[MCOL-4593] Multiple concurrent queries with aggregates are bottlenecked, result in lack of user scalability Created: 2021-03-08 Updated: 2023-12-22 |
|
| Status: | Stalled |
| Project: | MariaDB ColumnStore |
| Component/s: | None |
| Affects Version/s: | 1.2.0 |
| Fix Version/s: | 23.10 |
| Type: | Bug | Priority: | Trivial |
| Reporter: | Gregory Dorman (Inactive) | Assignee: | Roman |
| Resolution: | Unresolved | Votes: | 3 |
| Labels: | rm_perf | ||
| Issue Links: |
|
||||||||||||||||||||||||||||||||||||||||||||||||
| Epic Link: | ColumnStore Performance Improvements | ||||||||||||||||||||||||||||||||||||||||||||||||
| Sprint: | 2021-4, 2021-5, 2021-6, 2021-7, 2021-8, 2021-9, 2021-10, 2021-11, 2021-12, 2021-13, 2021-14, 2021-15, 2021-16, 2021-17, 2022-22, 2022-23, 2023-4, 2023-5, 2023-6, 2023-7, 2023-8, 2023-10, 2023-11 | ||||||||||||||||||||||||||||||||||||||||||||||||
| Description |
|
It has been proven by multiple experiments that Columnstore does not scale with increasing concurrency, when queries with aggregates are involved. Every additional query stream adds average latency to all other sessions regardless of the available resources and secret columnstore settings. Total CPU consumed by PrimProcs is likewise not linear (2 concurrent sessions spend more than 2x total CPU in PrimProc as compared to just one), indicating some sort of spin lock. The issue was escalated from a prospect (Quinstreet) who discovered it. |
| Comments |
| Comment by Roger Eisentrager [ 2022-06-29 ] |
|
yes, 2nd what Faisal stated. I have a client looking forward to this too. Use Case: smaller data loads with high frequency with multi-client (schema) in the CS engine. |
| Comment by JiraAutomate [ 2023-12-15 ] |
|
Automated message: |