Four aspects of optimizing data center performance and application performance

    In any virtual environment, a very delicate balance is maintained. On the one hand, you need to be sure that the infrastructure capacity is sufficient to meet application requirements without compromising overall performance. On the other hand, I want to avoid excessive reserve capacities, because this leads to inefficient use of resources and, consequently, an excessive waste of money.



    The right balance is what you want, according to VMTurbo, a virtualization management solution provider who recently introduced the new Operations Manager 4.0. Their software uses economic data to allocate virtual machines to resources. It can be resources in a data center, in a private cloud, or even resources in popular cloud solutions such as Amazon or Azure.

    These guys know a couple of ways how to make applications work better and improve the efficiency of the infrastructure, so you should listen to them. VMTurbo describes 4 key aspects in achieving this coveted balance.

    Smart workload placement in clusters


    Work processes consume cluster resources, such as processor time, memory, inbound / outbound channels, while the amount of resources consumed changes over time. Simple scheduling mechanisms that Microsoft, VMware, and the like offer, track usage and transfer the most demanding tasks to the least used machines, which helps balance load balancing across the cluster.

    But VMTurbo argues that a more holistic approach may be more effective in achieving the “desired state”. The company believes that by analyzing how to best place the workload in the environment, preserving the quality of service (preventing some processes from interfering with others while maximizing the efficiency of the infrastructure), it is possible to achieve an increase in efficiency of 20-40% compared to the built-in hypervisor scheduler.

    Reasonably distributed workload across clusters


    A software network simplified the movement of virtual machines. Virtual technologies, such as vMotion and Live Migration, allow moving running machines between clusters. VMTurbo points out what is being overlooked - the possibility of continuous continuous analysis of solutions for distributing tasks between clusters, which will bring the virtual infrastructure closer to the “desired state”.



    “The intelligent distribution of workload between clusters opens up a completely new opportunity to more efficiently fill the underloaded islands of computing resources,” the company says. “This will not only contribute to a more efficient use of resources by eliminating the need for reserving them for peak loads in clusters, but will also provide a protective mechanism to adapt to unforeseen surges in the load when running applications.”

    Equipment consolidation


    VMTurbo claims that many companies create their hardware infrastructure for specific projects, and for many this leads to the appearance of small clusters that are not used to their full capacity. And the right decision will be to combine all these small clusters into larger ones.



    According to the company, the ability to predict the possible impact of such consolidation, in which larger pools of resources are formed from existing equipment, is important. Releasing such unused resources will save significant resources.

    Release unused spare capacity


    VMware and Hyper-V offer a way to reserve resources for individual tasks, which ensures that resources are available to the application even when they are not needed, thereby mitigating performance issues.

    This way is not entirely effective, because much more resources are reserved than is actually necessary. Selection of the “optimal size” (calibration) of virtual servers - the ability to reserve resources based on the real needs of each specific task. This allows you to free up a significant amount of memory and processor resources, which in turn increases the efficiency of equipment use and reduces costs, said VMTurbo.

    What is the outcome of all this? Instead of trying to implement such balancing with load dispersion within and between clusters, consolidating resources and calibrating manually or using the primitive tools provided by developers of hypervisors, why not rely on specialized software?

    Of course, all this looks like an advertisement, because VMTurbo just sells software for resource allocation. But nevertheless, if the management software can increase the efficiency of the entire virtualization infrastructure by more than 40%, as the company says, it is worth taking a closer look at this decision.

    Also popular now: