Merge pull request 'Tries record their asks; the try limit counts tries on a build node; build_usage shows capacity, hours and steps (issue 1890)' (#78) from fix/capacity-follows-cpu-share into main

This commit was merged in pull request #78.
This commit is contained in:
2026-10-26 20:33:34 +00:00
11 changed files with 287 additions and 38 deletions
@@ -105,7 +105,7 @@ func TryTools(tr Trying) []stdio.Tool {
{Name: check.TryTool,
Description: "Try a pushed head before its pull request is opened: the checker judges it as it judges a pull request's head, merged onto its trunk's head, " +
"its unit and integration levels through the build modules, and owes the forge nothing. Answers the try's id at once; " + check.TryReadTool + " reads " +
"where it stands. A try of the same head that waits or runs is the answer to a second ask; at most 4 wait or run at once, mesh-wide. A repository " +
"where it stands. A try of the same head that waits or runs is the answer to a second ask; a new try is refused while 4 tries run on a build node or 8 wait for one, mesh-wide; tries let in while waiting may later all run at once, and each node's build capacity bounds what runs on it. A repository " +
"the checker checks no level of (one whose trunk the gate does not name) is refused. A try whose ask no build node took within the step " +
"bound ends as error; its ask stays in the build seat's stream and may still run later, judged by nobody (issue 734).",
Input: map[string]any{"type": "object", "required": []string{"repository", "head"}, "properties": map[string]any{
@@ -135,7 +135,8 @@ func TryTools(tr Trying) []stdio.Tool {
}},
{Name: check.TryReadTool,
Description: "Where a try stands, as stored: queued, running, or its end (pass, fail, or error when it could not run), with what was said of it, " +
"the head and the trunk commit it was merged onto, the time it took and what failed first. Read-only.",
"the head and the trunk commit it was merged onto, the time it took and what failed first; while it runs, each ask it put as soon as it is put, " +
"with the node that took it, its state and the phase its step says (fetch and merge, a level's digest, lint, tests) and since when. Read-only.",
Input: map[string]any{"type": "object", "required": []string{"id"}, "properties": map[string]any{
"id": map[string]any{"type": "string", "description": "the try's id, try-<digits>"}}},
Run: func(args map[string]any) (any, error) {
+1 -1
View File
@@ -3,7 +3,7 @@ module mesh-delivery-checker
go 1.26.0
require (
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026142434-65ee43f07583
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026202658-805b4d9a3536
github.com/nats-io/nats-server/v2 v2.11.17
github.com/nats-io/nats.go v1.54.0
)
+2 -2
View File
@@ -1,5 +1,5 @@
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026142434-65ee43f07583 h1:ikD/ggf9/5k23sxJOX1PFcGzb4M3+QeC66AT0MyQ9Zs=
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026142434-65ee43f07583/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026202658-805b4d9a3536 h1:+SoDdDXF7Tgj38WP4kRpUSps6DJVl6P+w5u/KfdtwnQ=
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026202658-805b4d9a3536/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op h1:Z/MZK75wC/NSrkgqeNIa7jexam9uWzhLmFTSCPI/kn0=
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op/go.mod h1:FQyySiasQQM8735Ddel3MRojmy4dA1IqCeyJ5jmPMbI=
github.com/google/go-tpm v0.9.8 h1:slArAR9Ft+1ybZu0lBwpSmpwhRXaa85hWtMinMyRAWo=
@@ -48,6 +48,11 @@ type Case struct {
notes []string
// asks are the ids of the asks the check put on the build seats' streams, in order: a try names them (Try.Asks).
asks []string
// Watch, when set, hears each ask the check puts, as it is put (step nil), and each value its step key takes while
// the check waits for it: the node that took it, the phase it says, its end. A try writes them into its record, so a
// running try names its asks and where each stands (issue 1890). Called from the check's goroutines; it must not block
// for long.
Watch func(askID string, step *delivery.Step)
// Progress says what the check is doing, so a check that ran past its bound names the step it was stuck at.
Progress *Progress
// Kind is what asked the check (KindNew, KindNodes, KindTrunk): a carry after a trunk or sibling move is asked on the
@@ -427,8 +427,14 @@ func (st *state) askNeeding(ctx context.Context, t *target, merged *[]Fetched, l
if err := st.j.Asks.Put(ctx, a); err != nil {
return fail(t.module, fmt.Sprintf("the check of %s#%d could not be asked: %v", p.Repository, p.Number, err))
}
waiting := ctx
if watch := st.c.Watch; watch != nil {
id := a.ID
watch(id, nil) // put: a try names it at once, not only when it ends (issue 1890)
waiting = buildrun.WithStepSeen(ctx, func(s delivery.Step) { watch(id, &s) })
}
var err error
step, err = st.j.Asks.Wait(ctx, a)
step, err = st.j.Asks.Wait(waiting, a)
if err != nil {
if ctx.Err() != nil {
return fail(t.module, ctx.Err().Error())
@@ -6,6 +6,7 @@ import (
"errors"
"fmt"
"regexp"
"slices"
"sort"
"strconv"
"strings"
@@ -29,8 +30,13 @@ const (
// TriesState is the checker's state of tries: the bucket mesh-delivery-checker_tries, keys try-<unix nanoseconds>.
TriesState = "tries"
TriesBucket = delivery.CheckerModule + "_" + TriesState
// MaxTries is how many tries may wait or run at once, mesh-wide: each holds a build node for minutes.
MaxTries = 4
// MaxTries and MaxTriesWaiting are checked when a try is asked, mesh-wide: a new try is refused while MaxTries tries run
// on a build node or MaxTriesWaiting wait for one (queued, or their asks not yet taken by a node). It is no bound on
// what runs later: tries let in while waiting may later all run at once, and each node's build capacity bounds what
// runs on it. A try waiting behind the seat's other asks holds no node, so it no longer blocks the next try (issue
// 1890: at 19:53 on 2026-10-26 four tries sat queued behind 44 checks for up to 47 minutes and no fifth could be asked).
MaxTries = 4
MaxTriesWaiting = 8
// TryScan is how many of the newest tries a new ask reads to find the ones that wait or run (issue 1827).
TryScan = 64
// TryKeep is how long an ended try's key is kept before the checker removes it.
@@ -79,12 +85,104 @@ type Try struct {
Machines []string `json:"machines,omitempty"`
// Asks are the ids of the asks the try put on the build seats' streams, each ending on the step key <node>.<id> of its
// build module: the delivery view counts those steps as a try's, not a candidate's check (build_usage).
Asks []string `json:"asks,omitempty"`
Asks []string `json:"asks,omitempty"`
// Steps say where each ask stands while the try runs and after: asked until a node takes it, then the node, its
// state, the phase its step says and when (issue 1890: a 31-minute try could not be told queued from running).
Steps []TryStep `json:"steps,omitempty"`
Asked time.Time `json:"asked"`
Started time.Time `json:"started,omitzero"`
Ended time.Time `json:"ended,omitzero"`
}
// TryAsked is a TryStep's state before a build node took its ask: it waits in the seat's stream.
const TryAsked = "asked"
// TryStep is one ask of a try as its step key last said it.
type TryStep struct {
Ask string `json:"ask"`
Node string `json:"node,omitempty"`
State string `json:"state"`
Phase string `json:"phase,omitempty"`
Started time.Time `json:"started,omitzero"`
PhaseAt time.Time `json:"phase-at,omitzero"`
Ended time.Time `json:"ended,omitzero"`
}
// tryWriter writes a running try's record again as its asks are put and their steps move: one writer per try, holding
// the revision it wrote last, so the try's end is written at that revision. A write refused (the try ended by hand)
// stops the writes; the end's own write then says it.
type tryWriter struct {
mu sync.Mutex
tr *Tryer
ctx context.Context
key string
t Try
rev uint64
stopped bool
}
// heard takes an ask put (step nil) or a value of its step key in, and writes the record when it changed.
func (w *tryWriter) heard(askID string, step *delivery.Step) {
w.mu.Lock()
defer w.mu.Unlock()
if w.stopped {
return
}
changed := false
if !slices.Contains(w.t.Asks, askID) {
w.t.Asks, changed = append(w.t.Asks, askID), true
}
i := slices.IndexFunc(w.t.Steps, func(s TryStep) bool { return s.Ask == askID })
if i < 0 {
w.t.Steps, changed = append(w.t.Steps, TryStep{Ask: askID, State: TryAsked}), true
i = len(w.t.Steps) - 1
}
if step != nil {
now := TryStep{Ask: askID, Node: step.Node, State: step.State, Phase: step.Phase, Started: step.Started,
PhaseAt: step.PhaseAt, Ended: step.Ended}
changed = changed || now != w.t.Steps[i]
w.t.Steps[i] = now
}
if changed {
w.write()
}
}
// write writes the record at the revision written last; a refusal stops the writes.
func (w *tryWriter) write() {
data, err := encodeTry(w.t)
if err != nil {
return
}
rev, err := w.tr.Tries.Update(w.ctx, w.key, data, w.rev)
if err != nil {
w.stopped = true
w.tr.logf("%s: its asks' progress is no longer written: %v", w.key, err)
return
}
w.rev = rev
}
// end stops the writes and answers the record and its revision, for the try's end.
func (w *tryWriter) end() (Try, uint64) {
w.mu.Lock()
defer w.mu.Unlock()
w.stopped = true
return w.t, w.rev
}
// HoldsANode says whether the try holds a build node now: it runs, and a step of its asks runs on a node, or it names
// no step (a checker that writes its asks only at the end, or one about to put its first).
func (t Try) HoldsANode() bool {
if t.State != TryRunning {
return false
}
if len(t.Steps) == 0 {
return true
}
return slices.ContainsFunc(t.Steps, func(s TryStep) bool { return s.State == delivery.StepRunning })
}
// Over says whether the try came to its end.
func (t Try) Over() bool { return t.State == TryPass || t.State == TryFail || t.State == TryError }
@@ -124,8 +222,8 @@ func NotChecked(repository string) error {
}
// AskTry writes a new try, queued, and answers its id: a try of the same head that waits or runs is the answer to a second
// ask, and at most MaxTries wait or run at once. trunks are the gate's trunk heads of every repository (source.main): a
// repository with none is no repository the checker checks. A trunk asked by name is its trunk head now.
// ask, and a new try is refused while MaxTries tries run on a build node or MaxTriesWaiting wait for one. trunks are the
// gate's trunk heads of every repository (source.main): a repository with none is no repository the checker checks. A trunk asked by name is its trunk head now.
func AskTry(store TryStore, trunks map[string]string, a TryAsk, now time.Time) (string, error) {
repo := strings.ToLower(strings.TrimSuffix(strings.TrimSpace(a.Repository), ".git"))
head := strings.ToLower(strings.TrimSpace(a.Head))
@@ -188,7 +286,7 @@ func AskTry(store TryStore, trunks map[string]string, a TryAsk, now time.Time) (
}); err != nil {
return "", err
}
var open []string
var holding, waiting []string
for i, cur := range tries {
if !live[i] {
continue
@@ -196,10 +294,18 @@ func AskTry(store TryStore, trunks map[string]string, a TryAsk, now time.Time) (
if cur.Repository == t.Repository && cur.Head == t.Head && cur.Trunk == t.Trunk && cur.Tests == t.Tests && cur.Level == t.Level {
return cur.ID, nil
}
open = append(open, fmt.Sprintf("%s (%s@%.12s, %s)", cur.ID, cur.Repository, cur.Head, cur.State))
said := fmt.Sprintf("%s (%s@%.12s, %s)", cur.ID, cur.Repository, cur.Head, cur.State)
if cur.HoldsANode() {
holding = append(holding, said)
} else {
waiting = append(waiting, said)
}
}
if len(open) >= MaxTries {
return "", fmt.Errorf("%d tries wait or run, the most at once: %s; ask again when one ends", len(open), strings.Join(open, ", "))
// Checked at this ask only: a try queued behind the seat's checks holds no node; tries let in while waiting may later
// all run at once, and each node's build capacity bounds what runs on it.
if len(holding) >= MaxTries || len(waiting) >= MaxTriesWaiting {
return "", fmt.Errorf("a new try is refused while %d tries run on a build node or %d wait for one; now %d run and %d wait: running %s; waiting %s; ask again when one ends",
MaxTries, MaxTriesWaiting, len(holding), len(waiting), orNone(holding), orNone(waiting))
}
t.ID = "try-" + strconv.FormatInt(now.UnixNano(), 10)
data, err := encodeTry(t)
@@ -395,7 +501,8 @@ func (tr *Tryer) run(ctx context.Context, key string) {
}
return
}
cs := &Case{Key: key, Group: key,
progress := &tryWriter{tr: tr, ctx: ctx, key: key, t: t, rev: rev}
cs := &Case{Key: key, Group: key, Watch: progress.heard,
Pulls: []Pull{{Repository: t.Repository, Head: t.Head, Trunk: t.Trunk}},
Trunk: map[string]string{t.Repository: t.Trunk},
Queued: t.Asked,
@@ -409,6 +516,7 @@ func (tr *Tryer) run(ctx context.Context, key string) {
if ctx.Err() != nil {
return // left running: the checker takes it over when it starts; or ended by hand, which wrote its end
}
t, rev = progress.end()
v := out.Verdict
t.Ended = tr.now().UTC()
t.Took = t.Ended.Sub(t.Started).Round(time.Second).String()
@@ -470,3 +578,11 @@ func judgeWithin(ctx context.Context, j Judge, cs *Case, bound time.Duration) (O
}
return out, true
}
// orNone joins the tries said, or says none.
func orNone(said []string) string {
if len(said) == 0 {
return "none"
}
return strings.Join(said, ", ")
}
@@ -3,6 +3,7 @@ package check
import (
"context"
"encoding/json"
"fmt"
"strings"
"testing"
"time"
@@ -23,6 +24,19 @@ func (m memTries) Create(key string, value []byte) error {
return err
}
// writtenTries is a memKV that keeps every running try it was given to write, in order.
type writtenTries struct {
*memKV
running []Try
}
func (w *writtenTries) Update(ctx context.Context, key string, value []byte, rev uint64) (uint64, error) {
if t, err := DecodeTry(value); err == nil && !t.Over() {
w.running = append(w.running, t)
}
return w.memKV.Update(ctx, key, value, rev)
}
var tryTrunks = map[string]string{repoA: trunkA, repoSDK: trunkS, hqRepo: trunkA}
func readTry(t testing.TB, kv *memKV, id string) Try {
@@ -54,14 +68,38 @@ func TestATryIsAskedQueuedOncePerHeadAndAtMostFourAtOnce(t *testing.T) { // ADR
if err != nil || again != id {
t.Errorf("a second ask of the same head answered %q, %v, want %q", again, err, id)
}
heads := []string{head2, trunkA2, trunkS2}
for i, h := range heads {
if _, err := AskTry(store, tryTrunks, TryAsk{Repository: repoA, Head: h, Trunk: trunkA}, at.Add(time.Duration(i+2)*time.Second)); err != nil {
t.Fatalf("try %d: %v", i+2, err)
}
// Issue 1890: tries on a build node (a step of theirs running, or none named yet) and tries waiting for one (queued, or
// their asks not taken) are bounded apart, MaxTries and MaxTriesWaiting; the refusal names both counts.
