Proceedings of the 7th International Conference on Autonomic Computing 2010
DOI: 10.1145/1809049.1809053
|View full text |Cite
|
Sign up to set email alerts
|

Autonomic mix-aware provisioning for non-stationary data center workloads

Abstract: Online Internet applications see dynamic workloads that fluctuate over multiple time scales. This paper argues that the non-stationarity in Internet application workloads, which causes the request mix to change over time, can have a significant impact on the overall processing demands imposed on data center servers. We propose a novel mix-aware dynamic provisioning technique that handles both the non-stationarity in the workload as well as changes in request volumes when allocating server capacity in Internet … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
73
0

Year Published

2013
2013
2023
2023

Publication Types

Select...
4
4
2

Relationship

0
10

Authors

Journals

citations
Cited by 121 publications
(73 citation statements)
references
References 24 publications
0
73
0
Order By: Relevance
“…A queueing network approach is taken in [66] to provision resources for data-center applications. As the workload mix is observed to fluctuate over time, the queueing model is enhanced with a clustering algorithm that determines the workload mix.…”
Section: Performance Modelsmentioning
confidence: 99%
“…A queueing network approach is taken in [66] to provision resources for data-center applications. As the workload mix is observed to fluctuate over time, the queueing model is enhanced with a clustering algorithm that determines the workload mix.…”
Section: Performance Modelsmentioning
confidence: 99%
“…However, they all come with the limitations that are proper of the employed techniques: [35], [36] exploit queuing theory, but avoiding to explicitly modeling data contention; [37], [38], [39] rely only on machine learning, thus being prone to poor effectiveness when facing previously unseen workloads.…”
Section: Reconfiguration Managermentioning
confidence: 99%
“…Weighted metrics: As pointed out in (Singh et al, 2010), provisioning decisions solely made on the basis of request rate or percentage of CPU usage can incur errors by under-or over-provisioning an application. We propose instead to use a collection of metrics (e.g.…”
Section: Feedback Provisioningmentioning
confidence: 99%