feat: Optimize PrestoSerializer decompress buffer #11836
+144
−8
Conversation
This file contains 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
facebook-github-bot
added
the
CLA Signed
✅ Deploy Preview for meta-velox canceled.
|
jinchengchenghh
force-pushed
the
opt_compress
branch
from
0a803d5 to
7cfade1
Compare
Yuhta
reviewed
Dec 12, 2024
jinchengchenghh
changed the title
jinchengchenghh
force-pushed
the
opt_compress
branch
from
7e78159 to
5dfe257
Compare
|
Can you help review again? Thanks! @Yuhta |
Yuhta
reviewed
Dec 13, 2024
velox/common/memory/ByteStream.cpp
Outdated
| auto newBuf = folly::IOBuf::wrapBuffer( | ||
| current_->buffer + current_->position, readBytes); | ||
| if (result) { | ||
| result->prev()->appendChain(std::move(newBuf)); |
There was a problem hiding this comment.
The order of buffers here is incorrect. Just do result->appendToChain(std::move(newBuf)).
There was a problem hiding this comment.
The order is same with IOBufOutputStream::getIOBuf(), appendToChain is also OK. I will change as you say.
| common::CompressionKind compressionKind, | ||
| memory::MemoryPool& pool) { | ||
| const auto codec = common::compressionKindToCodec(compressionKind); | ||
| if (dynamic_cast<BufferInputStream*>(source)) { |
There was a problem hiding this comment.
Just do the dynamic_cast once: if (const auto* bufferSource = dynamic_cast<BufferInputStream*>(source))
| auto byteStream = createStream(byteRanges); | ||
| auto bufferStream = dynamic_cast<BufferInputStream*>(byteStream.get()); | ||
| for (int offset = 0; offset < streamSize;) { | ||
| auto iobuf = bufferStream->readBytes(streamSize / 8); |
There was a problem hiding this comment.
We are not testing the case one IOBuf chain cross 2 buffers. Let's cover that as well.
jinchengchenghh
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Read the BufferInputStream by new added function readBytes to avoid copying from the buffer cache. Extract the uncompress process to a new function can help release the compressed buffer in time.
FileInputStream reuse the read buffer, so we can get the IOBuf without copy only if the required bytes is in one buffer, which is not the common case, so I don't do the optimization for it.