Proceedings of the 12th ACM SIGOPS Asia-Pacific Workshop on Systems 2021
DOI: 10.1145/3476886.3477505
|View full text |Cite
|
Sign up to set email alerts
|

Offloading load balancers onto SmartNICs

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
3

Relationship

1
5

Authors

Journals

citations
Cited by 13 publications
(4 citation statements)
references
References 6 publications
0
4
0
Order By: Relevance
“…From the evaluations, we observe that our implementation meets the processing rates required for control messages of offloaded applications. engines and runtime-configurable rules for routing packets [23].…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…From the evaluations, we observe that our implementation meets the processing rates required for control messages of offloaded applications. engines and runtime-configurable rules for routing packets [23].…”
Section: Discussionmentioning
confidence: 99%
“…In on-path smart-NICs, all traffic is handled by the NIC cores and tasks are executed on the smartNIC by adding logic to the processing pipeline [38]. The NIC cores are able to invoke special hardware accelerators for tasks such as crypto and compression [23]. In off-path smart-NICs, the NIC's cores are not directly on the data path from the host to the network, but instead, there exists a NIC-switch connecting the network ports, the host cores and the NIC cores [54].…”
Section: A Appendixmentioning
confidence: 99%
“…Will Hardware Offloading Reduce Service Mesh Overheads? Another direction researchers are currently exploring is to offload the sidecar logic to a programmable network hardware [26]. While this is a promising direction, there are substantial challenges.…”
Section: Discussion and Future Workmentioning
confidence: 99%
“…Second, service mesh developers should be able to understand the impact of their optimizations on real-world applications. Today, there are several ongoing directions in industry and academia to reduce the service mesh performance overheads [5,26]. However, these service mesh developers do not have a way to get these insights (without doing their own extensive benchmarking experiments).…”
Section: Modeling Service Mesh Overheadmentioning
confidence: 99%