afterincomparableyum commented on code in PR #3583:
URL: https://github.com/apache/celeborn/pull/3583#discussion_r2786046406
##########
cpp/celeborn/client/reader/CelebornInputStream.cpp:
##########
@@ -189,9 +196,45 @@ void CelebornInputStream::moveToNextReader() {
std::shared_ptr<PartitionReader> CelebornInputStream::createReaderWithRetry(
const protocol::PartitionLocation& location) {
- // TODO: support retrying when createReader failed. Maybe switch to peer
- // location?
- return createReader(location);
+ const protocol::PartitionLocation* currentLocation = &location;
+ std::exception_ptr lastException;
+
+ while (fetchChunkRetryCnt_ < fetchChunkMaxRetry_) {
+ try {
+ VLOG(1) << "Create reader for location " << currentLocation->host << ":"
+ << currentLocation->fetchPort;
+ auto reader = createReader(*currentLocation);
+ fetchChunkRetryCnt_ = 0;
+ return reader;
+ } catch (const std::exception& e) {
+ lastException = std::current_exception();
+ fetchChunkRetryCnt_++;
+
+ if (currentLocation->hasPeer()) {
+ if (fetchChunkRetryCnt_ % 2 == 0) {
+ std::this_thread::sleep_for(
+ std::chrono::milliseconds(retryWait_.count()));
+ }
+ LOG(WARNING) << "CreatePartitionReader failed " << fetchChunkRetryCnt_
+ << "/" << fetchChunkMaxRetry_ << " times for location "
+ << currentLocation->hostAndFetchPort()
+ << ", change to peer. Error: " << e.what();
+ currentLocation = currentLocation->getPeer();
+ } else {
+ LOG(WARNING) << "CreatePartitionReader failed " << fetchChunkRetryCnt_
+ << "/" << fetchChunkMaxRetry_ << " times for location "
+ << currentLocation->hostAndFetchPort()
+ << ", retry the same location. Error: " << e.what();
+ std::this_thread::sleep_for(
+ std::chrono::milliseconds(retryWait_.count()));
+ }
+ }
+ }
+
+ CELEBORN_FAIL(
+ "createPartitionReader failed after " +
+ std::to_string(fetchChunkRetryCnt_) + " retries for location " +
+ location.hostAndFetchPort());
Review Comment:
done
--
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]
