquidation sales or bargain hunting, to large and a mega block buster or two. Im thinking in terms of outside of the box, the type that will have people wondering perhaps confused as to why such a deal would be done until the whole picture is reveled and thought out.

In other words, outside of perhaps IBM, HP, Oracle, Intel or Microsoft among a few others, no vendor is too large not to be acquired, merged with, or even involved in a reverse merger. Im also thinking in terms of vendors filling in niche areas as well as building out their larger portfolio and IT stacks for integrated solutions.

Ok, lets take a look at some easy ones, lay ups or slam dunks:

  • More cluster, cloud conversations and confusion (public vs. private, service vs. product vs. architecture)
  • More server, desktop, IO and storage consolidation (excuse me, server virtualization)
  • Data footprint impact reduction ranging from deletion to archive to compress to dedupe among others
  • SSD and in particular flash continues to evolve with more conversations around PCM
  • Growing awareness of social media as yet another tool for customer relations management (CRM)
  • Security, data loss/leap prevention, digital forensics, PCI (payment card industry) and compliance
  • Focus expands from gaming/digital surveillance /security and energy to healthcare
  • Fibre Channel over Ethernet (FCoE) mainstream in discussions with some initial deployments
  • Continued confusion of Green IT and carbon reduction vs. economic and productivity (Green Gap)
  • No such thing as an information, data or processing recession, granted budgets are strained
  • Server, Storage or Systems Resource Analysis (SRA) with event correlation
  • SRA tools that provide and enable automation along with situational awareness

The green gap of confusion will continue with carbon or environment centric stories and messages continue to second back stage while people realize the other dimension of green being productivity.

As previously mentioned, virtualization of servers and storage continues to be popular with an expanding focus from just consolidation to one around agility, flexibility and enabling production, high performance or for other systems that do not lend themselves to consolidation to be virtualized.

6GB SAS interfaces as well as more SAS disk drives continue to gain popularity. I have said in the past there was a long shot that 8GFC disk drives might appear. We might very well see those in higher end systems while SAS drives continue to pick up the high performance spinning disk role in mid range systems.

Granted some types of disk drives will give way over time to others, for example high performance 3.5” 15.5K Fibre Channel disks will give way to 2.5” 15.5K SAS boosting densities, energy efficiency while maintaining performance. SSD will help to offload hot spots as they have in the past enabling disks to be more effectively used in their applicable roles or tiers with a net result of enhanced optimization, productivity and economics all of which have environmental benefits (e.g. the other Green IT closing the Green Gap).

What I dont see occurring, or at least in 2010

  • An information or data recession requiring less server, storage, I/O networking or software resources
  • OSD (object based disk storage without a gateway) at least in the context of T10
  • Mainframes, magnetic tape, disk drives, PCs, or Windows going away (at least physically)
  • Cisco cracking top 3, no wait, top 5, no make that top 10 server vendor ranking
  • More respect for growing and diverse SOHO market space
  • iSCSI taking over for all I/O connectivity, however I do see iSCSI expand its footprint
  • FCoE and flash based SSD reaching tipping point in terms of actual customer deployments
  • Large increases in IT Budgets and subsequent wild spending rivaling the dot com era
  • Backup, security, data loss prevention (DLP), data availability or protection issues going away
  • Brett Favre and the Minnesota Vikings winning the super bowl

What will be predicted at end of 2010 for 2011 (some of these will be DejaVU)

  • Many items that were predicted this year, last year, the year before that and so on…
  • Dedupe moving into primary and online active storage, rekindling of dedupe debates
  • Demise of cloud in terms of hype and confusion being replaced by federation
  • Clustered, grid, bulk and other forms of scale out storage grow in adoption
  • Disk, Tape, RAID, Mainframe, Fibre Channel, PCs, Windows being declared dead (again)
  • 2011 will be the year of Holographic storage and T10 OSD (an annual prediction by some)
  • FCoE kicks into broad and mainstream deployment adoption reaching tipping point
  • 16Gb (16GFC) Fibre Channel gets more attention stirring FCoE vs. FC vs. iSCSI debates
  • 100GbE gets more attention along with 4G adoption in order to move more data
  • Demise of iSCSI at the hands of SAS at low end, FCoE at high end and NAS from all angles

