Reducing Tail Latency via Safe and Simple Duplication
Duplication can be a powerful strategy for overcoming stragglers in cloud services, but is often used conservatively because of the risk of overloading the system. We present duplicate-aware scheduling or DAS, which makes duplication safe and easy to use, by leveraging the two well-known primitives...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| 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 | Bashir, Hafiz Mohsin Faisal, Abdullah Bin Jamshed, Muhammad Asim Vondras, Peter Iftikhar, Ali Musa Qazi, Ihsan Ayyub Dogar, Fahad R |
| description | Duplication can be a powerful strategy for overcoming stragglers in cloud
services, but is often used conservatively because of the risk of overloading
the system. We present duplicate-aware scheduling or DAS, which makes
duplication safe and easy to use, by leveraging the two well-known primitives
of prioritization and purging. To support DAS across diverse layers of a cloud
system (e.g., network, storage, etc), we propose the D-Stage abstraction, which
decouples the duplication policy from the mechanism, and facilitates working
with legacy layers of a system. Using this abstraction, we evaluate the
benefits of DAS for two data parallel applications (HDFS, an in-memory workload
generator) and a network function (snort-based IDS cluster). Our experiments on
the public cloud and Emulab show that DAS is safe to use, and the tail latency
improvement holds across a wide range of workloads |
| doi_str_mv | 10.48550/arxiv.1905.13352 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1905_13352</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1905_13352</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-67919b45923578ea6e3d363723b51ca7729677b9b9e902b6f56bd1353d0ca7543</originalsourceid><addsrcrecordid>eNotzr1uwjAUhmEvDBX0AjrhG0iwfXJsPFZAf6RISJA9Oo6dylIIUUgicvdtaadveKVPD2MvUqTZFlFsqL_HKZVWYCoBUD0xPAU_VrH94gXFhuc0hLaa-RSJn6kOnFrPz_HSNYHvx66JFQ3x2q7YoqbmFp7_d8mKt0Ox-0jy4_vn7jVPSBuVaGOldRlaBWi2gXQADxqMAoeyImOU1cY462ywQjldo3ZeAoIXPxUzWLL13-3DXXZ9vFA_l7_-8uGHb-N4PfQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Reducing Tail Latency via Safe and Simple Duplication</title><source>arXiv.org</source><creator>Bashir, Hafiz Mohsin ; Faisal, Abdullah Bin ; Jamshed, Muhammad Asim ; Vondras, Peter ; Iftikhar, Ali Musa ; Qazi, Ihsan Ayyub ; Dogar, Fahad R</creator><creatorcontrib>Bashir, Hafiz Mohsin ; Faisal, Abdullah Bin ; Jamshed, Muhammad Asim ; Vondras, Peter ; Iftikhar, Ali Musa ; Qazi, Ihsan Ayyub ; Dogar, Fahad R</creatorcontrib><description>Duplication can be a powerful strategy for overcoming stragglers in cloud
services, but is often used conservatively because of the risk of overloading
the system. We present duplicate-aware scheduling or DAS, which makes
duplication safe and easy to use, by leveraging the two well-known primitives
of prioritization and purging. To support DAS across diverse layers of a cloud
system (e.g., network, storage, etc), we propose the D-Stage abstraction, which
decouples the duplication policy from the mechanism, and facilitates working
with legacy layers of a system. Using this abstraction, we evaluate the
benefits of DAS for two data parallel applications (HDFS, an in-memory workload
generator) and a network function (snort-based IDS cluster). Our experiments on
the public cloud and Emulab show that DAS is safe to use, and the tail latency
improvement holds across a wide range of workloads</description><identifier>DOI: 10.48550/arxiv.1905.13352</identifier><language>eng</language><subject>Computer Science - Distributed, Parallel, and Cluster Computing ; Computer Science - Networking and Internet Architecture</subject><creationdate>2019-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1905.13352$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1905.13352$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bashir, Hafiz Mohsin</creatorcontrib><creatorcontrib>Faisal, Abdullah Bin</creatorcontrib><creatorcontrib>Jamshed, Muhammad Asim</creatorcontrib><creatorcontrib>Vondras, Peter</creatorcontrib><creatorcontrib>Iftikhar, Ali Musa</creatorcontrib><creatorcontrib>Qazi, Ihsan Ayyub</creatorcontrib><creatorcontrib>Dogar, Fahad R</creatorcontrib><title>Reducing Tail Latency via Safe and Simple Duplication</title><description>Duplication can be a powerful strategy for overcoming stragglers in cloud
services, but is often used conservatively because of the risk of overloading
