Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CELEBORN-1820] Failing to write and flush StreamChunk data should be counted as FETCH_CHUNK_FAIL #3051

Closed
wants to merge 2 commits into from
Closed

[CELEBORN-1820] Failing to write and flush StreamChunk data should be counted as FETCH_CHUNK_FAIL #3051

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9a70058
[fix] Failing to write and flush StreamChunk data should be counted a…
Z1Wu Jan 4, 2025
359437e
fix
Z1Wu Jan 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions worker/src/main/scala/org/apache/celeborn/service/deploy/worker/FetchHandler.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -511,7 +511,8 @@ class FetchHandler(
client: TransportClient,
streamChunkSlice: StreamChunkSlice,
req: RequestMessage): Unit = {
logDebug(s"Received req from ${NettyUtils.getRemoteAddress(client.getChannel)}" +
lazy val remoteAddr = NettyUtils.getRemoteAddress(client.getChannel)
logDebug(s"Received req from ${remoteAddr}" +
s" to fetch block $streamChunkSlice")

workerSource.recordAppActiveConnection(
Expand Down Expand Up @@ -548,14 +549,15 @@ class FetchHandler(
if (future.isSuccess) {
if (log.isDebugEnabled) {
logDebug(
s"Sending ChunkFetchSuccess operation succeeded, chunk $streamChunkSlice")
s"Sending ChunkFetchSuccess to $remoteAddr succeeded, chunk $streamChunkSlice")
}
workerSource.incCounter(WorkerSource.FETCH_CHUNK_SUCCESS_COUNT)
} else {
logWarning(
s"Sending ChunkFetchSuccess operation failed, chunk $streamChunkSlice",
s"Sending ChunkFetchSuccess to $remoteAddr failed, chunk $streamChunkSlice",
future.cause())
workerSource.incCounter(WorkerSource.FETCH_CHUNK_FAIL_COUNT)
}
workerSource.incCounter(WorkerSource.FETCH_CHUNK_SUCCESS_COUNT)
chunkStreamManager.chunkSent(streamChunkSlice.streamId)
if (fetchTimeMetric != null) {
fetchTimeMetric.update(System.nanoTime() - fetchBeginTime)
Expand Down
Loading