Primary-key table benchmarks (insert, upsert, point lookups)

[xx789633]

Fluss supports ultra-high QPS for primary key point lookups, making it an ideal solution for serving dimension tables. Besides, the primary key table also supports real-time streaming updates for large-scale data.

To benchmark those features of primary-key table, we can adopt Alibaba Hologres' end-to-end performance testing tool [1][2] as a foundational starting point.

[1] https://www.alibabacloud.com/help/en/hologres/user-guide/best-practices-for-performance-tests-on-data-writes-data-updates-and-point-queries
[2] https://github.com/aliyun/alibabacloud-hologres-connectors/tree/master/holo-e2e-performance-tool

[caozhen1937]

Hi @xx789633 , I'm interested in kv table and I want to take this job.

[xx789633]

Hi @wuchong , could you please assign this issue to @caozhen1937 ? Hi @caozhen1937 , you can reference my poc code: https://github.com/xx789633/fluss-e2e-performance-tool

[xx789633]

Hi @caozhen1937 , how's this task going?