分散式共筆 Group 4
===

# CAP Theorem

* [1-1 Perspectives on the CAP Theorem:](https://hackmd.io/@11220CS542600-group4/BJyZcHbx0)
* [1-2 CAP Twelve Years Later: How the “Rules” Have Changed](https://hackmd.io/@11220CS542600-group4/S1qHySbx0)
* [1-3 Time, Clocks, and the Ordering of Events in a Distributed System](https://hackmd.io/@11220CS542600-group4/rJN0S8Ea6)
* [1-4 Weighted Voting for Replicated Data](https://hackmd.io/@11220CS542600-group4/r1IqiHWlC)

# Consistency Protocol

* [2-1 Linearizability](https://hackmd.io/@11220CS542600-group4/Bk9rPdOA6)
* [2-2 Don't Settle for eventaul](https://hackmd.io/@11220CS542600-group4/HJOS1PT10)
* [2-3 Managing Update Conflicts in Bayou](https://hackmd.io/@11220CS542600-group4/Syc09H-x0)
* [2-4 The Potential Dangers of Causal Consistency](https://hackmd.io/@11220CS542600-group4/ByUgxr-xA)

# Consensus Protocol
* [3-1 A Majority Consensus Approach to Concurrency Control](https://hackmd.io/@11220CS542600-group4/SJ294C7eA)
* [3-2 Paxos Made Live - An Engineering Perspective](https://hackmd.io/@11220CS542600-group4/ryd7OiQgA)
* [3-3 Raft - In Search of an Understandable Consensus Algorithm](https://hackmd.io/@11220CS542600-group4/rJBvnvCkA)
* [3-4 The Chubby lock service for loosely-coupled distributed systems](https://hackmd.io/@11220CS542600-group4/Hkj3HFGlC)

# Data Processing Part I
* [4-1 Kafka: a Distributed Messaging System for Log Processing](/X-z7TO-eTQ6BUgRj7yT0zA)
* [4-2 Consistency and Completeness: Rethinking Distributed Stream Processing in Apache Kafka](/Cqd6VpkUTIieb5VlSGX9Vg)
* [4-3 Apache FlinkTM: Stream and Batch Processing in a Single Engine](/etA5kCA2QcKcgQNcI0GmQg)
* [4-4 Scaling Memcache at Facebook](/mFIFHVrURRauTTBDpP-nhw)

# Data Processing Part II
* [5-1 MapReduce: Simplified Data Processing on Large Clusters](/cwr9gRcqRYC5uu5V9f_kHw)
* [5-2 Spark & Resilient Distributed Datasets](/VKMtXx0CSn2F-jJFbMvV2Q)
* [5-3 Hive – A Petabyte Scale Data Warehouse Using Hadoop](/TEe7fBcRSaaCh9dWkwzszA)
* [5-4 Disk-Locality in Datacenter Computing Considered Irrelevant](/WhP_8tr4TV6kMR8ny07ChA)

# Distributed File Systems
* [6-1 Cluster-Based Scalable Network Services](/QlH2Q3wvRy651MshyIoG0g)
* [6-2 CephFS & CRUSH](/_Lv1dLOgTMOWi9xH_5z1Ew)
* [6-3 The Google File System](/oDqjPGBmQHyCTmffGVqbvw)
* [6-4 Chord & Consistent Hashing and Random Trees](/aTWgh3K5SGuA3KhRfqwO6A)

# Distributed Databse Systems
* [7-1 Bigtable: A Distributed Storage System for Structured Data](/uzQTSQLtSJmTZXFRs8ritQ)
* [7-2 Spanner: Google’s Globally-Distributed Database](/S6pwn5y0TjW7RfRksQ1u6w)
* [7-3 DynamoDB](/Gfj0iReRRH2KnR-Jh-ZaXQ)
* [7-4 PNUTS: Yahoo!'s hosted data serving platform](/uSaRyyO0RB2aMgXbsInh1A)

# Cluster Manager
* [8-1. Large-scale cluster management at Google with Borg](/ZF1N2ye9Q8WgKoSPRxXNAg)
* [8-2. Omega: flexible, scalable schedulers for large compute clusters](/R0LOUhxWS4OkNcrWLv3-GQ)
* [8-3 Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center](/twU-b7LLRf-6BuYuTF8GZg)
* [8-4 Apache Hadoop YARN: Yet Another Resource Negotiator](/U2kPBS5VT1yMeWb2vfa5YQ)