Challenges and Experiences in Building an Efficient Apache Beam Runner For IBM Streams
Summary: IBM Streams' Beam runner optimizes event-time windows by indexing inter-dependent states, garbage-collecting stale keys, and tuning bundle sizes. On NEXMark, it outruns Flink and Spark, demonstrating efficient, enterprise Beam integration on Streams. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Shen Li
- 2. Paul Gerver
- 3. John MacMillan
- 4. Daniel Debrunner
- 5. William Marshall
- 6. Kun-Lung Wu
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 288 | Storm @Twitter | 2014 | SIGMOD | 0.00028939871 |
| 314 | MillWheel: Fault-Tolerant Stream Processing at Internet Scale | 2013 | VLDB | 0.00028084774 |
| 538 | The Dataflow Model: A Practical Approach to Balancing Correctness, Latency, and Cost in Massive-Scale, Unbounded, Out-of-Order Data Processing | 2015 | VLDB | 0.00020678804 |
| 824 | Twitter Heron: Stream Processing at Scale | 2015 | SIGMOD | 0.0001623129 |
| 1,084 | Dhalion: Self-Regulating Stream Processing in Heron | 2017 | VLDB | 0.00014209714 |
| 2,338 | Samza: Stateful Scalable Stream Processing at LinkedIn | 2017 | VLDB | 9.00711e-05 |
| 3,378 | General Incremental Sliding-Window Aggregation | 2015 | VLDB | 7.1622572e-05 |
| 5,263 | Consistent Regions: Guaranteed Tuple Processing in IBM Streams | 2016 | VLDB | 5.5976361e-05 |
Previous
Page 1 / 1
Next