Category: metrics

Posted on

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

Posted on

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

Posted on

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

Posted on

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

Posted on

Should Everything Be Virtualized?

Storage I/O trends

Should everything, that is all servers, storage and I/O along with facilities, be virtualized?

The answer not surprisingly should be it depends!

Denny Cherry (aka Mrdenny) over at ITKE did a great recent post about applications not being virtualized, particularly databases. In general some of the points or themes we are on the same or similar page, while on others we slightly differ, not by very much.

Unfortunately consolidation is commonly misunderstood to be the sole function or value proposition of server virtualization given its first wave focus. I agree that not all applications or servers should be consolidated (note that I did not say virtualized).

From a consolidation standpoint, the emphasis is often on boosting resource use to cut physical hardware and management costs by boosting the number of virtual machines (VMs) per physical machine (PMs). Ironically, while VMs using VMware, Microsoft HyperV, Citrix/Xen among others can leverage a common gold image for cloning or rapid provisioning, there are still separate operating system instances and applications that need to be managed for each VM.

Sure, VM tools from the hypervisor along with 3rd party vendors help with these tasks as well as storage vendor tools including dedupe and thin provisioning help to cut the data footprint impact of these multiple images. However, there are still multiple images to manage providing a future opportunity for further cost and management reduction (more on that in a different post).

Getting back on track:

Some reasons that all servers or applications cannot be consolidated include among others:

  • Performance, response time, latency and Quality of Service (QoS)
  • Security requirements including keeping customers or applications separate
  • Vendor support of software on virtual or consolidated servers
  • Financial where different departments own hardware or software
  • Internal political or organizational barriers and turf wars

On the other hand, for those that see virtualization as enabling agility and flexibility, that is life beyond consolidation, there are many deployment opportunities for virtualization (note that I did not say consolidation). For some environments and applications, the emphasis can be on performance, quality of service (QoS) and other service characteristics where the ratio of VMs to PMs will be much lower, if not one to one. This is where Mrdenny and me are essentially on the same page, perhaps saying it different with plenty of caveats and clarification needed of course.

My view is that in life beyond consolidation, many more servers or applications can be virtualized than might be otherwise hosted by VMs (note that I did not say consolidated). For example, instead of a high number or ratio of VMs to PMs, a lower number and for some workloads or applications, even one VM to PM can be leveraged with a focus beyond basic CPU use.

Yes you read that correctly, I said why not configure some VMs on a one to one PM basis!

Here’s the premise, todays current wave or focus is around maximizing the number of VMs and/or the reduction of physical machines to cut capital and operating costs for under-utilized applications and servers, thus the move to stuff as many VMs into/onto a PM as possible.

However, for those applications that cannot be consolidated as outlined above, there is still a benefit of having a VM dedicated to a PM. For example, by dedicating a PM (blade, server or perhaps core) allows performance and QoS aims to be meet while still providing the ability for operational and infrastructure resource management (IRM), DCIM or ITSM flexibility and agility.

Meanwhile during busy periods, the application such as a database server could have its own PM, yet during off-hours, some over VM could be moved onto that PM for backup or other IRM/DCIM/ITSM activities. Likewise, by having the VM under the database with a dedicated PM, the application could be moved proactively for maintenance or in a clustered HA scenario support BC/DR.

What can and should be done?
First and foremost, decide how VMs is the right number to divide per PM for your environment and different applications to meet your particular requirements and business needs.

Identify various VM to PM ratios to align with different application service requirements. For example, some applications may run on virtual environments with a higher number of VMs to PMs, others with a lower number of VMs to PMs and some with a one VM to PM allocation.

Certainly there will be for different reasons the need to keep some applications on a direct PM without introducing a hypervisors and VM, however many applications and servers can benefit from virtualization (again note, I did not say consolation) for agility, flexibility, BC/DR, HA and ease of IRM assuming the costs work in your favor.

Additional general to do or action items include among others:

  • Look beyond CPU use also factoring in memory and I/O performance
  • Keep response time or latency in perspective as part of performance
  • More and fast memory are important for VMs as well as for applications including databases
  • High utilization may not show high hit rates or effectiveness of resource usage
  • Fast servers need fast memory, fast I/O and fast storage systems
  • Establish tiers of virtual and physical servers to meet different service requirements
  • See efficiency and optimization as more than simply driving up utilization to cut costs
  • Productivity and improved QoS are also tenants of an efficient and optimized environment

These are themes among others that are covered in chapters 3 (What Defines a Next-Generation and Virtual Data Center?), 4 (IT Infrastructure Resource Management), 5 (Measurement, Metrics, and Management of IT Resources), as well as 7 (Servers—Physical, Virtual, and Software) in my book “The Green and Virtual Data Center (CRC) that you can learn more about here.

Welcome to life beyond consolidation, the next wave of desktop, server, storage and IO virtualization along with the many new and expanded opportunities!

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

PUE, Are you Managing Power, Energy or Productivity?

With a renewed focus on Green IT including energy Efficiency and Optimization of servers, storage, networks and facilities, is your focus on managing power, energy, or, productivity?

For example, do you use or are interested in metrics such as Greengrid PUE or 80 Plus efficient power supplies along with initiatives such as EPA Energy Star for servers and emerging Energy Star for Data Center for Storage in terms of energy usage?

