Merge main (#227) into the grants step's branch

This commit is contained in:
2026-10-11 19:10:09 +02:00
24 changed files with 1162 additions and 23 deletions
+4
View File
@@ -514,6 +514,10 @@ func composedAndValidated(ctx context.Context, open *stores, node string, gens m
if declared.Epoch, err = open.inventory.SentEpoch(ctx, record.ID); err != nil {
return sendable{}, nil, err
}
// And the generation it was last sent, as the would-send is (novox/hq issue 234).
if declared.Generation, err = open.inventory.SentGeneration(ctx, record.ID); err != nil {
return sendable{}, nil, err
}
body, err := declared.Body()
if err != nil {
return sendable{}, nil, err
+222
View File
@@ -0,0 +1,222 @@
package main
import (
"context"
"fmt"
"io"
"os"
"sort"
"strings"
"time"
"github.com/novox/mesh-controller/internal/catalogue"
"github.com/novox/mesh-controller/internal/conditions"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
// The assignment generation a declaration was composed from, and the record of every send (novox/hq
// issue 234).
//
// On 2026-10-04 a declaration newer in sequence than every other named four fewer modules than the
// assignments held, and a machine applied it and undeclared all four. The sequence orders arrival and
// cannot tell a later send that carries an older view of the assignments. So a declaration now carries
// the generation of the assignments it was composed from — a counter the store raises in the same
// transaction as every assignment change — and a machine refuses one older than it applied, unless it is
// a gate's put-back. And every send is written down with who sent it, from which generation and naming
// which modules: the controller logged no send then, and which process sent the stale declaration could
// not be read back from anything the mesh kept.
// kindOlderGeneration is S20's kind: a machine refused a send for the generation it was composed from.
const kindOlderGeneration = "older-generation"
// generationRefusalsSaid is how long a refused send is said after its refusal: an hour, as an advisory is.
const generationRefusalsSaid = advisoryQuiet
// stamp gives a composed declaration the order allotted to it before it was composed: its sequence, and
// the epoch and generation when the machine reads them — and keeps the generation and acting epoch for the
// record of the send whether or not the machine is sent them.
//
// **No put-back mark is sent.** A gate puts a machine back by composing it again (sendRollout), so its
// declaration is allotted here like any other and carries the generation as it stands — never older than
// what the machine applied. The node-engine reads a `put_back` key (mesh-host#82); this controller never
// needs to send one.
func (o order) stamp(d *sendable) {
d.Sequence, d.Epoch = o.sequence, o.epoch
d.composedFrom, d.actingEpoch = o.generation, o.acting
d.Generation = 0
if o.readsGeneration && o.generation > 0 {
d.Generation = o.generation
}
}
// sentRecord is what the record of a send keeps beside its digest.
type sentRecord struct {
sequence int64
epoch uint64
generation int64
// toldGeneration is the generation on the wire, which the would-send is stamped with: zero for a machine
// whose node-engine has not said it reads one.
toldGeneration int64
sender string
modules []string
}
// sentRecordOf is a composed send's record: its sender is the caller this process acts for.
func sentRecordOf(ctx context.Context, d sendable) sentRecord {
return sentRecord{sequence: d.Sequence, epoch: d.actingEpoch, generation: d.composedFrom,
toldGeneration: d.Generation, sender: senderOf(callerOf(ctx)), modules: d.modules}
}
// callerOf is who asked for what this process does: the seat call's caller when ctx belongs to one, the
// caller the controller ran this command for, or the account at the shell.
func callerOf(ctx context.Context) string {
if c := link.CallerIn(ctx); c != "" {
return c
}
return link.Caller()
}
// senderOf is a send's sender in words: who asked, and the process and build that composed it — the
// answer issue 234 could not find, because two controllers and a one-shot push were all sending then.
func senderOf(caller string) string {
host, _ := os.Hostname()
return fmt.Sprintf("%s (pid %d on %s, build %s)", caller, os.Getpid(), host, version)
}
// namedModules are the modules a declaration names: its machine's set, less what was left out of it.
func namedModules(plan catalogue.Resolution, leftOut map[string]string) []string {
out := make([]string, 0, len(plan.Modules))
for _, m := range plan.Modules {
if _, left := leftOut[m.Module]; !left {
out = append(out, m.Module)
}
}
sort.Strings(out)
return out
}
// heardGenerationRefusal keeps a machine's refusal of a send for its generation, so S20 names its sender
// and says it (novox/hq issue 234): on the send it refused or — when the mesh has no record of sending that
// sequence — as a refusal of its own, naming the sender as unknown. Either way S20 is raised: a refusal the
// mesh cannot attribute is the louder fact, not a quieter one.
