skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Storage System Trace Characterization, Compression, and Synthesis using Machine Learning – An Extended Abstract
This study addresses the knowledge gap in request-level storage trace analysis by incorporating workload characterization, com- pression, and synthesis. The aim is to better understand workload behavior and provide unique workloads for storage system test- ing under different scenarios. Machine learning techniques like K-means clustering and PCA analysis are employed to understand trace properties and reduce manual workload selection. By gener- ating synthetic workloads, the proposed method facilitates simu- lation and modeling-based studies of storage systems, especially for emerging technologies like Storage Class Memory (SCM) with limited workload availability.  more » « less
Award ID(s):
1956229
PAR ID:
10413957
Author(s) / Creator(s):
Date Published:
Journal Name:
International Conference on Principles of Advanced Discrete Simulation (PADS)
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, 36th International Conference on Massive Storage Systems and Technology (MSST 2020))
    Understanding the different workloaddependent factors that impact the latency or reliability of a storage system is essential for SLA satisfaction and fair resource provisioning. However, due to the volatility of system behavior under multiple workloads, determining even the number of concurrent types of workload functions, a necessary precursor to workload separation, is an unsolved problem in the general case. We introduce CENSUS, a novel classification framework that combines time-series analysis with gradient boosting to identify the number of functional workloads in a shared storage system by projecting workload traces into a high-dimensional feature representation space. We show that CENSUS can distinguish the number of interleaved workloads in a real-world trace segment with up to 95% accuracy, leading to a decrement of the mean square error to as little as 5% compared to the 
    more » « less
  2. ; (, Machine Learning for Systems)
    Identifying the characteristics of a storage workload is critical for resource provisioning for metrics including performance, reliability, and utilization. Although multi-tenant systems are increasingly commonplace, characterization of multiple workloads within a single system trace is difficult because workloads are highly dynamic and typically not labeled. We show that, by converting a block I/O workload to a signal and applying blind source separation, we are able to successfully separate many application workloads. 
    more » « less
  3. ; (, Machine Learning in Systems)
    Identifying the characteristics of a storage workload is critical for resource provisioning for metrics including performance, reliability, and utilization. Although multi-tenant systems are increasingly commonplace, characterization of multiple workloads within a single system trace is difficult because workloads are highly dynamic and typically not labeled. We show that, by converting a block I/O workload to a signal and applying blind source separation, we are able to successfully separate many application workloads. 
    more » « less
  4. ; (, Machine Learning for Systems)
    Identifying the characteristics of a storage workload is critical for resource provisioning for metrics including performance, reliability, and utilization. Although multi-tenant systems are increasingly commonplace, characterization of multiple workloads within a single system trace is difficult because workloads are highly dynamic and typically not labeled. We show that, by converting a block I/O workload to a signal and applying blind source separation, we are able to successfully separate many application workloads. 
    more » « less
  5. ; ; ; (, ACM Transactions on Modeling and Performance Evaluation of Computing Systems)
    Traditional workload analysis uses discrete times measured by data accesses. An example is the classic independent reference model (IRM). Effective solutions have been developed to model workloads with stochastic access patterns, but they incur a high cost for Zipfian workloads, which may contain millions of items each accessed with a different frequency. This paper first presents a continuous-time model of locality for workloads with stochastic access patterns. It shows that two previous techniques by Dan and Towsley and by Denning and Schwartz can be interpreted as a single model using different discrete times. Using continuous time, it derives a closed-form solution for an item and a general solution that is a differentiable function. In addition, the paper presents an approximation technique by grouping items into partitions. When evaluated using Zipfian workloads, it shows that a workload with millions of items can be approximated using a small number of partitions, and the continuous-time model has greater accuracy and is faster to compute numerically. For the largest data size verifiable using trace generation and simulation, the new techniques reduce the time of locality analysis by 6 orders of magnitude. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email