Title :
Gumshoe: Diagnosing Performance Problems in Replicated File-Systems
Author :
Kavulya, Soila ; Gandhi, Rajeev ; Narasimhan, Priya
Author_Institution :
Electr. & Comput. Eng. Dept., Carnegie Mellon Univ., Pittsburgh, PA
Abstract :
Replicated file-systems can experience degraded performance that might not be adequately handled by the underlying fault-tolerant protocols. We describe the design and implementation of Gumshoe, a system that aims to diagnose performance problems in replicated file-systems. Gumshoe periodically gathers OS and protocol metrics and then analyzes these metrics to automatically localize the performance problem to the culprit node(s). We describe our results and experiences with problem diagnosis in two replicated file-systems (replicated-CoreFS and BFS) using two file-system benchmarks (Postmark and IOzone).
Keywords :
operating systems (computers); program diagnostics; replicated databases; software fault tolerance; software metrics; Gumshoe; IOzone; Postmark; fault-tolerant protocols; file-system benchmarks; problem diagnosis; protocol metrics; replicated file-systems; replicated-CoreFS; Computer crashes; Degradation; Distributed computing; Fault detection; Fault diagnosis; Fault tolerance; Fault tolerant systems; Peer to peer computing; Protocols; Reliability engineering; diagnosis; performance problems; replicated file-systems;
Conference_Titel :
Reliable Distributed Systems, 2008. SRDS '08. IEEE Symposium on
Conference_Location :
Naples
Print_ISBN :
978-0-7695-3410-7
DOI :
10.1109/SRDS.2008.35
