Carnegie Mellon University
Browse

System-Call Based Problem Diagnosis for PVFS

Download (117.07 kB)
journal contribution
posted on 2018-06-30, 13:30 authored by Michael P. Kasick, Keith A Bare, Eugene E Marinelli, Jiaqi Tan, Rajeev Ghandi, Priya Narasimhan
We present a syscall-based approach to automatically diagnose performance problems, server-to-client propagated errors, and server crash/hang problems in PVFS. Our approach compares the statistical and semantic attributes of syscalls across PVFS servers in order to diagnose the culprit server, under these problems, for different file-system benchmarks—dd, PostMark and IOzone—in a PVFS cluster.

History

Publisher Statement

All Rights Reserved

Usage metrics

    Categories

    Keywords

    Data StorageData Format not elsewhere classified

    Licence

    In Copyright

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC