jochen
1fc1e74cc3
mesh/merge-gate pass: builds mesh-host → ace, g14, novox, shanks; no bus step; every machine composes with the change as it did without (4 of 4 compose)
mesh/repo-check pass: its merge-check.sh passed
mesh/delivery delivered
mesh/delivery-group group feat/a-module-says-how-it-is-healthy delivered: every member is delivered
A container that crash-looped after its compose applied passed every check the gate had: nothing looked at what a module runs. The node-engine now judges every long-running resource on every look — one read of the runtime, one per service manager — keeps the restarts it counts across recreates and its own restarts, and says the state in every report and as an event on change, again every minute while not healthy. It reads only; nothing is restarted for being unhealthy.
53 lines
1.6 KiB
Go
53 lines
1.6 KiB
Go
package link
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
// A health statement is said on the link open now, as the machine's own word on its own subject, and
|
|
// not said — for the caller to say again — while no link is open (novox/hq ADR 0240, to-be 48 §4).
|
|
|
|
// sayingLink is a link that can say health.
|
|
type sayingLink struct {
|
|
*quietLink
|
|
said [][]byte
|
|
}
|
|
|
|
func (l *sayingLink) Health(_ context.Context, node string, body []byte) error {
|
|
l.said = append(l.said, body)
|
|
return nil
|
|
}
|
|
|
|
func TestAHealthStatementIsSaidOnTheLinkOpenNow(t *testing.T) {
|
|
q := &Queue{Membership: Membership{Node: "anchor"}}
|
|
h := Health{Contract: LivenessContract, At: time.Now().UTC(),
|
|
Resources: []ResourceHealth{{Module: "letta", Resource: "letta.server", State: StateUnhealthy, Reason: ReasonRestarting}}}
|
|
if q.SayHealth(t.Context(), h) {
|
|
t.Fatal("said with no link open")
|
|
}
|
|
l := &sayingLink{quietLink: newQuietLink()}
|
|
q.attach(t.Context(), l)
|
|
if !q.SayHealth(t.Context(), h) || len(l.said) != 1 {
|
|
t.Fatalf("not said on the open link: %d", len(l.said))
|
|
}
|
|
var got HealthSaid
|
|
if err := json.Unmarshal(l.said[0], &got); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
if got.Node != "anchor" || len(got.Health.Resources) != 1 || got.Health.Resources[0].State != StateUnhealthy {
|
|
t.Fatalf("said %+v", got)
|
|
}
|
|
// A link that cannot say it is not an error: the next report carries the statement.
|
|
q.detach(l)
|
|
q.attach(t.Context(), newQuietLink())
|
|
if q.SayHealth(t.Context(), h) {
|
|
t.Fatal("said on a link that cannot")
|
|
}
|
|
if HealthSubject("anchor") != "mesh.control.anchor.health" {
|
|
t.Fatalf("the subject %s is not inside the host's own grant", HealthSubject("anchor"))
|
|
}
|
|
}
|