A Framework To Compute Statistics of System Parameters From Very Large Trace Files
Submitted by Anonymous on Tue, 2013-02-19 16:27
The paper titled "A framework to compute statistics of system parameters from very large trace files" is published in ACM SIGOPS Oper. Syst. Rev.
In this paper, we present a framework to compute, store and
retrieve statistics of various system metrics from large traces
with unprecedented efficiency. The proposed framework en-
ables very fast interactive queries about system metrics values
for any given time interval.
Date:
Tuesday, February 19, 2013
Publication authors (members):
Michel Dagenais
Naser Ezzati Jivan
Publisher:
ACM SIGOPS Oper. Syst. Rev.
Publication version number:
1.00
Bibtex:
@article{Ezzati-Jivan:2013:FCS:2433140.2433151,
author = {Ezzati-Jivan, Naser and Dagenais, Michel R.},
title = {A framework to compute statistics of system parameters from very large trace files},
journal = {SIGOPS Oper. Syst. Rev.},
issue_date = {January 2013},
volume = {47},
number = {1},
month = jan,
year = {2013},
issn = {0163-5980},
pages = {43--54},
numpages = {12},
url = {http://doi.acm.org/10.1145/2433140.2433151},
doi = {10.1145/2433140.2433151},
acmid = {2433151},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {Linux kernel, statistics, system metrics, trace, trace abstraction},
}
Publication status:
Published
Publication link:
Tracks concerned:
- AHLS›Scalable Observation infrastructure - Advanced host-based Centralized data store and software pattern identification