[Distributed File System] A Berkeley View on Serverless Computing Overview
This blog is a paper summary of the paper, "A Berkeley View on Serverless Computing".
However, some limitations of it are:
What is the paper trying to do?
The paper serves as a good introduction to serverless computing. It gives an introduction to serverless computing then goes on to talk about how it started (the motivations), the limitations and what the authors predict serverless computing will become in the future. It does a good job in explaining how the serverless cloud handles virtually all the system administration operations and makes it easier for programmers do what they usually do on the cloud.What do you think is the contribution of the paper?
Again, the paper’s major contribution is its very detailed introduction of server less computing.What are its major strengths?
The major strengths of serverless computing are:- The appearance of infinite computing resources on demand.
- The elimination of an up-front commitment by cloud users.
- The ability to pay for use of computing resources on a short-term basis as needed.
- Economies of scale that significantly reduced cost due to many, very large data centers.
- Simplifying operation and increasing utilization via resource virtualization.
- Higher hardware utilization by multiplexing workloads from different organizations.
However, some limitations of it are:
- Serverless computing can have unpredictable costs (if it is a pay-as-you-go model)
- Vendor lock-in (especially with AWS)
Resource
A Berkeley View on Serverless Computing (https://www2.eecs.berkeley.edu/Pubs/TechRpts/2019/EECS-2019-3.html)
Comments
Post a Comment