afterincomparableyum commented on code in PR #3737:
URL: https://github.com/apache/celeborn/pull/3737#discussion_r3421540460
##########
worker/src/test/scala/org/apache/celeborn/service/deploy/MiniClusterFeature.scala:
##########
@@ -225,17 +236,24 @@ trait MiniClusterFeature extends Logging {
workerStarted = true
worker.initialize()
} catch {
+ case ie: InterruptedException =>
+
Utils.tryLogNonFatalError(worker.stop(CelebornExitKind.EXIT_IMMEDIATELY))
+ Utils.tryLogNonFatalError(worker.rpcEnv.shutdown())
+ Thread.currentThread().interrupt()
+ throw ie
case ex: Exception =>
- if (workers(i - 1) != null) {
- workers(i - 1).shutdownGracefully()
- }
+ Utils.tryLogNonFatalError(worker.exitImmediately())
+
Utils.tryLogNonFatalError(worker.stop(CelebornExitKind.EXIT_IMMEDIATELY))
+ Utils.tryLogNonFatalError(worker.rpcEnv.shutdown())
workerStarted = false
workerStartRetry += 1
logError(s"cannot start worker $i, retrying: ", ex)
if (workerStartRetry == maxRetries) {
logError(s"cannot start worker $i, reached to max retrying",
ex)
throw ex
}
+ TimeUnit.SECONDS.sleep(Math.pow(2, workerStartRetry).toLong)
+ worker = createWorker(workerConf)
Review Comment:
valid
##########
build/mvn:
##########
@@ -46,23 +47,44 @@ install_app() {
wget_opts="--progress=bar:force ${wget_opts}"
if [ -z "$3" -o ! -f "$binary" ]; then
- # check if we already have the tarball
- # check if we have curl installed
- # download application
- [ ! -f "${local_tarball}" ] && [ $(command -v curl) ] && \
- echo "exec: curl ${curl_opts} ${remote_tarball}" 1>&2 && \
- curl ${curl_opts} "${remote_tarball}" > "${local_tarball}"
- # if the file still doesn't exist, lets try `wget` and cross our fingers
- [ ! -f "${local_tarball}" ] && [ $(command -v wget) ] && \
- echo "exec: wget ${wget_opts} ${remote_tarball}" 1>&2 && \
- wget ${wget_opts} -O "${local_tarball}" "${remote_tarball}"
- # if both were unsuccessful, exit
- [ ! -f "${local_tarball}" ] && \
- echo -n "ERROR: Cannot download $2 with cURL or wget; " && \
- echo "please install manually and try again." && \
- exit 2
- cd "${_DIR}" && tar -xzf "$2"
- rm -rf "$local_tarball"
+ local attempt=1
+ while [ "${attempt}" -le "${max_attempts}" ]; do
+ # remove any partial/corrupt download left over from a previous attempt
+ rm -f "${local_tarball}"
+
+ # download application with `curl`, falling back to `wget`
+ if [ $(command -v curl) ]; then
+ echo "exec: curl ${curl_opts} ${remote_tarball}" 1>&2
+ curl ${curl_opts} "${remote_tarball}" > "${local_tarball}"
+ elif [ $(command -v wget) ]; then
+ echo "exec: wget ${wget_opts} ${remote_tarball}" 1>&2
+ wget ${wget_opts} -O "${local_tarball}" "${remote_tarball}"
+ else
+ echo "ERROR: Cannot download $2: neither cURL nor wget is installed."
1>&2
+ exit 2
+ fi
+
+ # Validate the download before trusting it. A flaky Apache mirror can
+ # return an HTML page (mirror chooser / error) with HTTP 200, which is
+ # not a gzip tarball; extracting it later would fail with a confusing
+ # exit code. `tar -tzf` lists the archive without extracting and
+ # exits non-zero on a non-tarball body.
+ if [ -f "${local_tarball}" ] && tar -tzf "${local_tarball}" >/dev/null
2>&1; then
+ cd "${_DIR}" && tar -xzf "$2"
+ rm -rf "${local_tarball}"
+ return 0
+ fi
Review Comment:
valid
--
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]
