The boundaries between personal and professional activities are becoming blurred in our pervasive digital world.  Social computing, while not strategic to every business, is changing consumer and employee behaviour, which ultimately has an effect on the entire IT infrastructure. 

These changing behaviours are marked by the explosion of remote and mobile working and the evaporation of the cloud hype into reality.  Employees work and play on the go, teams are interacting virtually, communicating via face time, collaborating in the cloud and bringing personal quick-access storage devices to work. The ties that bind workers to their desks have been cut, placing heavy demand on the data centre to serve enterprise data, process transactions and make available business applications quickly and efficiently, thus requiring the data centre to perform at maximum potential utilisation. 

The trend towards cloud computing, fabric based computing and advanced analytics creates a truly dynamic environment and requires more flexibility and more processing power.  In such a dynamic environment with its myriad permutations of configurations, the CIO is hard pushed to ensure application and server performance, while managing costs.  With all these interrelated settings between servers and clients comes the risk of decreasing workload densities and severe latency problems if these settings are not tuned for optimum performance. 

The challenge, as the data centre environment becomes more diverse and disparate is to avoid the decline in server and application performance that creates untold frustration, jeopardises productivity among users and costs the business millions in unnecessary investment.

As the demands on the data centre become more complex and immediate, the focus remains on cost management Data growth, system performance and scalability, and network congestion and connectivity architecture were ranked as the top three challenges among respondents to a recent survey by Gartner.

Latest generation servers with multicore processors demand significantly higher throughput, and if these servers are virtualized, this requirement further goes up. Increased reliance on WAN can be a trigger for network-related challenges as users are consolidating their IT systems, especially as individual users are increasingly working remotely or going mobile. These challenges must be met strategically rather than addressed with a silo approach.

To compound the issue, Gartner predicts that by 2016, sustainability will be the fastest-growing enterprise compliance expense worldwide.  As the UK power grid approaches saturation, more and more data centres are facing a hard limit on what power they can draw from the grid and it is simply not acceptable to throw more hardware (and all the associated overheads) at a problem.  We must make what we have work harder and smarter.

In this lean economic climate, while networks become more congested and application performance suffers, cost-saving technologies remain the lynch pin of IT strategies.  It makes no sense to send two half empty coaches to the same location when you could fill one and halve the fuel costs, so why add more servers to your infrastructure to gain better server utilisation, when you could tune your existing environment and reduce your IT’s Total Cost of Ownership?

Working your data centre assets smarter brings greater ROI, a smaller carbon footprint and satisfied users.

Gartner’s survey also revealed that the top three technologies that respondents plan to invest in through 2011 are server virtualization (67%), application consolidation or rationalization (56%) and blade servers (51%).  These are cost saving measures that negatively impact server performance and capacity, and saturate network bandwidth, creating an expanding drag on application performance.

Virtualisation remains an obvious choice for making the most of what you have, but once you’ve virtualised, how does this relate to the operating system, the CPU and memory utilisation?  There are myriad capacity planning tools available in the VMware world, but they all concentrate on the hypervisor down, looking at asset allocation for example, which uses actual memory used as a trend versus allocated memory.  What they fail to do is tune the underlying CPU, Memory and disk assents to the capabilities and needs of the application and operating system.  CIOs are facing limits to their ability to deliver the workload densities and ROI promised by virtualization.

Virtualized environments contain hundreds of interrelated settings that require active performance and capacity tuning. Without this tuning, workload densities fall and virtualization costs soar.  Because of this problem many enterprises operate at 30 to 50 percent below maximum available utilization. This translates to millions of pounds in unnecessary investment simply because enterprises are not squeezing the most out of their existing servers.

In order to accelerate application response times and mask the symptoms of a non-optimized infrastructure, IT departments frequently over provision server hardware, or purchase application delivery controllers and WAN accelerators.  This additional expense serves mostly to hide the root cause of performance problems for specific applications, increase the complexity of the environment, and does nothing to solve the underlying problem – an un-tuned system. 

In such a demanding environment as our increasingly remote and mobile workforce presents and given the truly dynamic nature of cloud, fabric based and virtualised environments, Active Continuous Optimisation (ACO) is the only answer to attaining maximum available utilisation to ensure you really get the best out of your existing infrastructure and avoid unnecessary investment.  ACO addresses the root cause, not the symptoms, by automatically tuning OS, server and delivery performance from both server-to-server and server-to-client, and while maximising server capacity.  In some cases this generates order-of-magnitude performance increases. The more complex the system the more it can benefit from ACO. ACO runs a series of simple queries to collect device-specific configuration information and baseline performance.  The correlation engine then calculates and recommends configuration changes that will improve performance.  These changes can be manually or automatically deployed. The cause of declining application performance is often simply that configurations are not optimised to the needs of the application and operating system.

Targeting and tuning the heart of the server, the operating system, maximizes the efficient use of all server and client components including; applications, databases, CPU, memory, network and storage.  Improving server utilisation by up to 50% represents significant savings in capital expenditure and operation expenses, as well as reducing carbon footprint and keeping end users satisfied.

Veloxum – Active Continuous Optimisation
As the first Active Continuous Optimization (ACO) infrastructure tuning solution for virtual environments, Veloxum is transforming the process of optimizing complex virtualized infrastructure configuration settings and allowing enterprises to realize the full potential of their IT infrastructure. Veloxum actively and continuously optimizes physical and virtual infrastructure by optimizing operating system and application settings. It leverages the existing systems and infrastructure by tuning the various components within their manufacturer supported settings.

The solution enables IT organizations to maximize performance, increase workload density, and minimize virtualization costs, dramatically reducing CAPEX and OPEX spending.

ShareThis

Tags: Virtualization, The Cloud

Read more White Papers»

More DCS TV»

More Audio»

Read more Web Exclusives»

Read more Magazine Articles»

Read more Supplements »

Keep up to date with the latest industry products, services and technologies from the world's leading IT companies.

• Virtualization Success Depends on Network Automation by Infoblox

• The Infoblox VMware vCenter Orchestrator Plug-in by Infoblox

• Automated Storage Tiering on Infortrend’s ESVA Solution by Infortrend

• Why Cloud Backup: Top 10 Reasons by Autonomy

• How to Measure the ROI of Cloud Data Protection by Autonomy

Latest IT jobs from leading companies.

Click here for full listings»