FLEET: Fluid Layout of End to End Topology
Madhumita Bharde, Karuna Nayak · 2023
Clustering, virtualization and multi-tenancy are so ubiquitous across all layers of enterprise software deployments, that the overall topology of these stacks has reached unprecedented levels of complexity. A lot of stress is given on independently monitoring all layers of the stack. Almost all SaaS, IaaS and PaaS vendors along with traditional compute and storage vendors provide descriptive, prescriptive and predictive analytics for individual layers of software and hardware. However, with complex layouts and schemes possible for differently juxtaposed parts, often coming from multiple vendors, it is almost impossible to sift through the barrage of dashboards, events, alerts and recommendations. The fundamental problem in deriving holistic insights lies in the fact that these layers are opaque to each other, or at least they have been treated as such for the most part. With Fluid Layout of End to End Topology (FLEET), we establish that adjacent layers of the stack have clues about each other which can be used to ‘‘stitch’’ them together and infer the exact footprint of entities across layers. We standardize a mechanism to collect dynamic configuration information across the stack, process it and store the woven topology at scale.