Project

General

Profile

Actions
Copy link

Tasks #45143

closed

cephadm: scheduler improvements

Added by Sebastian Wagner about 4 years ago. Updated almost 4 years ago.

Status:
Closed
Priority:
Normal
Assignee:
-
Category:
cephadm/scheduler
Target version:
-
% Done:

0%

Tags:
Reviewed:
Affected Versions:
Pull request ID:

Description

Prio = high

  • Removal: make sure, enough daemons joined the maps
  • Removal: priorize standby daemons
  • documentation: disable the scheduler: unmanaged=True + ceph cephadm daemon add ...

Prio = medium

  • Remove only on HEALTH_OK
  • Don't deploy on HEALTH_ERR (tbd)
  • Migrate servers via intermediate steps abc -> bcd -> cde -> def
  • Don't deploy on offline hosts

Prio = low

  • future: allow count=0

Related issues 6 (3 open — 3 closed)

Related to Orchestrator - Bug #43838: cephadm: Forcefully Remove Services (unresponsive hosts)Can't reproduce

Actions
Related to Orchestrator - Bug #44252: cephadm: mgr,mds scale-down should prefer standby daemonsResolvedAdam King

Actions
Related to Orchestrator - Feature #44255: cephadm: scheduler should consider other daemons on each nodeNew

Actions
Related to Orchestrator - Feature #43690: cephadm: service resource limitsResolved

Actions
Related to Orchestrator - Feature #43684: Make use of progress items for OSD deploymentNew

Actions
Related to Orchestrator - Feature #44993: cephadm: Resource-aware daemons placementNew

Actions
Actions
Copy link

Also available in: Atom PDF