pan3793 commented on code in PR #25899: URL: https://github.com/apache/spark/pull/25899#discussion_r1562356543
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSource.scala: ########## @@ -734,30 +735,52 @@ object DataSource extends Logging { * Checks and returns files in all the paths. */ private[sql] def checkAndGlobPathIfNecessary( - paths: Seq[String], + pathStrings: Seq[String], hadoopConf: Configuration, checkEmptyGlobPath: Boolean, checkFilesExist: Boolean): Seq[Path] = { - val allGlobPath = paths.flatMap { path => - val hdfsPath = new Path(path) - val fs = hdfsPath.getFileSystem(hadoopConf) - val qualified = hdfsPath.makeQualified(fs.getUri, fs.getWorkingDirectory) - val globPath = SparkHadoopUtil.get.globPathIfNecessary(fs, qualified) - - if (checkEmptyGlobPath && globPath.isEmpty) { - throw new AnalysisException(s"Path does not exist: $qualified") + val qualifiedPaths = pathStrings.map { pathString => + val path = new Path(pathString) + val fs = path.getFileSystem(hadoopConf) + path.makeQualified(fs.getUri, fs.getWorkingDirectory) + } + + // Split the paths into glob and non glob paths, because we don't need to do an existence check + // for globbed paths. + val (globPaths, nonGlobPaths) = qualifiedPaths.partition(SparkHadoopUtil.get.isGlobPath) + + val globbedPaths = + try { + ThreadUtils.parmap(globPaths, "globPath", 20) { globPath => + val fs = globPath.getFileSystem(hadoopConf) + val globResult = SparkHadoopUtil.get.globPath(fs, globPath) + + if (checkEmptyGlobPath && globResult.isEmpty) { + throw new AnalysisException(s"Path does not exist: $globPath") + } + + globResult + }.flatten + } catch { + case e: SparkException => throw e.getCause Review Comment: this silently drops the caller stack trace, I opened SPARK-47833(https://github.com/apache/spark/pull/46028) to fix it. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org