afterincomparableyum commented on code in PR #3583:
URL: https://github.com/apache/celeborn/pull/3583#discussion_r2844435446


##########
cpp/celeborn/client/reader/CelebornInputStream.cpp:
##########
@@ -189,9 +205,56 @@ 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;
+      if (isExcluded(*currentLocation)) {
+        CELEBORN_FAIL(
+            "Fetch data from excluded worker! {}",
+            currentLocation->hostAndFetchPort());
+      }
+      auto reader = createReader(*currentLocation);
+      return reader;
+    } catch (const std::exception& e) {
+      lastException = std::current_exception();
+      excludeFailedFetchLocation(currentLocation->hostAndFetchPort(), e);
+      fetchChunkRetryCnt_++;
+
+      if (currentLocation->hasPeer() && !readSkewPartitionWithoutMapRange_) {
+        if (fetchChunkRetryCnt_ % 2 == 0) {
+          std::this_thread::sleep_for(retryWait_);
+        }
+        LOG(WARNING) << "CreatePartitionReader failed " << fetchChunkRetryCnt_
+                     << "/" << fetchChunkMaxRetry_ << " times for location "
+                     << currentLocation->hostAndFetchPort()
+                     << ", change to peer. Error: " << e.what();
+        // TODO: When stream handlers are supported, send BUFFER_STREAM_END
+        // to close the active stream before switching to peer, matching the
+        // Java CelebornInputStream behavior. Currently, the C++ client does
+        // not have pre-opened stream handlers, so stream cleanup is handled
+        // by WorkerPartitionReader's destructor.
+        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(retryWait_);
+      }
+    }
+  }
+
+  // Max retries exceeded, rethrow the last exception wrapped with context
+  throw utils::CelebornRuntimeError(
+      lastException,
+      "createPartitionReader failed after " +
+          std::to_string(fetchChunkRetryCnt_) + " retries for location " +
+          location.hostAndFetchPort(),
+      false);

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]

Reply via email to