Scheduler: Utilization aware scheduling infrastructure.
There are situations where it is desirable to be able to schedule VMs based upon transient resource usage beyond the current reliance on specific metrics like memory usage and CPU utilization. Advanced scheduling decisions can be made based upon enhanced usage statistics encompasing things like memory cache utilization, memory bandwidth utilization, network bandwith utilization or other, currently undefined metrics, that might be available in future platforms. This bleprint will provide an extensible framework that can be used to take advantage of current and future platform utilization metrics.
Blueprint information
- Status:
- Complete
- Approver:
- Russell Bryant
- Priority:
- Low
- Drafter:
- Don Dugger
- Direction:
- Approved
- Assignee:
- Don Dugger
- Definition:
- Approved
- Series goal:
- Accepted for icehouse
- Implementation:
-
Implemented
- Milestone target:
-
2014.1
- Started by
- Russell Bryant
- Completed by
- John Garbutt
Related branches
Related bugs
Sprints
Whiteboard
this bp seems like this one: https:/
Gerrit topic: https:/
Addressed by: https:/
Stored metrics into compute_nodes as a json dictionary
Addressed by: https:/
Added plugin (e.g. CPU) to monitor and collect resource data
Addressed by: https:/
Extend the scheduler HostState for metrics from compute_node
Addressed by: https:/
Added a new scheduler resource weight plugin.
Addressed by: https:/
Make compute support plugins and store metrics in DB.
Addressed by: https:/
Added plugin (e.g. network) to monitor and collect resource data
Addressed by: https:/
Corrected typo in host_manager
Addressed by: https:/
Added a new scheduler filter for metrics
Addressed by: https:/
MetricsWeigher: Added support of unavailable metrics
Addressed by: https:/
Added temperature monitor for compute node
Addressed by: https:/
Added power monitor for compute node
Addressed by: https:/
Abstract add_timestamp out of ComputeDriverCP
Addressed by: https:/
Add node manager to read power/temperature of compute node
Addressed by: https:/
Change parameters of add_timestamp in ComputeDriverCP
Merged (Havanna):
===============
https:/
https:/
https:/
https:/
https:/
Merged (Icehouse):
===============
https:/
https:/
https:/
https:/
Pending:
=======
https:/
https:/
https:/
https:/
73139
Seems like all the above could be part of an "add-useful-
Apologies, this missed the deadline for Feature Freeze. Marking this one as Implemented, so please open a new blueprint for the remaining patches. Please rebase patches as soon as Juno opens, and we will try to get this in during that period. --johnthetubaguy (5th March 2014)
I created a new blueprint "add-useful-
Gerrit topic: https:/
Addressed by: https:/
Add useful metrics into utilization based scheduling
Gerrit topic: https:/
Addressed by: https:/
Add utilization based weighers on top of MetricsWeigher