Ilker ManapandClaude Opus 5.5
0d3eb82b9b
Nodes say where they are with llmgw.io/site, room, row, rack and pdu labels, from agent.yaml or `llmgw ctl label` (kept in the store, over the agent's). Placement spreads a model's replicas across racks and PDUs, keeps a multi-node replica within one domain when its profile says keep_within, places nothing in a domain held with `llmgw ctl facility hold` (optionally draining it), and refuses a shard that would take a domain past its power cap from facility.budgets, counting declared, derived and measured draw. Explain-placement names the domain, and keeps the rejections of a placed replica; `ctl nodes` gains LOCATION and --domain; `ctl facility` lists the domains; the console's Nodes view shows and sets location and holds. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
53 lines
1.5 KiB
Go
53 lines
1.5 KiB
Go
package config
|
|
|
|
import (
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
func TestFacilityBudgetsAreReadFromServerYAML(t *testing.T) {
|
|
p := write(t, `
|
|
facility:
|
|
margin: 0.1
|
|
gpu_watts: 700
|
|
node_watts: 350
|
|
budgets:
|
|
- domain: rack:r12-07
|
|
cap_watts: 16000
|
|
other_watts: 800
|
|
- domain: pdu:r12-07-a
|
|
cap_watts: 7400
|
|
`)
|
|
cfg, err := Load(p)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
pol, err := cfg.Facility.Policy()
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if b := pol.Budgets["rack:r12-07"]; b.CapWatts != 16000 || b.OtherWatts != 800 {
|
|
t.Errorf("rack budget %+v", b)
|
|
}
|
|
if pol.Limit("pdu:r12-07-a") != 7400*0.9 || pol.GPUWatts != 700 || pol.NodeWatts != 350 {
|
|
t.Errorf("policy %+v", pol)
|
|
}
|
|
}
|
|
|
|
func TestAFacilityBudgetThatCannotBeUsedIsRefused(t *testing.T) {
|
|
for yaml, want := range map[string]string{
|
|
"facility:\n budgets:\n - domain: r12-07\n cap_watts: 1000\n": "level:name",
|
|
"facility:\n budgets:\n - domain: rack:r1\n": "cap_watts must be above zero",
|
|
"facility:\n margin: 1.5\n": "facility.margin",
|
|
"facility:\n budgets:\n - {domain: rack:r1, cap_watts: 1}\n - {domain: rack:r1, cap_watts: 2}\n": "given twice",
|
|
} {
|
|
cfg, err := Load(write(t, yaml))
|
|
if err == nil {
|
|
err = cfg.Validate()
|
|
}
|
|
if err == nil || !strings.Contains(err.Error(), want) {
|
|
t.Errorf("%q: got %v, want %q", yaml, err, want)
|
|
}
|
|
}
|
|
}
|