Hadoop 201 -- Deeper into the Elephant
summary
Covers advanced internals and features of Apache Hadoop: a brief recap of HDFS and MapReduce, deeper HDFS capabilities, and how YARN enables large-scale multi-application clusters. Also explains Apache HBase (Bigtable-inspired): its data model, architecture, and typical use cases for solving challenging Big Data problems.
AI-written summary · about
chapters (38)
- 0:00Start
- 3:25Genesis of Hadoop
- 4:30Data brings value
- 6:06Big Data brings big value
- 6:55Entering: Industrial Data
- 12:05HDFS: not a POSIXfs
- 13:15How do I use it?
- 14:38Principle #1
- 15:24HDFS enables the stack
- 17:44Principle #2
- 19:27MapReduce Overview
- 20:36Shuffle
- 21:15Anatomy of MapReduce
- 21:45How do I run it?
- 24:07Principle #3
- 24:39Hadoop's childhood
- 28:15MapReduce 1.0
- 29:02YARN (AKA MR2.0)
- 32:17Hamster Components
- 32:59Hamster Architecture
- 34:24Hadoop ecosystem
- 36:26Apache Bigtop
- 37:06Principle #4
- 37:28Apache HBase
- 39:14Hbase datamodel
- 42:17Dataflow model
- 42:51When do I use it?
- 43:54Principle #5
- 44:18GemFire XD: a better HBase?
- 45:06YCSB Benchmark: Throughput is 2-12X
- 45:28Principle #6
- 47:15Querying data
- 48:17How do I use Pig?
- 50:45Can we short Oracle now?
- 51:20[Close to] real-time SQL
- 56:00Principle #7
- 57:31Getting data in: Flume
- 59:07Sqoop: RDBMS connection
related talks
47mSolving Real & Big (Data) Problems Using Hadoop
29mBig Data Analysis
15mThe Future of Hadoop: What Happened & What's Possible?
48mKey trends in Big Data and new reference architecture from HP
18mHadoop Ecosystem
48mKey trends in Big Data and new reference architecture from HP
55mApache HBase: crazy dances on the elephant back
57mBig Data: Threat or Opportunity?