Merge pull request #33481 from walsm232/fix/catalog-refresh-state-deadlock

fix(catalog): Fix catalog refresh_state deadlock when running multiple replicas

.changeset/fix-catalog-refresh-state-deadlock.md

@@ -0,0 +1,5 @@
+---
+'@backstage/plugin-catalog-backend': patch
+---
+
+Fixed a deadlock in the catalog processing loop that occurred when running multiple replicas. The `getProcessableEntities` method used `SELECT ... FOR UPDATE SKIP LOCKED` to prevent concurrent processors from claiming the same rows, but the call was not wrapped in a transaction, so the row locks were released before the subsequent `UPDATE` executed. This allowed multiple replicas to select and update overlapping rows, causing PostgreSQL deadlock errors (code 40P01).

plugins/catalog-backend/src/processing/DefaultCatalogProcessingEngine.ts

@@ -142,10 +142,13 @@ export class DefaultCatalogProcessingEngine {
       pollingIntervalMs: this.pollingIntervalMs,
       loadTasks: async count => {
         try {
-          const { items } =
-            await this.processingDatabase.getProcessableEntities(this.knex, {
-              processBatchSize: count,
-            });
+          const { items } = await this.processingDatabase.transaction(
+            async tx => {
+              return this.processingDatabase.getProcessableEntities(tx, {
+                processBatchSize: count,
+              });
+            },
+          );
           return items;
         } catch (error) {
           this.logger.warn('Failed to load processing items', error);