Grano

Abstract

We demonstrate Grano 1 , an end-to-end anomaly detection and root cause analysis (or RCA for short) system for cloud-native distributed data platform by providing a holistic view of the system component topology, alarms and application events. Grano provides: a Detection Layer to process large amount of time-series monitoring data to detect anomalies at logical and physical system components; an Anomaly Graph Layer with novel graph modeling and algorithms for leveraging system topology data and detection results to identify the root cause relevance at the system component level; and an Application Layer that automatically notifies on-call personnel and presents real-time and on-demand RCA support through an interactive graph interface. The system is deployed and evaluated using eBay's production data to help on-call personnel to shorten the identification of root cause from hours to minutes.

CausIL: Causal Graph for Instance Level Microservice Data

“…With the recent upsurge of work in the field of performance diagnosis of large and complex modern microservice architectures [10,11,17,27,29], researchers at many cloud-based companies are actively working on alerting and monitoring solutions [12,21,44]. Alerting services like Watchdog, New Relic and Splunk diagnose systems by constructing causal graphs between services or using thresholding techniques.…”

“…Service dependency graphs are also used to answer "what-if" based system questions on bandwidth management and application latencies [16,18,41,42]. Grano [44] builds a causal dependency graph among physical resources for fault diagnosis. However, performance diagnosis is often demanded at a more granular level.…”

Efficient end-to-end failure probing matrix construction in data center networks

“…With the growth of the DCN scale and the emerging application of new network devices, failures in DCNs have become the norm rather than occasional events. Failures in DCNs usually have more severe consequences than in general networks, from disruption of services to loss of critical data [5]. Meanwhile, the complexity of large-scale DCN management makes it difficult for network administrators to find and locate failures in a timely manner.…”