Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
High-speed Connection Tracking in Modern Servers
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Communication Systems, CoS, Network Systems Laboratory (NS Lab). KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0002-9400-324X
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Communication Systems, CoS, Network Systems Laboratory (NS Lab).ORCID iD: 0000-0002-9675-9729
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Communication Systems, CoS, Network Systems Laboratory (NS Lab).ORCID iD: 0000-0003-1269-2190
2021 (English)In: 2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR) (IEEE HPSR'21), 2021Conference paper, Published paper (Refereed)
Abstract [en]

The rise of commodity servers equipped with high-speed network interface cards poses increasing demands on the efficient implementation of connection tracking, i.e., the task of associating the connection identifier of an incoming packet to the state stored for that connection. In this work, we thoroughly investigate and compare the performance obtainable by different implementations of connection tracking using high-speed real traffic traces. Based on a load balancer use case, our results show that connection tracking is an expensive operation, achieving at most 24 Gbps on a single core. Core-sharding and lock-free hash tables emerge as the only suitable multi-thread approaches for enabling 100 Gbps packet processing. In contrast to recent beliefs, we observe that newly proposed techniques to "lazily" delete connection states are not more effective than properly tuned traditional deletion techniques based on timer wheels.

Place, publisher, year, edition, pages
2021.
Keywords [en]
connection tracking, load balancer, fastclick, hash tables, packet classification
National Category
Communication Systems
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-295413DOI: 10.1109/HPSR52026.2021.9481841ISI: 000806753600048Scopus ID: 2-s2.0-85113858387OAI: oai:DiVA.org:kth-295413DiVA, id: diva2:1556104
Conference
IEEE HPSR 2021
Projects
Time Critical Cloud
Funder
Swedish Foundation for Strategic Research, TCCEuropean Commission, 770889
Note

QC 20220627

Available from: 2021-05-20 Created: 2021-05-20 Last updated: 2022-06-27Bibliographically approved

Open Access in DiVA

fulltext(2898 kB)235 downloads
File information
File name FULLTEXT01.pdfFile size 2898 kBChecksum SHA-512
5e82a81ff54c58d44f7e40d62052fc890d52d9ffe95adf21bc51f7d1f0409c3157cacf94b663ef97498ea6f914bea54ce09f2d2de84e4b4035787d52b3b6c4a5
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Girondi, MassimoChiesa, MarcoBarbette, Tom
By organisation
Network Systems Laboratory (NS Lab)Software and Computer systems, SCS
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 235 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 343 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf