PPT-CSE 486/586 Distributed Systems

Case Study Facebook f4 Steve Ko Computer Sciences and Engineering University at Buffalo Recap Engineering principle Make the common case fast and rare cases correct Power law Haystack A design for warm photos. Domain Name System. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Last Time. Global states. A union of all process states. Consistent global state vs. inconsistent global state. Concurrency Control --- 3. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Strict execution of transactions?. Delay . both their read and write operations . on an . object until . Paxos. --- 2. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Paxos. is a consensus algorithm.. It allows multiple acceptors.. It allows multiple proposals to be accepted.. Graph Processing. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Byzantine generals problem. They must decide on a common plan of action.. But. , . some of the generals can be traitors. Consistency --- 3. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Consistency. Linearizability. ?. Sequential consistency?. Chain replication. Primary-backup (passive) replication. Consistency --- 2. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Linearizability. vs. Sequential Consistency. Both care about giving . an illusion of a single copy. .. From the outside observer, the system should (almost) behave as if there’s only a single copy.. Case Study: Amazon Dynamo. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. CAP Theorem?. Consistency, Availability, Partition Tolerance. Pick two. Eventual consistency?. Availability and partition tolerance over consistency. New Trends in Distributed Storage. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Two important components in a distributed file service?. Directory service. Flat file service. Byzantine Fault Tolerance. Steve Ko. Computer Sciences and Engineering. University at Buffalo. CSE 486/586 . Administrivia. Project 3 out. Please, please start right away!. Deadline: 4/30 (Monday) @ 11:59PM. Gossiping. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recall: Passive Replication. Request Communication. : the request is issued to the primary RM and carries a unique request id.. Case Study: . Facebook Haystack. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. DNS. Hierarchical servers. Root servers, top-level domain servers, authoritative servers. CDN. Leader . Election --- 2. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Algorithm 2: Modified Ring Election . election . message tracks . all. IDs of nodes that forwarded it, not just the highest. Reliable Multicast --- 2. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap: Multicast. How do a group of processes communicate?. Multicast. One-to-many: “Local” broadcast within a group . Paxos. --- 2. Steve Ko. Computer Sciences and Engineering. University at Buffalo. Recap. Paxos. is a consensus algorithm.. It allows multiple acceptors accepting multiple proposals.. A proposer always makes sure that,.