//
// **And raises the mesh's counter past what the machine applied, when the refused send was composed from
// the counter as it stands** (counterBehind): then the sender's view was not stale — the counter is behind
// the machine, which is a store put back from a backup — and every send after would be refused for ever. A
// stale sender's generation is below the counter, and the counter is left alone for it.
//
// Nothing is sent from here. This runs in the controller's receive loop, and a push from it would hold that
// loop, and the machine's hold, for as long as the push takes — the deaf controller of issues 184 and 185.
// S20 names `push <node>` for that case instead.
func heardGenerationRefusal(ctx context.Context, inv *inventory.Inventory, report link.Report) {
r := report.OlderGeneration
if r == nil || inv == nil || report.Node == "" {
return
}
node, err := inv.NodeByName(ctx, report.Node)
if err != nil {
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused a send for its generation, and the machine cannot be "+
"read, so it is not raised: %v\n", report.Node, err)
return
}
var raised int64
if now, err := inv.AssignmentGeneration(ctx); err != nil {
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused a send for its generation, and the mesh's own cannot be "+
"read: %v\n", report.Node, err)
} else if counterBehind(*r, now) {
if raised, err = inv.RaiseAssignmentGeneration(ctx, r.Applied); err != nil {
fmt.Fprintf(os.Stderr, "mesh-controller: the assignment generation (%d) is behind what %s applied (%d), "+
"and could not be raised: %v\n", now, report.Node, r.Applied, err)
raised = 0
} else {
fmt.Fprintf(os.Stderr, "mesh-controller: the assignment generation was %d, behind what %s applied (%d) — "+
"a store put back from a backup — and is raised to %d; `push %s` sends it what the mesh holds now\n",
now, report.Node, r.Applied, raised, report.Node)
}
}
send, found, err := inv.RefusedSend(ctx, node.ID, report.Sequence, r.Applied, raised)
if err == nil && !found {
send, err = inv.RecordUnrecordedRefusal(ctx, inventory.Send{Node: node.ID, Sequence: report.Sequence,
Epoch: report.Epoch, Generation: r.Generation, Digest: report.Declared, RefusedApplied: r.Applied,
CounterRaisedTo: raised})
}
if err != nil {
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused send %d for its generation, and the refusal could not be "+
"kept, so it is not raised: %v\n", report.Node, report.Sequence, err)
return
}
fmt.Fprintf(os.Stderr, "mesh-controller: %s refused send %d from %s: composed from assignment generation %d, "+
"and it applied %d\n", report.Node, report.Sequence, send.Sender, r.Generation, r.Applied)
}
// counterBehind says a refusal shows the mesh's counter behind the machine rather than a stale sender: the
// refused send carried the counter as it stands now, and the machine applied more than that.
func counterBehind(r link.GenerationRefusal, now int64) bool {
return r.Generation >= now && r.Applied > r.Generation
}
// watchGenerationRefusals is S20: every send a machine refused within the hour for the generation it was
// composed from, naming who sent it (novox/hq issue 234). One per machine, the newest refusal.
