Ilker ManapandClaude Opus 5.5
6289b01ed6
Everything in server.yaml that is not one machine's own is now a versioned document in the store (cluster_settings), the same on every control plane. The first start against a store imports the file's cluster keys, with the baseline guard policy when there is none; after that those keys in a file are ignored, with a warning. Each control plane polls the document's version and its own server.yaml's hash. A change is validated and applied: guard live (Gate.Replace), anything else by a graceful restart that systemd brings back, standbys first and the leader 30s later. A version that does not load on a machine is not applied; at start the newest one that loads is used, so a bad edit cannot keep every control plane down. llmgw ctl config show/get/set/unset/edit/history/rollback, the admin API under /api/v1/settings, and the console's Settings screen, which layers the store's document over the machine's file, write it. Commands beside the control plane that read cluster keys (init, node add, server add, backup, upgrade) read the layered configuration; init --bundle writes offline to the store once it holds the settings. A standby that becomes the leader re-reads models, engine choices and facility holds from the store. Retires appendGuardIfMissing: the import does it. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
78 lines
2.0 KiB
Go
78 lines
2.0 KiB
Go
package control
|
|
|
|
import (
|
|
"log/slog"
|
|
"path/filepath"
|
|
"testing"
|
|
"time"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/store"
|
|
)
|
|
|
|
func TestAStoppingLeaderHandsOverAtOnceAndNeverTakesItBack(t *testing.T) {
|
|
st, err := store.Open(t.Context(), filepath.Join(t.TempDir(), "s.db"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
defer st.Close()
|
|
log := slog.New(slog.DiscardHandler)
|
|
a := NewLeadership(st, time.Minute, log)
|
|
b := NewLeadership(st, time.Minute, log)
|
|
|
|
a.attempt(t.Context())
|
|
b.attempt(t.Context())
|
|
if !a.IsLeader() || b.IsLeader() {
|
|
t.Fatalf("a %v, b %v", a.IsLeader(), b.IsLeader())
|
|
}
|
|
|
|
// Stepping down gives the lease back, rather than leaving b to wait out
|
|
// the minute it was taken for.
|
|
a.StepDown()
|
|
if a.IsLeader() {
|
|
t.Error("still leading after stepping down")
|
|
}
|
|
// A renewal already on its way when the process began to stop must not
|
|
// take it back.
|
|
a.attempt(t.Context())
|
|
if a.IsLeader() {
|
|
t.Error("took the lease again after stepping down")
|
|
}
|
|
b.attempt(t.Context())
|
|
if !b.IsLeader() {
|
|
t.Error("the standby could not take the lease that was given up")
|
|
}
|
|
lease, err := st.Leadership(t.Context(), ControlRole)
|
|
if err != nil || lease.Owner != b.Owner() {
|
|
t.Errorf("the lease is %q (%v), not b's", lease.Owner, err)
|
|
}
|
|
if got := HolderName(b.Owner()); got == "" || got == b.Owner() {
|
|
t.Errorf("holder name %q from %q", got, b.Owner())
|
|
}
|
|
}
|
|
|
|
func TestAStandbyIsToldWhenItBecomesTheLeader(t *testing.T) {
|
|
st, err := store.Open(t.Context(), filepath.Join(t.TempDir(), "s.db"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
defer st.Close()
|
|
log := slog.New(slog.DiscardHandler)
|
|
a := NewLeadership(st, time.Minute, log)
|
|
b := NewLeadership(st, time.Minute, log)
|
|
led := make(chan struct{}, 4)
|
|
b.OnLead(func() { led <- struct{}{} })
|
|
ctx := t.Context()
|
|
a.attempt(ctx)
|
|
b.attempt(ctx)
|
|
if !a.IsLeader() || b.IsLeader() {
|
|
t.Fatal("a should lead, b stand by")
|
|
}
|
|
a.StepDown()
|
|
b.attempt(ctx)
|
|
select {
|
|
case <-led:
|
|
case <-time.After(time.Second):
|
|
t.Fatal("b became the leader and was not told")
|
|
}
|
|
}
|