[ https://issues.apache.org/jira/browse/IGNITE-8563?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Andrey Gura reassigned IGNITE-8563: ----------------------------------- Assignee: Andrey Gura > WAL file archiver does not propagate file archiving error to error handler > -------------------------------------------------------------------------- > > Key: IGNITE-8563 > URL: https://issues.apache.org/jira/browse/IGNITE-8563 > Project: Ignite > Issue Type: Improvement > Affects Versions: 2.5 > Reporter: Alexey Goncharuk > Assignee: Andrey Gura > Priority: Major > Fix For: 2.6 > > > I observed this error when a disk with WAL archive left out of space: > {code} > ... > at > org.apache.ignite.internal.processors.cache.distributed.dht.GridDhtTxLocal.finishTx(GridDhtTxLocal.java:464) > at > org.apache.ignite.internal.processors.cache.distributed.dht.GridDhtTxLocal.commitDhtLocalAsync(GridDhtTxLocal.java:517) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler.finishDhtLocal(IgniteTxHandler.java:940) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler.finish(IgniteTxHandler.java:819) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler.processNearTxFinishRequest(IgniteTxHandler.java:775) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler.access$200(IgniteTxHandler.java:97) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler$3.apply(IgniteTxHandler.java:189) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxHandler$3.apply(IgniteTxHandler.java:187) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.processMessage(GridCacheIoManager.java:1054) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.onMessage0(GridCacheIoManager.java:579) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.handleMessage(GridCacheIoManager.java:378) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.handleMessage(GridCacheIoManager.java:304) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager.access$100(GridCacheIoManager.java:99) > at > org.apache.ignite.internal.processors.cache.GridCacheIoManager$1.onMessage(GridCacheIoManager.java:293) > 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.run(StripedExecutor.java:511) > at java.lang.Thread.run(Thread.java:745) > Caused by: org.apache.ignite.IgniteException: Runtime failure on row: > Row@1ec13b23[ key: 4458000681143704309, val: <CUT> > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.doPut(BPlusTree.java:2119) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.putx(BPlusTree.java:2066) > at > org.apache.ignite.internal.processors.query.h2.database.H2TreeIndex.putx(H2TreeIndex.java:247) > at > org.apache.ignite.internal.processors.query.h2.opt.GridH2Table.addToIndex(GridH2Table.java:548) > at > org.apache.ignite.internal.processors.query.h2.opt.GridH2Table.update(GridH2Table.java:480) > at > org.apache.ignite.internal.processors.query.h2.IgniteH2Indexing.store(IgniteH2Indexing.java:659) > at > org.apache.ignite.internal.processors.query.GridQueryProcessor.store(GridQueryProcessor.java:1866) > at > org.apache.ignite.internal.processors.cache.query.GridCacheQueryManager.store(GridCacheQueryManager.java:403) > at > org.apache.ignite.internal.processors.cache.IgniteCacheOffheapManagerImpl$CacheDataStoreImpl.finishUpdate(IgniteCacheOffheapManagerImpl.java:1393) > at > org.apache.ignite.internal.processors.cache.IgniteCacheOffheapManagerImpl$CacheDataStoreImpl.invoke(IgniteCacheOffheapManagerImpl.java:1257) > at > org.apache.ignite.internal.processors.cache.persistence.GridCacheOffheapManager$GridCacheDataStore.invoke(GridCacheOffheapManager.java:1511) > at > org.apache.ignite.internal.processors.cache.IgniteCacheOffheapManagerImpl.invoke(IgniteCacheOffheapManagerImpl.java:352) > at > org.apache.ignite.internal.processors.cache.GridCacheMapEntry.storeValue(GridCacheMapEntry.java:3602) > at > org.apache.ignite.internal.processors.cache.GridCacheMapEntry.storeValue(GridCacheMapEntry.java:3578) > at > org.apache.ignite.internal.processors.cache.GridCacheMapEntry.innerSet(GridCacheMapEntry.java:1040) > at > org.apache.ignite.internal.processors.cache.transactions.IgniteTxLocalAdapter.userCommit(IgniteTxLocalAdapter.java:652) > ... 