Or are you interested in productivity such as amount of work or activity that can be done in a given amount of time,or how much information can be stored in a given footprint (power, cooling, floor space, budget, management)?

For many organizations, there tends to be a focus and in both managing power along with managing productivity. The two are or should interrelated, however there are some disconnects with some emphasis and metrics. For example, the Green grid PUE is a macro facilities centric metric that does not show the productivity, quality or measure of services being delivered by a data center or information factory. Instead, PUE provides a gauge of how the habitat, that is the building and power distribution along with cooling are efficient with respect to the total energy consumption of IT equipment.

As a refresher, PUE is a macro metric that is essentially a ratio of how much total power or energy goes into a facility vs. the amount of energy used by IT equipment. For example, if 12Kw (smaller room/site) or 12Mw (larger site) are required to power an IT data center or computer room for that matter, and of that energy load, 6kWh or 6Mw, the PUE would be 2. A PUE of 2 is an indicator that 50% of energy going to power a facility or computer room goes towards IT equipment (servers, storage, networks, telecom and related equipment) with the balance going towards running the facility or environment which typically has had the highest percentage being HVAC/cooling.

In the case of EPA Energy Star for Data Centers which initially is focused on the habitat or facility efficiency, the answer is measuring and managing energy use and facility efficiency as opposed to productivity or useful work. The metric for EPA Energy Star for Data Center initially will be Energy Usage Effectiveness (EUE) that will be used to calculate a ratting for a data center facility. Those data centers in the top25 percentile will qualify for Energy Star certification.

Note the word energy and not power which means that the data center macro metric based on Green grid PUE rating looks at all source of energy used by a data center and not just electrical power. What this means is that a macro and holistic facilities energy consumption could be a combination of electrical power, diesel, propane or natural gas or other fuel sources to generate or create power for IT equipment, HVAC/Cooling and other needs. By using a metric that factor in all energy sources, a facility that uses solar, radiant, heat pumps, economizers or other techniques to reduce demands on energy will make a better rating.

By using a macro metric such as EUE or PUE (ratio = Total_Power_Used / IT_Power_Needs), a starting point is available to decide and compare efficiency and cost to power or energize a facility or room also known as a habitat for technology.

Managing Productivity of Information Factories (E.g. Data Centers)
What EUE and PUE do not reflect or indicate is how much data is processed, moved and stored by servers, storage and networks within a facility. On the other hand or extreme from macro metrics are micro or component metrics that gauge energy usage on an individual device basis. Some of these micro metrics may have activity or productivity indicator measurements associated with them, some don’t. Where these leave a big gap and opportunity is to fill the span between the macro and micro.

This is where work is being done by various industry groups including SNIA GSI, SPC and SPEC among others along with EPA Energy Star among others to move beyond macro PUE indicators to more granular effectiveness and efficiency metrics that reflect productivity. Ultimately productivity is important to gauge,  the return on investment and business value of how much data can be processed by servers, moved via networks or stored on storage devices in a given energy footprint or cost.

In Figure 1 are shown four basic approaches (in addition to doing nothing) to energy efficiency. One approach is to avoid energy usage, similar to following a rationing model, but this approach will affect the amount of work that can be accomplished. Another approach is to do more work using the same amount of energy, boosting energy efficiency, or do same amount of work (or storage data) however with less energy.

Tiered Storage
Figure 1 the Many Faces of Energy Efficiency Source: The Green and Virtual Data Center(CRC)

The energy efficiency gap is the difference between the amount of work accomplished or information stored in a given footprint and the energy consumed. In other words, the bigger the energy efficiency gap, the better, as seen in the fourth scenario, doing more work or storing more information in a smaller footprint using less energy. Clock here to read more about Shifting from energy avoidance to energy efficiency.

Watch for new metrics looking at productivity and activity for servers, storage and networks ranging from MHz or GHz per watt, transactions or IOPS per watt, bandwidth, frames or packets processed per watt or capacity stored per watt in a given footprint. One of the confusing metrics is Gbytes or Tbytes per watt in that it can mean storage capacity or bandwidth, thus, understand the context of the metric. Likewise watch for metrics that reflect energy usage for active along with in-active including idle or dormant storage common with archives, backup or fixed content data.

What this all means is that work continues on developing usable and relevant metrics and measurement not only for macro energy usage, also, to gauge the effectiveness of delivering IT services. The business value proposition of driving efficiency and optimization including increased productivity along with storing more information in a given footprint is to support density and business sustainability.

 

Additional resources and where to learn in addition to those mentioned above include:

EPA Energy Star for Data Center Storage

Storage Efficiency and Optimization – The Other Green

Performance = Availability StorageIOblog featured ITKE guest blog

SPC and Storage Benchmarking Games

Shifting from energy avoidance to energy efficiency

Green IT Confusion Continues, Opportunities Missed!

Green Power and Cooling Tools and Calculators

Determining Computer or Server Energy Use

Examples of Green Metrics

Green IT, Power, Energy and Related Tools or Calculators

Chapter 10 (Performance and Capacity Planning)
Resilient Storage Networks (Elsevier)

Chapter 5 (Measurement, Metrics and Management of IT Resources)
The Green and Virtual Data Center (CRC)

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

Storage Efficiency and Optimization – The Other Green

For those of you in the New York City area, I will be presenting live in person at Storage Decisions September 23, 2009 conference The Other Green, Storage Efficiency and Optimization.

