Merge pull request 'Let a run read from a node's pacman log never hold back a new upgrade, so the mesh can upgrade nodes at all (issue 1841)' (#454) from fix/1841-stale-run into main

modules/pacman/cmd/pacman-tools/main.go

@@ -248,12 +248,12 @@ func tools(m *Machine) []stdio.Tool {
 			Name: "pacman_upgrades",
 			Description: "Every full upgrade and rollback of every node, from the bus (ADR 0508 §1): each run's node, kind, what started it, " +
 				"its round, when it began and ended, its outcome (refused, finished, failed or running) and whether its after-upgrade check passed; " +
-				"narrowed to a node and to days, newest first. With a node and a run, that run whole, every step with its time.",
+				"narrowed to a node and to days, newest first. With a run, that run whole, every step with its time: the node's named, else this one's.",
 			Input: schema(map[string]any{
 				"node":  map[string]any{"type": "string", "description": "only this node's runs"},
 				"from":  sinceArg,
 				"until": map[string]any{"type": "string", "description": "a day, YYYY-MM-DD, the last one listed"},
-				"run":   map[string]any{"type": "string", "description": "one run, by its id, with node"},
+				"run":   map[string]any{"type": "string", "description": "one run, by its id: of node, else of this node"},
 				"limit": limitArg(50, 1000),
 			}),
 			Run: func(args map[string]any) (any, error) {
@@ -269,6 +269,11 @@ func tools(m *Machine) []stdio.Tool {
 				if err != nil {
 					return nil, err
 				}
+				if v[3] != "" && v[0] == "" {
+					// An address naming the machine has its node taken out of the arguments (the console):
+					// the run is this machine's (issue 1841).
+					v[0] = thisNode()
+				}
 				return ListUpgrades(upgradeState(StateRuns), v[0], v[1], v[2], v[3], n)
 			},
 		},

modules/pacman/cmd/pacman-tools/rollback.go

@@ -228,7 +228,7 @@ func (u *Upgrades) StartRollback(of string, removeAdded bool, ask string) (Run,
 		if o.Run.Run == r.Run.Run {
 			return r.Run, fmt.Errorf("run %s of %s is there already: one run a second", o.Run.Run, u.Node)
 		}
-		if !ended(o.Run) && o.From != FromLog {
+		if holdsTheDatabase(o.Run) {
 			return r.Run, u.refuse(r, fmt.Sprintf("run %s is still going (its last step is %s): one run at a time", o.Run.Run, lastStep(o.Run)))
 		}
 	}

