nuKSM: NUMA-aware Memory De-duplication on Multi-socket Servers

An operating system has many memory management goals including reducing memory access latency, and reducing memory footprint. These goals can conflict with each other when independent subsystems optimize them in silos. In this work, we report one such conflict that appears between memory de-duplicat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT) S. 258 - 273
Hauptverfasser: Panda, Akash, Panwar, Ashish, Basu, Arkaprava
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.09.2021
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract An operating system has many memory management goals including reducing memory access latency, and reducing memory footprint. These goals can conflict with each other when independent subsystems optimize them in silos. In this work, we report one such conflict that appears between memory de-duplication and NUMA (non-uniform memory access) management. Linux's memory de-duplication subsystem, namely KSM, is NUMA unaware. Consequently, while de-duplicating pages across NUMA nodes, it can place de-duplicated pages in a manner that can lead to significant performance variations, unfairness, and subvert process priority. Toward this, we introduce NUMA-aware KSM, a.k.a., nuKSM, that makes judicious decisions about the placement of de-duplicated pages to reduce the impact of NUMA, unfairness, and avoid priority subversion. Independent of the NUMA effects, we observed that KSM scales poorly to systems with larger memory sizes due to its centralized design. Thus, we extended nuKSM to adopt a de-centralized design.
AbstractList An operating system has many memory management goals including reducing memory access latency, and reducing memory footprint. These goals can conflict with each other when independent subsystems optimize them in silos. In this work, we report one such conflict that appears between memory de-duplication and NUMA (non-uniform memory access) management. Linux's memory de-duplication subsystem, namely KSM, is NUMA unaware. Consequently, while de-duplicating pages across NUMA nodes, it can place de-duplicated pages in a manner that can lead to significant performance variations, unfairness, and subvert process priority. Toward this, we introduce NUMA-aware KSM, a.k.a., nuKSM, that makes judicious decisions about the placement of de-duplicated pages to reduce the impact of NUMA, unfairness, and avoid priority subversion. Independent of the NUMA effects, we observed that KSM scales poorly to systems with larger memory sizes due to its centralized design. Thus, we extended nuKSM to adopt a de-centralized design.
Author Panda, Akash
Basu, Arkaprava
Panwar, Ashish
Author_xml – sequence: 1
  givenname: Akash
  surname: Panda
  fullname: Panda, Akash
  email: akashpanda@iisc.ac.in
  organization: Indian Institute of Science,Department of Computer Science and Automation
– sequence: 2
  givenname: Ashish
  surname: Panwar
  fullname: Panwar, Ashish
  email: ashishpanwar@iisc.ac.in
  organization: Indian Institute of Science,Department of Computer Science and Automation
– sequence: 3
  givenname: Arkaprava
  surname: Basu
  fullname: Basu, Arkaprava
  email: arkapravab@iisc.ac.in
  organization: Indian Institute of Science,Department of Computer Science and Automation
BookMark eNotzN1KwzAYgOEICursFehBbyAzP02-xhMpdf7gqsK245FkXyDYtSNtld29gsILz9l7SU67vkNCbjibc87M7UdVr5UAo-aCCT5njAl9QjIDJddaFYWAEs5JNgzRMQUgQRh-Qe676XXV3OVvm6ai9tsmzBvc9-mYPyDdTYc2ejvGvst_a6Z2jHTo_SeO-QrTF6bhipwF2w6Y_Tsjm8fFun6my_enl7paUitKNdJd4YW3AblTFpXUMmjDnEOuuXYCrEFrQolGADLNmNfovAMECN6Hwkg5I9d_34iI20OKe5uOW6O0ZBLkD1rTSpw
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/PACT52795.2021.00026
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665442787
1665442786
EndPage 273
ExternalDocumentID 9563037
Genre orig-research
GrantInformation_xml – fundername: Microsoft Research India
  funderid: 10.13039/100006112
GroupedDBID 6IE
6IL
ACM
ALMA_UNASSIGNED_HOLDINGS
APO
CBEJK
LHSKQ
RIE
RIL
ID FETCH-LOGICAL-a285t-d4c2cafe1b5ae5363f690bbe1616b27a9ea9f8e927e0600c6ebcb7e77fccf4933
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000758464500019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Tue May 06 03:33:13 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a285t-d4c2cafe1b5ae5363f690bbe1616b27a9ea9f8e927e0600c6ebcb7e77fccf4933
PageCount 16
ParticipantIDs ieee_primary_9563037
PublicationCentury 2000
PublicationDate 2021-Sept.
