haiwan
/
sledge
0
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '8e91735e44'
${ noResults }
sledge/runtime/experiments/bimodal
History
Sean McBride adc730fc15
fix: correct experiment scripts to use new header 		4 years ago
..
.gitignore test: centralize bimodal and refactor concurrency 4 years ago
README.md test: centralize bimodal and refactor concurrency 4 years ago
edf_nopreemption.env chore: Enhance experimental framework with dotenv 4 years ago
edf_preemption.env chore: use triaged and fix small test nits 4 years ago
fifo_nopreemption.env chore: Enhance experimental framework with dotenv 4 years ago
fifo_preemption.env chore: Enhance experimental framework with dotenv 4 years ago
install.sh chore: make command check silent 4 years ago
run.sh fix: correct experiment scripts to use new header 4 years ago
spec.json test: centralize bimodal and refactor concurrency 4 years ago

README.md

Bimodal Distribution

This experiment drives a bimodal distribution of long-running low-priority and short-running high-priority workloads

Relative Deadlines are tuned such that the scheduler should always preempt the low-priority workload for the high-priority workload if preemption is disabled.

The two workloads are run separately as a baseline. They are then run concurrently, starting the low-priority long-running workload first such that the system begins execution and accumulates requests in the data structures. The high-priority short-running workload then begins.

Independent Variable

The Scheduling Policy: EDF versus FIFO

Dependent Variables

Latency of high priority workload