Modeling Performance and Energy trade-offs in Online Data-Intensive Applications

We consider energy minimization for data-intensive applications run on large number of servers, for given performance guarantees. We consider a system, where each incoming application is sent to a set of servers, and is considered to be completed if a subset of them finish serving it. We consider a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Badita, Ajay, Jinan, Rooji, Vamanan, Balajee, Parag, Parimal
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Badita, Ajay
Jinan, Rooji
Vamanan, Balajee
Parag, Parimal
description We consider energy minimization for data-intensive applications run on large number of servers, for given performance guarantees. We consider a system, where each incoming application is sent to a set of servers, and is considered to be completed if a subset of them finish serving it. We consider a simple case when each server core has two speed levels, where the higher speed can be achieved by higher power for each core independently. The core selects one of the two speeds probabilistically for each incoming application request. We model arrival of application requests by a Poisson process, and random service time at the server with independent exponential random variables. Our model and analysis generalizes to today's state-of-the-art in CPU energy management where each core can independently select a speed level from a set of supported speeds and corresponding voltages. The performance metrics under consideration are the mean number of applications in the system and the average energy expenditure. We first provide a tight approximation to study this previously intractable problem and derive closed form approximate expressions for the performance metrics when service times are exponentially distributed. Next, we study the trade-off between the approximate mean number of applications and energy expenditure in terms of the switching probability.
doi_str_mv 10.48550/arxiv.2108.08199
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2108_08199</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2108_08199</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-fdd745aa12a4f1c834e238f782efacd6e63ee71c4807e71e71527e616bb479743</originalsourceid><addsrcrecordid>eNotj71qwzAURrV0KGkfoFP1AnL1Z0keQ5q2gYRkyG5upKsgcGQjm9C8fd208MFZPg4cQl4Er7Sra_4G5TtdKym4q7gTTfNIDrs-YJfymR6wxL5cIHukkANdZyznG50KBGR9jCNNme7z_EX6DhOwTZ4wj-mKdDkMXfIwpT6PT-QhQjfi8z8X5PixPq6-2Hb_uVkttwyMbVgMweoaQEjQUXinNErlonUSI_hg0ChEK7x23M6cV0uLRpjTSdvGarUgr3_ae1I7lHSBcmt_09p7mvoBVXVJpA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Modeling Performance and Energy trade-offs in Online Data-Intensive Applications</title><source>arXiv.org</source><creator>Badita, Ajay ; Jinan, Rooji ; Vamanan, Balajee ; Parag, Parimal</creator><creatorcontrib>Badita, Ajay ; Jinan, Rooji ; Vamanan, Balajee ; Parag, Parimal</creatorcontrib><description>We consider energy minimization for data-intensive applications run on large number of servers, for given performance guarantees. We consider a system, where each incoming application is sent to a set of servers, and is considered to be completed if a subset of them finish serving it. We consider a simple case when each server core has two speed levels, where the higher speed can be achieved by higher power for each core independently. The core selects one of the two speeds probabilistically for each incoming application request. We model arrival of application requests by a Poisson process, and random service time at the server with independent exponential random variables. Our model and analysis generalizes to today's state-of-the-art in CPU energy management where each core can independently select a speed level from a set of supported speeds and corresponding voltages. The performance metrics under consideration are the mean number of applications in the system and the average energy expenditure. We first provide a tight approximation to study this previously intractable problem and derive closed form approximate expressions for the performance metrics when service times are exponentially distributed. Next, we study the trade-off between the approximate mean number of applications and energy expenditure in terms of the switching probability.</description><identifier>DOI: 10.48550/arxiv.2108.08199</identifier><language>eng</language><subject>Computer Science - Distributed, Parallel, and Cluster Computing ; Computer Science - Information Retrieval</subject><creationdate>2021-08</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2108.08199$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2108.08199$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Badita, Ajay</creatorcontrib><creatorcontrib>Jinan, Rooji</creatorcontrib><creatorcontrib>Vamanan, Balajee</creatorcontrib><creatorcontrib>Parag, Parimal</creatorcontrib><title>Modeling Performance and Energy trade-offs in Online Data-Intensive Applications</title><description>We consider energy minimization for data-intensive applications run on large number of servers, for