Archivio Istituzionale della RicercaWe 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.
MicroView: Cloud-Native Observability with Temporal Precision / Cornacchia, Alessandro; Benson, Theophilus; Bilal, Muhammad; Canini, Marco. - ELETTRONICO. - (2023), pp. 7-8. (Intervento presentato al convegno CoNEXT '23: The 19th International Conference on emerging Networking EXperiments and Technologies tenutosi a Paris (France) nel 8 December 2023) [10.1145/3630202.3630233].
MicroView: Cloud-Native Observability with Temporal Precision
Cornacchia,Alessandro;
2023
Abstract
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.
| File | Dimensione | Formato | |
|---|---|---|---|
|
3630202.3630233.pdf
non disponibili
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
1.06 MB
Formato
Adobe PDF
|
1.06 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
CoNeXT_23_Student_Workshop (8).pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
584.48 kB
Formato
Adobe PDF
|
584.48 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2983046