An anomaly detection approach for scale-out storage systems

Guthemberg Silvestre (1) , Carla Sauvanaud (1) , Mohamed Kaâniche (1, 2) , Karama Kanoun (1)

1 LAAS-TSF - Équipe Tolérance aux fautes et Sûreté de Fonctionnement informatique
2 PRES Université de Toulouse

—Scale-out storage systems (SoSS) have become in-creasingly important for meeting availability requirements of web services in cloud platforms. To enhance data availability, SoSS rely on a variety of built-in fault-tolerant mechanisms, including replication, redundant network topologies, advanced request scheduling, and other failover techniques. However, performance issues in cloud services still remain one of the main causes of discontentment among their tenants. In this paper, we propose an anomaly detection approach for SoSS that predicts cloud anomalies caused by memory and network faults. To evaluate our prediction model, we built a testbed simulating a virtual data center using VMware. Experimental results confirm that the injected faults are likely to undermine the data availability in SoSS. They suggest that although unsupervised learning has been the most common method for anomaly detection, a supervised-based implementation of the same model reduces the false positive rate by roughly 10%. Our analysis also points out that probing SoSS-specific monitoring data at the VM-level contributes to improve the anomaly prediction efficiency.

Domaines: Machine Learning [stat.ML]; Base de données [cs.DB]; Web; Automatique

Guthemberg Silvestre, Carla Sauvanaud, Mohamed Kaâniche, Karama Kanoun. An anomaly detection approach for scale-out storage systems. 26th International Symposium on Computer Architecture and High Performance Computing, Oct 2014, Paris, France. ⟨hal-01076212⟩