PPT-Distributed Consensus Paxos

Ethan Cecchetti October 18 2016 CS6410 Some structure taken from Robert Burgesss 2009 slides on this topic State Machine Replication SMR View a server as a state machine To replicate the server. Ali Ghodsi. alig@cs.berkeley.edu. Replicated State Machine (RSM). Distributed Systems 101. Fault-tolerance. . (partial, byzantine, recovery,...). Concurrency. (ordering, asynchrony, timing,...). Generic. Advanced Topics in Computer Systems. Lecture 24. Paxos/Megastore. November . 26. th. , . 2012. John . Kubiatowicz. and Anthony D. Joseph. Electrical Engineering and Computer Sciences. University of California, Berkeley. Paxos. --- 1. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. NFS. Caching with write-through policy at close(). Stateless server. One power efficient design: FAWN. Embedded CPUs & Flash . Replication. Lecture 16. , Oct 22. nd. 2015 . How’d we get here?. Failures & single systems; fault tolerance techniques added redundancy (ECC memory, RAID, etc.). Conceptually, ECC & RAID both put a “master” in front of the redundancy to mask it from clients -- ECC handled by memory controller, RAID looks like a very reliable hard drive behind a (special) controller. Burcu Canakci & Matt Burke. . Outline. Consensus. The Part-Time Parliament. Single-Decree Paxos. Liveness. Multi-Decree Paxos. Paxos Variants. Conclusion. Outline. Consensus. The Part-Time Parliament. Distributed Systems. Lecture 12. Michael Freedman. Let different replicas assume role of primary over time. System moves through a sequence of views. How do the nodes agree on view / primary?. 2. Recall the use of Views. Fault Tolerant Replication. CS 5204 – Fall, 2008. System Model. Messages. possible indefinite delay. possible duplication or loss. delivered messages not corrupted. . . .. replicas. client. Replicas. . Distributed. . Systems. Crash. . Fault. . Tolerance. Sisi. . Duan. Assistant. . Professor. Information. . Systems. sduan@umbc.edu. Outline. A. . brief. . history. . of. . consensus. Paxos. Lecture 11, . Oct 6. th. . 2016 . How’d we get here?. Failures & single systems; fault tolerance techniques added redundancy (ECC memory, RAID, etc.). Conceptually, ECC & RAID both put a “master” in front of the redundancy to mask it from clients -- ECC handled by memory controller, RAID looks like a very reliable hard drive behind a (special) controller. Paxos Made Simple One-shot Paxos: solving consensus Multipaxos: Efficient state machine replication One-shot Paxos: solving consensus Multipaxos: Efficient state machine replication Consensus Get N nodes to agree on a value Consensus I FLP Impossibility, Paxos COS 418: Distributed Systems Lecture 7 Michael Freedman 2 Recall our 2PC commit problem C  TC: “go!” TC  A, B: “prepare!” A, B  P: “yes” . Oct 22, 2018. What is consensus?. A group of people go to the same place for the same meal.. → A set of nodes have the same value for the same variable.. X=. 7. X=7. X=7. Why is it important?. In state machine replication (SMR):. Lecture 16. , Oct 22. nd. 2015 . How’d we get here?. Failures & single systems; fault tolerance techniques added redundancy (ECC memory, RAID, etc.). Conceptually, ECC & RAID both put a “master” in front of the redundancy to mask it from clients -- ECC handled by memory controller, RAID looks like a very reliable hard drive behind a (special) controller. Paxos. COS 418: Distributed Systems. Lecture . 10. Wyatt Lloyd. Let different replicas assume role of primary over time. System moves through a sequence of views. How do the nodes agree on view / primary?.