Bug 701784

Summary: Receiver dequeue rate slower when acking messages in batches greater than receiver capacity
Product: Red Hat Enterprise MRG Reporter: Andy Goldstein <agoldste>
Component: qpid-cppAssignee: messaging-bugs <messaging-bugs>
Status: NEW --- QA Contact: MRG Quality Engineering <mrgqe-bugs>
Severity: unspecified Docs Contact:
Priority: medium    
Version: 1.3CC: jross
Target Milestone: ---Keywords: Performance
Target Release: ---   
Hardware: Unspecified   
OS: Unspecified   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Bug Depends On:    
Bug Blocks: 698367, 794748    

Description Andy Goldstein 2011-05-03 20:28:19 UTC 
Description of problem: When a Receiver has a capacity (e.g. 10) that is less than the number of messages acknowledged in a batch (e.g. 11), the Receiver's dequeue rate drops significantly.


Version-Release number of selected component (if applicable): latest MRG-M 1.3 and 2.0 prerelease RPMs


How reproducible: 100%


Steps to Reproduce:
1. Send messages to a queue
2. Receive messages from queue using get(), with Receiver capacity 10
3. Call session.acknowledge() after every 11th message received
  
Actual results: on my server, can only receive somewhere between 250 and 600 messages/sec


Expected results: much more than 500 or so messages/second.  With capacity 10, batch size 10, I can receive several thousand messages/sec.