func watchGenerationRefusals(f *signalFacts) []conditions.Observation {
seen := map[string]bool{}
var out []conditions.Observation
for _, s := range f.refusedSends {
if s.RefusedAt == nil || f.now.Sub(*s.RefusedAt) > generationRefusalsSaid || seen[s.NodeName] {
continue
}
seen[s.NodeName] = true
o := conditions.Observation{Scope: conditions.ScopeMachine, ID: s.NodeName, Kind: kindOlderGeneration,
Machine: s.NodeName, Severity: conditions.Warning,
Summary: fmt.Sprintf("%s refused sequence %d from %s: it was composed from assignment generation %d, and "+
"%s applied generation %d — a sender composing from a view of the assignments the mesh has moved "+
"past; it named %s", s.NodeName, s.Sequence, s.Sender, s.Generation, s.NodeName, s.RefusedApplied,
modulesWords(s.Modules)),
Said: fmt.Sprintf("refused at %s", s.RefusedAt.UTC().Format(time.RFC3339)),
Headline: fmt.Sprintf("%s refused an out-of-date update", s.NodeName),
Explanation: fmt.Sprintf("Something sent %s an update made from an older list of what runs there. %s "+
"refused it, so nothing was removed. Nothing for you to do unless it repeats.", s.NodeName, s.NodeName),
Resolved: fmt.Sprintf("%s has had no out-of-date update for an hour", s.NodeName)}
if s.CounterRaisedTo > 0 {
// Not a stale sender: the mesh's counter was behind the machine (a store put back from a backup) and
// was raised; nothing has sent the machine its declaration since, so a person is asked to.
o.Summary = fmt.Sprintf("%s refused sequence %d from %s: it was composed from assignment generation %d, "+
"the mesh's own, and %s applied generation %d — the mesh's counter was behind the machine (a store "+
"put back from a backup?) and is raised to %d; `push %s` sends it what the mesh holds now",
s.NodeName, s.Sequence, s.Sender, s.Generation, s.NodeName, s.RefusedApplied, s.CounterRaisedTo,
s.NodeName)
o.Explanation = fmt.Sprintf("Needs you: push %s. The mesh's record was older than %s, so %s refused its "+
"update and kept what it had. The record is repaired; a push sends the update again.",
s.NodeName, s.NodeName, s.NodeName)
}
out = append(out, o)
}
return out
}
// modulesWords is a send's modules as a sentence says them.
func modulesWords(modules []string) string {
if len(modules) == 0 {
return "no module the mesh recorded"
}
return strings.Join(modules, ", ")
}
// writeLastSend says what a machine was last told, by whom and from which generation (novox/hq issue 234):
// nothing when the mesh has not recorded a send to it.
func writeLastSend(ctx context.Context, w io.Writer, inv *inventory.Inventory, node string) error {
s, found, err := inv.LastSend(ctx, node)
if err != nil || !found {
return err
}
generation := "no generation recorded"
if s.Generation > 0 {
generation = fmt.Sprintf("assignment generation %d", s.Generation)
}
fmt.Fprintf(w, "%s was last sent sequence %d at %s by %s, composed from %s, naming %s\n", node, s.Sequence, s.SentAt.Local().Format("2006-01-02 15:04:05"), s.Sender, generation, modulesWords(s.Modules))
if s.RefusedAt != nil {
fmt.Fprintf(w, " and refused it at %s: it had applied generation %d\n",
s.RefusedAt.Local().Format("2006-01-02 15:04:05"), s.RefusedApplied)
}
return nil
}
+148
View File
@@ -0,0 +1,148 @@
package main
import (
"encoding/json"
"strings"
"testing"
"time"
"github.com/novox/mesh-controller/internal/inventory"
"github.com/novox/mesh-controller/internal/link"
)
// The assignment generation a declaration was composed from (novox/hq issue 234).
func bodyKeys(t *testing.T, s sendable) map[string]any {
t.Helper()
raw, err := s.Body()
if err != nil {
t.Fatal(err)
}
var keys map[string]any
if err := json.Unmarshal(raw, &keys); err != nil {
t.Fatal(err)
}
return keys
}
// **The generation goes on the wire only to a machine whose node-engine said it reads one**: an older
// node-engine decodes strictly and refuses an unknown key, whole. No put-back mark is ever sent: a gate
// composes its put-back afresh, with the generation as it stands.
func TestTheGenerationIsSentOnlyToAMachineThatReadsOne(t *testing.T) {
resources := []map[string]any{{"id": "a", "type": "file", "path": "/etc/a", "content": "x\n"}}
reads := order{sequence: 12, epoch: 57, generation: 40, readsGeneration: true, acting: 57}
var told sendable
told.Resources = resources
reads.stamp(&told)
keys := bodyKeys(t, told)
if keys["generation"] != float64(40) || keys["sequence"] != float64(12) {
t.Fatalf("a machine that reads a generation was sent %v", keys)
}
if _, there := keys["put_back"]; there {
t.Fatalf("a put-back mark was sent: %v", keys)
}
if told.composedFrom != 40 || told.actingEpoch != 57 {
t.Errorf("the send does not keep what it was composed from for its record: %+v", told)
}
older := order{sequence: 12, epoch: 57, generation: 40, readsGeneration: false, acting: 57}
var untold sendable
untold.Resources = resources
older.stamp(&untold)
if _, there := bodyKeys(t, untold)["generation"]; there {
t.Fatal("a machine whose node-engine never said it reads a generation was sent one")
}
if untold.composedFrom != 40 {
t.Errorf("the generation it was composed from is recorded whether or not it was sent: %+v", untold)
}
}
// **The sender is named**: the caller of the seat call when there is one, else the shell's account, and the
// process and build that composed it.
func TestASendNamesItsSender(t *testing.T) {
said := senderOf("g14.node-tools, through the mesh-controller seat")
if !strings.Contains(said, "g14.node-tools") || !strings.Contains(said, "pid ") || !strings.Contains(said, "build ") {
t.Fatalf("the sender reads %q", said)
}
}
// refusedSend is a send a machine refused for its generation at a moment.
func refusedSend(at time.Time) inventory.Send {
return inventory.Send{NodeName: "anchor", Sequence: 12, Epoch: 57, Generation: 38, RefusedApplied: 40,
Sender: "a one-shot push by jochen at a shell on anchor (pid 4242 on anchor, build 2026.10.11)",
Modules: []string{"docker"}, SentAt: at.Add(-time.Second), RefusedAt: &at, Recorded: true}
}
// **A refused send is raised naming its sender** (novox/hq issue 234): who sent it, from which generation,
// against which the machine applied, and its sequence — the facts that took a morning to look for.
func TestARefusedSendIsRaisedNamingItsSender(t *testing.T) {
now := time.Date(2026, 10, 11, 12, 0, 0, 0, time.UTC)
f := calm(now)
f.refusedSends = []inventory.Send{refusedSend(now.Add(-time.Minute))}
got := watchGenerationRefusals(f)
if len(got) != 1 {
t.Fatalf("%+v", got)
}
o := got[0]
if o.Key() != "machine.anchor.older-generation" || o.Machine != "anchor" {
t.Errorf("raised as %s about %q", o.Key(), o.Machine)
}
for _, want := range []string{"a one-shot push by jochen", "generation 38", "generation 40", "sequence 12"} {
if !strings.Contains(o.Summary, want) {
t.Errorf("the summary does not say %q: %s", want, o.Summary)
}
}
if o.Headline == "" || o.Explanation == "" || o.Resolved == "" {
t.Errorf("the condition is not worded for the operator: %+v", o)
}
}
// **A refusal of a send the mesh has no record of is raised too, its sender said to be unknown** — never
// only a line on stderr.
func TestARefusalOfAnUnrecordedSendIsRaisedSayingTheSenderIsUnknown(t *testing.T) {
now := time.Date(2026, 10, 11, 12, 0, 0, 0, time.UTC)
f := calm(now)
s := refusedSend(now.Add(-time.Minute))
s.Recorded, s.Sender, s.Modules = false, "a sender the mesh has no record of (no send of this sequence was recorded)", nil
f.refusedSends = []inventory.Send{s}
got := watchGenerationRefusals(f)
if len(got) != 1 || !strings.Contains(got[0].Summary, "no record of") {
t.Fatalf("an unattributed refusal was not raised as one: %+v", got)
}
}
// **When the refusal showed the mesh's counter behind the machine, the condition asks for a push** — it was
// raised, and nothing has sent the machine its declaration since — and does not say there is nothing to do.