Gaining ground in 2010 however not yet in full stride (at least from customer deployment)

  • On the connectivity front, iSCSI, 6Gb SAS, 8Gb Fibre Channel, FCoE and 100GbE
  • SSD/flash based storage everywhere, however continued expansion
  • Dedupe  everywhere including primary storage – its still far from its full potential
  • Public and private clouds along with pNFS as well as scale out or clustered storage
  • Policy based automated storage tiering and transparent data movement or migration
  • Microsoft HyperV and Oracle based server virtualization technologies
  • Open source based technologies along with heterogeneous encryption
  • Virtualization life beyond consolidation addressing agility, flexibility and ease of management
  • Desktop virtualization using Citrix, Microsoft and VMware along with Microsoft Windows 7

Buzzword bingo hot topics and themes (in no particular order) include:

  • 2009 and previous year carry over items including cloud, iSCSI, HyperV, Dedupe, open source
  • Federation takes over some of the work of cloud, virtualization, clusters and grids
  • E2E, End to End management preferably across different technologies
  • SAS, Serial Attached SCSI for server to storage systems and as disk to storage interface
  • SRA, E23, Event correlation and other situational awareness related IRM tools
  • Virtualization, Life beyond consolidation enabling agility, flexibility for desktop, server and storage
  • Green IT, Transitions from carbon focus to economic with efficiency enabling productivity
  • FCoE, Continues to evolve and mature with more deployments however still not at tipping point
  • SSD, Flash based mediums continue to evolve however tipping point is still over the horizon
  • IOV, I/O Virtualization for both virtual and non virtual servers
  • Other new or recycled buzzword bingo candidates include PCoIP, 4G,

RAID will again be pronounced as being dead no longer relevant yet being found in more diverse deployments from consumer to the enterprise. In other words, RAID may be boring and thus no longer relevant to talk about, yet it is being used everywhere and enhanced in evolutionary ways, perhaps for some even revolutionary.

Tape remains being declared dead (e.g. on the Zombie technology list) yet being enhanced, purchased and utilized at higher rates with more data stored than in past history. Instead of being killed off by the disk drive, tape is being kept around for both traditional uses as well as taking on new roles where it is best suited such as long term or bulk off-line storage of data in ultra dense and energy efficient not to mention economical manners.

What I am seeing and hearing is that customers using tape are able to reduce the number of drives or transports, yet due to leveraging disk buffers or caches including from VTL and dedupe devices, they are able to operate their devices at higher utilization, thus requiring fewer devices with more data stored on media than in the past.

Likewise, even though I have been a fan of SSD for about 20 years and am bullish on its continued adoption, I do not see SSD killing off the spinning disk drive anytime soon. Disk drives are helping tape take on this new role by being a buffer or cache in the form of VTLs, disk based backup and bulk storage enhanced with compression, dedupe, thin provision and replication among other functionality.

There you have it, my predictions, observations and perspectives for 2010 and 2011. It is a broad and diverse list however I also get asked about and see a lot of different technologies, techniques and trends tied to IT resources (servers, storage, I/O and networks, hardware, software and services).

Lets see how they play out.

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

Posted on

EPA Server and Storage Workshop Feb 2, 2010

EPA Energy Star

Following up on a recent previous post pertaining to US EPA Energy Star(r) for Servers, Data Center Storage and Data Centers, there will be a workshop held Tuesday February 2, 2010 in San Jose, CA.

Here is the note (Italics added by me for clarity) from the folks at EPA with information about the event and how to participate.

 

Dear ENERGY STAR® Servers and Storage Stakeholders:

Representatives from the US EPA will be in attendance at The Green Grid Technical Forum in San Jose, CA in early February, and will be hosting information sessions to provide updates on recent ENERGY STAR servers and storage specification development activities.  Given the timing of this event with respect to ongoing data collection and comment periods for both product categories, EPA intends for these meetings to be informal and informational in nature.  EPA will share details of recent progress, identify key issues that require further stakeholder input, discuss timelines for the completion, and answer questions from the stakeholder community for each specification.

