afterincomparableyum commented on code in PR #3737:
URL: https://github.com/apache/celeborn/pull/3737#discussion_r3570838161
##########
worker/src/test/scala/org/apache/celeborn/service/deploy/MiniClusterFeature.scala:
##########
@@ -225,17 +226,30 @@ 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
}
+ try {
+ TimeUnit.SECONDS.sleep(Math.pow(2, workerStartRetry).toLong)
+ } catch {
+ case ie: InterruptedException =>
+ Thread.currentThread().interrupt()
+ throw ie
+ }
+ worker = createWorker(workerConf)
Review Comment:
I can apply a change
##########
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 >/dev/null 2>&1; then
+ echo "exec: curl ${curl_opts} ${remote_tarball}" 1>&2
+ curl ${curl_opts} "${remote_tarball}" > "${local_tarball}"
+ elif command -v wget >/dev/null 2>&1; then
Review Comment:
can look again
--
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]