Throw out the "green“: buzzword, and you’re still left with the task of saving or maximizing use of space, power, and cooling while stretching available IT dollars to support growth and business sustainability. For some environments the solution may be consolation while others need to maintain quality of service response time, performance and availability necessitating faster, energy efficient technologies to achieve optimization objectives.

To accomplish these and other related issues, you can turn to the cloud, virtualization, intelligent power management, data footprint reduction and data management not to mention various types of tiered storage and performance optimization techniques. The session will look at various techniques and strategies to optimize either on-line active or primary as well as near-line or secondary storage environment during tough economic times, as well as to position for future growth, after all, there is no such thing as a data recession!

Topics, technologies and techniques that will be discussed include among others:

  • Energy efficiency (strategic) vs. energy avoidance (tactical), whats different between them
  • Optimization and the need for speed vs. the need for capacity, finding the right balance
  • Metrics & measurements for management insight, what the industry is doing (or not doing)
  • Tiered storage and tiered access including SSD, FC, SAS, tape, clouds and more
  • Data footprint reduction (archive, compress, dedupe) and thin provision among others
  • Best practices, financial incentives and what you can do today

This is a free event for IT professionals, however space I hear is limited, learn more and register here.

For those interested in broader IT data center and infrastructure optimization, check out the on-going seminar series The Infrastructure Optimization and Planning Best Practices (V2.009) – Doing more with less without sacrificing storage, system or network capabilities Seminar series continues September 22, 2009 with a stop in Chicago. This is also a free Seminar, register and learn more here or 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

Performance = Availability StorageIOblog featured ITKE guest blog

ITKE - IT Knowledge Exchange

Recently IT Knowledge Exchange named me and StorageIOblog as their weekly featured IT blog too which Im flattered and honored. Consequently, I did a guest blog for them titled Performance = Availability, Availability = Performance that you can read about here.

For those not familiar with ITKE, take a few minutes and go over and check it out, there is a wealth of information there on a diversity of topics that you can read about, or, you can also get involved and participate in the questions and answers discussions.

Speaking of ITKE, interested in “The Green and Virtual Data Center” (CRC), check out this link where you can download a free chapter of my book, along with information on how to order your own copy along with a special discount code from CRC press.

Thank you very much to Sean Brooks of ITKE and his social media team of Michael Morisy and Jenny Mackintosh for being named featured IT blogger, as well as for being able to do a guest post for them. It has been fantastic working them and particularly Jenny who helped with all of the logistics in putting together the various pieces including getting the post up on the web as well as in their news letter.

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

Data Center I/O Bottlenecks Performance Issues and Impacts

This is an excerpt blog version of the popular Server and StorageIO Group white paper "IT Data Center and Data Storage Bottlenecks" originally published August of 2006 that is as much if not more relevant today than it was in the past.

Most Information Technology (IT) data centers have bottleneck areas that impact application performance and service delivery to IT customers and users. Possible bottleneck locations shown in Figure-1 include servers (application, web, file, email and database), networks, application software, and storage systems. For example users of IT services can encounter delays and lost productivity due to seasonal workload surges or Internet and other network bottlenecks. Network congestion or dropped packets resulting in wasteful and delayed retransmission of data can be the results of network component failure, poor configuration or lack of available low latency bandwidth.

Server bottlenecks due to lack of CPU processing power, memory or under sized I/O interfaces can result in poor performance or in worse case scenarios application instability. Application including database systems bottlenecks due to excessive locking, poor query design, data contention and deadlock conditions result in poor user response time. Storage and I/O performance bottlenecks can occur at the host server due to lack of I/O interconnect bandwidth such as an overloaded PCI interconnect, storage device contention, and lack of available storage system I/O capacity.

These performance bottlenecks, impact most applications and are not unique to the large enterprise or scientific high compute (HPC) environments. The direct impact of data center I/O performance issues include general slowing of the systems and applications, causing lost productivity time for users of IT services. Indirect impacts of data center I/O performance bottlenecks include additional management by IT staff to trouble shoot, analyze, re-configure and react to application delays and service disruptions.


Figure-1: Data center performance bottleneck locations

Data center performance bottleneck impacts (see Figure-1) include:

  • Under utilization of disk storage capacity to compensate for lack of I/O performance capability
  • Poor Quality of Service (QoS) causing Service Level Agreements (SLA) objectives to be missed
  • Premature infrastructure upgrades combined with increased management and operating costs
  • Inability to meet peak and seasonal workload demands resulting in lost business opportunity

I/O bottleneck impacts
It should come as no surprise that businesses continue to consume and rely upon larger amounts of disk storage. Disk storage and I/O performance fuel the hungry needs of applications in order to meet SLAs and QoS objectives. The Server and StorageIO Group sees that, even with efforts to reduce storage capacity or improve capacity utilization with information lifecycle management (ILM) and Infrastructure Resource Management (IRM) enabled infrastructures, applications leveraging rich content will continue to consume more storage capacity and require additional I/O performance. Similarly, at least for the next few of years, the current trend of making and keeping additional copies of data for regulatory compliance and business continue is expected to continue. These demands all add up to a need for more I/O performance capabilities to keep up with server processor performance improvements.


