 Streaming languages and operator semantics - CS 591 K1: Data Stream Processing and Analytics Spring 2020SQL extensions for streams Why SQL-based approaches? • Ideally, we would like to use the same language for querying both streaming and static data. Requirements (or why SQL is not enough) • Push-based INTO RETURN SELECT ttime-time FROM state WHERE tag=’start’; } } 51 Why do we need all INSERT blocks? Vasiliki Kalavri | Boston University 2020 Summary Today you learned:0 码力 | 53 页 | 532.37 KB | 1 年前3 Streaming languages and operator semantics - CS 591 K1: Data Stream Processing and Analytics Spring 2020SQL extensions for streams Why SQL-based approaches? • Ideally, we would like to use the same language for querying both streaming and static data. Requirements (or why SQL is not enough) • Push-based INTO RETURN SELECT ttime-time FROM state WHERE tag=’start’; } } 51 Why do we need all INSERT blocks? Vasiliki Kalavri | Boston University 2020 Summary Today you learned:0 码力 | 53 页 | 532.37 KB | 1 年前3
 Course introduction - CS 591 K1: Data Stream Processing and Analytics Spring 202015 Vasiliki Kalavri | Boston University 2020 Quiz #0 Vasiliki Kalavri | Boston University 2020 Why is stream processing important? Vasiliki Kalavri | Boston University 2020 By 2025, 30% of all com/2019/01/15/tech/alibaba-city- brain-hangzhou/index.html 27 Vasiliki Kalavri | Boston University 2020 Why is stream processing challenging? 28 Vasiliki Kalavri | Boston University 2020 Using pseudocode0 码力 | 34 页 | 2.53 MB | 1 年前3 Course introduction - CS 591 K1: Data Stream Processing and Analytics Spring 202015 Vasiliki Kalavri | Boston University 2020 Quiz #0 Vasiliki Kalavri | Boston University 2020 Why is stream processing important? Vasiliki Kalavri | Boston University 2020 By 2025, 30% of all com/2019/01/15/tech/alibaba-city- brain-hangzhou/index.html 27 Vasiliki Kalavri | Boston University 2020 Why is stream processing challenging? 28 Vasiliki Kalavri | Boston University 2020 Using pseudocode0 码力 | 34 页 | 2.53 MB | 1 年前3
 Fault-tolerance demo & reconfiguration - CS 591 K1: Data Stream Processing and Analytics Spring 2020events/s time throughput degradation events/s time rate increase : input rate : throughput Why is it necessary? ??? Vasiliki Kalavri | Boston University 2020 • Ensure result correctness • reconfiguration In practice, each node is mapped to multiple points on the ring using multiple hash functions. Why? Consistent hashing ??? Vasiliki Kalavri | Boston University 2020 • It ensures state is not moved0 码力 | 41 页 | 4.09 MB | 1 年前3 Fault-tolerance demo & reconfiguration - CS 591 K1: Data Stream Processing and Analytics Spring 2020events/s time throughput degradation events/s time rate increase : input rate : throughput Why is it necessary? ??? Vasiliki Kalavri | Boston University 2020 • Ensure result correctness • reconfiguration In practice, each node is mapped to multiple points on the ring using multiple hash functions. Why? Consistent hashing ??? Vasiliki Kalavri | Boston University 2020 • It ensures state is not moved0 码力 | 41 页 | 4.09 MB | 1 年前3
 Cardinality and frequency estimation - CS 591 K1: Data Stream Processing and Analytics Spring 2020// a is a constant, a 0.39701, for m 64. ≈ ≥ 12 ??? Vasiliki Kalavri | Boston University 2020 Why LogLog? Let’s assume we want to be able to count up to n distinct elements. We need a hash function0 码力 | 69 页 | 630.01 KB | 1 年前3 Cardinality and frequency estimation - CS 591 K1: Data Stream Processing and Analytics Spring 2020// a is a constant, a 0.39701, for m 64. ≈ ≥ 12 ??? Vasiliki Kalavri | Boston University 2020 Why LogLog? Let’s assume we want to be able to count up to n distinct elements. We need a hash function0 码力 | 69 页 | 630.01 KB | 1 年前3
共 4 条
- 1













