From 9012b7f6c896959e7ce42169c8ab9356c810426e Mon Sep 17 00:00:00 2001 From: codenohup Date: Tue, 15 Oct 2024 22:01:25 +0800 Subject: [PATCH] [CELEBORN-1652] Throw TransportableError for failure of sending PbReadAddCredit to avoid flink task get stuck ### What changes were proposed in this pull request? Throw `TransportableError` for failure of sending `PbReadAddCredit` to avoid flink task get stuck. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? by manual verification Closes #2811 from codenohup/fix-send-credit. Authored-by: codenohup Signed-off-by: Shuang (cherry picked from commit af930e7f6788cb040578884526c37241affd8005) Signed-off-by: Shuang --- .../plugin/flink/readclient/CelebornBufferStream.java | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/client-flink/common/src/main/java/org/apache/celeborn/plugin/flink/readclient/CelebornBufferStream.java b/client-flink/common/src/main/java/org/apache/celeborn/plugin/flink/readclient/CelebornBufferStream.java index d0571a14a95..43d3a61a551 100644 --- a/client-flink/common/src/main/java/org/apache/celeborn/plugin/flink/readclient/CelebornBufferStream.java +++ b/client-flink/common/src/main/java/org/apache/celeborn/plugin/flink/readclient/CelebornBufferStream.java @@ -100,10 +100,12 @@ public void onSuccess(ByteBuffer response) { @Override public void onFailure(Throwable e) { - logger.warn( - "Send PbReadAddCredit to {} failed, detail {}", + logger.error( + "Send PbReadAddCredit to {} failed, streamId {}, detail {}", NettyUtils.getRemoteAddress(client.getChannel()), + streamId, e.getCause()); + messageConsumer.accept(new TransportableError(streamId, e)); } }); }