Figure-2: Processing and I/O performance gap

Server and I/O performance gap
The continued need for accessing more storage capacity results in an alarming trend: the expanding gap between server processing power and available I/O performance of disk storage (Figure-2). This server to I/O performance gap has existed for several decades and continues to widen instead of improving. The net impact is that bottlenecks associated with the server to I/O performance lapse result in lost productivity for IT personal and customers who must wait for transactions, queries, and data access requests to be resolved.

Application symptoms of I/O bottlenecks
There are many applications across different industries that are sensitive to timely data access and impacted by common I/O performance bottlenecks. For example, as more users access a popular file, database table, or other stored data item, resource contention will increase. One way resource contention manifests itself is in the form of database “deadlock” which translates into slower response time and lost productivity. 

Given the rise and popularity of internet search engines, search engine optimization (SEO) and on-line price shopping, some businesses have been forced to create expensive read-only copies of databases. These read-only copies are used to support more queries to address bottlenecks from impacting time sensitive transaction databases.

In addition to increased application workload, IT operational procedures to manage and protect data help to contribute to performance bottlenecks. Data center operational procedures result in additional file I/O scans for virus checking, database purge and maintenance, data backup, classification, replication, data migration for maintenance and upgrades as well as data archiving. The net result is that essential data center management procedures contribute to performance challenges and impacting business productivity.

Poor response time and increased latency
Generally speaking, as additional activity or application workload including transactions or file accesses are performed, I/O bottlenecks result in increased response time or latency (shown in Figure-3). With most performance metrics more is better; however, in the case of response time or latency, less is better.  Figure-3 shows the impact as more work is performed (dotted curve) and resulting I/O bottlenecks have a negative impact by increasing response time (solid curve) above acceptable levels. The specific acceptable response time threshold will vary by applications and SLA requirements. The acceptable threshold level based on performance plans, testing, SLAs and other factors including experience serves as a guide line between acceptable and poor application performance.

As more workload is added to a system with existing I/O issues, response time will correspondingly decrease as was seen in Figure-3. The more severe the bottleneck, the faster response time will deteriorate (e.g. increase) from acceptable levels. The elimination of bottlenecks enables more work to be performed while maintaining response time below acceptable service level threshold limits.


Figure-3: I/O response time performance impact

Seasonal and peak workload I/O bottlenecks
Another common challenge and cause of I/O bottlenecks is seasonal and/or unplanned workload increases that result in application delays and frustrated customers. In Figure-4 a workload representing an eCommerce transaction based system is shown with seasonal spikes in activity (dotted curve). The resulting impact to response time (solid curve) is shown in relation to a threshold line of acceptable response time performance. For example, peaks due holiday shopping exchanges appear in January then dropping off increasing near mother’s day in May, then back to school shopping in August results in increased activity as does holiday shopping starting in late November.


Figure-4: I/O bottleneck impact from surge workload activity

Compensating for lack of performance
Besides impacting user productivity due to poor performance, I/O bottlenecks can result in system instability or unplanned application downtime. One only needs to recall recent electric power grid outages that were due to instability, insufficient capacity bottlenecks as a result of increased peak user demand.

I/O performance improvement approaches to address I/O bottlenecks have been to do nothing (incur and deal with the service disruptions) or over configure by throwing more hardware and software at the problem. To compensate for lack of I/O performance and counter the resulting negative impact to IT users, a common approach is to add more hardware to mask or move the problem.

However, this often leads to extra storage capacity being added to make up for a short fall in I/O performance. By over configuring to support peak workloads and prevent loss of business revenue, excess storage capacity must be managed throughout the non-peak periods, adding to data center and management costs. The resulting ripple affect is that now more storage needs to be managed, including allocating storage network ports, configuring, tuning, and backing up of data. This can and does result in environments that have storage utilization well below 50% of their useful storage capacity. The solution is to address the problem rather than moving and hiding the bottleneck elsewhere (rather like sweeping dust under the rug).

Business value of improved performance
Putting a value on the performance of applications and their importance to your business is a necessary step in the process of deciding where and what to focus on for improvement. For example, what is the value of reducing application response time and the associated business benefit of allowing more transactions, reservations or sales to be made? Likewise, what is the value of improving the productivity of a designer or animator to meet tight deadlines and market schedules? What is business benefit of enabling a customer to search faster for and item, place an order, access media rich content, or in general improve their productivity?

Server and I/O performance gap as a data center bottleneck
I/O performance bottlenecks are a wide spread issue across most data centers, affecting many applications and industries. Applications impacted by data center I/O bottlenecks to be looked at in more depth are electronic design automation (EDA), entertainment and media, database online transaction processing (OLTP) and business intelligence. These application categories represent transactional processing, shared file access for collaborative work, and processing of shared, time sensitive data.

Electronic design
Computer aided design (CAD), computer assisted engineering (CAE), electronic design automaton (EDA) and other design tools are used for a wide variety of engineering and design functions. These design tools require fast access to shared, secured and protected data. The objective of using EDA and other tools is to enable faster product development with better quality and improved worker productivity. Electronic components manufactured for the commercial, consumer and specialized markets rely on design tools to speed the time-to-market of new products as well as to improve engineer productivity.

EDA tools, including those from Cadence, Synopsis, Mentor Graphics and others, are used to develop expensive and time sensitive electronic chips, along with circuit boards and other components to meet market windows and suppler deadlines. An example of this is a chip vendor being able to simulate, develop, test, produce and deliver a new chip in time for manufacturers to release their new products based on those chips. Another example is aerospace and automotive engineering firms leveraging design tools, including CATIA and UGS, on a global basis relying on their suppler networks to do the same in a real-time, collaborative manner to improve productivity and time-to-market. These results in contention of shared file and data access and, as a work-around, more copies of data kept as local buffers.