The sessions will take place on February 2, 2010, from 10:00 AM to 4:00 PM PT, at the San Jose Marriott.  A conference line and Webinar will be available for participants who cannot attend the meeting in person.  The preliminary agenda is as follows:

Servers (10:00 AM to 12:30 PM)

  • Draft 1 Version 2.0 specification development overview & progress report
    • Tier 1 Rollover Criteria
    • Power & Performance Data Sheet
    • SPEC efficiency rating tool development
  • Opportunities for energy performance data disclosure

 

Storage (1:30 PM to 4:00 PM)

  • Draft 1 Version 1.0 specification development overview & progress report
  • Preliminary stakeholder feedback & lessons learned from data collection 

A more detailed agenda will be distributed in the coming weeks.  Please RSVP to storage@energystar.gov or servers@energystar.gov no later than Friday, January 22.  Indicate in your response whether you will be participating in person or via Webinar, and which of the two sessions you plan to attend.

Thank you for your continued support of ENERGY STAR.

 

End of EPA Transmission

For those attending the event, I look forward to seeing you there in person on Tuesday before flying down to San Diego where I will be presenting on Wednesday the 3rd at The Green Data Center Conference.

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

Posted on

Poll: Networking Convergence, Ethernet, InfiniBand or both?

I just received an email in my inbox from Voltaire along with a pile of other advertisements, advisories, alerts and announcements from other folks.

What caught my eye on the email was that it is announcing a new survey results that you can read here as well as below.

The question that this survey announcements prompts for me and hence why I am posting it here is how dominant will InfiniBand be on a go forward basis, the answer I think is it depends…

It depends on the target market or audience, what their applications and technology preferences are along with other service requirements.

I think that there is and will remain a place for Infiniband, the question is where and for what types of environments as well as why have both InfiniBand and Ethernet including Fibre Channel over Ethernet (FCoE) in support of unified or converged I/O and data networking.

So here is the note that I received from Voltaire:

 

Hello,

A new survey by Voltaire (NASDAQ: VOLT) reveals that IT executives plan to use InfiniBand and Ethernet technologies together as they refresh or build new data centers. They’re choosing a converged network strategy to improve fabric performance which in turn furthers their infrastructure consolidation and efficiency objectives.

The full press release is below.  Please contact me if you would like to speak with a Voltaire executive for further commentary.

Regards,
Christy

____________________________________________________________
Christy Lynch| 978.439.5407(o) |617.794.1362(m)
Director, Corporate Communications
Voltaire – The Leader in Scale-Out Data Center Fabrics
christyl@voltaire.com | www.voltaire.com
Follow us on Twitter: www.twitter.com/voltaireltd

FOR IMMEDIATE RELEASE:

IT Survey Finds Executives Planning Converged Network Strategy:
Using Both InfiniBand and Ethernet

Fabric Performance Key to Making Data Centers Operate More Efficiently

CHELMSFORD, Mass. and ANANA, Israel January 12, 2010 – A new survey by Voltaire (NASDAQ: VOLT) reveals that IT executives plan to use InfiniBand and Ethernet technologies together as they refresh or build new data centers. They’re choosing a converged network strategy to improve fabric performance which in turn furthers their infrastructure consolidation and efficiency objectives.

Voltaire queried more than 120 members of the Global CIO & Executive IT Group, which includes CIOs, senior IT executives, and others in the field that attended the 2009 MIT Sloan CIO Symposium. The survey explored their data center networking needs, their choice of interconnect technologies (fabrics) for the enterprise, and criteria for making technology purchasing decisions.

“Increasingly, InfiniBand and Ethernet share the ability to address key networking requirements of virtualized, scale-out data centers, such as performance, efficiency, and scalability,” noted Asaf Somekh, vice president of marketing, Voltaire. “By adopting a converged network strategy, IT executives can build on their pre-existing investments, and leverage the best of both technologies.”

When asked about their fabric choices, 45 percent of the respondents said they planned to implement both InfiniBand with Ethernet as they made future data center enhancements. Another 54 percent intended to rely on Ethernet alone.

