Advanced Operating System (Focusing on Storage System )

1. AdvancedOperating System(Focusing on Storage System) Dept. of Computer Science and Engineering Dankook University September 2, 2019 Jongmoo Choi choijm@dankook.ac.kr http://embedded.dankook.ac.kr/~choijm

2. Course Objective • Understanding recent storage system research trends • Flash memory, NVRAM, In-storage processing, … • File system, Key-value store, Bigdata framework, … • Other operating system research trends • Get accustomed to papers written in English • Find out the general structure of a paper • How to review a paper • Enhance presentation skill • How to make a successful presentation • How to discuss or argue • Make our own paper • How to write a good paper • Submit if possible (or mandatory?)

3. Course text • Where you can find papers? <FAST> <ATC> <SOSP> <ASPLOS> <Eurosys> <OSDI>

4. Paperlists (Candidates) • Week 1 (9/2): Introduction • Course introduction • Paper selection (4 papers per person) • Week 2 (9/9): OS classics • D. Ritchie and K. Thompson, “The UNIX Time-sharing system”, CACM, 1974. • M. Accetta et al., “Mach: A New Kernel Foundation for UNIX Development”, USENIX Summer Conference, 1986. • D. Engler et al., “Exokernel: An Operating System Architecture for Application-Level Resource Management”, SOSP, 1995. • Week 3 (9/16): FS classics • M. Rosenblum and J. Ousterhout, "The Design and Implementation of a Log-Structured File System", ACM ToCS, 1992. • C. Lee et al., "F2FS: A New File System for Flash Storage", FAST, 2015. • V. Chidambaram et al., “Optimistic Crash Consistency”, SOSP, 2013. • Week 4 (9/23): Resource management classics • C. A. Waldspurger and W. E. Weihl “Lottery Scheduling: Flexible Proportional-Share Resource Management”, OSDI, 1994. • H. Park et al., "Regularities considered harmful: forcing randomness to memory accesses to reduce row buffer conflicts for multi-core, multi-bank systems", ASPLOS, 2013. • S. Zhuravlev et al., "Addressing Shared Resource Contention in Multicore Processors via Scheduling", ASPLOS, 2010. • Week 5 (9/30): Personal Project • Ice break, Brainstorming (10 minutes per person)

5. Paperlists (Candidates) • Week 6 (10/7): Virtualization • P. Barham et al., "Xen and the Art of Virtualization", SOSP, 2003. • C. A. Waldspurger, “Memory Resource Management in VMware ESX Server”, OSDI, 2002. • F. Manco et al., “My VM is Lighter (and Safer) than your Container”, SOSP, 2017. • Week 7 (10/14): Flash memory • S. Lee et al., “A Log Buffer-Based Flash Translation Layer Using Fully-Associative Sector Translation”, ACM TECS, 2007. • A. Gupta et al., “DFTL: A Flash Translation Layer Employing Demand-based Selective Caching of Page-level Address Mappings”, ASPLOS, 2009. • N. Agrawal et al., “Design Tradeoffs for SSD Performance”, ATC, 2008. • Week 8 (10/21): Key-Value Store • L. Lu, T. Pillai, A. Arpaci-Dusseau and R. Arpaci-Dusseau, "WiscKey: Separating Keys from Values in SSD-Conscious Storage“, FAST, 2016. • O. Balmau et al, “SILK: Preventing Latency Spikes in Log-Structured Merge Key-Value Stores”, ATC, 2019. • P. Raju et al., "PebblesDB: Building Key-Value Stores using Fragmented Log-Structured Merge Trees", SOSP, 2017. • Week 9 (10/28): Key-Value Store with Flash-awareness • J. Zhang et al., “FlashKV: Accelerating KV Performance with Open-Channel SSDs”, ACM Transactions on Embedded Computer systems, 2017. • P. Wang et al., “An efficient design and implementation of LSM-tree based key-value store on Open-channel SSD”, Eurosys, 2014. • L. Marmol et al., “NVMKV: A scalable, lightweight, FTL-aware key-value store”, USENIX ATC, 2015. • Week 10 (11/4): Personal Project • Related paper survey + Progress (Design) presentation (10 minutes) • Preliminary results if possible

