[ 
https://issues.apache.org/jira/browse/IGNITE-27638?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Ivan Bessonov updated IGNITE-27638:
-----------------------------------
    Reviewer: Roman Puchkovskiy

> Exception in AbortWriteInvokeClosure#onUpdate
> ---------------------------------------------
>
>                 Key: IGNITE-27638
>                 URL: https://issues.apache.org/jira/browse/IGNITE-27638
>             Project: Ignite
>          Issue Type: Bug
>          Components: storage engines ai3
>            Reporter: Ivan Bessonov
>            Assignee: Ivan Bessonov
>            Priority: Major
>              Labels: ignite-3
>          Time Spent: 10m
>  Remaining Estimate: 0h
>
> Deletion from WI list is performed twice sometimes. Considering this comment:
> {code:java}
> // We don't zero out removed write intent's WI links because we already 
> unlinked it everywhere except for WI list itself,
> // so no one can read its WI links, and we are going to remove it from WI 
> list under the WI list lock. {code}
> the data consistency is violated and we get an error:
> {code:java}
> Caused by: 
> org.apache.ignite.internal.pagememory.freelist.CorruptedFreeListException: 
> IGN-STORAGE-2 Failed to update data row TraceId:4cc5584d
> at 
> org.apache.ignite.internal.pagememory.freelist.FreeListImpl.updateDataRow(FreeListImpl.java:674)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.WriteIntentListSupport.removeNodeFromWriteIntentsList(WriteIntentListSupport.java:42)
> ... 64 more
> Caused by: java.lang.IllegalStateException: Item not found: 17
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.findIndirectItemIndex(DataPageIo.java:453)
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.resolveDirectItemIdFromIndirectItemId(DataPageIo.java:605)
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.getDataOffset(DataPageIo.java:596)
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.getPayloadOffset(DataPageIo.java:720)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.UpdateNextWiLinkHandler.run(UpdateNextWiLinkHandler.java:34)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.UpdateNextWiLinkHandler.run(UpdateNextWiLinkHandler.java:19)
> at 
> org.apache.ignite.internal.pagememory.util.PageHandler.writePage(PageHandler.java:220)
> at 
> org.apache.ignite.internal.pagememory.datastructure.DataStructure.write(DataStructure.java:271)
> at 
> org.apache.ignite.internal.pagememory.freelist.FreeListImpl.updateDataRow(FreeListImpl.java:664)
> ... 65 more
> 2026-01-21 15:07:34:526 +0000 
> [WARNING][%cac-dpd-cde-gg-aks-dev-3%partition-operations-4][TxCleanupRequestSender]
>  First cleanup attempt failed (the transaction outcome is not affected) 
> [txId=019be118-132c-00ab-399b-327000000001]
> java.util.concurrent.CompletionException: 
> org.apache.ignite.internal.storage.StorageException: IGN-CMN-65535 Error 
> while updating WI links: [link=1081145415610400959, rowId=RowId 
> [partitionId=7, uuid=0000019b-e109-68e4-04dc-cf202c264365], 
> txId=019be118-132c-00ab-399b-327000000001, tableId=1171, partitionId=7] 
> TraceId:65a31616
> at java.base/java.util.concurrent.CompletableFuture.encodeThrowable(Unknown 
> Source)
> at java.base/java.util.concurrent.CompletableFuture.uniApplyNow(Unknown 
> Source)
> at java.base/java.util.concurrent.CompletableFuture.uniApplyStage(Unknown 
> Source)
> at java.base/java.util.concurrent.CompletableFuture.thenApply(Unknown Source)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.processTableWriteIntentSwitchAction(PartitionReplicaListener.java:1986)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.processOperationRequest(PartitionReplicaListener.java:660)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.processOperationRequestWithTxOperationManagementLogic(PartitionReplicaListener.java:4235)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.processRequest(PartitionReplicaListener.java:520)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.processRequestInContext(PartitionReplicaListener.java:480)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.process(PartitionReplicaListener.java:472)