Among additional survey results:

  • When asked to rank the most important characteristics for their data center fabric, the largest number (31 percent) cited high bandwidth. Twenty-two percent cited low latency, and 17 percent said scalability.
  • When asked about their top data center networking priorities for the next two years, 34 percent again cited performance. Twenty-seven percent mentioned reducing costs, and 16 percent cited improving service levels.
  • A majority (nearly 60 percent) favored a fabric/network that is supported or backed by a global server manufacturer.

InfiniBand and Ethernet interconnect technologies are widely used in today’s data centers to speed up and make the most of computing applications, and to enable faster sharing of data among storage and server networks. Voltaire’s server and storage fabric switches leverage both technologies for optimum efficiency. The company provides InfiniBand products used in supercomputers, high-performance computing, and enterprise environments, as well as its Ethernet products to help a broad array of enterprise data centers meet their performance requirements and consolidation plans.

About Voltaire
Voltaire (NASDAQ: VOLT) is a leading provider of scale-out computing fabrics for data centers, high performance computing and cloud environments. Voltaire’s family of server and storage fabric switches and advanced management software improve performance of mission-critical applications, increase efficiency and reduce costs through infrastructure consolidation and lower power consumption. Used by more than 30 percent of the Fortune 100 and other premier organizations across many industries, including many of the TOP500 supercomputers, Voltaire products are included in server and blade offerings from Bull, HP, IBM, NEC and Sun. Founded in 1997, Voltaire is headquartered in Ra’anana, Israel and Chelmsford, Massachusetts. More information is available at www.voltaire.com or by calling 1-800-865-8247.

Forward Looking Statements
Information provided in this press release may contain statements relating to current expectations, estimates, forecasts and projections about future events that are "forward-looking statements" as defined in the Private Securities Litigation Reform Act of 1995. These forward-looking statements generally relate to Voltaire’s plans, objectives and expectations for future operations and are based upon management’s current estimates and projections of future results or trends. They also include third-party projections regarding expected industry growth rates. Actual future results may differ materially from those projected as a result of certain risks and uncertainties. These factors include, but are not limited to, those discussed under the heading "Risk Factors" in Voltaire’s annual report on Form 20-F for the year ended December 31, 2008. These forward-looking statements are made only as of the date hereof, and we undertake no obligation to update or revise the forward-looking statements, whether as a result of new information, future events or otherwise.

###

All product and company names mentioned herein may be the trademarks of their respective owners.

 

End of Voltaire transmission:

I/O, storage and networking interface wars come and go similar to other technology debates of what is the best or that will be supreme.

Some recent debates have been around Fibre Channel vs. iSCSI or iSCSI vs. Fibre Channel (depends on your perspective), SAN vs. NAS, NAS vs. SAS, SAS vs. iSCSI or Fibre Channel, Fibre Channel vs. Fibre Channel over Ethernet (FCoE) vs. iSCSI vs. InfiniBand, xWDM vs. SONET or MPLS, IP vs UDP or other IP based services, not to mention the whole LAN, SAN, MAN, WAN POTS and PAN speed games of 1G, 2G, 4G, 8G, 10G, 40G or 100G. Of course there are also the I/O virtualization (IOV) discussions including PCIe Single Root (SR) and Multi Root (MR) for attachment of SAS/SATA, Ethernet, Fibre Channel or other adapters vs. other approaches.

Thus when I routinely get asked about what is the best, my answer usually is a qualified it depends based on what you are doing, trying to accomplish, your environment, preferences among others. In other words, Im not hung up or tied to anyone particular networking transport, protocol, network or interface, rather, the ones that work and are most applicable to the task at hand

Now getting back to Voltaire and InfiniBand which I think has a future for some environments, however I dont see it being the be all end all it was once promoted to be. And outside of the InfiniBand faithful (there are also iSCSI, SAS, Fibre Channel, FCoE, CEE and DCE among other devotees), I suspect that the results would be mixed.

