Performance modeling and analysis of flash-based storage devices

Huang, H. Howie; Li, Shan; Szalay, A. S.; Terzis, Andreas

doi:10.1109/msst.2011.5937213

Cited by 49 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CART trees predict performance of the SSD disk with ε ∈ (0.17, ..., 0.25) [19] and the traditional hard drive with ε ∈ (0.17, ..., 0.38) [40]. However, collecting the training set (X, Y ) requires running the system in many different configurations, which is overly time-consuming and costly.…”

Section: Related Workmentioning

confidence: 99%

“…Thus we compare our approach to a wider group of models, including analytical and statistical models, and models of distributed systems. These models have ε ∈ (0.02, ..., 0.15) for CPU-bound workloads [11], [24], [34], [42], [21], [43], and ε ∈ (0.12, ..., 0.34) for I/O-bound workloads [40], [14], [19], [28], [29]. Our models have accuracy ε ∈ (0.032, ..., 0.122) for CPUbound and ε ∈ (0.262, ..., 0.269) for disk I/O-bound workloads, which is comparable to the state of the art.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automated analysis of multithreaded programs for performance modeling

Tarvo

Reiss

2014

Proceedings of the 29th ACM/IEEE International Conference on Automated Software Engineering

View full text Add to dashboard Cite

The behavior of multithreaded programs is often difficult to understand and predict. Synchronization operations and limited computational resources combine to produce complex non-linear dependencies between a program's configuration parameters and its performance. Performance models are used to understand these dependencies. Such models are complex, and constructing them requires a solid understanding of the program's behavior. As a result, building models of complex applications manually is extremely timeconsuming and error-prone. In this paper we demonstrate that such models can be built automatically.This paper presents our approach for automatically modeling multithreaded programs. Our framework uses a combination of static and dynamic analyses of a single representative run of a system to build a model that can then be explored under a variety of configurations. We show how the models are constructed and show they accurately predict the performance of various multithreaded programs, including complex industrial applications.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Automated analysis of multithreaded programs for performance modeling

Tarvo

Reiss

2014

Proceedings of the 29th ACM/IEEE International Conference on Automated Software Engineering

View full text Add to dashboard Cite

show abstract

“…1) Hardware Layer: for a general overview concerning hard disks, we refer to [5]; analogue concepts hold for solid state disks [6]. The two major aspects of mass storages are bandwidth and latency.…”

Section: B Disk Accessmentioning

confidence: 99%

FASTDD: An Open Source Forensic Imaging Tool

Bertasi

Zago

2013

2013 International Conference on Availability, Reliability and Security

View full text Add to dashboard Cite

Nowadays electronic devices are ubiquitous and their storage capacity has steadily been growing over time. It is not surprising that acquiring a copy of the storage of such devices has become a crucial task in digital forensics, resulting in the development of fast and still reliable tools. In this work we introduce fastdd, a new disk imaging tool that achieves unmatched performance while having fewer resource requirements than the currently available tools and being designed to be easily extendable. After reviewing the existing programs for disk image acquisition, we compare their functionalities and performance to fastdd, demonstrating that our tool is fast, lightweight, hence suitable to be used in embedded devices.

show abstract

“…For this reason, many SSD manufactures produce various types of their own SSDs [3]. SSD manufactures release a little information on SSDs such as bandwidth, capacity, and so on.…”

Section: Introductionmentioning

confidence: 99%

The uFLIP benchmark revisited for evaluating SSDs

Kang

Cha

et al. 2015

Int J Communication

View full text Add to dashboard Cite

SUMMARYSolid-state drives (SSDs) provide higher bandwidth and lower access latency than hard disk drives (HDDs) and thus have been rapidly replacing HDDs. SSD manufacturers, which produce different types of SSDs, do not open their SSD architecture and control firmware in detail. To find the best SSD for a given application, it is necessary to compare and analyze the performances of different kinds of SSDs. A benchmark is widely used to analyze the storage devices performance. However, most existing benchmarks are mainly targeted for HDDs. The uFLIP (understanding Flash IO Patterns) is a benchmark proposed to consider flash devices' characteristics. In this paper, we first exploit the uFLIP benchmark to analyze and to evaluate the performances of different types of SSDs. Through extensive experiments, we have identified common SSD characteristics: (1) the input/output (IO) size and queue depth affect the parallelism that is an inherent characteristic in SSDs; (2) the size of SSDs access space considerably affects the SSDs performance. Then, via a series of experiments, we verify whether the uFLIP benchmark could correctly characterize applications by its micro-benchmarks. The results reveal that the performance of the uFLIP micro-benchmarks, produced to have features similar to that of a target application, is quite different from the performance of the target application.

show abstract

Performance modeling and analysis of flash-based storage devices

Cited by 49 publications

References 28 publications

Automated analysis of multithreaded programs for performance modeling

Automated analysis of multithreaded programs for performance modeling

FASTDD: An Open Source Forensic Imaging Tool

The uFLIP benchmark revisited for evaluating SSDs

Contact Info

Product

Resources

About