6. Paperlists (Candidates) • Week 11 (11/11): Storage system • S. Lee et al., “ Application-managed flash”, FAST, 2016. • S. Liang et al., “Cognitive SSD: A Deep Learning Engine for In-Storage Data Retrieval”, ATC, 2019. • B. Kim, "Design Tradeoffs for SSD Reliability", FAST, 2019. • Week 12 (11/18): Well-known framework • J. Dean and S. Ghemawat, “MapReduce: Simplified Data Processing on Large Clusters”, OSDI, 2004. • M. Abadi et al., “TensorFlow: A System for Large-Scale Machine Learning”, OSDI, 2016. • R. L. site, “Benchmarking Hello World“, http://web.stanford.edu/class/cs240/readings/p10-sites.pdf • Week 13 (11/25): Hot topics • Y. Liu et al., “Optimizing CNN Model Inference on CPUs”, ATC, 2019. • G. Franken et al., “Who Left Open the Cookie Jar? A Comprehensive Evaluation of Third-Party Cookie Policies”, USENIXSecurity Symposium, 2018. • B. Davis et al., “CheriABI: Enforcing Valid Pointer Provenance and Minimizing Pointer Privilege in the POSIX C Run-time Environment”, ASPLOS, 2019. • Week 14 (12/2): Best series • Z. Liu et al., “DistCache: Provable Load Balancing for Large-Scale Storage Systems with Distributed Caching”, FAST, 2019. • Y. Shan et al, “LegoOS: A Disseminated, Distributed OS for Hardware Resource Disaggregation”, OSDI, 2018. • Q. Ge et al, “Time Protection: the Missing OS Abstraction”, Eurosys, 2019. • Week 15 (12/9): Personal project • Final (evaluation result) presentation (20 minutes) • Submit your paper

7. Paperlists (Candidates) • Recommended for reading • Roy Levin and David D. Redell, "How (and How Not) to Write a Good Systems Paper", 1983. • B. Griswold, “How to Read and Evaluate Technical Papers ”, http://www.cs.kent.edu/~jmaletic/howtoread.html • B. Lampson, “Hints for Computer System Design”, http://web.stanford.edu/class/cs240/readings/acrobat-17.pdf • Recommended for paper selection • P. Chen et al., “RAID: High-Performance, Reliable Secondary Storage", ACM Computing Surveys, 1994. • C. Dall et al., “KVM/ARM: The Design and Implementation of the Linux ARM Hypervisor”, ASPLOS, 2014. • E. Boutin et al., “Apollo: Scalable and Coordinated Scheduling for Cloud-Scale Computing", OSDI, 2014. • M. Bjørling, J. Gonzalez, and P. Bonnet, “LightNVM: The Linux open-channel SSD subsystem”, FAST, 2017. • Y. Cai et al., “Data Retention in MLC NAND Flash Memory: Characterization, Optimization and Recovery”, HPCA, 2015. • H. Herodotou, S. Babu, “Profiling, What-if Analysis and Cost-based Optimization of MapReduce Programs”, VLDB, 2011. • … • Papers used in other universities • http://web.stanford.edu/class/cs240/ • https://www.seltzer.com/margo/teaching/CS508.19/syllabus.html • http://pages.cs.wisc.edu/~dusseau/Classes/CS736/CS736-F13/papers.html • https://www3.nd.edu/~cpoellab/teaching/cse60641/links.html • https://www.cs.utexas.edu/~vijay/cs380l/schedule.htm • Please let me know if you want to present other papers (after 2017)

8. Lecture details • Presentation (roughly 3 times per person) • Less than 25 minutes • Q & A are quite important • Paper Review • Personal project • Write a paper • No examination

9. How to present • Presentation • Time • Presentation: 25 min, Q&A: 10 min • Slide • Less than 15 lines per each page • More than half pages must contain figures • Must include humor slides (if not, less points) • Must include references (if not, less points) • Each slide must be put in the lecture site (send it to choijm@dankook.ac.kruntil the previous day of presentation) • Audience • Obligation of audience: at least one question per person a day • Without questions, you can not get a good grade. • Count the number of questions

10. How to review a paper • Paper Review • All student must submit reviews about papers assigned to the corresponding week. • Format • Summary • 3 sentences • Motivation, Proposal, Evaluation • Strength • What are positive things in this paper? • Weakness • What are the down sides of this paper? • Questions or Suggestions • At least 3

11. How to make a proposal • Personal project • Idea presentation (last week of the first month) • Research area, Brainstorming • Survey presentation and initial design (last week of the second month) • Related papers (prepare references in advance) • Related industrial trends • Final presentation (last week of this semester) • Idea, Related work, New proposal, Evaluation results • Enhance the idea obtained form your presentation • 1) presentation (ppt), 2) paper (tex, hwp, word) • I strongly recommend to submit KCC or KSC or any conferences/workshops

12. Evaluation • Evaluation • Presentation(30%) • Questions and Answers(20%) • Paper review (30%) • Final proposal (20%)