@online{huang2024apache,
  author       = {Huang, Xuanqiang Angelo},
  title        = {Apache Spark},
  date         = {2024-12-27},
  organization = {Xuanqiang Angelo Huang's Blog},
  url          = {https://flecart.github.io/notes/apache-spark/},
  langid       = {english},
  abstract     = {This is a new framework that is faster than MapReduce (See Massive Parallel Processing ). It is written in Scala and has a more functional approach to programming. Spark extends the previous MapReduce framework to a generic distributed dataflow, properly modeled as a DAG. There a}
}