22 common frames omitted > Caused by: org.apache.ignite.IgniteException: Failed to archive WAL segment > [srcFile=/gridgain/ssd/storage/wal/consistentID_47500/0000000000000000.wal, > dstFile=/gridgain/ssd/storage/wal_archive/consistentID_47500/0000000000004290.wal.tmp] > at > org.apache.ignite.internal.processors.cache.persistence.pagemem.PageMemoryImpl.beforeReleaseWrite(PageMemoryImpl.java:1615) > at > org.apache.ignite.internal.processors.cache.persistence.pagemem.PageMemoryImpl.writeUnlockPage(PageMemoryImpl.java:1478) > at > org.apache.ignite.internal.processors.cache.persistence.pagemem.PageMemoryImpl.writeUnlock(PageMemoryImpl.java:449) > at > org.apache.ignite.internal.processors.cache.persistence.pagemem.PageMemoryImpl.writeUnlock(PageMemoryImpl.java:443) > at > org.apache.ignite.internal.processors.cache.persistence.tree.util.PageHandler.writeUnlock(PageHandler.java:377) > at > org.apache.ignite.internal.processors.cache.persistence.tree.util.PageHandler.writePage(PageHandler.java:352) > at > org.apache.ignite.internal.processors.cache.persistence.DataStructure.write(DataStructure.java:274) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.access$11100(BPlusTree.java:83) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree$Put.tryInsert(BPlusTree.java:2954) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree$Put.access$7600(BPlusTree.java:2642) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.putDown(BPlusTree.java:2367) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.putDown(BPlusTree.java:2348) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.putDown(BPlusTree.java:2348) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.putDown(BPlusTree.java:2348) > at > org.apache.ignite.internal.processors.cache.persistence.tree.BPlusTree.doPut(BPlusTree.java:2086) > ... 37 common frames omitted > Caused by: org.apache.ignite.IgniteCheckedException: Failed to archive WAL > segment > [srcFile=/gridgain/ssd/storage/wal/consistentID_47500/0000000000000000.wal, > dstFile=/gridgain/ssd/storage/wal_archive/consistentID_47500/0000000000004290.wal.tmp] > at > org.apache.ignite.internal.processors.cache.persistence.wal.FileWriteAheadLogManager$FileArchiver.archiveSegment(FileWriteAheadLogManager.java:1777) > at > org.apache.ignite.internal.processors.cache.persistence.wal.FileWriteAheadLogManager$FileArchiver.run(FileWriteAheadLogManager.java:1582) > Caused by: java.nio.file.FileSystemException: > /gridgain/ssd/storage/wal/consistentID_47500/0000000000000000.wal -> > /gridgain/ssd/storage/wal_archive/consistentID_47500/0000000000004290.wal.tmp: > No space left on device > at > sun.nio.fs.UnixException.translateToIOException(UnixException.java:91) > at > sun.nio.fs.UnixException.rethrowAsIOException(UnixException.java:102) > at sun.nio.fs.UnixCopyFile.copyFile(UnixCopyFile.java:253) > at sun.nio.fs.UnixCopyFile.copy(UnixCopyFile.java:581) > at > sun.nio.fs.UnixFileSystemProvider.copy(UnixFileSystemProvider.java:253) > at java.nio.file.Files.copy(Files.java:1274) > at > org.apache.ignite.internal.processors.cache.persistence.wal.FileWriteAheadLogManager$FileArchiver.archiveSegment(FileWriteAheadLogManager.java:1764) > ... 1 common frames omitted > {code} > This resulted in TX heuristic error, which in turn resulted in hanging > transaction. The reason is that WAL archiver try-catches the attempt to > archive the file and later re-throws it in {{log(...)}} method (see cleanErr > field usages). > I think instead we should get rid of the try-catch block altogether and route > the exception directly to the error handler. -- This message was sent by Atlassian JIRA (v7.6.3#76005)