Affiliation:
1. Peking University, China
2. University College London, United Kingdom
3. Advanced Institute of Big Data, Beijing, China
4. Huazhong University of Science and Technology, China
Abstract
Serverless computing is a popular cloud computing paradigm that frees developers from server management. Function-as-a-Service (FaaS) is the most popular implementation of serverless computing, representing applications as event-driven and stateless functions. However, existing studies report that functions of FaaS applications severely suffer from cold-start latency.
In this article, we propose an approach, namely,
FaaSLight
, to accelerating the cold start for FaaS applications through application-level optimization. We first conduct a measurement study to investigate the possible root cause of the cold-start problem of FaaS. The result shows that application code loading latency is a significant overhead. Therefore, loading only indispensable code from FaaS applications can be an adequate solution. Based on this insight, we identify code related to application functionalities by constructing the function-level call graph and separate other code (i.e., optional code) from FaaS applications. The separated optional code can be loaded on demand to avoid the inaccurate identification of indispensable code causing application failure. In particular, a key principle guiding the design of
FaaSLight
is inherently general, i.e.,
platform
- and
language-agnostic
. In practice,
FaaSLight
can be effectively applied to FaaS applications developed in different programming languages (Python and JavaScript), and can be seamlessly deployed on popular serverless platforms such as AWS Lambda and Google Cloud Functions, without having to modify the underlying OSes or hypervisors, nor introducing any additional manual engineering efforts to developers. The evaluation results on real-world FaaS applications show that
FaaSLight
can significantly reduce the code loading latency (up to 78.95%, 28.78% on average), thereby reducing the cold-start latency. As a result, the total response latency of functions can be decreased by up to 42.05% (19.21% on average). Compared with the state-of-the-art,
FaaSLight
achieves a 21.25× improvement in reducing the average total response latency.
Funder
National Key Research and Development Program of China
National Natural Science Foundation of China
National Natural Science Fund
Excellent Young Scientists Fund Program
ERC Advanced Grant
Publisher
Association for Computing Machinery (ACM)
Reference114 articles.
1. 2016. Image resize. Retrieved on November 10 2021 from https://github.com/gxx/aws-lambda-python/tree/master/image_resize.
2. 2017. Lambda Pandas. Retrieved on November 10 2021 from https://github.com/nicor88/aws-python-lambdas/tree/master/src/hello_pandas.
3. 2017. Python OpenCV module for AWS Lambda. Retrieved on November 10 2021 from https://github.com/aeddi/aws-lambda-python-opencv.
4. 2017. TensorFlow to AWS Lambda. Retrieved on November 10 2021 from https://github.com/jacopotagliabue/tensorflow_to_lambda_serverless.
5. 2018. 2018 serverless community survey: huge growth in serverless usage. Retrieved on May 01 2022 from https://www.serverless.com/blog/2018-serverless-community-survey-huge-growth-usage.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. The Gap Between Serverless Research and Real-world Systems;Proceedings of the 2023 ACM Symposium on Cloud Computing;2023-10-30
2. Serverless Computing: Architectural Paradigms, Challenges, and Future Directions in Cloud Technology;2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC);2023-10-11
3. Deadline Sensitive And Function Placement In Multi-tier Serverless Platform;2023 International Conference on IT and Industrial Technologies (ICIT);2023-10-09
4. Prediction-driven resource provisioning for serverless container runtimes;2023 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS);2023-09-25
5. ACPM: adaptive container provisioning model to mitigate serverless cold-start;Cluster Computing;2023-05-11