given performance guarantees. We consider a system, where each incoming application is sent to a set of servers, and is considered to be completed if a subset of them finish serving it. We consider a simple case when each server core has two speed levels, where the higher speed can be achieved by higher power for each core independently. The core selects one of the two speeds probabilistically for each incoming application request. We model arrival of application requests by a Poisson process, and random service time at the server with independent exponential random variables. Our model and analysis generalizes to today's state-of-the-art in CPU energy management where each core can independently select a speed level from a set of supported speeds and corresponding voltages. The performance metrics under consideration are the mean number of applications in the system and the average energy expenditure. We first provide a tight approximation to study this previously intractable problem and derive closed form approximate expressions for the performance metrics when service times are exponentially distributed. Next, we study the trade-off between the approximate mean number of applications and energy expenditure in terms of the switching probability.</description><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><subject>Computer Science - Information Retrieval</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71qwzAURrV0KGkfoFP1AnL1Z0keQ5q2gYRkyG5upKsgcGQjm9C8fd208MFZPg4cQl4Er7Sra_4G5TtdKym4q7gTTfNIDrs-YJfymR6wxL5cIHukkANdZyznG50KBGR9jCNNme7z_EX6DhOwTZ4wj-mKdDkMXfIwpT6PT-QhQjfi8z8X5PixPq6-2Hb_uVkttwyMbVgMweoaQEjQUXinNErlonUSI_hg0ChEK7x23M6cV0uLRpjTSdvGarUgr3_ae1I7lHSBcmt_09p7mvoBVXVJpA</recordid><startdate>20210818</startdate><enddate>20210818</enddate><creator>Badita, Ajay</creator><creator>Jinan, Rooji</creator><creator>Vamanan, Balajee</creator><creator>Parag, Parimal</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210818</creationdate><title>Modeling Performance and Energy trade-offs in Online Data-Intensive Applications</title><author>Badita, Ajay ; Jinan, Rooji ; Vamanan, Balajee ; Parag, Parimal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-fdd745aa12a4f1c834e238f782efacd6e63ee71c4807e71e71527e616bb479743</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Distributed, Parallel, and Cluster Computing</topic><topic>Computer Science - Information Retrieval</topic><toplevel>online_resources</toplevel><creatorcontrib>Badita, Ajay</creatorcontrib><creatorcontrib>Jinan, Rooji</creatorcontrib><creatorcontrib>Vamanan, Balajee</creatorcontrib><creatorcontrib>Parag, Parimal</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Badita, Ajay</au><au>Jinan, Rooji</au><au>Vamanan, Balajee</au><au>Parag, Parimal</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Modeling Performance and Energy trade-offs in Online Data-Intensive Applications</atitle><date>2021-08-18</date><risdate>2021</risdate><abstract>We consider energy minimization for data-intensive applications run on large number of servers, for given performance guarantees. We consider a system, where each incoming application is sent to a set of servers, and is considered to be completed if a subset of them finish serving it. We consider a simple case when each server core has two speed levels, where the higher speed can be achieved by higher power for each core independently. The core selects one of the two speeds probabilistically for each incoming application request. We model arrival of application requests by a Poisson process, and random service time at the server with independent exponential random variables. Our model and analysis generalizes to today's state-of-the-art in CPU energy management where each core can independently select a speed level from a set of supported speeds and corresponding voltages. The performance metrics under consideration are the mean number of applications in the system and the average energy expenditure. We first provide a tight approximation to study this previously intractable problem and derive closed form approximate expressions for the performance metrics when service times are exponentially distributed. Next, we study the trade-off between the approximate mean number of applications and energy expenditure in terms of the switching probability.</abstract><doi>10.48550/arxiv.2108.08199</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2108.08199
ispartof
issn
language eng
recordid cdi_arxiv_primary_2108_08199
source arXiv.org
subjects Computer Science - Distributed, Parallel, and Cluster Computing
Computer Science - Information Retrieval
title Modeling Performance and Energy trade-offs in Online Data-Intensive Applications
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T13%3A24%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Modeling%20Performance%20and%20Energy%20trade-offs%20in%20Online%20Data-Intensive%20Applications&rft.au=Badita,%20Ajay&rft.date=2021-08-18&rft_id=info:doi/10.48550/arxiv.2108.08199&rft_dat=%3Carxiv_GOX%3E2108_08199%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true