x
/
synergy-scheduler-manager
Code Issues Proposed changes
Provide advanced scheduling capability for OpenStack using a fairshare algorithm. This is a manager for synergy-service.
21 Commits 2 Branches 16 Tags 1 MiB
Python 95.4%
RPM Spec 2.1%
Shell 1.7%
Dockerfile 0.4%
Makefile 0.3%
Go to file
Vincent Llorens edac23cba4 Bump to v1.0.1 
Change-Id: I2caecaa50c80fb583d4d3fa3291a226e702babf4
 		2016-07-26 14:02:47 +02:00
doc/source import project from launchpad 2016-06-02 15:04:52 +02:00
packaging Bump to v1.0.1 2016-07-26 14:02:47 +02:00
synergy_scheduler_manager getExpiredServers() fixed 2016-06-17 09:38:19 +00:00
.coveragerc import project from launchpad 2016-06-02 15:04:52 +02:00
.gitreview Added .gitreview 2016-03-23 08:36:50 +00:00
.testr.conf import project from launchpad 2016-06-02 15:04:52 +02:00
CONTRIBUTING.rst import project from launchpad 2016-06-02 15:04:52 +02:00
HACKING.rst import project from launchpad 2016-06-02 15:04:52 +02:00
LICENSE import project from launchpad 2016-06-02 15:04:52 +02:00
MANIFEST.in import project from launchpad 2016-06-02 15:04:52 +02:00
README.rst Fix broken link to doc in README 2016-07-25 10:54:33 +02:00
babel.cfg import project from launchpad 2016-06-02 15:04:52 +02:00
requirements.txt bump to version 1.0.0 2016-06-17 15:43:56 +02:00
setup.cfg Bump to v1.0.1 2016-07-26 14:02:47 +02:00
setup.py import project from launchpad 2016-06-02 15:04:52 +02:00
test-requirements.txt add more unit tests to managers 2016-06-16 17:32:37 +02:00
tox.ini import project from launchpad 2016-06-02 15:04:52 +02:00

README.rst

SYNERGY SCHEDULER MANAGER

The Scheduler Manager

Synergy is as a new extensible general purpose management OpenStack service. Its capabilities are implemented by a collection of managers which are specific and independent pluggable tasks, executed periodically or interactively. The managers can interact with each other in a loosely coupled way. The Scheduler Manager provides advanced scheduling (fairshare) capability for OpenStack. In particular it aims to address the resource utilization issues coming from the static allocation model inherent in the Cloud paradigm, by adopting the dynamic partitioning strategy implemented by the advanced batch schedulers.