func TestACounterBehindTheMachineAsksForAPush(t *testing.T) {
now := time.Date(2026, 10, 11, 12, 0, 0, 0, time.UTC)
f := calm(now)
s := refusedSend(now.Add(-time.Minute))
s.Generation, s.RefusedApplied, s.CounterRaisedTo = 12, 40, 41
f.refusedSends = []inventory.Send{s}
got := watchGenerationRefusals(f)
if len(got) != 1 {
t.Fatalf("%+v", got)
}
if !strings.Contains(got[0].Summary, "`push anchor`") || !strings.Contains(got[0].Explanation, "push anchor") ||
strings.Contains(got[0].Explanation, "Nothing for you to do") {
t.Errorf("a counter behind the machine does not ask for a push: %s / %s", got[0].Summary, got[0].Explanation)
}
}
// **Only a refusal of the counter as it stands is the counter behind**: a stale sender's generation is below
// it, and the counter is left alone for that.
func TestOnlyARefusalOfTheCounterAsItStandsRaisesIt(t *testing.T) {
for _, c := range []struct {
refused, applied, now int64
behind bool
}{
{refused: 12, applied: 40, now: 12, behind: true}, // the store was put back: the mesh says 12, the machine had 40
{refused: 38, applied: 40, now: 41, behind: false}, // a stale sender: the counter is already past
{refused: 38, applied: 40, now: 40, behind: false}, // a stale sender: the counter is where the machine is
} {
r := link.GenerationRefusal{Generation: c.refused, Applied: c.applied}
if got := counterBehind(r, c.now); got != c.behind {
t.Errorf("refused %d, applied %d, counter %d: behind %v, want %v", c.refused, c.applied, c.now, got, c.behind)
}
}
}
+1 -1
View File
@@ -128,7 +128,7 @@ func (r *recordedDelivery) grant(context.Context, []readyNode) error { return ni
func (r *recordedDelivery) declare(ctx context.Context, s readyNode, body []byte) (string, error) {
r.declared = append(r.declared, s.node)
return recordSent(ctx, r.inv, s.node, body, s.declared.Builds, s.declared.Epoch)
return recordSent(ctx, r.inv, s.node, body, s.declared.Builds, s.declared.Epoch, sentRecordOf(ctx, s.declared))
}
// aResolver is a module built from a repository, at a commit, with something on the machine that
+1 -1
View File
@@ -77,7 +77,7 @@ func TestASendIsRecordedEvenWhenTheSenderIsBeingCancelled(t *testing.T) {
}
cancel() // the sender is going away: its context is cancelled between the send and the record
body := []byte(`{"declaration":1,"resources":[]}`)
digest, err := recordSent(ctx, inv, "anchor", body, nil, 0)
digest, err := recordSent(ctx, inv, "anchor", body, nil, 0, sentRecord{sender: "a test"})
if err != nil {
// NodeByName on the cancelled context may itself refuse; the record must still be possible
// through the detached context, so look the node up again on a live one.
+7 -1
View File
@@ -420,7 +420,8 @@ func declarationWith(ctx context.Context, open *stores, node string,
out := sendable{Resources: composed.Resources, Adoption: adoption,
Received: composed.Received, Mesh: with.Mesh, BusUsers: with.BusUsers,
LeftOut: sortedKeysOf(composed.LeftOut), leftOutWhy: composed.LeftOut, withheld: with.Withheld,
unbound: with.Unbound, foreseen: composed.Foreseen, unplaced: composed.Unplaced}
unbound: with.Unbound, foreseen: composed.Foreseen, unplaced: composed.Unplaced,
modules: namedModules(plan, composed.LeftOut)}
// And which build of each module it carries, for the send to record (novox/hq issue 259, ADR
// 0221). Read only on the send path: a question about what would be sent records nothing.
if choosing == Allocating {
@@ -1290,6 +1291,11 @@ func planCommand(ctx context.Context, args []string) error {
return nil
}
// What the machine was last told, by whom and from which assignment generation (novox/hq issue 234),
// beside what it would be told now. A record that cannot be read is said, not taken for none.
if err := writeLastSend(ctx, os.Stdout, open.inventory, args[0]); err != nil {
fmt.Printf("what %s was last sent could not be read: %v\n", args[0], err)
}
// Which modules a push would leave out, and why — said before the plan, since the plan is of
// what the machine would be told (novox/hq ADR 0163, rule 6). Judged, never composed: `plan`
// without --json allocates nothing.
