yuqi1129 commented on code in PR #12547:
URL: https://github.com/apache/gravitino/pull/12547#discussion_r3841978011
##########
trino-connector/trino-connector/src/main/java/org/apache/gravitino/trino/connector/catalog/CatalogConnectorManager.java:
##########
@@ -186,14 +216,102 @@ private void loadMetalake() {
LOG.debug("Load metalake: {}", usedMetalake);
loadCatalogs(metalake);
} catch (Exception e) {
- LOG.error("Load Metalake {} failed.", usedMetalake, e);
+ recordMetalakeError(usedMetalake, e);
}
}
- } catch (Exception e) {
- LOG.error("Error when loading metalake", e);
+
+ pruneMissingMetalakes(usedMetalakes);
+
+ if (metalakeErrors.isEmpty()) {
+ lastSuccessfulLoadTimeMs = System.currentTimeMillis();
+ recordLoadSuccess();
+ } else {
+ // Some metalake failed. The loop reaching its last line is not a
health signal, so do not
+ // advance the success time or clear the error, or load_status would
report a healthy loop
+ // while no catalog is being registered at all.
+ recordLoadFailure(
+ String.format(
+ "%d of %d metalakes failed to load: %s",
+ metalakeErrors.size(), usedMetalakes.size(), new
TreeMap<>(metalakeErrors)),
+ null);
+ }
+ } catch (Throwable t) {
+ // Catch Throwable, not Exception: scheduleWithFixedDelay silently
cancels the task forever
+ // the first time the runnable throws, and loading a Trino connector
plugin can raise
+ // NoClassDefFoundError. A dead loop must not look like a healthy one.
+ recordLoadFailure(toErrorMessage(t), t);
}
}
+ private void pruneMissingMetalakes(Set<String> usedMetalakes) {
+ // A metalake that was deleted, or that dropped out of the configuration,
leaves its catalog
+ // rows behind. Without this they keep reporting REGISTERED for catalogs
that no longer exist.
+ catalogStates.values().removeIf(state ->
!usedMetalakes.contains(state.getMetalake()));
+ metalakeErrors.keySet().removeIf(metalakeName ->
!usedMetalakes.contains(metalakeName));
Review Comment:
You should also clear `metalakes`, `catalogConnectors` and all registerd
catalogs that belong to the deleted metalake.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
