[
https://issues.apache.org/jira/browse/HDDS-15592?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Andrey Yarovoy updated HDDS-15592:
----------------------------------
Description: Allocate direct in ChunkBuffer triggers slow byte-by-byte
NioByteString path, in case if it is replaced by heap allocation
UnsafeByteOperations.unsafeWrap() would return a BoundedByteString with a
backing array, enabling a single System.arraycopy into the gRPC/Netty wire
buffer. (was: Allocate direct in ChunkBuffer triggers slow byte-by-byte
NioByteString path for direct buffers, in case if it is replaced by heap
allocation UnsafeByteOperations.unsafeWrap() would return a BoundedByteString
with a backing array, enabling a single System.arraycopy into the gRPC/Netty
wire buffer)
> Allocate direct memory in ChunkBuffer code slows down GRPC serialization
> ------------------------------------------------------------------------
>
> Key: HDDS-15592
> URL: https://issues.apache.org/jira/browse/HDDS-15592
> Project: Apache Ozone
> Issue Type: Bug
> Reporter: Andrey Yarovoy
> Assignee: Andrey Yarovoy
> Priority: Major
>
> Allocate direct in ChunkBuffer triggers slow byte-by-byte NioByteString path,
> in case if it is replaced by heap allocation
> UnsafeByteOperations.unsafeWrap() would return a BoundedByteString with a
> backing array, enabling a single System.arraycopy into the gRPC/Netty wire
> buffer.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