modules/pacman/cmd/pacman-tools/stale_run_test.go

@@ -0,0 +1,115 @@
+package main
+
+// A run read from pacman's log, or a run whose transaction ended, never holds a new run back (issue 1841, the
+// refusal of 2026-10-22 22:00 on the control-node: "run 20220123T194900Z is still going (its last step is finished): one
+// run at a time"); and pacman_upgrades reads one run whole at an address that names the machine.
+
+import (
+	"strings"
+	"testing"
+	"time"
+)
+
+// installLogHead is the first twelve lines of the control-node's /var/log/pacman.log, captured 2026-10-22 22:10
+// with node-reads.read: the install's `pacman -Syu` with nothing to do, which became run 20220123T194900Z, its
+// last step finished at the moment it began (pacman_upgrades there, 2026-10-22: from log, outcome finished,
+// began 2022-01-23T19:49:00Z, ended 2022-01-23T20:49:00+01:00).
+const installLogHead = "[2022-01-23T20:49:00+0100] [PACMAN] Running 'pacman -Syu'\n" +
+	"[2022-01-23T20:49:00+0100] [PACMAN] synchronizing package lists\n" +
+	"[2022-01-23T20:49:00+0100] [PACMAN] starting full system upgrade\n" +
+	"[2022-01-23T20:50:45+0100] [PACMAN] Running 'pacman -S nano'\n" +
+	"[2022-01-23T20:50:49+0100] [ALPM] transaction started\n" +
+	"[2022-01-23T20:50:50+0100] [ALPM] installed nano (6.0-1)\n" +
+	"[2022-01-23T20:50:50+0100] [ALPM] transaction completed\n" +
+	"[2022-01-23T20:50:50+0100] [ALPM] running '30-systemd-update.hook'...\n" +
+	"[2022-01-23T20:55:31+0100] [PACMAN] Running 'pacman -S docker'\n" +
+	"[2022-01-23T20:55:36+0100] [ALPM] transaction started\n" +
+	"[2022-01-23T20:55:36+0100] [ALPM] installed bridge-utils (1.7.1-1)\n" +
+	"[2022-01-23T20:55:36+0100] [ALPM] installed libtool (2.4.6+42+gb88cebd5-16)\n"
+
+// 1841/AC20: given the run read from the control-node's log, when an upgrade is asked, then it starts.
+func TestARunReadFromTheLogIsHistoryAndNeverHoldsAnAsk(t *testing.T) {
+	k := newKeeperBed(t)
+	past := PastUpgrades("node-a", installLogHead)
+	if len(past) != 1 || past[0].Run != "20220123T194900Z" || steps(past[0]) != "started finished" || past[0].From != FromLog {
+		t.Fatalf("the captured log reads as the record the control-node holds: %+v", past)
+	}
+	if _, err := k.runs.Create(NodeKey("node-a", past[0].Run), past[0]); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := k.u.StartUpgrade(FromAsk, "", "a1"); err != nil {
+		t.Fatal(err)
+	}
+	var r Run
+	k.runs.value("node-a.20261004T120000Z", &r)
+	if lastStep(r) == StepRefused || len(k.root.started) != 1 {
+		t.Errorf("a run read from the log held the ask back: %s %+v", steps(r), r.Steps)
+	}
+}
+
+// 1841/AC21: given a run the mesh ran whose last step is finished, failed or refused (no after-upgrade check
+// yet, no end time of the run itself), when another run would start, then the earlier one does not hold it;
+// a run whose transaction may still go on (no step, recorded, checked before, started) does.
+func TestARunWhoseTransactionEndedNeverHoldsTheNext(t *testing.T) {
+	at := time.Date(2026, 10, 22, 20, 0, 0, 0, time.UTC)
+	for last, holds := range map[string]bool{
+		StepFinished: false, StepFailed: false, StepRefused: false, StepCheckedAfter: false,
+		"": true, StepRecorded: true, StepCheckedBefore: true, StepStarted: true,
+	} {
+		r := Run{Node: "node-a", Run: "20261022T200000Z", Kind: RunUpgrade, From: FromAsk}
+		if last != "" {
+			r.Steps = []Step{{Step: last, At: at}}
+		}
+		if got := holdsTheDatabase(r); got != holds {
+			t.Errorf("last step %q: holds %v, want %v", last, got, holds)
+		}
+		r.From = FromLog
+		if holdsTheDatabase(r) {
+			t.Errorf("a run read from the log, last step %q, holds the next", last)
+		}
+	}
+
+	k := newKeeperBed(t)
+	done := Run{Node: "node-a", Run: "20261004T110000Z", Kind: RunUpgrade, From: FromAsk,
+		Steps: []Step{{Step: StepStarted, At: k.now}, {Step: StepFinished, At: k.now}}}
+	if _, err := k.runs.Create(NodeKey("node-a", done.Run), done); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := k.u.StartUpgrade(FromAsk, "", "a1"); err != nil {
+		t.Fatal(err)
+	}
+	var r Run
+	k.runs.value("node-a.20261004T120000Z", &r)
+	if lastStep(r) == StepRefused {
+		t.Errorf("a finished run held the next: %+v", r.Steps)
+	}
+}
+
+// 1841/AC22: given an address that names the machine (the console takes `node` out of the arguments), when
+// pacman_upgrades is asked for one run, then that machine's run is answered whole.
+func TestPacmanUpgradesReadsOneRunOfThisNodeWithoutANode(t *testing.T) {
+	runs := newBucket()
+	past := PastUpgrades("node-a", installLogHead)[0]
+	if _, err := runs.Create(NodeKey("node-a", past.Run), past); err != nil {
+		t.Fatal(err)
+	}
+	savedState, savedNode := upgradeState, thisNode
+	upgradeState = func(string) Bucket { return runs }
+	thisNode = func() string { return "node-a" }
+	defer func() { upgradeState, thisNode = savedState, savedNode }()
+	for _, tool := range tools(machine(nil, 1000)) {
+		if tool.Name != "pacman_upgrades" {
+			continue
+		}
+		out, err := tool.Run(map[string]any{"run": past.Run})
+		if err != nil {
+			t.Fatalf("one run without a node: %v", err)
+		}
+		whole := out.(map[string]any)["run"].(Run)
+		if whole.Node != "node-a" || steps(whole) != "started finished" || !strings.Contains(whole.Steps[1].Why, "no transaction") {
+			t.Errorf("one run whole: %+v", whole)
+		}
+		return
+	}
+	t.Fatal("no pacman_upgrades")
+}

modules/pacman/cmd/pacman-tools/transaction.go

@@ -63,6 +63,22 @@ func ended(r Run) bool {
 	return false
 }
 
+// holdsTheDatabase says whether a run holds a new run back (one run at a time, ADR 0508 §8): only a run the
+// mesh ran whose transaction may still go on. A run read from pacman's log is history (ADR 0508 §1), and a run
+// whose last step is finished, failed, refused or checked after has no transaction left: its after-upgrade
+// check, still to be written by Follow, reads and changes nothing (issue 1841: every run read from the log
+// ended at finished and held every ask back).
+func holdsTheDatabase(r Run) bool {
+	if r.From == FromLog {
+		return false
+	}
+	switch lastStep(r) {
+	case StepFinished, StepFailed, StepRefused, StepCheckedAfter:
+		return false
+	}
+	return true
+}
+
 // ownRuns are the node's runs, oldest first, each with the revision of its key.
 func (u *Upgrades) ownRuns() ([]openRun, error) {
 	keys, err := u.Runs.Keys()
@@ -117,7 +133,7 @@ func (u *Upgrades) startUpgrade(r *openRun) error {
 		if o.Run.Run == r.Run.Run {
 			return fmt.Errorf("run %s of %s is there already: one run a second", o.Run.Run, u.Node)
 		}
-		if !ended(o.Run) {
+		if holdsTheDatabase(o.Run) {
 			return u.refuse(r, fmt.Sprintf("run %s is still going (its last step is %s): one run at a time", o.Run.Run, lastStep(o.Run)))
 		}
 	}