How Operations Manager Works

Document created by madison.collins on Jul 15, 2015Last modified by fran.schwarzmann on Aug 15, 2016
Version 2Show Document
  • View in full screen mode

This information can also be found in the user manual in your VMTurbo Operations Manager.


How Operations Manager Works


To keep your infrastructure in the desired state, Operations Manager performs Intelligent Workload Management.

This is an ongoing process that solves the problem of assuring application performance while simultaneously achieving

the most efficient use of resources that is possible.


This is not a simple problem to solve. Intelligent Workload Management has to consider many different resources,

numerous control points for each device, and how devices and resources are used in relation to each other. As you

add devices to your infrastructure, the factors for each decision increase exponentially. On top of that, the environment

is constantly changing — to stay in the desired state, you are constantly trying to hit a moving target.


To perform Intelligent Workload Management, Operations Manager models the environment as a market made up of

buyers and sellers. These buyers and sellers make up a supply chain that represents tiers of devices in your inventory.

See the The Supply Chain View on page 105 for a visual layout of the buyer and seller relationships.

Operations Manager uses Virtual Currency to give a budget to buyers and assign cost to resources. This virtual currency

assigns value across all tiers of your environment, making it possible to compare the cost of application transactions

with the cost of space on a disk or physical space in a data center.


The price that a seller charges for a resource changes according to the seller’s supply. As demand increases, prices

increase. As prices change, buyers and sellers react. Buyers are free to look for other sellers that offer a better price,

and sellers can duplicate themselves (open new storefronts) to meet increasing demand. Operations Manager uses its

Economic Scheduling Engine to analyze the market and make these decisions. The effect is an invisible hand that

dynamically guides your IT infrastructure to the optimal use of resources.


To get the most out of Operations Manager, you should understand how it models your environment, the kind of analysis

it performs, and the desired state it works to achieve.


The Desired State



The goal of Intelligent Workload Management is to assure performance while maintaining efficient use of resources.

When performance and efficiency are both maintained, you are in the desired state. You can measure performance as

a function of delay, where zero delay gives the ideal QoS for a given service. Efficient use of resources is a function of

utilization where 100% utilization of a resource is the ideal for the most efficient utilization.


If you plot delay and utilization, the result is a curve that shows a correlation between utilization and delay. Up to a

point, as you increase utilization, the increase in delay is slight. There comes a point on the curve where a slight

increase in utilization results in an unacceptable increase in delay. On the other hand, there is a point in the curve

where a reduction in utilization doesn’t yield a meaningful increase in QoS. The desired state lies within these points

on the curve.


You could set a threshold to post an alert whenever the upper limit is crossed. In that case, you would never react to a

problem until delay has already become unacceptable. To avoid that late reaction you could set the threshold to post

an alert before the upper limit is crossed. In that case, you guarantee QoS at the cost of over‐provisioning — you

increase operating costs and never achieve efficient utilization.

Instead of responding after a threshold is crossed, Operations Manager analyzes the operating conditions and constantly

recommends actions to keep the entire environment within the desired state. If you execute these actions (or

let Operations Manager execute them for you), the environment will maintain operating conditions that assure performance

for your customers, while ensuring the lowest possible cost thanks to efficient utilization of your resources.


The Market and Virtual Currency


To perform Intelligent Workload Management, Operations Manager models the environment as a market, and uses

market analysis to manage resource supply and demand. For example, bottlenecks form when local workload demand

exceeds the local capacity — in other words, when demand exceeds supply. By modeling the environment as a market,

Operations Manager can use economic solutions to efficiently redistribute the demand or increase the supply.


Operations Manager uses two sets of abstraction to model the environment:


• Modeling the physical and virtual IT stack as a service supply chain


The supply chain models devices in your environment as managed entities. These include applications, VMs, host

machines (physical machines, or PMs), storage, and data centers. Every entity is a buyer, a seller, or both. A host

machine buys physical space, power, and cooling from a data center. The physical machine sells host resources

such as CPU cycles and memory to VMs. In turn, VMs buy host services, and then sell their resources (VMem and

VCPU) to applications.


See the The Supply Chain View on page 105for a visual layout of the buyer and seller relationships.


• Using virtual currency to represent delay or QoS degradation, and to manage the supply and demand of services

along the modeled supply chain


The system uses virtual currency to value these buy/sell transactions. Each managed entity has a running budget

— the entity adds to its budget by providing resources to consumers, and the entity draws from its budget to pay

for the resources it consumes. The price of a resource is driven by its utilization — the more demand for a

resource, the higher its price.



Modeling the Environment as a Market


These abstractions open the whole spectrum of the environment to a single mode of analysis — market analysis.

Resources and services can be priced to reflect changes in supply and demand, and pricing can drive resource allocation

decisions. For example, a bottleneck (excess demand over supply) results in rising prices for the given resource.

Applications competing for the same resource can lower their costs by shifting their workloads to other resource suppliers.

As a result, utilization for that resource evens out across the environment and the bottleneck is resolved.

1 person found this helpful