TeraHeap
Uložené v:
| Názov: | TeraHeap |
|---|---|
| Autori: | Kolokasis, Iacovos G., Evdorou, Giannos, Akram, Shoaib, Kozanitis, Christos, Papagiannis, Anastasios, Zakkak, Foivos S., Pratikakis, Polyvios, Bilas, Angelos |
| Zdroj: | ACM Transactions on Programming Languages and Systems |
| Rok vydania: | 2024 |
| Zbierka: | Australian National University: ANU Digital Collections |
| Predmety: | fast storage devices, garbage collection, Java Virtual Machine (JVM), large analytics, large managed heaps, memory hierarchy, memory management, serialization |
| Popis: | Big data analytics frameworks, such as Spark and Giraph, need to process and cache massive datasets that do not always fit on the managed heap. Therefore, frameworks temporarily move long-lived objects outside the heap (off-heap) on a fast storage device. However, this practice results in (1) high serialization/deserialization (S/D) cost and (2) high memory pressure when off-heap objects are moved back for processing. In this article, we propose TeraHeap, a system that eliminates S/D overhead and expensive GC scans for a large portion of objects in analytics frameworks. TeraHeap relies on three concepts: (1) It eliminates S/D by extending the managed runtime (JVM) to use a second high-capacity heap (H2) over a fast storage device. (2) It offers a simple hint-based interface, allowing analytics frameworks to leverage object knowledge to populate H2. (3) It reduces GC cost by fencing the collector from scanning H2 objects while maintaining the illusion of a single managed heap, ensuring memory safety. We implement TeraHeap in OpenJDK8 and OpenJDK17 and evaluate it with fifteen widely used applications in two real-world big data frameworks, Spark and Giraph. We find that for the same DRAM size, TeraHeap improves performance by up to 73% and 28% compared to native Spark and Giraph. Also, it can still provide better performance by consuming up to and less DRAM than native Spark and Giraph, respectively. TeraHeap can also be used for in-memory frameworks and applying it to the Neo4j Graph Data Science library improves its performance by up to 26%. Finally, it outperforms Panthera, a state-of-the-art garbage collector for hybrid DRAM-NVM memories, by up to 69%. ; We thankfully acknowledge the support of the European Commission under the Horizon 2020 Framework Programme for Research and Innovation through the projects AERO (Grant agreement No. 10048318). Iacovos G. Kolokasis is also supported by the Meta Research PhD Fellowship and the State Scholarship Foundation of Cyprus. ; Peer-reviewed |
| Druh dokumentu: | article in journal/newspaper |
| Jazyk: | English |
| Relation: | http://www.scopus.com/inward/record.url?scp=86000552868&partnerID=8YFLogxK; https://hdl.handle.net/1885/733752737; 86000552868 |
| DOI: | 10.1145/3700593 |
| Dostupnosť: | https://hdl.handle.net/1885/733752737 http://www.scopus.com/inward/record.url?scp=86000552868&partnerID=8YFLogxK https://doi.org/10.1145/3700593 |
| Rights: | Publisher Copyright: © 2024 Copyright held by the owner/author(s). |
| Prístupové číslo: | edsbas.DBF30768 |
| Databáza: | BASE |
Nájsť tento článok vo Web of Science | FullText | Text: Availability: 0 CustomLinks: – Url: https://hdl.handle.net/1885/733752737# Name: EDS - BASE (s4221598) Category: fullText Text: View record from BASE – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Kolokasis%20IG Name: ISI Category: fullText Text: Nájsť tento článok vo Web of Science Icon: https://imagesrvr.epnet.com/ls/20docs.gif MouseOverText: Nájsť tento článok vo Web of Science |
|---|---|
| Header | DbId: edsbas DbLabel: BASE An: edsbas.DBF30768 RelevancyScore: 969 AccessLevel: 3 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 968.605590820313 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: TeraHeap – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Kolokasis%2C+Iacovos+G%2E%22">Kolokasis, Iacovos G.</searchLink><br /><searchLink fieldCode="AR" term="%22Evdorou%2C+Giannos%22">Evdorou, Giannos</searchLink><br /><searchLink fieldCode="AR" term="%22Akram%2C+Shoaib%22">Akram, Shoaib</searchLink><br /><searchLink fieldCode="AR" term="%22Kozanitis%2C+Christos%22">Kozanitis, Christos</searchLink><br /><searchLink fieldCode="AR" term="%22Papagiannis%2C+Anastasios%22">Papagiannis, Anastasios</searchLink><br /><searchLink fieldCode="AR" term="%22Zakkak%2C+Foivos+S%2E%22">Zakkak, Foivos S.