I/O performance impacts and challenges for EDA, CAE and CAD systems include:

  • Delays in drawing and file access resulting in lost productivity and project delays
  • Complex configurations to support computer farms (server grids) for I/O and storage performance
  • Proliferation of dedicated storage on individual servers and workstations to improve performance

Entertainment and media
While some applications are characterized by high bandwidth or throughput, such as streaming video and digital intermediate (DI) processing of 2K (2048 pixels per line) and 4K (4096 pixels per line) video and film, there are many other applications that are also impacted by I/O performance time delays. Even bandwidth intensive applications for video production and other applications are time sensitive and vulnerable to I/O bottleneck delays. For example, cell phone ring tone, instant messaging, small MP3 audio, and voice- and e-mail are impacted by congestion and resource contention.

Prepress production and publishing requiring assimilation of many small documents, files and images while undergoing revisions can also suffer. News and information websites need to look up breaking stories, entertainment sites need to view and download popular music, along with still images and other rich content; all of this can be negatively impacted by even small bottlenecks.  Even with streaming video and audio, access to those objects requires accessing some form of a high speed index to locate where the data files are stored for retrieval. These indexes or databases can become bottlenecks preventing high performance storage and I/O systems from being fully leveraged.

Index files and databases must be searched to determine the location where images and objects, including streaming media, are stored. Consequently, these indices can become points of contention resulting in bottlenecks that delay processing of streaming media objects. When cell phone picture is taken phone and sent to someone, chances are that the resulting image will be stored on network attached storage (NAS) as a file with a corresponding index entry in a database at some service provider location. Think about what happens to those servers and storage systems when several people all send photos at the same time.

I/O performance impacts and challenges for entertainment and media systems include:

  • Delays in image and file access resulting in lost productivity
  • Redundant files and storage local servers to improve performance
  • Contention for resources causing further bottlenecks during peak workload surges

OLTP and business intelligence
Surges in peak workloads result in performance bottlenecks on database and file servers, impacting time sensitive OLTP systems unless they are over configured for peak demand. For example, workload spikes due to holiday and back-to-school shopping, spring break and summer vacation travel reservations, Valentines or Mothers Day gift shopping, and clearance and settlement on peak stock market trading days strain fragile systems. For database systems maintaining performance for key objects, including transaction logs and journals, it is important to eliminate performance issues as well as maintain transaction and data integrity.

An example tied to eCommerce is business intelligence systems (not to be confused with back office marketing and analytics systems for research). Online business intelligence systems are popular with online shopping and services vendors who track customer interests and previous purchases to tailor search results, views and make suggestions to influence shopping habits.

Business intelligence systems need to be fast and support rapid lookup of history and other information to provide purchase histories and offer timely suggestions. The relative performance improvements of processors shift the application bottlenecks from the server to the storage access network. These applications have, in some cases, resulted in an exponential increase in query or read operations beyond the capabilities of single database and storage instances, resulting in database deadlock and performance problems or the proliferation of multiple data copies and dedicated storage on application servers.

A more recent contribution to performance challenges, caused by the increased availability of on-line shopping and price shopping search tools, is low cost craze (LCC) or price shopping. LCC has created a dramatic increase in the number of read or search queries taking place, further impacting database and file systems performance. For example, an airline reservation system that supports price shopping while preventing impact to time sensitive transactional reservation systems would create multiple read-only copies of reservations databases for searches. The result is that more copies of data must be maintained across more servers and storage systems thus increasing costs and complexity. While expensive, the alternative of doing nothing results in lost business and market share.

I/O performance impacts and challenges for OLTP and business intelligence systems include:

  • Application and database contention, including deadlock conditions, due to slow transactions
  • Disruption to application servers to install special monitoring, load balance or I/O driver software
  • Increased management time required to support additional storage needed as a I/O workaround

Summary/Conclusion
It is vital to understand the value of performance, including response time or latency, and numbers of I/O operations for each environment and particular application. While the cost per raw TByte may seem relatively in-expensive, the cost for I/O response time performance also needs to be effectively addressed and put into the proper context as part of the data center QoS cost structure.

There are many approaches to address data center I/O performance bottlenecks with most centered on adding more hardware or addressing bandwidth or throughput issues. Time sensitive applications depend on low response time as workload including throughput increase and thus latency can not be ignored. The key to removing data center I/O bottlenecks is to find and address the problem instead of simply moving or hiding it with more hardware and/or software. Simply adding fast devices such as SSD may provide relief, however if the SSDs are attached to high latency storage controllers, the full benefit may not be realized. Thus, identify and gain insight into data center and I/O bottleneck paths eliminating issues and problems to boost productivity and efficiency.

Where to Learn More
Additional information about IT data center, server, storage as well as I/O networking bottlenecks along with solutions can be found at the Server and StorageIO website in the tips, tools and white papers, as well as news, books, and activity on the events pages. If you are in the New York area on September 23, 2009, check out my presentation on The Other Green – Storage Optimization and Efficiency that will touch on the above and other related topics. Download your copy of "IT Data Center and Storage Bottlenecks" by clicking 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

Upcoming Out and About Events

Following up on previous Out and About updates ( here and here ) of where I have been, heres where I’m going to be over the next couple of weeks.

