Skip to content

Adjustable Priority Multidimensional Hot Scheduler Tasklist #3869

@nolouch

Description

@nolouch

Background

The current hotspot identification mainly uses byte and key dimensions, which are not very fit for load requests with high CPU overhead but low hard disk overhead, we plan to add QPS dimension to better describe the distribution of CPU resources.

After adding more dimension in the statistics, the hotspot scheduler can extract to a multi-objective optimized problem. For example, we have a simple workload about the IndexLoopUp scenario:
image

As you can see in the picture, the IO is very imbalanced but the QPS is balanced. In the hot read scenario, we priority to choose the QPS dimension because this scenario is CPU bound in most cases. consider there are many cases and the priority dimension may be changed in different cases, we need to support some relative dimension statistics and make the dimension's priority or weight can be turned.

Development Task

Reformat hot statistic and hot scheduler

Introduce QPS statistic

write qps

Support multi priorities

Reduce different dim conflict

Misc

Introduce the weight and priority

  • TBD

Advance

Metadata

Metadata

Assignees

Labels

type/enhancementThe issue or PR belongs to an enhancement.

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions