Bug 1464951 - Automated CRUSH weight optimisation
Summary: Automated CRUSH weight optimisation
Keywords:
Status: CLOSED CURRENTRELEASE
Alias: None
Product: Red Hat Ceph Storage
Classification: Red Hat Storage
Component: RADOS
Version: 3.0
Hardware: Unspecified
OS: Unspecified
unspecified
medium
Target Milestone: rc
: 3.*
Assignee: Josh Durgin
QA Contact: Manohar Murthy
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2017-06-26 09:46 UTC by John Spray
Modified: 2022-02-21 18:06 UTC (History)
3 users (show)

Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Clone Of:
Environment:
Last Closed: 2019-08-14 15:11:50 UTC
Embargoed:

Attachments (Terms of Use)

Description John Spray 2017-06-26 09:46:51 UTC 
A manager module that runs on demand, or in the background, to adjust CRUSH weights based on OSD utilisation, in small enough increments to avoid excessive data movement.

Should satisfy two use cases:
 * Fixing statistical OSD imbalance to avoid one drive going full too soon
 * Automating gradual weight-in/weight-out of drives so that administrator doesn't have to personally keep adjusting weight.
Comment 5 Josh Durgin 2017-07-19 00:00:41 UTC 
Not started yet upstream, but should be backportable.
Comment 6 Giridhar Ramaraju 2019-08-05 13:07:04 UTC 
Updating the QA Contact to a Hemant. Hemant will be rerouting them to the appropriate QE Associate. 

Regards,
Giri
Comment 7 Giridhar Ramaraju 2019-08-05 13:09:38 UTC 
Updating the QA Contact to a Hemant. Hemant will be rerouting them to the appropriate QE Associate. 

Regards,
Giri
Comment 8 Josh Durgin 2019-08-14 15:11:50 UTC 
This is the balancer module.
Note You need to log in before you can comment on or make changes to this bug.