Note: This bug is displayed in read-only format because the product is no longer active in Red Hat Bugzilla.

Bug 1228780

Summary: [GSS](6.4.z) Replication: The DELTA_WRITE flag should force a remote get during state transfer
Product: [JBoss] JBoss Enterprise Application Platform 6 Reporter: dereed
Component: ClusteringAssignee: Ryan Emerson <remerson>
Status: CLOSED CURRENTRELEASE QA Contact: Jitka Kozana <jkudrnac>
Severity: unspecified Docs Contact:
Priority: unspecified    
Version: 6.2.4CC: bbaranow, bmaxwell, cdewolf, istraka, istudens, paul.ferraro, remerson, rhusar
Target Milestone: CR1   
Target Release: EAP 6.4.4   
Hardware: Unspecified   
OS: Unspecified   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2017-01-17 10:46:37 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Bug Depends On:    
Bug Blocks: 1202355, 1228783, 1235744    

Description dereed 2015-06-05 17:21:58 UTC 
Same issue as ISPN-3184, but for repl caches in Infinispan 5.2.x.
(ISPN-3184 only fixed dist caches, since repl uses the same code in 5.3+).

AtomicHashMap and FineGrainedAtomicHashMap, as well as custom DeltaAware implementations, use PutKeyValueCommands with the DELTA_WRITE flag to execute incremental updates. These commands need the previous value of the entry in order to work.

If a node is joining and it receives a PutKeyValueCommand with the DELTA_WRITE flag before it has received the value of the affected key, it should do a remote get to retrieve the previous value and apply the change on top of that value, just like we do for conditional commands. Not doing so leads to data loss.
Comment 1 dereed 2015-06-15 18:24:37 UTC 
Test case: org/infinispan/atomic/ReplAtomicMapStateTransferTest
Comment 8 dereed 2015-06-17 15:36:35 UTC 
4 commits for this BZ:
    13da8da7206dacf3daf82f3d449e59789e4bec45
    5d7dab4cb154535be7d0d676f306f102950768f7
    dc9bb74029c6f34206cce85ceaa2aa699b76529c
    baed5c6d5c2c9a37b286eac7d7fe141a7a790990
Comment 10 Ivan Straka 2015-09-24 10:29:07 UTC 
We do not see org/infinispan/atomic/ReplAtomicMapStateTransferTest failing, verified.
Comment 11 Petr Penicka 2017-01-17 10:46:37 UTC 
Retroactively bulk-closing issues from released EAP 6.4 cumulative patches.