Files
LocalAI/core/application
Ettore Di Giacinto f0ab68e352 feat(distributed): durable backend fan-out + state reconciliation
Two connected problems handled together:

1) Backend delete/install/upgrade used to silently skip non-healthy nodes,
   so a delete during an outage left a zombie on the offline node once it
   returned. The fan-out now records intent in a new pending_backend_ops
   table before attempting the NATS round-trip. Currently-healthy nodes
   get an immediate attempt; everyone else is queued. Unique index on
   (node_id, backend, op) means reissuing the same operation refreshes
   next_retry_at instead of stacking duplicates.

2) Loaded-model state could drift from reality: a worker OOM'd, got
   killed, or restarted a backend process would leave a node_models row
   claiming the model was still loaded, feeding ghost entries into the
   /api/nodes/models listing and the router's scheduling decisions.

The existing ReplicaReconciler gains two new passes that run under a
fresh KeyStateReconciler advisory lock (non-blocking, so one wedged
frontend doesn't freeze the cluster):

  - drainPendingBackendOps: retries queued ops whose next_retry_at has
    passed on currently-healthy nodes. Success deletes the row; failure
    bumps attempts and pushes next_retry_at out with exponential backoff
    (30s → 15m cap). ErrNoResponders also marks the node unhealthy.

  - probeLoadedModels: gRPC-HealthChecks addresses the DB thinks are
    loaded but hasn't seen touched in the last probeStaleAfter (2m).
    Unreachable addresses are removed from the registry. A pluggable
    ModelProber lets tests substitute a fake without standing up gRPC.

DistributedBackendManager exposes DeleteBackendDetailed so the HTTP
handler can surface per-node outcomes ("2 succeeded, 1 queued") to the
UI in a follow-up commit; the existing DeleteBackend still returns
error-only for callers that don't care about node breakdown.

Multi-frontend safety: the state pass uses advisorylock.TryWithLockCtx
on a new key so N frontends coordinate — the same pattern the health
monitor and replica reconciler already rely on. Single-node mode runs
both passes inline (adapter is nil, state drain is a no-op).

Tests cover the upsert semantics, backoff math, the probe removing an
unreachable model but keeping a reachable one, and filtering by
probeStaleAfter.
2026-04-19 08:34:57 +00:00
..
2026-03-30 00:47:27 +02:00