框架对比

yahoo做的spark，storm 和 flink 性能对比测试

https://yahooeng.tumblr.com/post/135321837876/benchmarking-streaming-computation-engines-at

---

spark streaming， storm 浅度对比

结论：

storm低延迟，spark streaming吞吐量高

https://tsicilian.wordpress.com/2015/02/16/streaming-big-data-storm-spark-and-samza/

---

（很好）Spark Streaming vs Flink vs Storm vs Kafka Streams vs Samza : Choose Your Stream Processing Framework

1. 几个框架之间的对比

spark 和 flink比较重量级，flink比较前沿，streaming特性好，但batch特性还没有大公司采用，社区比spark细，但发展快，可以考虑。简单的业务场景可以使用其他框架，例如简单的IOT告警系统可以使用storm

2. Important Aspects of Stream Processing

Delivery Guarantees，Fault Tolerance ，State Management，Performance，Advanced Features : Event Time Processing, Watermarks, Windowing，Maturity 

3. Two Types of Stream Processing

Native Streaming

Micro-batching

链接

https://www.linkedin.com/pulse/spark-streaming-vs-flink-storm-kafka-streams-samza-choose-prakash

作者的blog（可以参考）

https://why-not-learn-something.blogspot.com/2018/03/spark-streaming-vs-flink-vs-storm-vs.html

---

（未读）High-throughput, low-latency, and exactly-once stream processing with Apache Flink™

https://data-artisans.com/blog/high-throughput-low-latency-and-exactly-once-stream-processing-with-apache-flink