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.

A large population of users gets affected by sudden slowdown or shutdown of an enterprise application. System administrators and analysts spend considerable amount of time dealing with functional and performance bugs. These problems are particularly hard to detect and diagnose in most computer systems, since there is a huge amount of system generated supportability data (counters, logs etc.) that need to be analyzed. Most often, there isn't a very clear or obvious root cause. Timely identification of significant change in application behavior is very important to prevent negative impact on the service. In this paper, we present ADELE, an empirical, data-driven methodology for early detection of anomalies in data storage systems. The key feature of our solution is diligent selection of features from system logs and development of effective machine learning techniques for anomaly prediction. ADELE learns from system's own history to establish the baseline of normal behavior and gives accurate indications of the time period when something is amiss for a system. Validation on more than 4800 actual support cases shows~83% true positive rate and~12% false positive rate in identifying periods when the machine is not performing normally. We also establish the existence of problem “signatures” which help map customer problems to already seen issues in the field. ADELE's capability to predict early paves way for online failure prediction for customer systems.