+54 -8
View File
@@ -356,10 +356,16 @@ func declare(ctx context.Context, args []string) error {
// the mesh did not compose it, so a push that does not name this machine treats it as held.
// The epoch it carried, if a person wrote one in, is what the machine heard.
var carried struct {
Epoch uint64 `json:"epoch"`
Epoch uint64 `json:"epoch"`
Sequence int64 `json:"sequence"`
Generation int64 `json:"generation"`
}
_ = json.Unmarshal(raw, &carried)
if _, err := recordSent(ctx, inv, node, raw, nil, carried.Epoch); err != nil {
// And recorded as every send is (novox/hq issue 234): by hand, from what it carried; the modules it
// named are not known, since the mesh did not compose it.
if _, err := recordSent(ctx, inv, node, raw, nil, carried.Epoch, sentRecord{sequence: carried.Sequence,
epoch: carried.Epoch, generation: carried.Generation, toldGeneration: carried.Generation,
sender: senderOf(callerOf(ctx)) + ", a declaration sent by hand"}); err != nil {
return err
}
fmt.Printf("sent %s a signed declaration (%d bytes)\n", node, len(raw))
@@ -798,7 +804,7 @@ func composeEach(names []string, allot func(node string) (order, error),
refusals = append(refusals, fmt.Sprintf("%s:\n%v", name, err))
continue
}
declared.Sequence, declared.Epoch = numbered.sequence, numbered.epoch
numbered.stamp(&declared)
if len(declared.Resources) == 0 {
// Sent, not skipped (novox/hq issue 127). A node whose declaration composes to
// nothing may have HELD something before — the broker opening a placement gave it,
@@ -1016,7 +1022,8 @@ func (b overTheBus) declare(ctx context.Context, s readyNode, body []byte) (stri
}
// After it is away, not before. A digest recorded for something that failed to send would make
// the machine look current for a declaration it never received.
digest, err := recordSent(ctx, b.open.inventory, s.node, body, s.declared.Builds, s.declared.Epoch)
digest, err := recordSent(ctx, b.open.inventory, s.node, body, s.declared.Builds, s.declared.Epoch,
sentRecordOf(ctx, s.declared))
if err != nil {
return "", err
}
@@ -1228,7 +1235,7 @@ func sendToEach(ctx context.Context, open *stores, names []string) ([]string, er
refusals = append(refusals, fmt.Sprintf("%s:\n%v", name, err))
continue
}
declared.Sequence, declared.Epoch = numbered.sequence, numbered.epoch
numbered.stamp(&declared)
reportLeftOut(name, declared)
sending = append(sending, readyNode{name, declared})
}
@@ -1393,6 +1400,11 @@ func wouldSendFrom(ctx context.Context, open *stores,
if declared.Epoch, err = open.inventory.SentEpoch(ctx, n.ID); err != nil {
return nil, err
}
// And the generation it was last sent, for the same reason (novox/hq issue 234): an assignment
// elsewhere in the mesh is not a change of this machine.
if declared.Generation, err = open.inventory.SentGeneration(ctx, n.ID); err != nil {
return nil, err
}
body, err := declared.Body()
if err != nil {
return nil, err
@@ -1531,6 +1543,12 @@ var epochForActs = func(ctx context.Context) (uint64, error) { return theLease.e
type order struct {
sequence int64
epoch uint64
// generation is the assignment generation read before the composition, and readsGeneration whether the
// machine's node-engine said it reads one (novox/hq issue 234); acting is the lease epoch the sender acts
// under, whether or not the machine is sent it — both kept for the record of the send.
generation int64
readsGeneration bool
acting uint64
}
// allot takes the next sequence for a machine — the number its next declaration carries — under the
@@ -1544,6 +1562,7 @@ func allot(ctx context.Context, inv *inventory.Inventory, node string) (order, e
if err != nil {
return order{}, err
}
acting := epoch
if epoch > 0 {
reads, err := inv.ReadsEpoch(ctx, record.ID)
if err != nil {
@@ -1553,11 +1572,24 @@ func allot(ctx context.Context, inv *inventory.Inventory, node string) (order, e
epoch = 0
}
}
// **The generation is read here, before the composition reads a single assignment** (novox/hq issue
// 234). A generation only grows, so one read before is never newer than the view composed after it:
// the declaration may claim a generation older than its content, never newer — and a claim newer than
// the content is exactly the stale send the machine must be able to refuse.