onNode := func(i int) Try {
return Try{ID: fmt.Sprintf("try-%d", i), Repository: repoA, Head: fmt.Sprintf("%040x", i), Trunk: trunkA, State: TryRunning,
Steps: []TryStep{{Ask: "a", State: delivery.StepRunning}}}
}
if _, err := AskTry(store, tryTrunks, TryAsk{Repository: repoSDK, Head: head1}, at.Add(time.Minute)); err == nil || !strings.Contains(err.Error(), "4 tries wait or run") {
t.Errorf("a fifth try answered %v, want refused naming the four", err)
waitingFor := func(i int) Try {
return Try{ID: fmt.Sprintf("try-%d", i), Repository: repoA, Head: fmt.Sprintf("%040x", i), Trunk: trunkA, State: TryRunning,
Steps: []TryStep{{Ask: "a", State: TryAsked}}}
}
for _, c := range []struct {
what string
holding, wait int
refused string
}{
{"four queued behind the checks, none on a node: a fifth is taken", 0, 4, ""},
{"four on a node", MaxTries, 0, "now 4 run and 0 wait"},
{"three on a node, eight waiting", 3, MaxTriesWaiting, "a new try is refused while 4 tries run on a build node or 8 wait for one; now 3 run and 8 wait"},
} {
kv := newMemKV()
for i := range c.holding + c.wait {
tr := waitingFor(i + 1)
if i < c.holding {
tr = onNode(i + 1)
}
data, _ := encodeTry(tr)
_, _ = kv.Create(context.Background(), tr.ID, data)
}
_, err := AskTry(memTries{kv}, tryTrunks, TryAsk{Repository: repoSDK, Head: head1}, at.Add(time.Minute))
if (c.refused == "") != (err == nil) || (err != nil && !strings.Contains(err.Error(), c.refused)) {
t.Errorf("%s: answered %v, want refused %q", c.what, err, c.refused)
}
}
}
@@ -89,7 +127,8 @@ func TestATryIsJudgedAsAPullRequestsHeadAndOwesTheForgeNothing(t *testing.T) { /
t.Fatal(err)
}
b := newBench(t)
tr := &Tryer{Tries: kv, Judge: b.ex}
written := &writtenTries{memKV: kv}
tr := &Tryer{Tries: written, Judge: b.ex}
raw, _, _, _ := kv.Get(ctx, id)
tr.Put(ctx, id, raw)
tr.Wait()
@@ -97,6 +136,15 @@ func TestATryIsJudgedAsAPullRequestsHeadAndOwesTheForgeNothing(t *testing.T) { /
if got.State != TryPass || got.Took == "" || got.Head != head1 || got.Trunk != trunkA || got.Said == "" || got.Levels[delivery.LevelUnit].Run != 2 {
t.Fatalf("try = %+v", got)
}
// Issue 1890: while it runs, the try names its ask as soon as it is put, and then where its step stands; the end
// keeps each ask's node and state.
if len(written.running) < 3 || len(written.running[1].Asks) != 1 || written.running[1].Steps[0].State != TryAsked ||
written.running[2].Steps[0].Node != "shanks" {
t.Errorf("the running try's writes = %+v, want its ask named while it ran, then its node", written.running)
}
if len(got.Steps) != 1 || got.Steps[0].Node != "shanks" || got.Steps[0].State != delivery.StepPassed {
t.Errorf("the ended try's steps = %+v", got.Steps)
}
// The try names the asks it put, so the delivery view counts their steps as a try's (build_usage).
