[MINOR][CORE] Use ArrayDeque instead of LinkedList in TransportFrameDecoder - #58857
Open
david-mollitor-db wants to merge 1 commit into
Open
david-mollitor-db wants to merge 1 commit into
david-mollitor-db wants to merge 1 commit into
Conversation
…ecoder `TransportFrameDecoder.buffers` holds the input `ByteBuf`s not yet consumed into a frame and is used purely as a FIFO queue: `add` at the tail, `getFirst`/`removeFirst` at the head, plus iteration and `clear`. It was a `LinkedList`, which allocates a node object on every `add`. `channelRead` runs on every inbound read of every connection, so that is a steady per-read allocation on a hot path. Switch it to `ArrayDeque`, which offers the same operations with identical FIFO semantics but reuses a small preallocated backing array (the queue is typically just one buffer), avoiding the per-read node allocation and improving locality. This mirrors SPARK-59431, which made the same change for `BytesToBytesMap.dataPages`. No behavior change; `TransportFrameDecoderSuite` passes. Co-authored-by: Isaac <no-reply@databricks.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changes were proposed in this pull request?
TransportFrameDecodersits at the head of the Netty receive pipeline and reassembleslength-prefixed frames from incoming socket reads. It keeps the input
ByteBufs that havenot yet been consumed into a frame in a
buffersfield, which is accessed purely as a FIFOqueue: appended at the tail on each
channelRead, read/removed from the head as frames aredecoded, plus iteration and
clearon cleanup.This changes
buffersfromLinkedList<ByteBuf>toArrayDeque<ByteBuf>. Every operationused (
add/addLast,getFirst,removeFirst, enhanced-for iteration,clear) hasidentical FIFO semantics on
ArrayDeque, so the swap is behavior-preserving.Why are the changes needed?
LinkedListallocates a node object on everyadd.TransportFrameDecoder.channelReadruns on every inbound read of every connection (RPC and block transfer), so the old code
produced a steady stream of short-lived list-node allocations on a hot path.
ArrayDequesupports the same add-at-tail / poll-at-head access pattern with a single reused backing
array -- the queue is typically just one buffer -- eliminating the per-read node allocation
and improving cache locality.
This mirrors SPARK-59431, which replaced
LinkedListwithArrayDequeforBytesToBytesMap.dataPagesfor the same reason. It is an allocation micro-optimization; itis not expected to move throughput on its own, since the shuffle data path is dominated by
zero-copy
FileRegiontransfers rather than framing.Does this PR introduce any user-facing change?
No.
How was this patch tested?
Existing
TransportFrameDecoderSuitepasses (7 tests), covering frame decoding, a lengthfield split across buffers, retained frames, interception, empty/negative frame sizes, and
consolidation -- the cases that exercise
buffersacross multiple reads. This is aninternal data-structure change with no behavior difference, so no new tests were added.
Was this patch authored or co-authored using generative AI tooling?
Generated-by: Isaac
This pull request and its description were written by Isaac.