On September 15th and 16th 2009, I will be the keynote speaker along with doing a deep dive discussion around data deduplication in Minneapolis, MN and Toronto ON. Free Seminar, register and learn more here.

The Infrastructure Optimization and Planning Best Practices (V2.009) – Doing more with less without sacrificing storage, system or network capabilities Seminar series continues September 22, 2009 with a stop in Chicago. Free Seminar, register and learn more here.

On September 23, 2009 I will be in New York City at Storage Decisions conference participating in the Ask the Experts during the expo session as well as presenting The Other Green — Storage Efficiency and Optimization.

Throw out the "green“: buzzword, and you’re still left with the task of saving or maximizing use of space, power, and cooling while stretching available IT dollars to support growth and business sustainability. For some environments the solution may be consolation while others need to maintain quality of service response time, performance and availability necessitating faster, energy efficient technologies to achieve optimization objectives. To accomplish these and other related issues, you can turn to the cloud, virtualization, intelligent power management, data footprint reduction and data management not to mention various types of tiered storage and performance optimization techniques. The session will look at various techniques and strategies to optimize either on-line active or primary as well as near-line or secondary storage environment during tough economic times, as well as to position for future growth, after all, there is no such thing as a data recession!

Topics, technologies and techniques that will be discussed include among others:

  • Energy efficiency (strategic) vs. energy avoidance (tactical)
  • Optimization and the need for speed vs. the need for capacity
  • Metrics and measurements for management insight
  • Tiered storage and tiered access including SSD, FC, SAS and clouds
  • Data footprint reduction (archive, compress, dedupe) and thin provision
  • Best practices, financial incentives and what you can do today

Free event, learn more and register here.

Check out the events page for other upcoming events and hope to see you this fall while Im out and about.

Cheers – gs

Greg Schulz – StorageIOblog, twitter @storageio Author “The Green and Virtual Data Center” (CRC)

Posted on

Recent tips, videos, articles and more

Its been a busy year so far and there is still plenty more to do. Taking advantage of a short summer break, I’m getting caught up on some items including putting up a link to some of the recent articles, tips, reports, webcasts, videos and more that I have eluded to in recent posts. Realizing that some prefer blogs to webs to tweets to other venues, here are some links to recent articles, tips, videos, podcasts, webcasts, white papers and more that can be found on the StorageIO Tips, tools and White Papers pages.

Recent articles, columns, tips, white papers and reports:

  • ITworld: The new green data center: From energy avoidance to energy efficiency August 2009
  • SearchSystemsChannel: Comparing I/O virtualization and virtual I/O benefits July 2009
  • SearchDisasterRecovery: Top server virtualization myths in DR and BC July 2009
  • Enterprise Storage Forum: Saving Money with Green Data Storage Technology July 2009
  • SearchSMB ATE Tips: SMB Tips and ATE by Greg Schulz
  • SearchSMB ATE Tip: Tape library storage July 2009
  • SearchSMB ATE Tip: Server-based operating systems vs. PC-based operating systems June 2009
  • SearchSMB ATE Tip: Pros/cons of block/variable block dedupe June 2009
  • FedTechAt the Ready: High-availability storage hinges on being ready for a system failure May 2009
  • Byte & Switch Part XI – Key Elements For A Green and Virtual Data Center May 2009
  • Byte & Switch Part X – Basic Steps For Building a Green and Virtual Data Center May 2009
  • InfoStor Technology Options for Green Storage: April 2009
  • Byte & Switch Part IX – I/O, I/O, Its off to Virtual Work We Go: Networks role in Virtual Data Centers April 2009
  • Byte & Switch Part VIII – Data Storage Can Become Green: There are many steps you can take April 2009
  • Byte & Switch Part VII – Server Virtualization Can Save Costs April 2009
  • Byte & Switch Part VI – Building a Habitat for Technology April 2009
  • Byte & Switch Part V – Data Center Measurement, Metrics & Capacity Planning April 2009
  • zJournal Storage & Data Management: Tips for Enabling Green and Virtual Efficient Data Management March 2009
  • Serial Storage Wire (STA): Green and SASy = Energy and Economic, Effective Storage March 2009
  • SearchSystemsChannel: FAQs: Green IT strategies for solutions providers March 2009
  • Computer Technology Review: Recent Comments on The Green and Virtual Data Center March 2009
  • Byte & Switch Part IV – Virtual Data Centers Can Promote Business Growth March 2009
  • Byte & Switch Part III – The Challenge of IT Infrastructure Resource Management March 2009
  • Byte & Switch Part II – Building an Efficient & Ecologically Friendly Data Center March 2009
  • Byte & Switch Part I – The Green Gap – Addressing Environmental & Economic Sustainability March 2009
  • Byte & Switch Green IT and the Green Gap February 2009
  • GreenerComputing: Enabling a Green and Virtual Data Center February 2009

    • Some recent videos and podcasts include:

  • bmighty.com The dark side of SMB virtualization July 2009
  • bmighty.com SMBs Are Now Virtualization’s “Sweet Spot” July 2009
  • eWeek.com Green IT is not dead, its new focus is about efficiency July 2009
  • SearchSystemsChannel FAQ: Using cloud computing services opportunities to get more business July 2009
  • SearchStorage FAQ guide – How Fibre Channel over Ethernet can combine networks July 2009
  • SearchDataCenter Business Benefits of Boosting Web hosting Efficiency June 2009
  • SearchStorageChannel Disaster recovery services for solution providers June 2009
  • The Serverside The Changing Dynamic of the Data Center April 2009
  • TechTarget Virtualization and Consolidation for Agility: Intels Xeon Processor 5500 series May 2009
  • TechTarget Virtualization and Consolidation for Agility: Intels Xeon Processor 5500 series May 2009
  • Intel Reduce Energy Usage while Increasing Business Productivity in the Data Center May 2009
  • WSRadio Closing the green gap and shifting towards an IT efficiency and productivity April 2009
  • bmighty.com July 2009

    • Check out the Tips, Tools and White Papers, and News pages for more 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

    Green IT Confusion Continues, Opportunities Missed!

    I continue to see those looking for fast silver bullets in the quest to be green, efficient, optimized or sustainable while addressing issues ranging from power/energy, cooling, floor-space/footprint, EH&S (environmental health & safety) not to mention recycling. Yet, I’m also continued to be  amazed by the focus and emphasis around reduce as in reduce your capacity and your performance or processing capabilities in the form of consolidation or aggregation along with energy avoidance which for some is applicable.

    However, there is also the other side of the tale which is shifting from avoidance to becoming more efficient, that is doing more with what you have or with less while boosting productivity. For example, having a server or processor that can do more work in the same or smaller physical footprint drawing the same or less energy and requiring less cooling is a form of reducing overall impact yet boosting productivity. The same can be done with data and I/O networks, storage and even software.

    Similar to automobiles after the 1970s oil and energy crisis, the focus was on reduction, conservation and avoidance as the form of being efficient. Over time, this approach gave way to levering more efficient engines and vehicles that boosted the MPG city and highway, change in driving or usage habits, awareness of issues including applicable metrics and energy costs, as well as the continuing quest for alternative fuels.

    This is no different than what is happening with the IT organizations or compute focused entities in that there has been an initial focus of avoidance to meet short term tactical requirements, not to mention all of the green hype of a few years ago. Today there is a shift taking place towards efficiency and awareness that optimization and efficiency is more than consolidation, that it also includes boosting productivity as part of achieving reduced energy and cooling demands.

    How this can be done is to leverage multiple different techniques including new servers with processors that have intelligent power management (IPM) also known as adaptive voltage scaling (AVS) or other marketing terms enabling variable performance and energy consumption. For example, vary clock cycles and turn on cores when needed, then to turn off cores, slow clock speed down when there is less work to be done. Likewise there are improvements with cooling closer to the heat source ranging from leveraging inert liquid cooling inside the cabinet of computers to surface attached cooling to emerging micro cooling located inside silicon. There is a fascination with using virtualization to consolidate and reduce servers that are underutilized, which again is applicable for some environments and applications.

    However not all servers including many that are underutilized lend themselves to being consolidated for various reasons including quality of service (QoS) or performance, security, vendor support or software compatibility, politics or finance among others. This however does not mean that they cannot be virtualized, it more than likely mean that they cannot be consolidated. There is a common myth that virtualization equals consolidation and vice versa, however virtualization can also be used for abstraction, transparency, emulation and enabling agility including support for load-balancing, scale-up and scale-out performance oriented clustering among other uses. Thus there is another side of virtualization and that is to achieve   efficiency, life beyond consolidation.

    Needless to say there are many more technologies and techniques to address various issues now along with those that are emerging. The good news in all of this is the growing awareness that there are many different faces or facets of being green. That green wash and green hype may be on the endangered species list, that green means more than reducing carbon footprints or recycling or energy avoidance. That green is really about shifting and becoming more efficient, more optimized to support more processing, more work in a cost effective manner to sustain growth on a go forward basis. For high performance compute (HPC) or other large scale IT organizations, there is a notion that small improvements on a large broad scale have significant impact.

    Some organizations are in pursuit of technologies of solutions that promise significant saving ratios over small sets or instances, solutions that provide  smaller reduction or savings over a larger basis can prove to be more effective. For example, if power is a concern, powering down servers or storage that promises 85-100% savings might only be applicable to less than 5% of the devices. However, if 85-100% of the devices can be upgraded to newer models that boost productivity by 5-15% (or more) in the same or smaller footprint, using 5-15% (or more) less power, the results add up quickly. Think of it this way, a 1% saving for an environment using 1,000 kilo watt hour (kWh) or 1mWh of energy is a savings of 10kWh. The point being that for large environments, don’t forget to look at small savings that apply to a large installed base that then add up to big benefits.

    The net result is that one can pursue being green or being perceived as being green which can have a high cost, or, can pursue various efficiency that help the overall organization by boosting productivity, helping the top and bottom line, doing more in a smaller footprint and guess what, the result is not only economic, it’s also environmental positive. Thus, the byproduct of shifting towards efficiency (and not just avoidance) is to become green!

    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

    Mirror mirror on the wall, who’s the greenest of them all?

    If you subscribe to the notion that Green IT is all about carbon footprints, you may be missing out on some real opportunities to go green. After all, carbon is part of the green movement, there are many other aspects including supply chain, efficiency, sustainability in addition to recycling, not to mention optimizing power, cooling footprints in order to do more work in a productive manner.