if len(got.Asks) != 1 {
t.Errorf("asks = %v, want the one check ask the try put", got.Asks)
+1 -1
View File
@@ -3,7 +3,7 @@ module mesh-delivery-view
go 1.26.0
require (
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026125731-2aae6f5580f2
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026202658-805b4d9a3536
github.com/nats-io/nats-server/v2 v2.11.17
github.com/nats-io/nats.go v1.54.0
)
+2 -2
View File
@@ -1,5 +1,5 @@
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026125731-2aae6f5580f2 h1:s1WcG7Ll1OkEwwvMKEabdWvPvTiFCHghlXiY1LoIJDA=
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026125731-2aae6f5580f2/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026202658-805b4d9a3536 h1:+SoDdDXF7Tgj38WP4kRpUSps6DJVl6P+w5u/KfdtwnQ=
git.novox.be/novox/mesh-sdk/go v0.1.14-0.20261026202658-805b4d9a3536/go.mod h1:ouERNpZizzwZ0HLEtAypsY9FR20FyUgUYRni6J7kVCY=
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op h1:Z/MZK75wC/NSrkgqeNIa7jexam9uWzhLmFTSCPI/kn0=
github.com/antithesishq/antithesis-sdk-go v0.7.0-default-no-op/go.mod h1:FQyySiasQQM8735Ddel3MRojmy4dA1IqCeyJ5jmPMbI=
github.com/google/go-tpm v0.9.8 h1:slArAR9Ft+1ybZu0lBwpSmpwhRXaa85hWtMinMyRAWo=
@@ -67,7 +67,8 @@ type UsageAnswer struct {
At time.Time `json:"at"`
Nodes []NodeUsage `json:"nodes"`
Backlog []BacklogRow `json:"backlog"`
// TriesRunning are the tries the checker runs now; their asks are counted under check until the try ends and names them.
// TriesRunning are the tries the checker runs now, each with its asks and where each stands (a checker that names its
// asks as they are put, issue 1890; an older one names them only at the end, and they are counted under check until then).
TriesRunning []TryRunning `json:"tries_running"`
Notes []string `json:"notes,omitempty"`
}
@@ -77,6 +78,9 @@ type TryRunning struct {
ID string `json:"id"`
Repository string `json:"repository"`
Started time.Time `json:"started,omitzero"`
Asks []string `json:"asks,omitempty"`
// Steps are the try's own words for each ask: asked, or the node that took it, its state and the phase its step says.
Steps json.RawMessage `json:"steps,omitempty"`
}
// NodeUsage is one node: each build seat it holds or is set to build for, whether it is eligible to build, and its CPU.
@@ -101,7 +105,17 @@ type SeatUsage struct {
// Capacity is the asks it runs at once; CapacityFrom where that came from.
Capacity int `json:"capacity"`
CapacityFrom string `json:"capacity_from"`
Paused bool `json:"paused"`
// Configured is mesh-config's capacity when the module says it judges by a lower one (capacity.<node> of its pauses
// state: the configured capacity bounded by its node's build CPU, issue 1806's follow-up); Capacity is then the
// module's and CapacityFrom its why.
Configured int `json:"configured,omitempty"`
// BuildHours is the node's build window as the module says it (HH:MM-HH:MM and its zone), absent when it builds at any
// hour; OutsideHours says the module judged the time outside it, so it takes nothing new (the operator, 2026-10-26).
BuildHours string `json:"build_hours,omitempty"`
OutsideHours bool `json:"outside_hours,omitempty"`
// BuildHoursFault is why the module cannot read its node's build-hours value, naming it: it then builds at any hour.
BuildHoursFault string `json:"build_hours_fault,omitempty"`
Paused bool `json:"paused"`
// Eligible says it takes asks: it holds the seat, has a capacity above 0 and is not paused; WhyNot says why not.
// EligibleKnown is false when this tool cannot tell (it cannot read mesh-config's capacities): Eligible is then
// absent, never false, and WhyNot starts "not known: ".
@@ -384,8 +398,9 @@ func (u UsageReader) Usage() UsageAnswer {
}
}
// Pauses: paused.<node> of each module.