I suspect that the Voltaire survey reflects that as well as if I surveyed an Ethernet dominate environment I can take a pretty good guess at the results, likewise for a Fibre Channel, or FCoE influenced environment. Not to mention the composition of the environment, focus and business or applications being supported. One would also expect a slightly different survey results from the likes of Aprius, Broadcom, Brocade, Cisco, Emulex, Mellanox (they also are involved with InfiniBand), NextIO, Qlogic (they actually do some Infiniband activity as well), Virtensys or Xsigo (actually, they support convergence of Fibre Channel and Ethernet via Infiniband) among others.

Ok, so what is your take?

Whats your preffered network interface for convergence?

For additional reading, here are some related links:

  • I/O Virtualization (IOV) Revisited
  • I/O, I/O, Its off to Virtual Work and VMworld I Go (or went)
  • Buzzword Bingo 1.0 – Are you ready for fall product announcements?
  • StorageIO in the News Update V2010.1
  • The Green and Virtual Data Center (Chapter 9)
  • Also check out what others including Scott Lowe have to say about IOV here or, Stuart Miniman about FCoE here, or of Greg Ferro here.

    • Oh, and for what its worth for those concerned about FTC disclosure, Voltaire is not nor have they been a client of StorageIO, however, I did used to work for a Fibre Channel, iSCSI, IP storage, LAN, SAN, MAN, WAN vendor and wrote a book on the topics :).

    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

    Posted on

    StorageIO in the News Update V2010.1

    StorageIO is regularly quoted and interviewed in various industry and vertical market venues and publications both on-line and in print on a global basis.

    The following are some coverage, perspectives and commentary by StorageIO on IT industry trends including servers, storage, I/O networking, hardware, software, services, virtualization, cloud, cluster, grid, SSD, data protection, Green IT and more since the last update.

    Realizing that some prefer blogs to webs to twitter to other venues, here are some recent links among others to media coverage and comments by me on a different topics that are among others found at www.storageio.com/news.html:

  • SearchSMBStorage: Comments on EMC Iomega v.Clone for PC data syncronization – Jan 2010
  • Computerworld: Comments on leveraging cloud or online backup – Jan 2010
  • ChannelProSMB: Comments on NAS vs SAN Storage for SMBs – Dec 2009
  • ChannelProSMB: Comments on Affordable SMB Storage Solutions – Dec 2009
  • SearchStorage: Comments on What to buy a geek for the holidays, 2009 edition – Dec 2009
  • SearchStorage: Comments on EMC VMAX storage and 8GFC enhancements – Dec 2009
  • SearchStorage: Comments on Data Footprint Reduction – Dec 2009
  • SearchStorage: Comments on Building a private storage cloud – Dec 2009
  • SearchStorage: Comments on SSD in storage systems – Dec 2009
  • SearchStorage: Comments on slow adoption of file virtualization – Dec 2009
  • IT World: Comments on maximizing data security investments – Nov 2009
  • SearchCIO: Comments on storage virtualization for your organisation – Nov 2009
  • Processor: Comments on how to win approval for hardware upgrades – Nov 2009
  • Processor: Comments on the Future of Servers – Nov 2009
  • SearchITChannel: Comments on Energy-efficient technology sales depend on pitch – Nov 2009
  • SearchStorage: Comments on how to get from Fibre Channel to FCoE – Nov 2009
  • Minneapolis Star Tribune: Comments on Google Wave and Clouds – Nov 2009
  • SearchStorage: Comments on EMC and Cisco alliance – Nov 2009
  • SearchStorage: Comments on HP virtualizaiton enhancements – Nov 2009
  • SearchStorage: Comments on Apple canceling ZFS project – Oct 2009
  • Processor: Comments on EPA Energy Star for Server and Storage Ratings – Oct 2009
  • IT World Canada: Cloud computing, dot be scared, look before you leap – Oct 2009
  • IT World: Comments on stretching your data protection and security dollar – Oct 2009
  • Enterprise Storage Forum: Comments about Fragmentation and Performance? – Oct 2009
  • SearchStorage: Comments about data migration – Oct 2009
  • SearchStorage: Comments about What’s inside internal storage clouds? – Oct 2009
  • Enterprise Storage Forum: Comments about T-Mobile and Clouds? – Oct 2009
  • Storage Monkeys: Podcast comments about Sun and Oracle- Sep 2009
  • Enterprise Storage Forum: Comments on Maxiscale clustered, cloud NAS – Sep 2009
  • SearchStorage: Comments on Maxiscale clustered NAS for web hosting – Sep 2009
  • Enterprise Storage Forum: Comments on whos hot in data storage industry – Sep 2009
  • SearchSMBStorage: Comments on SMB Fibre Channel switch options – Sep 2009
  • SearchStorage: Comments on using storage more efficiently – Sep 2009
  • SearchStorage: Comments on Data and Storage Tiering including SSD – Sep 2009
  • Enterprise IT Planet: Comments on Data Deduplication – Sep 2009
  • SearchDataCenter: Comments on Tiered Storage – Sep 2009
  • Enterprise Storage Forum: Comments on Sun-Oracle Wedding – Aug 2009
  • Processor.com: Comments on Storage Network Snags – Aug 2009
  • SearchStorageChannel: Comments on I/O virtualizaiton (IOV) – Aug 2009
  • SearchStorage: Comments on Clustered NAS storage and virtualization – Aug 2009
  • SearchITChannel: Comments on Solid-state drive prices still hinder adoption – Aug 2009