    So who is the greenest of them all? Could it be Brocade, CA, Cisco, EMC, Hitachi, IBM, Intel, LSI, Microsoft, NetApp, Oracle, Symantec, VMware or 3PAR? What about the cloud crowd or perhaps one of the industry trade groups such as Green grid, SNIA GSI, Climate Savers Computing or Carbon disclosure project perhaps among others?

    You might be surprised, now granted, this list is for consumer products. However, given their broad adoption, and looking at Green as more than carbon impact, and with the EPA implanting Energy Star for Servers and now Energy Star for storage in the works, not to mention factoring in the green supply chain, have a look here.

    Here’s an interesting read about how the Internet is causing global warming. How ironic, given Al Gore’s carbon crusade, and the folk-lore claim about  (or mistaken have claimed) to have invented the Internet, no wonder he has been able to cash-in and transform Green to Gold.

    For those interested in saving money with efficient and optimized storage (e.g. the new Green) to boost productivity, here’s an article to check out.

    Ok, that’s enough "Green" fun for now.

    Cheers gs

    Posted on

    SPC and Storage Benchmarking Games

    Storage I/O trends

    There is a post over in one of the LinkedIn Discussion forums about storage performance council (SPC) benchmarks being miss-leading that I just did a short response post to. Here’s the full post as LinkedIn has a short post response limit.

    While the SPC is far from perfect, it is at least for block, arguably better than doing nothing.

    For the most part, SPC has become a de facto standard for at least block storage benchmarks independent of using IOmeter or other tools or vendor specific simulations, similar how MSFT ESRP is for exchange, TPC for database, SPEC for NFS and so forth. In fact, SPC even recently rather quietly rolled out a new set of what could be considered the basis for Green storage benchmarks. I would argue that SPC results in themselves are not misleading, particularly if you take the time to look at both the executive and full disclosures and look beyond the summary.

    Some vendors have taken advantage of the SPC results playing games with discounting on prices (something that’s allowed under SPC rules) to show and make apples to oranges comparisons on cost per IOP or other ploys. This proactive is nothing new to the IT industry or other industries for that matter, hence benchmark games.

    Where the misleading SPC issue can come into play is for those who simply look at what a vendor is claiming and not looking at the rest of the story, or taking the time to look at the results and making apples to apples, instead of believing the apples to oranges comparison. After all, the results are there for a reason. That reason is for those really interested to dig in and sift through the material, granted not everyone wants to do that.

    For example, some vendors can show a highly discounted list price to get a better IOP per cost on an apple to oranges basis, however, when processes are normalized, the results can be quite different. However here’s the real gem for those who dig into the SPC results, including looking at the configurations and that is that latency under workload is also reported.

    The reason that latency is a gem is that generally speaking, latency does not lie.

    What this means is that if vendor A doubles the amount of cache, doubles the number of controllers, doubles the number of disk drives, plays games with actual storage utilization (ASU), utilizes fast interfaces from 10 GbE  iSCSI to 8Gb FC or FCoE or SAS to get a better cost per IOP number with discounting, look at the latency numbers. There have been some recent examples of this where vendor A has a better cost per IOP while achieving a higher number of IOPS at a lower cost compared to vendor B, which is what is typically reported in a press release or news story. (See a blog entry that also points to a CMG presentation discussion around this topic here.

    Then go and look at the two results, vendor B may be at list price while vendor A is severely discounted which is not a bad thing, as that is then the starting list price as to which customers should start negotiations. However to be fair, normalize the pricing for fun, look at how much more equipment vendor A may need while having to discount to get the price to offset the increased amount of hardware, then look at latency.

    In some of the recent record reported results, the latency results are actually better for a vendor B than for a vendor A and why does latency matter? Beyond showing what a controller can actually do in terms of levering  the number of disks, cache, interface ports and so forth, the big kicker is for those talking about SSD (RAM or FLASH) in that SSD generally is about latency. To fully effectively utilize SSD which is a low latency device, you would want a controller that can do a decent job at handling IOPS; however you also need a controller that can do a decent job of handling IOPS with low latency under heavy workload conditions.

    Thus the SPC again while far from perfect, at least for a thumb nail sketch and comparison is not necessarily misleading, more often than not it’s how the results are utilized that is misleading. Now in the quest for the SPC administrators to try and gain more members and broader industry participation and thus secure their own future, is the SPC organization or administration opening itself up to being used more and more as a marketing tool in ways that potentially compromise all the credibility (I know, some will dispute the validity of SPC, however that’s reserved for a different discussion ;) )?

    There is a bit of Déjà here for those involved with RAID and storage who recall how the RAID Advisory Board (RAB) in its quest to gain broader industry adoption and support succumbed to marketing pressures and use or what some would describe as miss-use and is now a member of the “Where are they now” club!

    Don’t get me wrong here; I like the SPC tests/results/format, there is a lot of good information in the SPC. The various vendor folks who work very hard behind the scenes to make the SPC actually work and continue to evolve it also all deserve a great big kudos, an “atta boy” or “atta girl” for the fine work that have been doing, work that I hope does not become lost in the quest to gain market adoption for the SPC.

    Ok, so then this should all then beg the question of what is the best benchmark. Simple, the one that most closely resembles your actual applications, workload, conditions, configuration and environment.

    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