// Pauses: paused.<node> of each module; and capacity.<node>, the capacity the module says it judges by.
paused := map[string]bool{} // <node>.<language>
judged := map[string]delivery.Capacity{}
for _, lang := range delivery.AskLanguages {
module, _ := delivery.BuildModuleOf(lang)
pr, ok := u.Pauses[lang]
@@ -411,6 +426,13 @@ func (u UsageReader) Usage() UsageAnswer {
paused[node+"."+lang] = p.Paused
}
}
if key, err := delivery.CapacityKey(node); err == nil {
if raw, err := pr.Get(key); err == nil && len(raw) > 0 {
if c, err := delivery.DecodeCapacity(raw); err == nil {
judged[node+"."+lang] = c
}
}
}
}
}
@@ -452,6 +474,18 @@ func (u UsageReader) Usage() UsageAnswer {
s.Capacity = (&buildrun.Places{Capacity: caps}).CapacityOf(node)
s.CapacityFrom = fmt.Sprintf("the modules' default %q: mesh-config holds no resolved value for %s on %s", buildstep.DefaultCapacities, s.Module, node)
}
if c, ok := judged[node+"."+lang]; ok && s.Holds && unknown == "" && !isBad && c.Configured == s.Capacity {
// The module running on the node says its build hours, and judges by less than mesh-config gives when its
// node's build CPU bounds it or the time is outside its build hours.
s.BuildHours, s.OutsideHours = c.BuildHours, c.OutsideHours
if c.BuildHoursFault != "" {
s.BuildHours, s.BuildHoursFault = "any hour", c.BuildHoursFault
}
if c.Effective != c.Configured {
s.Configured, s.Capacity = s.Capacity, c.Effective
s.CapacityFrom = fmt.Sprintf("%s, as %s on %s judges it (said %s)", c.Why, s.Module, node, c.At.UTC().Format(time.RFC3339))
}
}
s.Paused = paused[node+"."+lang]
s.EligibleKnown = true
switch {
@@ -466,6 +500,8 @@ func (u UsageReader) Usage() UsageAnswer {
s.WhyNot = "not known: this tool cannot read its capacity (" + unknown + ")"
case isBad:
s.WhyNot = "its capacity on " + node + " cannot be read, so its puller uses 0"
case s.OutsideHours:
s.WhyNot = "outside its build hours " + s.BuildHours + " on " + node + ": it takes nothing new until they open"
case s.Capacity == 0:
s.WhyNot = "its capacity on " + node + " is 0"
}
@@ -517,6 +553,7 @@ func (u UsageReader) tries(now time.Time, ans *UsageAnswer, note func(string, ..
want = append(want, k)
}
}
unnamed := 0
raws, err := u.Tries.values(want)
if err != nil {
note("the checker's tries cannot all be read: %v", err)
@@ -526,11 +563,12 @@ func (u UsageReader) tries(now time.Time, ans *UsageAnswer, note func(string, ..
continue
}
var t struct {
ID string `json:"id"`
Repository string `json:"repository"`
State string `json:"state"`
Started time.Time `json:"started"`
Asks []string `json:"asks"`
ID string `json:"id"`
Repository string `json:"repository"`
State string `json:"state"`
Started time.Time `json:"started"`
Asks []string `json:"asks"`
Steps json.RawMessage `json:"steps"`
}
if json.Unmarshal(raws[i], &t) != nil {
continue
@@ -539,11 +577,14 @@ func (u UsageReader) tries(now time.Time, ans *UsageAnswer, note func(string, ..
asks[a] = true
}
if t.State == "running" {
ans.TriesRunning = append(ans.TriesRunning, TryRunning{ID: t.ID, Repository: t.Repository, Started: t.Started})
ans.TriesRunning = append(ans.TriesRunning, TryRunning{ID: t.ID, Repository: t.Repository, Started: t.Started, Asks: t.Asks, Steps: t.Steps})
if len(t.Asks) == 0 {
unnamed++
}
}
}
if len(ans.TriesRunning) > 0 {
note("a running try's asks are counted under check until the try ends and names them")
if unnamed > 0 {
note("%d running tries name no ask yet (none put yet, or a checker that names them only at the end): their asks are counted under check until then", unnamed)
}
return asks
}
@@ -191,4 +191,36 @@ func TestBuildUsageAnswersEveryNodesUseFromTheStates(t *testing.T) {
if verdict["shanks"] != "not known" || verdict["ace"] != "not eligible" {
t.Errorf("verdicts with mesh-config unreadable = %v, want shanks not known, ace not eligible (paused)", verdict)
}
// Issue 1806's follow-up: the module on shanks says it judges by 1 of mesh-config's 2 (its build CPU bounds it); the
// seat says the module's capacity and why. And issue 1890: a running try that names its asks is said with them.
