fix(scheduler): resolve guest routing when check_defs.target_type is blank
Older writeCheck inserts omitted target_type, so every seed-created check_def had a NULL/empty target_type. checkSSHScript's IsGuest check then never matched, and guest checks silently fell back to their baked (often mesh-only) address — keeping them 'down' even after the pct-exec routing and deployed scripts were in place. rclone stayed down for exactly this reason after the host-hop fix. writeCheck now writes target_type, and checkSSHScript resolves the type from the target_id when the column is blank (a runtime safety net for existing rows; the seed rows were also backfilled in the live DB).
This commit is contained in:
@@ -299,14 +299,15 @@ func writeCheck(ctx context.Context, tx pgx.Tx, t Target, idx int, def checkDef)
|
||||
// absent from the DO UPDATE below — a re-seed must not reset the schedule
|
||||
// and re-herd everything.
|
||||
tag, err := tx.Exec(ctx,
|
||||
`INSERT INTO check_defs (entity_id, target_id, kind, config, interval_s, timeout_s, enabled, last_run_at)
|
||||
VALUES ($1, $2, $3, $4, $5, 30, true,
|
||||
`INSERT INTO check_defs (entity_id, target_id, target_type, kind, config, interval_s, timeout_s, enabled, last_run_at)
|
||||
VALUES ($1, $2, $6, $3, $4, $5, 30, true,
|
||||
now() - make_interval(secs => random() * $5::int))
|
||||
ON CONFLICT (entity_id) DO UPDATE
|
||||
SET target_id = EXCLUDED.target_id, kind = EXCLUDED.kind,
|
||||
SET target_id = EXCLUDED.target_id, target_type = EXCLUDED.target_type,
|
||||
kind = EXCLUDED.kind,
|
||||
config = EXCLUDED.config, interval_s = EXCLUDED.interval_s,
|
||||
updated_at = now()`,
|
||||
checkID, t.ID, def.kind, configJSON, def.interval)
|
||||
checkID, t.ID, def.kind, configJSON, def.interval, t.Type)
|
||||
if err != nil {
|
||||
return false, fmt.Errorf("upsert check_def %s: %w", checkSlug, err)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user