[ARTEMIS-3449] Speedup AMQP large message streaming

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 2.19.0
• Assignee: Francesco Nigro
• Reporter: Francesco Nigro
• Created: 29/Aug/21 16:37
• Updated: 12/Oct/21 00:56
• Resolved: 12/Oct/21 00:56

Description

AMQP is using unpooled heap ByteBuffer(s) to stream AMQP large messages: given that the underline NIO sequential file can both use FileChannel or RandomAccessFile (depending if the ByteBuffer used is direct/heap based), both approaches would benefit from using Netty pooled direct buffers and save additional copies (performed by RandomAccessFile) to happen, reducing GC too.

Issue Links

• Testing discovered: ARTEMIS-3465 BufferSplitter::split shouldn't consume input buffer
• links to: GitHub Pull Request #3711
• links to: GitHub Pull Request #3730