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.
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2018 Server StorageIO and UnlimitedIO LLC All Rights Reserved