> at 
> org.apache.ignite.internal.partition.replicator.handlers.WriteIntentSwitchRequestHandler.lambda$invokeTableWriteIntentSwitchReplicaRequest$4(WriteIntentSwitchRequestHandler.java:179)
> at java.base/java.util.concurrent.CompletableFuture.uniComposeStage(Unknown 
> Source)
> at java.base/java.util.concurrent.CompletableFuture.thenCompose(Unknown 
> Source)
> at 
> org.apache.ignite.internal.partition.replicator.handlers.WriteIntentSwitchRequestHandler.invokeTableWriteIntentSwitchReplicaRequest(WriteIntentSwitchRequestHandler.java:165)
> at 
> org.apache.ignite.internal.partition.replicator.handlers.WriteIntentSwitchRequestHandler.lambda$handle$0(WriteIntentSwitchRequestHandler.java:118)
> at java.base/java.util.stream.ReferencePipeline$3$1.accept(Unknown Source)
> at java.base/java.util.Iterator.forEachRemaining(Unknown Source)
> at 
> java.base/java.util.Spliterators$IteratorSpliterator.forEachRemaining(Unknown 
> Source)
> at java.base/java.util.stream.AbstractPipeline.copyInto(Unknown Source)
> at java.base/java.util.stream.AbstractPipeline.wrapAndCopyInto(Unknown Source)
> at java.base/java.util.stream.ReduceOps$ReduceOp.evaluateSequential(Unknown 
> Source)
> at java.base/java.util.stream.AbstractPipeline.evaluate(Unknown Source)
> at java.base/java.util.stream.ReferencePipeline.collect(Unknown Source)
> at 
> org.apache.ignite.internal.partition.replicator.handlers.WriteIntentSwitchRequestHandler.handle(WriteIntentSwitchRequestHandler.java:119)
> at 
> org.apache.ignite.internal.partition.replicator.ZonePartitionReplicaListener.processRequest(ZonePartitionReplicaListener.java:232)
> at 
> org.apache.ignite.internal.partition.replicator.ZonePartitionReplicaListener.lambda$invoke$0(ZonePartitionReplicaListener.java:208)
> at java.base/java.util.concurrent.CompletableFuture.uniComposeStage(Unknown 
> Source)
> at java.base/java.util.concurrent.CompletableFuture.thenCompose(Unknown 
> Source)
> at 
> org.apache.ignite.internal.partition.replicator.ZonePartitionReplicaListener.invoke(ZonePartitionReplicaListener.java:208)
> at 
> org.apache.ignite.internal.replicator.ZonePartitionReplicaImpl.processRequest(ZonePartitionReplicaImpl.java:67)
> at 
> org.apache.ignite.internal.replicator.ReplicaManager.handleReplicaRequest(ReplicaManager.java:382)
> at 
> org.apache.ignite.internal.replicator.ReplicaManager.lambda$onReplicaMessageReceived$0(ReplicaManager.java:313)
> at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
> at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown 
> Source)
> at java.base/java.lang.Thread.run(Unknown Source)
> Caused by: org.apache.ignite.internal.storage.StorageException: IGN-CMN-65535 
> Error while updating WI links: [link=1081145415610400959, rowId=RowId 
> [partitionId=7, uuid=0000019b-e109-68e4-04dc-cf202c264365], 
> txId=019be118-132c-00ab-399b-327000000001, tableId=1171, partitionId=7] 
> TraceId:65a31616
> at 
> org.apache.ignite.internal.storage.pagememory.mv.WriteIntentListSupport.removeNodeFromWriteIntentsList(WriteIntentListSupport.java:55)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.WiLinkableRowVersionOperations.removeFromWriteIntentsList(WiLinkableRowVersionOperations.java:42)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.AbortWriteInvokeClosure.onUpdate(AbortWriteInvokeClosure.java:110)
> at 
> org.apache.ignite.internal.pagememory.tree.BplusTree$Put.replaceRowInPage(BplusTree.java:4246)
> at 
