- Introduction
- Motivation or Background
- Detailed Design
- Test Design
- Impacts & Risks
- Investigation & Alternatives
- Future Work
This proposal describes the implementation of Unparalleled HashAgg that can spill intermediate data when memory usage is higher than memory quota. Spilling for paralleled HashAgg will be supported later.
Currently, the calculation logic of the aggregate executors in the TiDB is divided into two types, parallel and unparallel. However, when SQL memory usage exceeds the memory quota, neither implementation can use external memory to control memory usage and can only kill the SQL that is executing. In order to enable SQL to execute normally in the case of insufficient memory, we introduce the spilling algorithm for the unparallel aggregate executor.
In aggregate processing, memory increases when tuples are inserted into the hash table. So we can use the following algorithm to control the memory increasing:
- When the memory usage is higher than the mem-quota, switch the HashAgg executor to spill-mode.
- When HashAgg is in spill-mode, keep the tuple in the hashMap no longer growing. a. If the processing key exists in the Map, aggregate the result. b. If the processing key doesn't exist in the Map, spill the data to disk.
- After all data have been processed, output the aggregate result in the Map, clear the Map. Then read the spilling data from disk, repeat the Step1-Step3 until all data have been aggregated.
- Querying using aggregate functions should give correct result.
- When the unparallel-agg exceeds the memory quota, this feature helps reduce memory usage and run the sql successfully.
- When the parallel-agg exceeds the memory quota, the SQL will be canceled before. After the agg-concurrency args are set to 1, the SQL can run successfully.
- When the ndv of the data is low, the SQL contains distinct function will be canceled before. This feature helps the SQL run successfully.
- When the ndv of the data is high, the SQL contains distinct function will be canceled before. The SQL can be canceled successfully if there is insufficient memory.
- N/A
- The feature shouldn't cause any obvious performance regression (< 2%) on non-spilling scenario.
- Memory will still grow without increasing the number of new tuples in HashMap for distinct aggregate function.
- Support friendly spilling implementation for the distinct aggregate functions.
- Support spilling for paralleled HashAgg.