The Hadoop Distributed File System Flashcards
Hadoop provides ___
a distributed filesystem and a framework for the analysis and transformation of very large data sets using the MapReduce paradigm
A Hadoop cluster ___ by simply adding servers.
scales computation capacity, storage capacity, and I/O bandwidth
HDFS stores ___ and ___ separately.
filesystem metadata
application data
HDFS’ architectural pieces (NIJDHcCBFs)
Never Intentionally Just Dropin Here ‘cause Charlie Brings Friends sometimes
NameNode Image Journal DataNodes HDFS Client CheckpointNode BackupNode Filesystem Snapshots
Files and directories are represented on the NameNode by ___
inodes
inodes record attributes like ___
permissions
modification and access times
namespace and disk space quotas
The NameNode maintains ___
the namespace tree and the mapping of blocks to DataNodes
image
the inodes and the list of blocks that define the metadata of the name system