generation, err := inv.AssignmentGeneration(ctx)
if err != nil {
return order{}, err
}
readsGeneration, err := inv.ReadsGeneration(ctx, record.ID)
if err != nil {
return order{}, err
}
seq, err := inv.NextSequence(ctx, record.ID)
if err != nil {
return order{}, err
}
return order{sequence: seq, epoch: epoch}, nil
return order{sequence: seq, epoch: epoch, generation: generation, readsGeneration: readsGeneration,
acting: acting}, nil
}
// recordSent writes down what a machine was just sent, and returns the digest.
@@ -1572,7 +1604,7 @@ func allot(ctx context.Context, inv *inventory.Inventory, node string) (order, e
// And the build of each module it carried (novox/hq issue 259, ADR 0221), nil when that is not known:
// what tells a machine held back by a policy or a plan from one a push left behind.
func recordSent(ctx context.Context, inv *inventory.Inventory, node string, body []byte,
builds map[string]string, epoch uint64) (string, error) {
builds map[string]string, epoch uint64, sent sentRecord) (string, error) {
kept, cancel := context.WithTimeout(context.WithoutCancel(ctx), 10*time.Second)
defer cancel()
record, err := inv.NodeByName(kept, node)
@@ -1580,7 +1612,21 @@ func recordSent(ctx context.Context, inv *inventory.Inventory, node string, body
return "", err
}
digest := digestOf(body)
if err := inv.RecordSentUnder(kept, record.ID, digest, builds, epoch); err != nil {
// The digest and the generation it carried are written in one transaction (novox/hq issue 234), so the
// would-send is never stamped with a generation the machine was not sent; and the send itself, who sent
// it and from which generation, beside them. A record of the send that cannot be written does not make a
// send that is away look failed: it is said, loudly, and the machine's own record stands.
err = inv.RecordSentWith(kept, record.ID, digest, builds, epoch, sent.toldGeneration, inventory.Send{
Sequence: sent.sequence, Epoch: int64(sent.epoch), Sender: sent.sender, Generation: sent.generation,
Digest: digest, Modules: sent.modules})
var unrecorded *inventory.SendNotRecordedError
switch {
case errors.As(err, &unrecorded):
fmt.Fprintf(os.Stderr, "mesh-controller: SEND NOT RECORDED: %s was sent declaration %s (sequence %d), and who "+
"sent it and from which generation could not be written down, so a refusal of it will name no sender "+
"(novox/hq issue 234): %v\n", node, short(digest), sent.sequence, unrecorded.Err)
fmt.Printf("%s: sent, and the record of who sent it could NOT be written: %v\n", node, unrecorded.Err)
case err != nil:
return "", err
}
// And what it was, summarised, so the next push can be compared with it (novox/hq ADR 0217).
+16
View File
@@ -27,6 +27,19 @@ type sendable struct {
// said it reads one is sent none, because an older node-engine refuses a key it does not know, whole
// (link/order.go, the contract).
Epoch uint64
// Generation is the assignment generation it was composed from (novox/hq issue 234): a machine that
// applied a later one refuses it, so a send composed from a view of the assignments the mesh has moved
// past cannot undeclare what is still assigned. Zero is not sent at all — every machine whose
// node-engine has not said it reads one is sent none, for the reason the epoch is not (an older
// node-engine refuses a key it does not know, whole).
Generation int64
// composedFrom is the generation read before this declaration was composed, and actingEpoch the
// lease epoch its sender acted under — whether or not the machine is sent either — for the record of
// the send; never on the wire.
composedFrom int64
actingEpoch uint64
// modules are the modules this declaration names, for the record of the send; never on the wire.
modules []string
// Adoption is nil for a converged node, and then the body is byte for byte what it was before
// adoption existed: an older host parses the envelope strictly and would refuse the key.