    • Check out the Content, Tips, Tools, Videos, Podcasts plus White Papers, and News pages for additional commentary, coverage and related content or events.

    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

    Posted on

    Recent tips, videos, articles and more update V2010.1

    Realizing that some prefer blogs to webs to twitter to other venues, here are some recent links to articles, tips, videos, webcasts and other content that have appeared in different venues since August 2009.

  • i365 Guest Interview: Experts Corner: Q&A with Greg Schulz December 2009

  • SearchCIO Midmarket: Remote-location disaster recovery risks and solutions December 2009

  • BizTech Magazine: High Availability: A Delicate Balancing Act November 2009

  • ESJ: What Comprises a Green, Efficient and Effective Virtual Data Center? November 2009

  • SearchSMBStorage: Determining what server to use for SMB November 2009

  • SearchStorage: Performance metrics: Evaluating your data storage efficiency October 2009

  • SearchStorage: Optimizing capacity and performance to reduce data footprint October 2009

  • SearchSMBStorage: How often should I conduct a disaster recovery (DR) test? October 2009

  • SearchStorage: Addressing storage performance bottlenecks in storage September 2009

  • SearchStorage AU: Is tape the right backup medium for smaller businesses? August 2009

  • ITworld: The new green data center: From energy avoidance to energy efficiency August 2009

    • Video and podcasts include:
    December 2009 Video: Green Storage: Metrics and measurement for management insight
    Discussion between Greg Schulz and Mark Lewis of TechTarget the importance of metrics and measurement to gauge productivity and efficiency for Green IT and enabling virtual information factories. Click here to watch the Video.

    December 2009 Podcast: iSCSI SANs can be a good fit for SMB storage
    Discussion between Greg Schulz and Andrew Burton of TechTarget about iSCSI and other related technologies for SMB storage. Click here to listen to the podcast.

    December 2009 Podcast: RAID Data Protection Discussion
    Discussion between Greg Schulz and Andrew Burton of TechTarget about RAID data proteciton, techniques and technologies. Click here to listen to the podcast.

    December 2009 Podcast: Green IT, Effiency and Productivity Discussion
    Discussion between Greg Schulz and Jon Flower of Adaptec about data Green IT, energy effiency, inteligent power management (IPM) also known as MAID 2.0 and other forms of optimization techniques including SSD. Click here to listen to the podcast sponsored by Adaptec.

    November 2009 Podcast: Reducing your data footprint impact
    Even though many enterprise data storage environments are coping with tightened budgets and reduced spending, overall net storage capacity is increasing. In this interview, Greg Schulz, founder and senior analyst at StorageIO Group, discusses how storage managers can reduce their data footprint. Schulz touches on the importance of managing your data footprint on both online and offline storage, as well as the various tools for doing so, including data archiving, thin provisioning and data deduplication. Click here to listen to the podcast.

