spdf/elektron
Archived
1
0
Fork 0
Code Issues 4 Pull requests 1 Projects Releases Packages Wiki Activity
Elektron is a lightweight, power-aware, pluggable Mesos framework that behaves as a playground to experiment with different scheduling policies to schedule ad-hoc jobs in docker containers.
This repository has been archived on 2024-04-10. You can view files and clone it, but you cannot make any changes to it's state, such as pushing and creating new issues, pull requests or comments.
23 commits 4 branches 0 tags 2.4 MiB
Find a file
Renan DelValle 3cb60d0ca2 Detection of co-scheduled benchmarks is complete
2016-12-22 22:58:58 -05:00
pcp Tied metric columns to values, next step will be determining how to store them and retrieve them 2016-12-22 22:58:58 -05:00
config basic configuration for pcp 2016-12-22 22:58:58 -05:00
metrics.go PCP code is now able to deal with receiving information asynchronously from pmdumptext 2016-12-22 22:58:58 -05:00
README.md Scheduler now has a first fit algorithm based on memory, cpu, and watts. Watts need to be set by the user but should be calculated through heuristics. Framework now also works by having a set of tasks and launching them. 2016-12-22 22:58:58 -05:00
scheduler.go Detection of co-scheduled benchmarks is complete 2016-12-22 22:58:58 -05:00
states.go Scheduler now has a first fit algorithm based on memory, cpu, and watts. Watts need to be set by the user but should be calculated through heuristics. Framework now also works by having a set of tasks and launching them. 2016-12-22 22:58:58 -05:00
task.go Fixed deadlock issue while running a large number of benchmarks. Changed names of tasks to indicate what they are running. Added name to task schema to append it to the name more easily. 2016-12-22 22:58:58 -05:00
workload_1.json Electron now launches a series of benchmarks and then shuts down when everything has been sucessfully scheduled 2016-12-22 22:58:58 -05:00

README.md

Electron: A power budget manager

To Do:

  • Define schema for what workload would look like
  • Add queue for jobs to be executed
  • Create metrics for each task launched [Time to schedule, run time, power used]
  • Have calibration phase?
  • Add ability to use constraints