知识卡片
MapReduce分解批处理
MapReduce把大数据处理分成局部转换的Map和聚合结果的Reduce,使多个节点并行分担计算,并把部分分布式执行复杂性交给框架。它解决的是处理如何分解与汇总,[[GFS的容错存储目标]]解决的是数据怎样可靠保存,两者职责不同。
这张卡片看不懂?
这张卡片的反馈已满 10 条,暂时无法继续提交。
已有反馈 · 0 / 10 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- Distributed Systems Fundamentals · 查看原书依据
MapReduce took on another big question on how do you make sense of all that data spread across your computers? Imagine you have a jigsaw puzzle spread out over several tables. MapReduce is like having a bunch of friends come over, each working on pieces of the puzzle at their table, and then bringing it all together to see the big picture. It made processing
参考来源
- 位置:《Building Distributed Systems Designing scalable architectures with microservices, event-driven patterns, and robust deployment…》第01章《Distributed Systems Fundamentals》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Building Distributed Systems Designing scalable architectures with microservices, event-driven patterns, and robust deployment…/_epub-src/OPS/ch01.xhtml)
- 结论依据:原文通过相关定义、应用情境及扩展约束支撑本卡;对自动获得性能或可靠性的说法保留条件,不扩大原文保证。
- 原始内容:MapReduce took on another big question on how do you make sense of all that data spread across your computers? Imagine you have a jigsaw puzzle spread out over several tables. MapReduce is like having a bunch of friends come over, each working on pieces of the puzzle at their table, and then bringing it all together to see the big picture. It made processing