ctl restart --max-surge and --max-unavailable
A model's replicas restarted one at a time, always. RestartPace says how many restart at once: MaxSurge beside themselves (replacement first), MaxUnavailable stopped first (no room needed, out while loading); the reconciler begins that many per model per pass. The admin API takes max_surge and max_unavailable on POST /api/v1/restart. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
619dd751ab
commit
5ae870e1b2
6 files changed
+155
-18
No files matched your search
@@ -5592,6 +5592,13 @@
|
||||
"in_place": {
|
||||
"type": "boolean",
|
||||
"description": "InPlace stops each replica before starting its replacement, rather than starting the replacement beside it first."
|
||||
},
|
||||
"max_surge": {
|
||||
"type": "integer",
|
||||
"description": "MaxSurge is how many of a model's replicas are replaced beside themselves at once, MaxUnavailable how many are stopped first at once; both zero is one at a time, replaced beside itself."
|
||||
},
|
||||
"max_unavailable": {
|
||||
"type": "integer"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
Reference in new issue
Block a user