Adoption *adoptionEnvelope
@@ -94,6 +107,9 @@ func (s sendable) Body() ([]byte, error) {
if len(s.LeftOut) > 0 {
envelope["left_out"] = s.LeftOut
}
if s.Generation > 0 {
envelope["generation"] = s.Generation
}
// An empty declaration is deliberate here — the node owns nothing the mesh put there
// (novox/hq issue 127) — and the host refuses an empty body unless it is told the emptiness
// is meant, so a truncated or mis-composed body is never mistaken for "own nothing".
+14
View File
@@ -226,6 +226,20 @@ var signalsTable = []signalRow{
newest: func(f *signalFacts) time.Time {
return newestOf(f.batches, func(b batchFacts) time.Time { return b.closed })
}},
{Row: "S20", Signal: "a send refused for the assignment generation it was composed from",
Emitter: "node-engine", Trigger: "each refusal (novox/hq issue 234)",
Bound: "none: raised at the first refusal, naming its sender, the generation it came from and the one the " +
"machine applied; cleared an hour after the last",
Kind: kindOlderGeneration, Severity: conditions.Warning, Phase: 2,
needs: func(f *signalFacts) error { return f.refusedSendsErr }, watch: watchGenerationRefusals,
newest: func(f *signalFacts) time.Time {
return newestOf(f.refusedSends, func(s inventory.Send) time.Time {
if s.RefusedAt == nil {
return time.Time{}
}
return *s.RefusedAt
})
}},
{Row: "S17", Signal: "a send held for the bus's planned step is told to a person", Emitter: "controller's plan",
Trigger: "each send refused because it would replace the bus outside its step (novox/hq issue 336)",
Bound: "none: raised at the first refusal, for the operator, naming what waits, the bus build from and to, " +
+8
View File
@@ -178,6 +178,14 @@ var suppressions = map[string]suppression{
commit: "c0ffee001122", modules: []string{"app"}, since: f.now.Add(-time.Second)}}}
},
},
// A send refused by its machine for the generation it was composed from (novox/hq issue 234): said at
// once, naming its sender, for an hour after. Inside: the last such refusal was more than an hour ago.
"S20": {
inside: func(f *signalFacts) {
f.refusedSends = []inventory.Send{refusedSend(f.now.Add(-61 * time.Minute))}
},
past: func(f *signalFacts) { f.refusedSends = []inventory.Send{refusedSend(f.now.Add(-time.Second))} },
},
// Twice by hand within a fortnight is a healer wanted; once, or the first of two a day too old, is not.
"S15": {
inside: func(f *signalFacts) {
+5
View File
@@ -196,6 +196,11 @@ func (l nudgingListener) Heard(ctx context.Context, report link.Report) (bool, e
if report.Ordered() {
link.StaleRefusals.Lifetime(report.Node, report.RefusedOlder, now)
}
// A send refused for the generation it was composed from is kept on the send it refused, so S20 names
// its sender (novox/hq issue 234).
if report.OlderGeneration != nil {
heardGenerationRefusal(ctx, l.Enrolment.Inventory, report)
}
// What the machine's witnesses put back and stand by (novox/hq ADR 0236): read by the gate and its
// probe. Only from an account of the machine — not a word that a declaration was set aside, nor a rekey.
if report.Superseded == "" && report.Rekey == nil && report.Node != "" {
+5
View File
@@ -55,6 +55,10 @@ type signalFacts struct {
waits []waitFacts
// batches are the batches not yet cut (S18, S19, novox/hq ADR 0276).
batches []batchFacts
// refusedSends are the sends a machine refused within the hour for the generation they were composed
// from, each naming its sender (S20, novox/hq issue 234).
refusedSends []inventory.Send
refusedSendsErr error
loop loopFacts
loopErr error
@@ -364,6 +368,7 @@ func (w *watchdogs) gather(ctx context.Context) *signalFacts {
}
}
f.handActs, f.handActsErr = w.gatherHandActs(ctx, now)
f.refusedSends, f.refusedSendsErr = inv.RefusedSendsSince(ctx, now.Add(-generationRefusalsSaid))
f.facts.taken, _, f.facts.began, f.facts.err = exportedFacts.last()
return f
}