2026-04-23 13:52:30 +00:00
|
|
|
-- Post data migration script for Task workflow cutover - OpenMetadata 2.0.1
|
2026-05-14 14:30:57 +00:00
|
|
|
|
2026-05-15 16:49:48 +00:00
|
|
|
-- RdfIndexApp: switch to weekly Saturday cron and full-rebuild every run.
|
2026-05-14 14:30:57 +00:00
|
|
|
-- Previous defaults (daily, incremental) were producing unbounded triple growth
|
|
|
|
|
-- because relationship-removal paths weren't fully reconciled. With per-run
|
2026-05-15 16:49:48 +00:00
|
|
|
-- CLEAR ALL the dataset always converges to MySQL state; weekly cadence keeps
|
|
|
|
|
-- per-run cost from saturating Fuseki.
|
|
|
|
|
--
|
|
|
|
|
-- Also rewrite `entities` to `["all"]`. Pre-upgrade, an operator could have
|
|
|
|
|
-- narrowed RDF indexing to a subset of entity types; the new recreateIndex=true
|
|
|
|
|
-- semantics issues a CLEAR ALL before indexing, which would otherwise wipe
|
|
|
|
|
-- triples for entity types still in MySQL but missing from the subset list.
|
|
|
|
|
-- Forcing the subset list back to `["all"]` ensures the post-CLEAR-ALL run
|
|
|
|
|
-- repopulates the graph fully; operators can re-narrow after the migration if
|
|
|
|
|
-- they need partial indexing.
|
2026-05-14 14:30:57 +00:00
|
|
|
UPDATE installed_apps
|
|
|
|
|
SET json = JSON_SET(
|
2026-05-15 16:49:48 +00:00
|
|
|
JSON_SET(
|
|
|
|
|
json,
|
|
|
|
|
'$.appConfiguration.recreateIndex', CAST('true' AS JSON),
|
|
|
|
|
'$.appSchedule.cronExpression', '0 0 * * 6'
|
|
|
|
|
),
|
|
|
|
|
'$.appConfiguration.entities', JSON_ARRAY('all')
|
2026-05-14 14:30:57 +00:00
|
|
|
)
|
|
|
|
|
WHERE name = 'RdfIndexApp';
|
|
|
|
|
|
|
|
|
|
UPDATE apps_marketplace
|
|
|
|
|
SET json = JSON_SET(json, '$.appConfiguration.recreateIndex', CAST('true' AS JSON))
|
|
|
|
|
WHERE name = 'RdfIndexApp';
|