EN.601.619-Cloud Computing Final Exam Soved

    This exam is openbook, which means you are permitted to use any materials from your own notes from the course, the papers you reviewed, and anything on the course website and its Piazza page.

•    The exam must be taken completely alone. Showing it or discussing it with anyone is strictly forbidden.

•    You may not consult with any other person regarding the exam. You may not check your exam answers with any person. You may not discuss any of the materials or concepts with any other person.

•    You may not consult any external resources. This means no Internet searches, materials from other classes or books or any notes you have taken in other classes, etc. You may not use Google or any other search engines for any reason. You may not use any shared documents including Google documents.

•    Your work must be original and you may not solicit or obtain assistance from or provide assistance to other people for any speci c content on the exam. Activities considered cheating include (but are not limited to) copying or closely paraphrasing content from websites, discussing exam questions with other students, and asking for help with speci c questions on Internet forums. All exams are checked for originality and copied content and anyone found cheating will be assigned a failing score for the exam.

•    The exam should be submitted via email by 12pm on May 12, 2020 to the instructor: soudeh@cs.jhu.edu. Please email the instructor if you are unable to submit the exam at that time.

I have read and followed the instructions above.

 

Name, Date

Section 1
Please answer all the questions in this section (100 points). Please remember to explain all your answers (e.g., an answer with a numerical result should show how you derived it).

1.    [15 points] We saw in the Jupiter paper that large-scale datacenters are built as Clos, a topology that we had seen earlier in the Fat-tree paper. Discuss two advantages and two disadvantages of Clos-based datacenters compared to datacenter designs based on random graphs such as Jelly sh.

2.    [10 points] Suppose ASes run standard BGP routing policies (Gao-Rexford model), an undirected link between Si and Sj means that Si and Sj are peers, and a link from Si to Sj (Si → Sj) means that Si is a provider of Sj (equivalently, Sj is a customer of Si). In the network below, will S5 be able to reach S9?

 

•    If yes, what path does S5 take to reach S9? Compute the path stretch, de ned as the ratio of the length of the BGP policy compliant path to that of the shortest path.

•    If no, explain why several of the paths in the network (at least three) from S5 to S9 violate Gao-Rexford policies.

3.    [15 points] We saw that, similar to vanilla TCP, datacenter transport protocols such as DCTCP harness Additive Increase, Multiplicative Decrease (AIMD). This allows them to dynamically adjust their sending rates, in a fully distributed manner, while converging to both fairness and e ciency. From two possible alternatives to AIMD Multiplicative Increase, Additive Decrease (MIAD) and Additive Increase, Additive Decrease (AIAD) which one(s) converge to fairness and e ciency? Draw the Chiu Jain plots to demonstrate your answers.

4.    [15 points] What is the max-min fair bandwidth allocation in the network below? A,B,C,D are hosts that each wish to send at the maximum possible rate to E. The arrows are links and the numbers denote link capacities.

 

5.    [10 points] What does agility mean and why is it an important property in designing cloud infrastructures and systems? Discuss at least one technique that cloud providers deploy to maximize agility.

6.    [20 points] The OpenFlow paper that we read discusses the original design of SDN.

•    Analyze, in a qualitative manner, (a) scalability, (b) fault-tolerance, and (c) performance limitations of this design.

•    Discuss two approaches that cloud providers deploy to target and mitigate any of these limitations. You can discuss any SDN-based cloud systems and their solutions to SDN’s original shortcomings.

7.    [15 points] Failure detectors are key building blocks of many cloud systems including keyvalue stores. We saw that it is impossible to build failure detectors that guarantee both completeness (each failure is eventually detected by at least one non-faulty node) and accuracy (no mistaken detection) in unreliable networks that occasionally drop packets.

•    Which of these two properties completeness and accuracy practical cloud systems guarantee and why?

•    Explain how a Ring failure detector works and why it is not complete.

•    Why o -the-shelf gossip-based failure detectors can have poor accuracy in datacenters?

Section 2: Peer Validation
8. [10 points] The       nal task for the project is to evaluate a peer project. Similar to the second assignment, we need you to validate and comment on the reproducibility of the results of the group project assigned to you. The group-validator assignments has been posted on Piazza.

•    Write a brief summary (1 paragraph) of the project assigned to you: What problem they target? Why is it important? Their approach? Their progress?

•    Write a comment or question for that project.

•    Please use the following rubric to leave a score on the reproducibility of their results. Note that this is not their nal grade. The teaching sta will be evaluating the projects and reproduce the results separately. This is just to give us another perspective and practice peer-validation.

(a)      Code ran to completion and results matched very well with the report.

(b)     Code ran to completion and results matched fairly well with the report.

(c)      Code ran to completion but results did not match the ones in the report, or all results in the report were not produced with the default run con guration.

(d)     Code did not run to completion (exceptions, in nite loops, no progress/debug output/log output, etc.)

(e)      Instructions were so vague or incomplete that the setup could not be completed to even start the code.

(f)       Instructions not found.

•    [Optional] Feel free to write some additional feedback in addition to the reproducibility score. We will also appreciate if you can comment on the quality of analysis and if you thought it was interesting.