Because the methods used before do not give systematic understanding of cloud-based browsing in design level. For cloud-based browser, moving functionality to the cloud is not always saving energy and download time. So the author makes a evaluation to show when to move functionality to the cloud.
Main points:
The author compares two extreme points and then argues that Cloud Browser can not provide clear benefits in energy and download time.
Setup and Methodology:
1. Testing first download page, which means that both direct browser and cloud-based browser can not use local cache.
2. Just testing first download page is not enough, because it is not real. So the author add user interactivity into the test.
3. The conclusion of first method shows that compaction ratio affects the performance of Cloud Browser. So the third method is to test the impact of compaction.
4. The fourth test is to download the non-JS version of the pages by CB and Direct.
The reason why CB is worse is :
1. There exist redundant data since CB streams multiple CBML for the page.
2. Even though adding user interactivity, CB's performance is still worse than Direct method. The reason is also CBML.
3. Downloading the page from the server and performing data compaction is the bottle neck.
4. It may be that CB consumes more CPU cycles to decompress the CBML thereby consuming more CPU energy than Direct.
3. Downloading the page from the server and performing data compaction is the bottle neck.
4. It may be that CB consumes more CPU cycles to decompress the CBML thereby consuming more CPU energy than Direct.
Based on the measurement, the author conclude that :
1. Offloading JS to the cloud is not necessarily beneficial
2. Considering user interactivity when offloading JS is important
3. Data compaction is not always beneficial
Critiques:
I do not agree with the conclusion "Data compaction is not always beneficial". Because in order to get this conclusion, we need to compare CB and CB without compaction instead of Direct.
Based on the analysis of the paper, the bottleneck of CB is CBML. How to improve that part? How to avoid the redundant data? If we modified this part, the outcome maybe different.
I do not agree with the conclusion "Data compaction is not always beneficial". Because in order to get this conclusion, we need to compare CB and CB without compaction instead of Direct.
Based on the analysis of the paper, the bottleneck of CB is CBML. How to improve that part? How to avoid the redundant data? If we modified this part, the outcome maybe different.
Good critical comments. For point #1, I think they are referring to whether data compaction provides a benefit over Direct - they are not interested in "self" comparisons since they are trying to establish the performance/energy of CB vs. Direct. Good observation about point #2 - though, one would think/hope the commercial interest would dictate a good solution.
ReplyDelete