novox/mesh-controller
6
0
Fork 0
Code Issues Pull Requests 4 Releases Wiki Activity

Merge pull request 'Hand a delivery build out before pull-request checks (issue 558)' (#276) from fix/558-a-delivery-build-goes-first into main

Browse Source
This commit was merged in pull request #276.
This commit is contained in:
mesh-admin
2026-10-12 21:20:19 +00:00
parent 2f157148c6 fc573f951a
commit 961f2e82ea
7 changed files with 978 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/mesh-controller/queue.go
+56 -14
View File
@@ -14,7 +14,6 @@ import (
"time"
"github.com/nats-io/nats.go"
"github.com/nats-io/nats.go/jetstream"
"github.com/novox/mesh-controller/internal/broker"
"github.com/novox/mesh-controller/internal/inventory"
@@ -81,6 +80,30 @@ func listQueue(ctx context.Context, args []string, w io.Writer) error {
return nil
}
// keepingTheQueueInOrder runs the build queue's passes while this controller acts (novox/hq issue 558):
// the one process that puts the queue in order, so no two passes pause and resume it over each other.
// The build seat is read from the catalogue at most every half minute.
func keepingTheQueueInOrder(ctx context.Context, open *stores, js *broker.JetStream) {
if js == nil {
return
}
seat, readAt := link.TheBuildMachine, time.Time{}
seatNow := func() string {
if time.Since(readAt) < watchEvery {
return seat
}
if entries, err := open.inventory.Catalogued(ctx); err == nil {
seat, readAt = buildSeatAmong(entries), time.Now()
} else {
fmt.Printf("the build seat is read as %s: the catalogue cannot be read: %v\n", seat, err)
}
return seat
}
link.KeepingInOrder(ctx, js, seatNow, link.Holding, func(format string, args ...any) {
fmt.Printf(format+"\n", args...)
})
}
// queueAnswer is the queue as data (novox/hq issue 455): what a caller reads to say how far back an ask
// waits — "waiting in the build queue behind 2" — which the table alone could not tell it. Text is the
// table, written from the same read: the verb answers it as its output and the rest as its answer, so the
@@ -100,7 +123,8 @@ type queueAnswer struct {
type queuedAnswer struct {
ID string `json:"id"`
State string `json:"state"`
// Kind is "check" for a pull request's merge check, "build" for anything else.
// Kind is "delivery" for a build a walk waits for, "check" for a pull request's check and any ask
// whose kind cannot be told (link.KindOf, novox/hq issue 558).
Kind string `json:"kind"`
Repository string `json:"repository"`
Path string `json:"path,omitempty"`
@@ -129,10 +153,7 @@ func queueAnswerOf(q link.Queue, now time.Time) queueAnswer {
out := queueAnswer{Seat: q.Seat, Waiting: len(waiting), InFlight: len(running), Dead: len(dead),
MaxDeliver: q.MaxDeliver, Asks: []queuedAnswer{}, Text: queueText(q, now)}
one := func(a link.QueuedAsk, position int) queuedAnswer {
kind := "build"
if a.Request.Check != nil {
kind = "check"
}
kind := link.KindOf(a.Request)
since := a.AskedAt
