Lesson-02: Challenges in Resource Management

Resource management

Various challenges arise to resource allocation due to the capacity scale, complexities of datacenters, and varying workload characteristics while providing guaranteed capacity within a region.

The following sections explain Facebook’s region layout and discuss the impacts of hardware heterogeneity, diverse capacity requests, and server unavailability events on services and capacity allocation.

Region layout

Facebook operates in many regions around the globe. The following figure denotes the organization of a region consisting of several data center buildings. Each of them is connected via high bandwidth and low latency network. The figure below shows that each data center building is composed of failure domains called the Main Switch Board (MSB) designed to fail independently.

Due to the close locality of data centers, the network latency within a region is very low. This allows resource management to accumulate resources across datacenters. However, the network bandwidth across datacenters is lower ...