PublicationDateYYYYMMDD 2021-09-01
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-Sept.
PublicationDecade 2020
PublicationTitle 2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT)
PublicationTitleAbbrev PACT
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib057737291
Score 2.186868
Snippet An operating system has many memory management goals including reducing memory access latency, and reducing memory footprint. These goals can conflict with...
SourceID ieee
SourceType Publisher
StartPage 258
SubjectTerms Linux
Memory de duplication
Memory management
Operating systems
Parallel architectures
Process control
Servers
Virtualization
Title nuKSM: NUMA-aware Memory De-duplication on Multi-socket Servers
URI https://ieeexplore.ieee.org/document/9563037
WOSCitedRecordID wos000758464500019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5t8eBJpRXf5ODR2N08NhsvUqpF0JaCrfRW8piACFupu4r_3mRbqwcvQg4hEMJkQmYmme8bhM4hkSYPvj3hlFvCrWFEZ9YST0FyrjT4mnbx6UGORvlspsYNdLHBwgBAnXwGl7Fb_-W7ha3iU1lXRTIrJpuoKWW2wmp9nx0hY70Vla7RcWmiuuNefyKoVCJEgTSNRIWRQeFXDZXahAx2_rf4Lur8YPHweGNl9lADija6Lqr7x-EVHk2HPaI_9BLwMKbMfuIbIK7a_Enj0GqILQlKeIESx6shOHwdNB3cTvp3ZF0KgWiai5I4bqnVHlIjNAiWMR-iWmMg-GuZoVIr0MrnoKiEJLgwNgNjjQQpvbWeK8b2UatYFHCAcCyFzrhLXB4ss3ZhDtd5KiIxGoVMuUPUjsLPX1dsF_O13Ed_Dx-j7bi7q6yrE9QqlxWcoi37Xj6_Lc9qFX0Bt0eSBA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFH7MKehJZRN_24NH49o0bRovMqZjsrUM3GS3kaSvIEIns1X87026Oj14EXIIgRCSF_Jekvd9H8AlulxFJrYnjDJNmFY-kaHWJKPIGRMSs4p28WnEkySazcS4AVdrLAwiVslneG2r1V9-utClfSrrCEtm5fMN2LTKWTVa63v3BNwqrgivxsd5ruiMu71JQLkIzD2Qepaq0HIo_FJRqZxIf_d_w-9B-weN54zXfmYfGpi34DYvh4_xjZNM4y6RH3KJTmyTZj-dOyRpuf6VdkypQLbEmOEFC8ceDibka8O0fz_pDUgthkAkjYKCpExTLTP0VCAx8EM_M_dapdBEbKGiXAqUIotQUI6uCWJ0iEorjpxnWmdM-P4BNPNFjofgWDF0n6VuGhnfLFPTh8nICyw1GsVQpEfQspOfv674Lub1vI__br6A7cEkHs1HD8nwBHbsSq9ysE6hWSxLPIMt_V48vy3PK3N9AYYXlU0
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2021+30th+International+Conference+on+Parallel+Architectures+and+Compilation+Techniques+%28PACT%29&rft.atitle=nuKSM%3A+NUMA-aware+Memory+De-duplication+on+Multi-socket+Servers&rft.au=Panda%2C+Akash&rft.au=Panwar%2C+Ashish&rft.au=Basu%2C+Arkaprava&rft.date=2021-09-01&rft.pub=IEEE&rft.spage=258&rft.epage=273&rft_id=info:doi/10.1109%2FPACT52795.2021.00026&rft.externalDocID=9563037