</searchLink><br /><searchLink fieldCode="AR" term="%22Pratikakis%2C+Polyvios%22">Pratikakis, Polyvios</searchLink><br /><searchLink fieldCode="AR" term="%22Bilas%2C+Angelos%22">Bilas, Angelos</searchLink> – Name: TitleSource Label: Source Group: Src Data: ACM Transactions on Programming Languages and Systems – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Australian National University: ANU Digital Collections – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22fast+storage+devices%22">fast storage devices</searchLink><br /><searchLink fieldCode="DE" term="%22garbage+collection%22">garbage collection</searchLink><br /><searchLink fieldCode="DE" term="%22Java+Virtual+Machine+%28JVM%29%22">Java Virtual Machine (JVM)</searchLink><br /><searchLink fieldCode="DE" term="%22large+analytics%22">large analytics</searchLink><br /><searchLink fieldCode="DE" term="%22large+managed+heaps%22">large managed heaps</searchLink><br /><searchLink fieldCode="DE" term="%22memory+hierarchy%22">memory hierarchy</searchLink><br /><searchLink fieldCode="DE" term="%22memory+management%22">memory management</searchLink><br /><searchLink fieldCode="DE" term="%22serialization%22">serialization</searchLink> – Name: Abstract Label: Description Group: Ab Data: Big data analytics frameworks, such as Spark and Giraph, need to process and cache massive datasets that do not always fit on the managed heap. Therefore, frameworks temporarily move long-lived objects outside the heap (off-heap) on a fast storage device. However, this practice results in (1) high serialization/deserialization (S/D) cost and (2) high memory pressure when off-heap objects are moved back for processing. In this article, we propose TeraHeap, a system that eliminates S/D overhead and expensive GC scans for a large portion of objects in analytics frameworks. TeraHeap relies on three concepts: (1) It eliminates S/D by extending the managed runtime (JVM) to use a second high-capacity heap (H2) over a fast storage device. (2) It offers a simple hint-based interface, allowing analytics frameworks to leverage object knowledge to populate H2. (3) It reduces GC cost by fencing the collector from scanning H2 objects while maintaining the illusion of a single managed heap, ensuring memory safety. We implement TeraHeap in OpenJDK8 and OpenJDK17 and evaluate it with fifteen widely used applications in two real-world big data frameworks, Spark and Giraph. We find that for the same DRAM size, TeraHeap improves performance by up to 73% and 28% compared to native Spark and Giraph. Also, it can still provide better performance by consuming up to and less DRAM than native Spark and Giraph, respectively. TeraHeap can also be used for in-memory frameworks and applying it to the Neo4j Graph Data Science library improves its performance by up to 26%. Finally, it outperforms Panthera, a state-of-the-art garbage collector for hybrid DRAM-NVM memories, by up to 69%. ; We thankfully acknowledge the support of the European Commission under the Horizon 2020 Framework Programme for Research and Innovation through the projects AERO (Grant agreement No. 10048318). Iacovos G. Kolokasis is also supported by the Meta Research PhD Fellowship and the State Scholarship Foundation of Cyprus. ; Peer-reviewed – Name: TypeDocument Label: Document Type Group: TypDoc Data: article in journal/newspaper – Name: Language Label: Language Group: Lang Data: English – Name: NoteTitleSource Label: Relation Group: SrcInfo Data: http://www.scopus.com/inward/record.url?scp=86000552868&partnerID=8YFLogxK; https://hdl.handle.net/1885/733752737; 86000552868 – Name: DOI Label: DOI Group: ID Data: 10.1145/3700593 – Name: URL Label: Availability Group: URL Data: https://hdl.handle.net/1885/733752737<br />http://www.scopus.com/inward/record.url?scp=86000552868&partnerID=8YFLogxK<br />https://doi.org/10.1145/3700593 – Name: Copyright Label: Rights Group: Cpyrght Data: Publisher Copyright: © 2024 Copyright held by the owner/author(s). – Name: AN Label: Accession Number Group: ID Data: edsbas.DBF30768 |
| PLink | https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.DBF30768 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1145/3700593 Languages: – Text: English Subjects: – SubjectFull: fast storage devices Type: general – SubjectFull: garbage collection Type: general – SubjectFull: Java Virtual Machine (JVM) Type: general – SubjectFull: large analytics Type: general – SubjectFull: large managed heaps Type: general – SubjectFull: memory hierarchy Type: general – SubjectFull: memory management Type: general – SubjectFull: serialization Type: general Titles: – TitleFull: TeraHeap Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Kolokasis, Iacovos G. – PersonEntity: Name: NameFull: Evdorou, Giannos – PersonEntity: Name: NameFull: Akram, Shoaib – PersonEntity: Name: NameFull: Kozanitis, Christos – PersonEntity: Name: NameFull: Papagiannis, Anastasios – PersonEntity: Name: NameFull: Zakkak, Foivos S. – PersonEntity: Name: NameFull: Pratikakis, Polyvios – PersonEntity: Name: NameFull: Bilas, Angelos IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2024 Identifiers: – Type: issn-locals Value: edsbas – Type: issn-locals Value: edsbas.oa Titles: – TitleFull: ACM Transactions on Programming Languages and Systems Type: main |
| ResultId | 1 |