> org.apache.ignite.internal.pagememory.tree.BplusTree$Put.finishTail(BplusTree.java:4020)
> at 
> org.apache.ignite.internal.pagememory.tree.BplusTree$Invoke.tryFinish(BplusTree.java:4501)
> at 
> org.apache.ignite.internal.pagememory.tree.BplusTree.invoke(BplusTree.java:2204)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.AbstractPageMemoryMvPartitionStorage.lambda$abortWrite$19(AbstractPageMemoryMvPartitionStorage.java:672)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.AbstractPageMemoryMvPartitionStorage.busy(AbstractPageMemoryMvPartitionStorage.java:1086)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.AbstractPageMemoryMvPartitionStorage.abortWrite(AbstractPageMemoryMvPartitionStorage.java:664)
> at 
> org.apache.ignite.internal.table.distributed.raft.snapshot.SnapshotAwarePartitionDataStorage.abortWrite(SnapshotAwarePartitionDataStorage.java:149)
> at 
> org.apache.ignite.internal.table.distributed.StorageUpdateHandler.performAbortWrite(StorageUpdateHandler.java:478)
> at 
> org.apache.ignite.internal.table.distributed.StorageUpdateHandler.lambda$switchWriteIntents$2(StorageUpdateHandler.java:422)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.PersistentPageMemoryMvPartitionStorage.lambda$runConsistently$1(PersistentPageMemoryMvPartitionStorage.java:207)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.AbstractPageMemoryMvPartitionStorage.busy(AbstractPageMemoryMvPartitionStorage.java:1086)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.PersistentPageMemoryMvPartitionStorage.runConsistently(PersistentPageMemoryMvPartitionStorage.java:197)
> at 
> org.apache.ignite.internal.table.distributed.raft.snapshot.SnapshotAwarePartitionDataStorage.runConsistently(SnapshotAwarePartitionDataStorage.java:83)
> at 
> org.apache.ignite.internal.table.distributed.StorageUpdateHandler.switchWriteIntents(StorageUpdateHandler.java:409)
> at 
> org.apache.ignite.internal.table.distributed.StorageUpdateHandler.switchWriteIntents(StorageUpdateHandler.java:376)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.applyWriteIntentSwitchCommandLocally(PartitionReplicaListener.java:2042)
> at 
> org.apache.ignite.internal.table.distributed.replicator.PartitionReplicaListener.lambda$processTableWriteIntentSwitchAction$76(PartitionReplicaListener.java:1988)
> ... 34 more
> Caused by: 
> org.apache.ignite.internal.pagememory.freelist.CorruptedFreeListException: 
> IGN-STORAGE-2 Failed to update data row TraceId:65a31616
> at 
> org.apache.ignite.internal.pagememory.freelist.FreeListImpl.updateDataRow(FreeListImpl.java:674)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.WriteIntentListSupport.removeNodeFromWriteIntentsList(WriteIntentListSupport.java:42)
> ... 54 more
> Caused by: java.lang.IllegalStateException: Item not found: 17
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.findIndirectItemIndex(DataPageIo.java:453)
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.resolveDirectItemIdFromIndirectItemId(DataPageIo.java:605)
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.getDataOffset(DataPageIo.java:596)
> at 
> org.apache.ignite.internal.pagememory.io.DataPageIo.getPayloadOffset(DataPageIo.java:720)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.UpdateNextWiLinkHandler.run(UpdateNextWiLinkHandler.java:34)
> at 
> org.apache.ignite.internal.storage.pagememory.mv.UpdateNextWiLinkHandler.run(UpdateNextWiLinkHandler.java:19)
> at 
> org.apache.ignite.internal.pagememory.util.PageHandler.writePage(PageHandler.java:220)
> at 
> org.apache.ignite.internal.pagememory.datastructure.DataStructure.write(DataStructure.java:271)
> at 
> org.apache.ignite.internal.pagememory.freelist.FreeListImpl.updateDataRow(FreeListImpl.java:664)
> ... 55 more {code}



--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to