u = usageFixture()
u.Pauses["go"] = states(map[string]string{"capacity.shanks": `{"v":1,"effective":1,"configured":2,"quota-from":"the cpu.max of /meshyield.slice","quota-cores":6,"cores-per-step":6,"by-cpu":1,"why":"1, bounded by the CPU","at":"2026-10-26T11:00:00Z"}`,
"capacity.ace": `{"v":1,"effective":2,"configured":3,"why":"stale: mesh-config says 2 now"}`})
u.Tries = states(map[string]string{"try-" + strconv.FormatInt(at("11:58").UnixNano(), 10): `{"id":"try-2","repository":"novox/mesh-delivery","head":"h","trunk":"t","state":"running","asks":["` + tryAsk0 + `"],"steps":[{"ask":"` + tryAsk0 + `","node":"shanks","state":"running","phase":"unit: tests of 3 packages"}]}`})
bound := u.Usage()
sc := seatOf(t, bound, "shanks", "node-build-go")
if sc.Capacity != 1 || sc.Configured != 2 || !strings.HasPrefix(sc.CapacityFrom, "1, bounded by the CPU, as mesh-build-go on shanks judges it") {
t.Errorf("a seat its CPU bounds: capacity %d of %d, from %q", sc.Capacity, sc.Configured, sc.CapacityFrom)
}
if sa := seatOf(t, bound, "ace", "node-build-go"); sa.Capacity != 2 || sa.Configured != 0 {
t.Errorf("a module's word older than mesh-config's value is not taken: %+v", sa)
}
// The operator, 2026-10-26: outside its build hours the seat takes nothing new, and says so.
u.Pauses["go"] = states(map[string]string{"capacity.shanks": `{"v":1,"effective":0,"configured":2,"build-hours":"18:00-06:00 CET","outside-hours":true,"why":"0, outside its build hours 18:00-06:00 CET until 18:00 (otherwise 2)","at":"2026-10-26T11:00:00Z"}`})
if so := seatOf(t, u.Usage(), "shanks", "node-build-go"); so.Capacity != 0 || !so.OutsideHours || so.Eligible == nil || *so.Eligible ||
so.WhyNot != "outside its build hours 18:00-06:00 CET on shanks: it takes nothing new until they open" {
t.Errorf("a seat outside its build hours: %+v", so)
}
// A build-hours value the module cannot read: it builds at any hour, and the seat says the value and why.
u.Pauses["go"] = states(map[string]string{"capacity.shanks": `{"v":1,"effective":2,"configured":2,"build-hours-fault":"the build hours \"shanks=18:00-6\": \"6\" is not a time HH:MM","why":"2; at any hour, because its build hours cannot be read","at":"2026-10-26T11:00:00Z"}`})
if sf := seatOf(t, u.Usage(), "shanks", "node-build-go"); sf.BuildHours != "any hour" || !strings.Contains(sf.BuildHoursFault, "shanks=18:00-6") || sf.Eligible == nil || !*sf.Eligible {
t.Errorf("a seat whose build hours cannot be read: %+v", sf)
}
if len(bound.TriesRunning) != 1 || len(bound.TriesRunning[0].Asks) != 1 || !strings.Contains(string(bound.TriesRunning[0].Steps), "unit: tests") ||
strings.Contains(strings.Join(bound.Notes, " | "), "name no ask yet") {
t.Errorf("a running try naming its asks: %+v, notes %v", bound.TriesRunning, bound.Notes)
}
}
var tryAsk0 = stepID(at("11:58"), "a00010")