Files
mesh-controller/internal/broker/plans_building_live_test.go
T
jschoubben a14dc04b7b Hold the build seat's checks while a delivery builds, and let one check that waited 30 minutes through
ADR 0483: the controller keeps a key per plan in its build phase; holders read it and
take no new check while one is there, but for the oldest check past 30 minutes, one
at a time by a let-through key. The queue says why checks wait.
2026-10-21 19:32:47 +02:00

135 lines
4.6 KiB
Go

//go:build integration
package broker
import (
"context"
"errors"
"os"
"path/filepath"
"testing"
"time"
"github.com/nats-io/nats-server/v2/server"
"github.com/nats-io/nats.go"
"github.com/nats-io/nats.go/jetstream"
"golang.org/x/crypto/bcrypt"
)
// **A holder of the build seat reads the plans building and the server refuses its write** (novox/hq ADR 0483 clause 2, issue
// 1687): on a real server whose users are composed as the controller composes them, the controller makes the bucket and puts a
// plan's key; the build agent's credential lists the keys and gets one, and its put of a key is refused with a permissions
// violation. It also reads the first waiting ask of a check queue by a direct get, which takes nothing from the queue.
func TestNatsTheBuildSeatsHoldersReadThePlansBuildingAndTheServerRefusesTheirWrite(t *testing.T) { // 1687
hash, err := bcrypt.GenerateFromPassword([]byte("pw"), bcrypt.MinCost)
if err != nil {
t.Fatal(err)
}
seat := Seat{Name: TheBuildSeat, Scope: "node", Accepts: []string{"build"}, Emits: []string{"built", "started"}}
users, err := Users(Records{Nodes: []string{"alpha"}, Assigned: map[string][]Declared{
"alpha": {{Module: RuntimeModule}, {Module: "build-agent", Holds: []Seat{seat}}},
}})
if err != nil {
t.Fatal(err)
}
for i := range users {
users[i].PasswordHash = string(hash)
}
accounts, err := ComposeAccounts(users)
if err != nil {
t.Fatal(err)
}
conf := filepath.Join(t.TempDir(), "bus.conf")
if err := os.WriteFile(conf, []byte("listen: 127.0.0.1:-1\njetstream { store_dir: "+
`"`+t.TempDir()+`"`+" }\n"+accounts), 0o600); err != nil {
t.Fatal(err)
}
opts, err := server.ProcessConfigFile(conf)
if err != nil {
t.Fatalf("the composed accounts do not parse: %v", err)
}
opts.NoLog, opts.NoSigs = true, true
s, err := server.NewServer(opts)
if err != nil {
t.Fatal(err)
}
go s.Start()
if !s.ReadyForConnections(10 * time.Second) {
t.Fatal("the bus did not come up")
}
t.Cleanup(s.Shutdown)
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
connect := func(user string) (*nats.Conn, chan error) {
t.Helper()
refused := make(chan error, 8)
nc, err := nats.Connect(s.ClientURL(), nats.UserInfo(user, "pw"), nats.CustomInboxPrefix("_INBOX."+user),
nats.ErrorHandler(func(_ *nats.Conn, _ *nats.Subscription, err error) { refused <- err }))
if err != nil {
t.Fatalf("%s cannot connect: %v", user, err)
}
t.Cleanup(nc.Close)
return nc, refused
}
controller, _ := connect(ControllerName)
cj := OnConn(controller)
if err := AssertMeshStreams(cj); err != nil {
t.Fatalf("the controller cannot make the streams: %v", err)
}
if err := cj.EnsureControllerBuckets(); err != nil {
t.Fatalf("the controller cannot make its buckets: %v", err)
}
cjs, _ := jetstream.New(controller)
ckv, err := cjs.KeyValue(ctx, PlansBuildingBucket)
if err != nil {
t.Fatal(err)
}
if _, err := ckv.Put(ctx, "plan-1", []byte(`{"plan":"plan-1"}`)); err != nil {
t.Fatalf("the controller cannot put a plan's key: %v", err)
}
holder, refused := connect("alpha.build-agent")
hjs, err := jetstream.New(holder)
if err != nil {
t.Fatal(err)
}
kv, err := hjs.KeyValue(ctx, PlansBuildingBucket)
if err != nil {
t.Fatalf("a holder of the build seat cannot bind %s: %v", PlansBuildingBucket, err)
}
keys, err := kv.Keys(ctx)
if err != nil || len(keys) != 1 || keys[0] != "plan-1" {
t.Fatalf("the holder lists %v (%v), want plan-1", keys, err)
}
if e, err := kv.Get(ctx, "plan-1"); err != nil || e == nil {
t.Fatalf("the holder cannot get the key: %v", err)
}
// Its write is refused by the server.
if err := holder.Publish("$KV."+PlansBuildingBucket+".plan-2", []byte(`{}`)); err != nil {
t.Fatal(err)
}
_ = holder.Flush()
select {
case err := <-refused:
if !errors.Is(err, nats.ErrPermissionViolation) {
t.Errorf("the server said %v, want a permissions violation", err)
}
case <-time.After(3 * time.Second):
t.Error("the server did not refuse the holder's put of a plan's key")
}
if _, err := ckv.Get(ctx, "plan-2"); !errors.Is(err, jetstream.ErrKeyNotFound) {
t.Errorf("the refused put left a key: %v", err)
}
// And the direct get of a check queue's first waiting ask, which is granted.
reply, err := holder.RequestWithContext(ctx, "$JS.API.DIRECT.GET."+ChecksOtherStream, []byte(`{"seq":1,"next_by_subj":"`+
CheckSubjectPrefix(TheBuildSeat, false)+`>"}`))
if err != nil {
t.Fatalf("the holder's direct get of %s was not answered: %v", ChecksOtherStream, err)
}
if reply.Header.Get("Status") != "404" {
t.Errorf("an empty queue answered %q, want 404", reply.Header.Get("Status"))
}
}