Github user felixcheung commented on a diff in the pull request: https://github.com/apache/spark/pull/19851#discussion_r154029237 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/HiveExternalCatalogVersionsSuite.scala --- @@ -50,14 +52,24 @@ class HiveExternalCatalogVersionsSuite extends SparkSubmitTestUtils { super.afterAll() } - private def downloadSpark(version: String): Unit = { - import scala.sys.process._ + private def tryDownloadSpark(version: String, path: String): Unit = { + // Try mirrors a few times until one succeeds + for (i <- 0 until 3) { + val preferredMirror = + Seq("wget", "https://www.apache.org/dyn/closer.lua?preferred=true", "-q", "-O", "-").!!.trim + val url = s"$preferredMirror/spark/spark-$version/spark-$version-bin-hadoop2.7.tgz" + logInfo(s"Downloading Spark $version from $url") + if (Seq("wget", url, "-q", "-P", path).! == 0) { + return + } + logWarning(s"Failed to download Spark $version from $url") + } + fail(s"Unable to download Spark $version") --- End diff -- btw, I've also seen a mirror abruptly ending a download but not getting reported as an error, resulting in an incomplete/corrupted tgz. it's possible the mirror misreports the response byte size in that case.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org