if a.State == link.AskInFlight && a.On != "" && !a.Started.IsZero() {
since = a.Started
@@ -189,19 +210,20 @@ func queueText(q link.Queue, now time.Time) string {
case a.Was != "":
where = fmt.Sprintf("handed back by %s, to be handed out again", a.Was)
}
fmt.Fprintf(&b, " %-26s %s — %s, %s (seq %d)\n", a.ID, what(a), where, ago(a.AskedAt), a.Seq)
fmt.Fprintf(&b, " %-26s %-8s %s — %s, %s (seq %d)\n", a.ID, link.KindOf(a.Request), what(a), where,
ago(a.AskedAt), a.Seq)
}
}
if len(waiting) > 0 {
fmt.Fprintln(&b, "\nwaiting:")
fmt.Fprintln(&b, "\nwaiting, in the order they are handed out:")
for _, a := range waiting {
fmt.Fprintf(&b, " %-26s %s — %s (seq %d)\n", a.ID, what(a), ago(a.AskedAt), a.Seq)
fmt.Fprintf(&b, " %-26s %-8s %s — %s (seq %d)\n", a.ID, link.KindOf(a.Request), what(a), ago(a.AskedAt), a.Seq)
}
}
if len(dead) > 0 {
fmt.Fprintf(&b, "\ndead — handed out as often as the worker allows (%d) and never settled, still held:\n", q.MaxDeliver)
for _, a := range dead {
fmt.Fprintf(&b, " %-26s %s — %s (seq %d)\n", a.ID, what(a), ago(a.AskedAt), a.Seq)
fmt.Fprintf(&b, " %-26s %-8s %s — %s (seq %d)\n", a.ID, link.KindOf(a.Request), what(a), ago(a.AskedAt), a.Seq)
}
}
switch {
@@ -275,6 +297,15 @@ func cancelAsk(ctx context.Context, js *broker.JetStream, open *stores, seat str
}
}
worker, _ := broker.HolderConsumerFor("", "", broker.DeclaredSeat{Name: seat, Accepts: []string{"build"}})
// **Where it waits now** (novox/hq issue 558): moved into order since it was read, a waiting ask has a
// later sequence, and the worker handing out what was behind its old one is not it being taken.
if ask.State == link.AskWaiting {
if q, err := link.ReadQueue(ctx, js, seat); err == nil {
if now, ok := q.Find(ask.ID); ok && now.State == link.AskWaiting {
ask.Seq = now.Seq
}
}
}
switch ask.State {
case link.AskWaiting:
if taken, err := takenSince(js, worker, ask.Seq); err != nil {
@@ -296,14 +327,25 @@ func cancelAsk(ctx context.Context, js *broker.JetStream, open *stores, seat str
"ends it there", ask.ID, started, ask.ID)
}
}
if err := js.Context().DeleteMsg(worker.Stream, ask.Seq); err != nil && !errors.Is(err, nats.ErrMsgNotFound) &&
!errors.Is(err, jetstream.ErrMsgNotFound) && !strings.Contains(err.Error(), "no message found") {
// Found by its id when it was moved into order since it was read (novox/hq issue 558).
removed, err := link.DeleteAsk(ctx, js, seat, ask)
if err != nil {
return "", fmt.Errorf("%s is marked cancelled and could not be deleted from the queue (seq %d): %w — a "+
"holder taking it ends it as cancelled", ask.ID, ask.Seq, err)
}
recordCancelled(ctx, open, ask)
return fmt.Sprintf("cancelled %s (%s, %s): deleted from the %s queue and recorded failed, %s — a plan "+
"that asked for it fails with that", ask.ID, ask.Repository, ask.State, seat, link.CancelledByHand), nil
return cancelSaid(ask, seat, removed), nil
}
// cancelSaid is what a cancel says: deleted from the queue only when it was.
