Github user viirya commented on a diff in the pull request: https://github.com/apache/spark/pull/17064#discussion_r103348444 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/CacheManager.scala --- @@ -168,15 +168,16 @@ class CacheManager extends Logging { (fs, path.makeQualified(fs.getUri, fs.getWorkingDirectory)) } - cachedData.foreach { - case data if data.plan.find(lookupAndRefresh(_, fs, qualifiedPath)).isDefined => - val dataIndex = cachedData.indexWhere(cd => data.plan.sameResult(cd.plan)) - if (dataIndex >= 0) { - data.cachedRepresentation.cachedColumnBuffers.unpersist(blocking = true) - cachedData.remove(dataIndex) - } - sparkSession.sharedState.cacheManager.cacheQuery(Dataset.ofRows(sparkSession, data.plan)) - case _ => // Do Nothing + cachedData.filter { --- End diff -- This kind of collection can't be modified during iterating. Some elements are not iterated over if we delete/add elements.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org