[poolifier.git] / src / pools / selection-strategies / README.md

# Worker choice strategies

## Strategies

### Fair share

Its goal is to distribute the load evenly across all workers. To achieve this, the strategy keeps track of the average task execution time for each worker and assigns the next task to the worker with the lowest task end prediction time: `task_end_prediction = max(current_time, task_end_prediction) + average_task_execution_time`.  
By default, the strategy uses the average task execution time for each worker but it can be configured to use the event loop utilization (ELU) active time instead.

### Weighted round robin

### Interleaved weighted round robin

## Statistics

### Median

Strategies using the average task execution time for each worker can use the median instead. Median is more robust to outliers and can be used to avoid assigning tasks to workers that are currently overloaded. Median usage introduces a small overhead: measurement history must be kept for each worker and the median must be recomputed each time a new task has finished.
Commit	Line	Data
9e2ab226 JB	1	# Worker choice strategies
	2
	3	## Strategies
	4
	5	### Fair share
	6
	7	Its goal is to distribute the load evenly across all workers. To achieve this, the strategy keeps track of the average task execution time for each worker and assigns the next task to the worker with the lowest task end prediction time: `task_end_prediction = max(current_time, task_end_prediction) + average_task_execution_time`.
	8	By default, the strategy uses the average task execution time for each worker but it can be configured to use the event loop utilization (ELU) active time instead.
	9
	10	### Weighted round robin
	11
	12	### Interleaved weighted round robin
	13
	14	## Statistics
	15
	16	### Median
	17
	18	Strategies using the average task execution time for each worker can use the median instead. Median is more robust to outliers and can be used to avoid assigning tasks to workers that are currently overloaded. Median usage introduces a small overhead: measurement history must be kept for each worker and the median must be recomputed each time a new task has finished.