SOSP 2017 - Proceedings of the 26th ACM Symposium on Operating Systems Principles https://dl.acm.org/doi/pdf/10.1145/3132747.3132763
1. Summarize the problem(s) the paper want to solve. VM and container has pros and cons related to performance and isolation. Is there any other way to catch both of them? Do they have to be separated?
2. Why is/are the problem(s) important? State your opinion. Recently, there exist huge shift toward container from VM. The main reason for this shift is fast boot time and less memory foot print which more adaptable to currently cloud computing or PaSS infrastructures. However, isolation in container is inherently weak compare to the VM. Thus, there is need for reducing the heavy overhead of traditional VM for increasing performance also with isolations.
3 Summarize the (at most) key main ideas of the paper. -> Reduce the size of the VM by unikernel. -> Re-implement the Xen library. For example, remove XenStore and replacing message passing to direct shared pages. -> Polling the creation of the VM.
4. State the main contributions of the paper. -> Remind the usefulness of VM in surge of the containers. -> With intensive engineering works, provide that VM can be smaller and faster as like as container.
5. Criticize the main contributions (Limitations of the proposed design. Limitations of applicability etc.) Rate the significance of the paper on a scale of 5 (breakthrough), 4 (significant contribution), 3 (modest contribution), 2 (incremental contribution), 1 (no contribution or negative contribution). Explain your rating. -> Not fantastically new idea, cause using lots of previous features such as unikernel or VM pooling. However this paper shows intensive analysis for performance evaluation in both container and VM. Also with lots of engineering works, this paper present how to and how much we could achieve by VM. Thus, I will give 5/4 If I am a reviewer of this paper.
6. Rate how convincing is the evaluation methodology (Refer to the following questions). Do the claims and conclusions follow from the experiments? Are the assumptions realistic? Are the experiments well designed? Are there different experiments that would be more convincing? Are there other alternatives the authors should have considered? (And, of course, is the paper free of methodological errors.) -> I think major point of this paper is evaluations. Plots and graphs in this papers requires lots of works for evaluating I think. -> I think these paper’s evolution could be used good baseline for further research for comparing VM and container. -> Thus I think these paper’s evolution part and other graphs are well designed and structured.
7. Answer one of the following three questions (whichever is most relevant for this paper): What lessons should system researchers and builders take away from this work? -> We could make VM as faster as like docker. Is there any reason for using docker in this case?
What is the lasting impact of this work? What (if any) questions does this work leave open? -> How to reduce the efforts for building smaller kernel. Is there any other way to reduce kernel of the library operating system? -> So as reversed, is there any other way to provide strong isolation to docker using technique we used in VM? Or other way? Then, how to do it?
2 - 3 sentences are fine for each question..