[ https://issues.apache.org/jira/browse/IGNITE-9739?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Alexey Goncharuk updated IGNITE-9739: ------------------------------------- Ignite Flags: (was: Docs Required) > Critical exception in transaction processing in case we have nodes out of > baseline and non-persisted cache > ---------------------------------------------------------------------------------------------------------- > > Key: IGNITE-9739 > URL: https://issues.apache.org/jira/browse/IGNITE-9739 > Project: Ignite > Issue Type: Bug > Components: persistence > Reporter: Sergey Kosarev > Assignee: Sergey Kosarev > Priority: Major > > Activation finished > {code:java} > 2018-09-20 20:47:05.169 [INFO > ][sys-#307%DPL_GRID%DplGridNodeName%][o.g.g.i.p.c.d.GridSnapshotAwareClusterStateProcessorImpl] > Successfully performed final activation steps > [nodeId=382437eb-fd8a-4f92-acd5-d9ea562c8557, client=false, > topVer=AffinityTopologyVersion [topVer=160, minorTopVer=1]] > {code} > but we have nodes not in base line > {code:java} > 2018-09-20 20:45:36.116 [INFO > ][sys-#305%DPL_GRID%DplGridNodeName%][o.g.g.i.p.c.d.GridSnapshotAwareClusterStateProcessorImpl] > Local node is not included in Baseline Topology and will not be used for > persistent data storage. Use control.(sh|bat) script or IgniteCluster > interface to include the node to Baseline Topology. > {code} > And we have cache (869481129) in the data region with persistanceEnabled=false > {code:java} > 2018-09-20 20:49:01.825 [INFO > ][exchange-worker-#154%DPL_GRID%DplGridNodeName%][o.a.i.i.p.cache.GridCacheProcessor] > Started cache [name=DPL_PUBLISHED_CACHES_REGISTRY$, *id=869481129*, group=SY > STEM_CACHEGROUP_PUBLISHED_REGISTRY, memoryPolicyName=not-persisted, > mode=PARTITIONED, atomicity=TRANSACTIONAL, backups=3] > {code} > Transaction on this cache(869481129) > {code:java} > 869481129{code} > leads to critical error causing nodes by faulure handler: > {code:java} > 2018-09-20 20:50:24.275 > [ERROR][sys-stripe-41-#42%DPL_GRID%DplGridNodeName%][o.a.i.i.p.cache.GridCacheIoManager] > Failed processing message [senderId=62e986f0-62b5-4ec8-8cc7-27b74d345235, > msg=GridDhtTxPrepareRequest [nearNodeId=814af7c4-2de5-4511-b1ea-065b91eaa774, > futId=520e308f561-255fdea5-a996-4102-a120-afa380c54570, miniId=1, > topVer=AffinityTopologyVersion [topVer=160, minorTopVer=2], > invalidateNearEntries={}, nearWrites=null, owned=null, > nearXidVer=GridCacheVersion [topVer=148944365, order=1537511036821, > nodeOrder=132], subjId=814af7c4-2de5-4511-b1ea-065b91eaa774, taskNameHash=0, > preloadKeys=null, skipCompletedVers=false, > super=GridDistributedTxPrepareRequest [threadId=58, concurrency=PESSIMISTIC, > isolation=READ_COMMITTED, writeVer=GridCacheVersion [topVer=148944365, > order=1537511036824, nodeOrder=7], timeout=299970, reads=null, > writes=ArrayList [ > IgniteTxEntry [key=KeyCacheObjectImpl [part=27254, > val=com.sbt.api.entities.out.IPublishedDocType, hasValBytes=true], > *cacheId=869481129*, > txKey=IgniteTxKey [key=KeyCacheObjectImpl [part=27254, > val=com.sbt.api.entities.out.IPublishedDocType, hasValBytes=true], > *cacheId=869481129*], val=[op=CREATE, > val=com.sbt.dpl.gridgain.PublishedRegistry$PublishedCacheTuple > [idHash=811765531, hash=1522508040, > cacheName=com.sbt.gbk.entities.DocType_DPL_union-module,indexes=ArrayList > {com.sbt.dpl.gridgain.newModel.base.indexes.PublishedIndexType > [idHash=1583970836, hash=363194492, isSoftReference=false, > unselectiveBuckets=4096, fieldNames=ArrayList > \{isDeleted},moduleName=union-module > , cachedUnselectives=10000, selectors=ArrayList {isDeleted}, > exceptUnselectives=false, primitiveCollection=false, isVersioned=false, > isComposite=false, isSystemTypeBelongs=false, > name=com.sbt.gbk.entities.DocType_DPL_isDeleted, isIndexedCollection=false, > isGlobal=false, maxSelective=1000], > com.sbt.dpl.gridgain.newModel.base.indexes.PublishedIndexType > [idHash=2060926101, hash=1983794578, isSoftReference=false, > unselectiveBuckets=4096, fieldNames=ArrayList ,moduleName=union-module, > cachedUnselectives=10000, selectors=ArrayList, exceptUnselectives=false, > primitiveCollection=false, isVersioned=false, isComposite=false, > isSystemTypeBelongs=false, name=com.sbt.gbk.entities.DocType_DPL_code, > isIndexedCollection=false, isGlobal=true, maxSelective=1000] > , com.sbt.dpl.gridgain.newModel.base.indexes.PublishedIndexType > [idHash=1821682714, hash=-1245813786, isSoftReference=false, > unselectiveBuckets=4096, fieldNames=ArrayList {globalId}, > moduleName=union-module, cachedUnselectives=10000, selectors=ArrayList > {globalId}, exceptUnselectives=false, primitiveCollection=false, > isVersioned=false, isComposite=false, isSystemTypeBelongs=false, > name=com.sbt.gbk.entities.DocType_DPL_globalId, isIndexedCollection=false, > isGlobal=false, maxSelective=1000] > }, partitionDependencyClassName=null, moduleName=union-module, > cacheModuleName=union-module] > ], prevVal=[op=NOOP, val=null], oldVal=[op=NOOP, val=null], > entryProcessorsCol=null, ttl=-1, conflictExpireTime=-1, conflictVer=null, > explicitVer=null, dhtVer=null, filters=CacheEntryPredicate[] [], > filtersPassed=false, filtersSet=false, entry=GridCacheMapEntry > [key=KeyCacheObjectImpl [part=27254, > val=com.sbt.api.entities.out.IPublishedDocType, hasValBytes=true], val=null, > startVer=1537511036806, ver=GridCacheVersion [topVer=148944365, > order=1537511036806, nodeOrder=86], hash=-1897857526, > extras=GridCacheMvccEntryExtras [mvcc=GridCacheMvcc [locs=null, rmts=Link > edList [GridCacheMvccCandidate [nodeId=62e986f0-62b5-4ec8-8cc7-27b74d345235, > ver=GridCacheVersion [topVer=148944365, order=1537511036822, nodeOrder=7], > threadId=302, id=2, topVer=AffinityTopologyVersion [topVer=-1, > minorTopVer=0], reentry=null, > otherNodeId=814af7c4-2de5-4511-b1ea-065b91eaa774, otherVer=null, > mappedDhtNodes=null, mappedNearNodes=null, ownerVer=null, serOrder=null, > key=KeyCacheObjectImpl [part=27254, > val=com.sbt.api.entities.out.IPublishedDocType, hasValBytes=true], > masks=local=0|owner=0|ready=0|reentry=0|used=0|tx=1|single_implicit=0|dht_local=0|near_loc > al=0|removed=0|read=0, prevVer=null, nextVer=null]]]], > flags=2]GridDistributedCacheEntry [super=]GridDhtCacheEntry [rdrs=ReaderId[] > [], part=27254, super=], prepared=1, locked=false, nodeId=null, > locMapped=false, expiryPlc=null, transferExpiryPlc=false, flags=0, > partUpdateCntr=0, serReadVer=null, xidVer=null]], dhtVers=null, txSize=0, > plc=2, txState=null, flags=last, super=GridDistributedBaseMessage > [ver=GridCacheVersion [topVer=148944365, order=1537511036822, nodeOrder=7], > committedVers=null, rolledbackVers=null, cnt=0, super=GridCacheIdMessage > [cacheId=0]]]]] > java.lang.IllegalStateException: Unable to find consistentId by UUID > [*nodeId=382437eb-fd8a-4f92-acd5-d9ea562c8557*, > topVer=AffinityTopologyVersion [topVer=160, minorTopVer=2]] > at > org.apache.ignite.internal.managers.discovery.ConsistentIdMapper.mapToCompactId(ConsistentIdMapper.java:62) > at > org.apache.ignite.internal.managers.discovery.ConsistentIdMapper.mapToCompactIds(ConsistentIdMapper.java:123) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxAdapter.state(IgniteTxAdapter.java:1108) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxAdapter.state(IgniteTxAdapter.java:959) > at > org.apache.ignite.internal.processors.cache.distributed.GridDistributedTxRemoteAdapter.prepareRemoteTx(GridDistributedTxRemoteAdapter.java:409) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler.startRemoteTx(IgniteTxHandler.java:1758) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler.processDhtTxPrepareRequest(IgniteTxHandler.java:1125) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler.access$400(IgniteTxHandler.java:101) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler$5.apply(IgniteTxHandler.java:205) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler$5.apply(IgniteTxHandler.java:203) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.processMessage(GridCacheIoManager.java:1056) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.onMessage0(GridCacheIoManager.java:581) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.handleMessage(GridCacheIoManager.java:380) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.handleMessage(GridCacheIoManager.java:306) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.access$100(GridCacheIoManager.java:101) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager$1.onMessage(GridCacheIoManager.java:295) > at > org.apache.ignite.internal.managers.communication.GridIoManager.invokeListener(GridIoManager.java:1556) > at > org.apache.ignite.internal.managers.communication.GridIoManager.processRegularMessage0(GridIoManager.java:1184) > at > org.apache.ignite.internal.managers.communication.GridIoManager.access$4200(GridIoManager.java:125) > at > org.apache.ignite.internal.managers.communication.GridIoManager$9.run(GridIoManager.java:1091) > at > org.apache.ignite.internal.util.StripedExecutor$Stripe.body(StripedExecutor.java:496) > at > org.apache.ignite.internal.util.worker.GridWorker.run(GridWorker.java:110) > at java.lang.Thread.run(Thread.java:745) > 2018-09-20 20:50:24.277 > [ERROR][sys-stripe-41-#42%DPL_GRID%DplGridNodeName%][org.apache.ignite.Ignite] > Critical system error detected. Will be handled accordingly to configured > handler > {code} > nodeId (382437eb-fd8a-4f92-acd5-d9ea562c8557) causing the error belongs to > the node out of baseline. > I found this issue only happens if system property IGNITE_WAL_LOG_TX_RECORDS > = true > when we try write to WAL information about transaction. -- This message was sent by Atlassian JIRA (v7.6.3#76005)