func cancelSaid(ask link.QueuedAsk, seat string, removed uint64) string {
where := fmt.Sprintf("deleted from the %s queue", seat)
if removed == 0 {
where = fmt.Sprintf("no longer in the %s queue to delete, and marked cancelled, so a holder taking it "+
"ends it", seat)
}
return fmt.Sprintf("cancelled %s (%s, %s): %s and recorded failed, %s — a plan "+
"that asked for it fails with that", ask.ID, ask.Repository, ask.State, where, link.CancelledByHand)
}
// holderLooks is how long a cancel waits for a holder that took the ask before the mark to say it
cmd/mesh-controller/queue_answer_test.go
+22 -2
View File
@@ -24,7 +24,7 @@ func aQueueOfEachKind(now time.Time) link.Queue {
State: link.AskInFlight, On: "ace", Started: started,
Request: link.BuildRequest{ID: "build-running", Check: &link.CheckRequest{Owner: "novox", Repo: "mesh-host"}}},
{Seq: 3, ID: "build-first", Repository: "ssh://forge/novox/mesh-catalog", Ref: "main", AskedAt: asked,
State: link.AskWaiting},
State: link.AskWaiting, Request: link.BuildRequest{ID: "build-first", Repository: "ssh://forge/novox/mesh-catalog"}},
{Seq: 4, ID: "build-second", Repository: "ssh://forge/novox/mesh-catalog", Path: "modules/gitea", Ref: aCommit,
AskedAt: now.Add(-time.Minute), State: link.AskWaiting,
Request: link.BuildRequest{ID: "build-second", Check: &link.CheckRequest{Owner: "novox", Repo: "mesh-catalog"}}},
@@ -51,7 +51,7 @@ func TestTheQueueVerbAnswersEachAskAsData(t *testing.T) {
t.Errorf("in flight: %+v", running)
}
first, second := byID["build-first"], byID["build-second"]
if first.Position != 1 || first.Kind != "build" || first.Commit != "" || first.Ref != "main" || first.Machine != "" ||
if first.Position != 1 || first.Kind != "delivery" || first.Commit != "" || first.Ref != "main" || first.Machine != "" ||
!first.Since.Equal(now.Add(-5*time.Minute)) {
t.Errorf("first waiting: %+v", first)
}
@@ -62,6 +62,13 @@ func TestTheQueueVerbAnswersEachAskAsData(t *testing.T) {
if dead := byID["build-dead"]; dead.Position != 0 || dead.State != link.AskDead {
t.Errorf("dead: %+v", dead)
}
// And the table says each ask's kind too (novox/hq issue 558).
for _, line := range []string{"build-running check ", "build-first delivery ",
"build-second check ", "build-dead check "} {
if !strings.Contains(got.Text, line) {
t.Errorf("the table does not say %q:\n%s", line, got.Text)
}
}
// In the table's order: in flight, then the waiting by position, then the dead.
var order []string
for _, a := range got.Asks {
@@ -135,3 +142,16 @@ func TestTheQueueNeverShowsARepositorysPassword(t *testing.T) {
}
}
}
// A cancel says it deleted the ask only when it did: moved into order and gone since, it says so (novox/hq
// issue 558).
func TestACancelSaysDeletedOnlyWhenItDeleted(t *testing.T) {
ask := link.QueuedAsk{ID: "build-1", Repository: "novox/x", State: link.AskWaiting, Seq: 4}
if said := cancelSaid(ask, link.TheBuildMachine, 9); !strings.Contains(said, "deleted from the") {
t.Errorf("removed, it says: %s", said)
}
if said := cancelSaid(ask, link.TheBuildMachine, 0); strings.Contains(said, "deleted from") ||
!strings.Contains(said, "no longer in the") {
t.Errorf("gone already, it says: %s", said)
}
}
cmd/mesh-controller/watchdogs.go
+3
View File
@@ -739,6 +739,9 @@ func watchTheMesh(ctx context.Context, open *stores, server *link.Server, bus li
// and the answer chosen is performed on its warrant.
startAsking(watching, open, server, bus.Conn, keeper)
go forgettingOldHeals(watching, open.inventory)
// And the build queue's order (novox/hq issue 558): a check that has waited its while goes ahead of the
// deliveries asked after it even when nothing new is asked.
go keepingTheQueueInOrder(watching, open, server.JetStream())
fmt.Printf("watching the mesh: %d signal(s) every %s, %d probe(s) every %s; what is wrong is kept in %s "+
"and said as %s events\n", len(watchedRows()), watchEvery, len(runnableProbes()), doctorEvery,
broker.ConditionsBucket, conditions.Seat)