TY - GEN
T1 - MicroView
T2 - 2023 CoNEXT Student Workshop, CoNEXT-SW 2023
AU - Cornacchia, Alessandro
AU - Benson, Theophilus A.
AU - Bilal, Muhammad
AU - Canini, Marco
N1 - Publisher Copyright:
© 2023 Owner/Author.
PY - 2023/12/8
Y1 - 2023/12/8
N2 - We present MicroView, a system designed to improve the accuracy and timeliness of observability in cloud-native applications, while minimizing overhead. MicroView stands out from conventional observability tools by incorporating metrics processing stages at every node within a local lightweight data-plane. We preliminary demonstrate its benefits for distributed tracing and outline a set of architectural choices focused on offloading the MicroView data-plane to IPU accelerators, such as a BlueField-3 SmartNIC, thus limiting the interference with running services.
AB - We present MicroView, a system designed to improve the accuracy and timeliness of observability in cloud-native applications, while minimizing overhead. MicroView stands out from conventional observability tools by incorporating metrics processing stages at every node within a local lightweight data-plane. We preliminary demonstrate its benefits for distributed tracing and outline a set of architectural choices focused on offloading the MicroView data-plane to IPU accelerators, such as a BlueField-3 SmartNIC, thus limiting the interference with running services.
KW - cloud-native
KW - microservices observability
KW - programmable networks
KW - SmartNIC
UR - http://www.scopus.com/inward/record.url?scp=85181834031&partnerID=8YFLogxK
U2 - 10.1145/3630202.3630233
DO - 10.1145/3630202.3630233
M3 - Conference contribution
AN - SCOPUS:85181834031
T3 - CoNEXT-SW 2023 - Proceedings of the CoNEXT Student Workshop 2023
SP - 7
EP - 8
BT - CoNEXT-SW 2023 - Proceedings of the CoNEXT Student Workshop 2023
PB - Association for Computing Machinery, Inc
Y2 - 8 December 2023
ER -