the system. We present duplicate-aware scheduling or DAS, which makes
duplication safe and easy to use, by leveraging the two well-known primitives
of prioritization and purging. To support DAS across diverse layers of a cloud
system (e.g., network, storage, etc), we propose the D-Stage abstraction, which
decouples the duplication policy from the mechanism, and facilitates working
with legacy layers of a system. Using this abstraction, we evaluate the
benefits of DAS for two data parallel applications (HDFS, an in-memory workload
generator) and a network function (snort-based IDS cluster). Our experiments on
the public cloud and Emulab show that DAS is safe to use, and the tail latency
improvement holds across a wide range of workloads</description><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><subject>Computer Science - Networking and Internet Architecture</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr1uwjAUhmEvDBX0AjrhG0iwfXJsPFZAf6RISJA9Oo6dylIIUUgicvdtaadveKVPD2MvUqTZFlFsqL_HKZVWYCoBUD0xPAU_VrH94gXFhuc0hLaa-RSJn6kOnFrPz_HSNYHvx66JFQ3x2q7YoqbmFp7_d8mKt0Ox-0jy4_vn7jVPSBuVaGOldRlaBWi2gXQADxqMAoeyImOU1cY462ywQjldo3ZeAoIXPxUzWLL13-3DXXZ9vFA_l7_-8uGHb-N4PfQ</recordid><startdate>20190530</startdate><enddate>20190530</enddate><creator>Bashir, Hafiz Mohsin</creator><creator>Faisal, Abdullah Bin</creator><creator>Jamshed, Muhammad Asim</creator><creator>Vondras, Peter</creator><creator>Iftikhar, Ali Musa</creator><creator>Qazi, Ihsan Ayyub</creator><creator>Dogar, Fahad R</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190530</creationdate><title>Reducing Tail Latency via Safe and Simple Duplication</title><author>Bashir, Hafiz Mohsin ; Faisal, Abdullah Bin ; Jamshed, Muhammad Asim ; Vondras, Peter ; Iftikhar, Ali Musa ; Qazi, Ihsan Ayyub ; Dogar, Fahad R</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-67919b45923578ea6e3d363723b51ca7729677b9b9e902b6f56bd1353d0ca7543</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Distributed, Parallel, and Cluster Computing</topic><topic>Computer Science - Networking and Internet Architecture</topic><toplevel>online_resources</toplevel><creatorcontrib>Bashir, Hafiz Mohsin</creatorcontrib><creatorcontrib>Faisal, Abdullah Bin</creatorcontrib><creatorcontrib>Jamshed, Muhammad Asim</creatorcontrib><creatorcontrib>Vondras, Peter</creatorcontrib><creatorcontrib>Iftikhar, Ali Musa</creatorcontrib><creatorcontrib>Qazi, Ihsan Ayyub</creatorcontrib><creatorcontrib>Dogar, Fahad R</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bashir, Hafiz Mohsin</au><au>Faisal, Abdullah Bin</au><au>Jamshed, Muhammad Asim</au><au>Vondras, Peter</au><au>Iftikhar, Ali Musa</au><au>Qazi, Ihsan Ayyub</au><au>Dogar, Fahad R</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Reducing Tail Latency via Safe and Simple Duplication</atitle><date>2019-05-30</date><risdate>2019</risdate><abstract>Duplication can be a powerful strategy for overcoming stragglers in cloud
services, but is often used conservatively because of the risk of overloading
the system. We present duplicate-aware scheduling or DAS, which makes
duplication safe and easy to use, by leveraging the two well-known primitives
of prioritization and purging. To support DAS across diverse layers of a cloud
system (e.g., network, storage, etc), we propose the D-Stage abstraction, which
decouples the duplication policy from the mechanism, and facilitates working
with legacy layers of a system. Using this abstraction, we evaluate the
benefits of DAS for two data parallel applications (HDFS, an in-memory workload
generator) and a network function (snort-based IDS cluster). Our experiments on
the public cloud and Emulab show that DAS is safe to use, and the tail latency
improvement holds across a wide range of workloads</abstract><doi>10.48550/arxiv.1905.13352</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1905.13352 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1905_13352 |
| source | arXiv.org |
| subjects | Computer Science - Distributed, Parallel, and Cluster Computing Computer Science - Networking and Internet Architecture |
| title | Reducing Tail Latency via Safe and Simple Duplication |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T13%3A00%3A11IST&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=Reducing%20Tail%20Latency%20via%20Safe%20and%20Simple%20Duplication&rft.au=Bashir,%20Hafiz%20Mohsin&rft.date=2019-05-30&rft_id=info:doi/10.48550/arxiv.1905.13352&rft_dat=%3Carxiv_GOX%3E1905_13352%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 |