TY - GEN
T1 - Kappa
T2 - 11th ACM Symposium on Cloud Computing, SoCC 2020
AU - Zhang, Wen
AU - Fang, Vivian
AU - Panda, Aurojit
AU - Shenker, Scott
N1 - Funding Information:
We thank the anonymous reviewers, James McCauley, Edward Oakes, other members of the UC Berkeley NetSys Lab, Pratyush Patel, Gur-Eyal Sela, Irene Zhang, and Akshay Narayan for their feedback. This work was funded in part by NSF Grants 1817115, 1817116, and 1704941, and by grants from Intel, VMware, Ericsson, Futurewei, Cisco, Amazon, and Microsoft.
Publisher Copyright:
© 2020 Owner/Author.
PY - 2020/10/12
Y1 - 2020/10/12
N2 - Serverless computing has recently emerged as a new paradigm for running software on the cloud. In this paradigm, programs need to be expressed as a set of short-lived tasks, each of which can complete within a short bounded time (e.g., 15 minutes on AWS Lambda). Serverless computing is beneficial to cloud providers - -by allowing them to better utilize resources - -and to users - -by simplifying management and enabling greater elasticity. However, developing applications to run in this environment is challenging, requiring users to appropriately partition their code, develop new coordination mechanisms, and deal with failure recovery. In this paper, we propose Kappa, a framework that simplifies serverless development. It uses checkpointing to handle lambda function timeouts, and provides concurrency mechanisms that enable parallel computation and coordination.
AB - Serverless computing has recently emerged as a new paradigm for running software on the cloud. In this paradigm, programs need to be expressed as a set of short-lived tasks, each of which can complete within a short bounded time (e.g., 15 minutes on AWS Lambda). Serverless computing is beneficial to cloud providers - -by allowing them to better utilize resources - -and to users - -by simplifying management and enabling greater elasticity. However, developing applications to run in this environment is challenging, requiring users to appropriately partition their code, develop new coordination mechanisms, and deal with failure recovery. In this paper, we propose Kappa, a framework that simplifies serverless development. It uses checkpointing to handle lambda function timeouts, and provides concurrency mechanisms that enable parallel computation and coordination.
KW - distributed computing
KW - serverless
UR - http://www.scopus.com/inward/record.url?scp=85095438979&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85095438979&partnerID=8YFLogxK
U2 - 10.1145/3419111.3421277
DO - 10.1145/3419111.3421277
M3 - Conference contribution
AN - SCOPUS:85095438979
T3 - SoCC 2020 - Proceedings of the 2020 ACM Symposium on Cloud Computing
SP - 328
EP - 343
BT - SoCC 2020 - Proceedings of the 2020 ACM Symposium on Cloud Computing
PB - Association for Computing Machinery, Inc
Y2 - 19 October 2020 through 21 October 2020
ER -