2019
DOI: 10.1016/j.jss.2018.11.006
|View full text |Cite
|
Sign up to set email alerts
|

Combining malleability and I/O control mechanisms to enhance the execution of multiple applications

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
1
1

Relationship

2
4

Authors

Journals

citations
Cited by 6 publications
(6 citation statements)
references
References 48 publications
0
6
0
Order By: Relevance
“…By comparing the exclusively-collected and the shared-collected metrics, the system is able to identify if there is performance degradation. Using this information, the scheduler can make decisions about the scheduling (Aupy et al, 2019; Carretero et al, 2020; Cascajo et al, 2019, 2021, 2022; Ekanadham et al, 1995; Sing David, 2019), for instance migrating one of them to avoid the interference, or evaluating if that interference is mitigated when the number of processes is increased or decreased for one of them.…”
Section: Building Synthetic Micro-benchmarks: Application Clonesmentioning
confidence: 99%
See 1 more Smart Citation
“…By comparing the exclusively-collected and the shared-collected metrics, the system is able to identify if there is performance degradation. Using this information, the scheduler can make decisions about the scheduling (Aupy et al, 2019; Carretero et al, 2020; Cascajo et al, 2019, 2021, 2022; Ekanadham et al, 1995; Sing David, 2019), for instance migrating one of them to avoid the interference, or evaluating if that interference is mitigated when the number of processes is increased or decreased for one of them.…”
Section: Building Synthetic Micro-benchmarks: Application Clonesmentioning
confidence: 99%
“…Efficient balancing of computational and I/O resources is one of the existing challenges in the HPC infrastructures (Panziera, 2017). This balance depends on different factors, such as the interaction between the hardware components, the software stack and the performed operations by the applications (Sing David, 2019). All of these factors may interfere with the I/O producing performance variations.…”
Section: Building Synthetic Micro-benchmarks: Application Clonesmentioning
confidence: 99%
“…In the presence of competing applications, other solutions try to use the elasticity of applications and resources. Recently, Singh and Carretero Singh and Carretero (2019) proposed a middleware that would allow using the malleability of an application to shift forward or backward the time when an application is supposed to do its I/O movements. The solution AHPI/OS Isaila et al (2008) allows using elastic partitions that can scale up or down the number of storage resources available to an application.…”
Section: Architecture and I/o Optimizationmentioning
confidence: 99%
“…A second solution is to use the elasticity of applications or file system levels. Singh et al [25] present a strategy that combines I/O conflict prediction and application malleability. By means of prediction, the future I/O conflicts are forecast.…”
Section: Related Workmentioning
confidence: 99%
“…• We pick the proportion β of applications with low I/O load at random on [0, 1] (0 meaning all applications have high I/O load, 1 meaning they all have low I/O load). • We generate the number of applications of each workload uniformly at random in [25,100].…”
Section: Synthetic Workload Generationmentioning
confidence: 99%