Feat v0.6.0 cluster registry + HA
All checks were successful
CI/CD / detect-changes (pull_request) Successful in 21s
CI/CD / test-frontend (pull_request) Successful in 5s
CI/CD / test-go-pg (pull_request) Successful in 2m58s
CI/CD / test-sqlite (pull_request) Successful in 3m2s
CI/CD / build-and-deploy (pull_request) Successful in 1m15s
All checks were successful
CI/CD / detect-changes (pull_request) Successful in 21s
CI/CD / test-frontend (pull_request) Successful in 5s
CI/CD / test-go-pg (pull_request) Successful in 2m58s
CI/CD / test-sqlite (pull_request) Successful in 3m2s
CI/CD / build-and-deploy (pull_request) Successful in 1m15s
PG-backed cluster registry for horizontal scaling — zero new infrastructure (no etcd/Consul/Redis). MVP convergence point. - node_registry UNLOGGED table (migration 013) - Self-registration, heartbeat tick (10s), stale sweep (30s), self-eviction (os.Exit on 0 rows → K8s restarts) - GET /api/v1/admin/cluster returns nodes with runtime stats - Health endpoints include node_id + cluster size/peers - cluster-dashboard admin surface with auto-refresh - 3-replica E2E test (docker-compose-e2e.yml + ci/e2e-cluster-test.sh) - chat + cluster-dashboard added to curated default bundle - 5 new tests (3 unit + 2 handler), all passing Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
78
server/store/postgres/cluster.go
Normal file
78
server/store/postgres/cluster.go
Normal file
@@ -0,0 +1,78 @@
|
||||
package postgres
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"switchboard-core/store"
|
||||
)
|
||||
|
||||
// ClusterStore manages node_registry — Postgres-only UNLOGGED table.
|
||||
type ClusterStore struct{}
|
||||
|
||||
func NewClusterStore() *ClusterStore { return &ClusterStore{} }
|
||||
|
||||
func (s *ClusterStore) Register(ctx context.Context, nodeID, endpoint string) error {
|
||||
_, err := DB.ExecContext(ctx, `
|
||||
INSERT INTO node_registry (node_id, endpoint)
|
||||
VALUES ($1, $2)
|
||||
ON CONFLICT (node_id) DO UPDATE
|
||||
SET endpoint = EXCLUDED.endpoint,
|
||||
registered_at = now(),
|
||||
heartbeat = now(),
|
||||
stats = '{}'
|
||||
`, nodeID, endpoint)
|
||||
return err
|
||||
}
|
||||
|
||||
func (s *ClusterStore) Heartbeat(ctx context.Context, nodeID string, stats json.RawMessage) (int64, error) {
|
||||
result, err := DB.ExecContext(ctx, `
|
||||
UPDATE node_registry
|
||||
SET heartbeat = now(), stats = $2
|
||||
WHERE node_id = $1
|
||||
`, nodeID, stats)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
return result.RowsAffected()
|
||||
}
|
||||
|
||||
func (s *ClusterStore) SweepStale(ctx context.Context, threshold time.Duration) (int64, error) {
|
||||
result, err := DB.ExecContext(ctx, `
|
||||
DELETE FROM node_registry
|
||||
WHERE heartbeat < now() - $1 * interval '1 second'
|
||||
`, threshold.Seconds())
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
return result.RowsAffected()
|
||||
}
|
||||
|
||||
func (s *ClusterStore) ListNodes(ctx context.Context) ([]store.ClusterNode, error) {
|
||||
rows, err := DB.QueryContext(ctx, `
|
||||
SELECT node_id, endpoint, seq, registered_at, heartbeat, stats
|
||||
FROM node_registry
|
||||
ORDER BY seq
|
||||
`)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer rows.Close()
|
||||
|
||||
var nodes []store.ClusterNode
|
||||
for rows.Next() {
|
||||
var n store.ClusterNode
|
||||
if err := rows.Scan(&n.NodeID, &n.Endpoint, &n.Seq, &n.RegisteredAt, &n.Heartbeat, &n.Stats); err != nil {
|
||||
return nil, fmt.Errorf("scan cluster node: %w", err)
|
||||
}
|
||||
nodes = append(nodes, n)
|
||||
}
|
||||
return nodes, rows.Err()
|
||||
}
|
||||
|
||||
func (s *ClusterStore) Deregister(ctx context.Context, nodeID string) error {
|
||||
_, err := DB.ExecContext(ctx, `DELETE FROM node_registry WHERE node_id = $1`, nodeID)
|
||||
return err
|
||||
}
|
||||
Reference in New Issue
Block a user