Delete the controller's plan machinery: plans, batches, merge window, tiers, gate, retry and healers H1 and H2 (release 6, issue 1945 B7)

This commit is contained in:
2026-10-24 16:27:55 +02:00
parent 1b0fd8b442
commit dc456d5660
236 changed files with 572 additions and 44491 deletions
-32
View File
@@ -115,26 +115,11 @@ var probeRegistry = []probe{
kindDataUnmeasured, kindDataMissing, kindArrayDegraded, kindProtectionMissing, kindCleanupWaiting},
Phase: 2, run: probeData,
Asks: []broker.SeatVerb{{Seat: "node-backup", Verb: "backed-up"}}},
// The delivery's owner (novox/hq ADR 0239): what it holds past a bound of its own table is said here, by
// the controller, and H2 works it through the owner's `close`.
{ID: probeDeliveriesID, Asserts: "no delivery is held past its state's bound unsaid: mesh-delivery's " +
"`stalled`, each with the transition its table lets healer H2 take", From: "ADR 0239",
Kind: kindDeliveryStalled, Phase: 3, run: probeDeliveries},
// What the watchman says stopped moving (ADR 0433 §2, issue 1156): each key of its stuck bucket not moved, but a
// node's presence, which the silent check takes.
{ID: probeStuckID, Asserts: "no key the watchman says stopped moving is left unsaid: each key of its stuck bucket " +
"not moved is a condition of the delivery scope until it says moved", From: "ADR 0433 §2, issue 1156",
Kind: kindStuck, Phase: 3, run: probeStuck},
// A first merge into a repository the mesh builds nothing from, kept waiting for mesh-delivery's word on the
// operator's Approve (novox/hq ADR 0432, issue 1146): said past a bound, never only in a log line (ADR 0426 §3, §8).
{ID: probeFirstBuildsID, Asserts: "no first merge into a repository the mesh builds nothing from waits more than ten " +
"minutes for mesh-delivery's announcement of the operator's Approve of its head", From: "ADR 0432, issue 1146",
Kind: kindFirstBuildUnasked, Phase: 3, run: probeFirstBuilds},
// The delivery budgets (novox/hq ADR 0282 decision 7): the newest delivery of each class within its budget,
// read from mesh-delivery's `times`; a measurement said, never a delivery held.
{ID: probeBudgetsID, Asserts: "the newest delivery of a leaf module ran on every machine within three minutes of " +
"its merge, and of a core module within ten: mesh-delivery's `times`", From: "ADR 0282, ADR 0304",
Kind: kindOverBudget, Phase: 3, run: probeBudgets},
// A client of the bus reconnecting in a loop (novox/hq issue 327), from the server's record of closed
// connections, which the bus's own module reads.
{ID: probeReconnectsID, Asserts: "no user of the bus had its connection dropped more than twelve times in the " +
@@ -168,30 +153,13 @@ var probeRegistry = []probe{
{ID: "H-controller", Asserts: "the controller lease is held, renewed in time, by a controller that says it is " +
"ready: its self-check ran and status answered in full within ten seconds", From: "ADR 0236, to-be 45 §8",
Kind: kindCoreUnhealthy, Phase: 4, run: probeControllerHealth},
{ID: "H-engine", Asserts: "every machine heard from has reported its current declaration, under a node-engine " +
"build it names", From: "ADR 0236, to-be 45 §8", Kind: kindCoreUnhealthy, Phase: 4, run: probeEngineHealth},
{ID: "H-tools", Asserts: "every machine heard from that runs the node tools has them answering the bus",
From: "ADR 0236, to-be 45 §8", Kind: kindCoreUnhealthy, Phase: 4, run: probeToolsHealth},
{ID: "H-bus", Asserts: "every stream and durable consumer the mesh defines is on the bus, and a request crosses " +
"it to the machines' node tools and back", From: "ADR 0236, to-be 45 §8", Kind: kindCoreUnhealthy, Phase: 4,
run: probeBusHealth},
// The gate's verdicts and the witnesses' rollbacks (ADR 0236): each build that failed its gate keeps its
// condition until a newer build passes; each rollback a witness stands by is said.
{ID: gateProbe, Asserts: "no build that failed its gate, and no core component a witness put back, goes unsaid; " +
"a newer build that passes its gate clears it", From: "ADR 0236, to-be 45 §8", Kind: kindRolledBack,
Raises: []string{kindRollbackFailed}, Phase: 4, run: probeGates},
// The bus's planned step (ADR 0236): open while a person's bus upgrade runs, then checked by H-bus.
{ID: busStepProbe, Asserts: "a bus upgrade a person started is said while it runs, and is followed by the bus's " +
"health within its bound — or is said failed, with its snapshot as the way back", From: "ADR 0236, to-be 45 §8",
Kind: kindBusMaintenance, Raises: []string{kindBusUpgradeFailed}, Phase: 4, run: probeBusStep},
// A delivery plan held for a backup that failed or stayed silent (ADR 0404 decision 4): one condition per plan.
{ID: backupHeldProbe, Asserts: "no delivery plan is held for a backup before its send that failed or did not " +
"answer in ten minutes", From: "ADR 0404 decision 4, issue 1066", Kind: kindBackupHeld, Phase: 1,
run: probeBackupHeld},
// A plan's send key the bus refused (ADR 0433 §4, issue 1157): in place of the timer that stood in for it.
{ID: sendKeyRefusedID, Asserts: "no delivery plan's key that watches a machine for its report was refused by the " +
"bus at the newest look", From: "ADR 0433 §4, issue 1157", Kind: kindSendKeyRefused, Phase: 1,
run: probeSendKeyRefused},
}
// probeVerdict is one probe's outcome in a run.