    October 2009 Podcast: Enterprise data storage technologies rise from the dead
    In this interview, Greg Schulz, founder and senior analyst of the Storage I/O group, classifies popular technologies such as solid-state drives (SSDs), RAID and Fibre Channel (FC) as “zombie” technologies. Why? These are already set to become part of standard storage infrastructures, says Schulz, and are too old to be considered fresh. But while some consider these technologies to be stale, users should expect to see them in their everyday lives. Click here to listen to the podcast.

    Check out the Tips, Tools and White Papers, and News pages for additional commentary, coverage and related content or events.

    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

    Posted on

    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

    Posted on

    SSD and Storage System Performance

    Jacob Gsoedl has a new article over at SearchStorage titled How to add solidstate storage to your enterprise data storage systems.

    In his article which includes some commentary by me, Jacob lays out various options on where and how to deploy solid state devices (SSD) in and with enterprise storage systems.

    While many vendors have jumped on the latest SSD bandwagon adding flash based devices to storage systems, where and how they implement the technologies varies.

    Some vendors take a simplistic approach of qualify flash SSD devices for attachment to their storage controllers similar to how any other Fibre Channel, SAS or SATA hard disk drive (HDD) would be.

    Yet others take a more in depth approach including optimizing controller software, firmware or micro code to leverage flash SSD devices along with addressing wear leveling, read and write performance among other capabilities.

    Performance is another area where on paper a flash SSD device might appear to be fast and enable a storage system to be faster.

    However, systems that are not optimized for higher throughput and or increased IOPs needing lower latency may end up placing restrictions on the number of flash SSD devices or other configuration constraints. Even worse is when expected performance improvements are not realized as after all, fast controllers need fast devices, and fast devices need fast controllers.

    RAM and flash based SSD are great enabling technologies for boosting performance, productivity and enabling a green efficient environment however do your homework.

    Look at how various vendors implement and support SSD particularly flash based products with enhancements to storage controllers for optimal performance.

    Likewise check out the activity of  the SNIA Solid State Storage Initiative (SSSI) among other industry trade group or vendor initiatives around enhancing along with best practices for SSD.

    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

    Posted on

    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

    Posted on

    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

    Posted on

    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

    Posted on

    Going Rouge or Rogue in IT

    Given all of the hype and buzz lately around Sarah Palins new book Going Rogue, how long until we see the term or phrase used in IT? After all, we saw some jump on the cash for clunkers theme. I wonder who will be the first to jump on the Going Rogue or rogue theme bandwagon. Here are a few ideas that might stimulate some thought, or, to keep an eye out to see who jumps on the bandwagon.

    Going rogue on Acadia
    Going rogue on Analysts
    Going rogue on Archiving
    Going rogue on Automated tiering
    Going rogue on Backup
    Going rogue on Blade servers
    Going rogue on Bloggers
    Going rogue on Clouds (public or private)
    Going rogue on Compliance
    Going rogue on Consultants
    Going rogue on Dedupe
    Going rogue on Disks drives
    Going rogue on FCoE
    Going rogue on FLASH or SSD
    Going rogue on Green IT
    Going rogue on Hosting
    Going rogue on IOV
    Going rogue on iSCSI
    Going rogue on Kindle
    Going rogue on Managed service providers (MSP)
    Going rogue on Media venues or reporters
    Going rogue on Networking
    Going rogue on OSD
    Going rogue on Performance
    Going rogue on Polls and surveys
    Going rogue on RAID
    Going rogue on Security
    Going rogue on SOA
    Going rogue on Social media
    Going rogue on Tape
    Going rogue on Testing
    Going rogue on Thin provision
    Going rogue on Training and certifications
    Going rogue on Twitter
    Going rogue on VCE
    Going rogue on Vendors
    Going rogue with Virtualization
    Going rogue on Virtual machines
    Going rogue on VMware or HyperV
    Going rogue on VoIP
    Going rogue on Windows
    Going rogue with XaaS

    Alright, enough is enough for now at the risk of being perceived as snarky, after all, this is also just in fun.

    Lets sit back and see who comes up with something about going rogue from an IT perspective.

    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