Commit d9faad9c authored by unknown's avatar unknown
Browse files

bug#9924 - ndb backup abort handling 

  Redo abort handling according to descr. in Backup.txt
bug#9960 - ndb backup
      increase wait completed timeout to 48 hours


ndb/include/kernel/signaldata/BackupImpl.hpp:
  Add nodeid to reply to be able to fake reply during NF
ndb/include/kernel/signaldata/BackupSignalData.hpp:
  new error codes
ndb/src/common/debugger/signaldata/BackupImpl.cpp:
  fix printout
ndb/src/kernel/blocks/backup/Backup.cpp:
  bug#9924 - ndb backup abort handling
    Redo abort handling according to descr. in Backup.txt
ndb/src/kernel/blocks/backup/Backup.hpp:
  bug#9924 - ndb backup abort handling
    Redo abort handling according to descr. in Backup.txt
ndb/src/kernel/blocks/backup/Backup.txt:
  bug#9924 - ndb backup abort handling
    Redo abort handling according to descr. in Backup.txt
ndb/src/kernel/blocks/backup/BackupInit.cpp:
  bug#9924 - ndb backup abort handling
    Redo abort handling according to descr. in Backup.txt
ndb/src/kernel/blocks/cmvmi/Cmvmi.cpp:
  Init own version
ndb/src/mgmapi/mgmapi.cpp:
  bug#9960 - ndb backup
    increase wait completed timeout to 48 hours
ndb/src/mgmsrv/MgmtSrvr.cpp:
  Handle node failures activly
    (mainly for backup...)
ndb/src/mgmsrv/MgmtSrvr.hpp:
  Handle node failures activly
    (mainly for backup...)
ndb/src/mgmsrv/MgmtSrvrGeneralSignalHandling.cpp:
  Handle node failures activly
    (mainly for backup...)
ndb/src/ndbapi/ndberror.c:
  new error codes
ndb/test/ndbapi/testBackup.cpp:
  fix return codes
ndb/test/run-test/daily-basic-tests.txt:
  Add failure test cases to autotest
ndb/test/src/NdbBackup.cpp:
  fix error codes
  introduce checking of backup resources after each test
parent 135c7b5a

ndb/include/kernel/signaldata/BackupImpl.hpp

+7 −5
Original line number Diff line number Diff line
@@ -75,7 +75,7 @@ class DefineBackupRef { 


  friend bool printDEFINE_BACKUP_REF(FILE *, const Uint32 *, Uint32, Uint16);

public:

  STATIC_CONST( SignalLength = 3 );

  STATIC_CONST( SignalLength = 4 );

  

  enum ErrorCode {

    Undefined = 1340,
@@ -92,6 +92,7 @@ private: 
  Uint32 backupId;

  Uint32 backupPtr;

  Uint32 errorCode;

  Uint32 nodeId;

};



class DefineBackupConf {
@@ -158,7 +159,7 @@ class StartBackupRef { 


  friend bool printSTART_BACKUP_REF(FILE *, const Uint32 *, Uint32, Uint16);

public:

  STATIC_CONST( SignalLength = 4 );

  STATIC_CONST( SignalLength = 5 );



  enum ErrorCode {

    FailedToAllocateTriggerRecord = 1
@@ -168,6 +169,7 @@ private: 
  Uint32 backupPtr;

  Uint32 signalNo;

  Uint32 errorCode;

  Uint32 nodeId;

};



class StartBackupConf {
@@ -232,9 +234,8 @@ public: 
private:

  Uint32 backupId;

  Uint32 backupPtr;

  Uint32 tableId;

  Uint32 fragmentNo;

  Uint32 errorCode;

  Uint32 nodeId;

};



class BackupFragmentConf {
@@ -296,12 +297,13 @@ class StopBackupRef { 


  friend bool printSTOP_BACKUP_REF(FILE *, const Uint32 *, Uint32, Uint16);

public:

  STATIC_CONST( SignalLength = 3 );

  STATIC_CONST( SignalLength = 4 );



private:

  Uint32 backupId;

  Uint32 backupPtr;

  Uint32 errorCode;

  Uint32 nodeId;

};



class StopBackupConf {

ndb/include/kernel/signaldata/BackupSignalData.hpp

+3 −0
Original line number Diff line number Diff line
@@ -240,6 +240,9 @@ public: 
    FileOrScanError = 1325, //                       slave -> coordinator

    BackupFailureDueToNodeFail = 1326, //             slave -> slave

    OkToClean = 1327                  //             master -> slave

    

    ,AbortScan = 1328

    ,IncompatibleVersions = 1329

  };

private:

  Uint32 requestType;

ndb/src/common/debugger/signaldata/BackupImpl.cpp

+2 −4
Original line number Diff line number Diff line
@@ -90,10 +90,8 @@ printBACKUP_FRAGMENT_REQ(FILE * out, const Uint32 * data, Uint32 l, Uint16 bno){ 
bool 

printBACKUP_FRAGMENT_REF(FILE * out, const Uint32 * data, Uint32 l, Uint16 bno){

  BackupFragmentRef* sig = (BackupFragmentRef*)data;

  fprintf(out, " backupPtr: %d backupId: %d\n",

	  sig->backupPtr, sig->backupId);

  fprintf(out, " tableId: %d fragmentNo: %d errorCode: %d\n",

	  sig->tableId, sig->fragmentNo, sig->errorCode);

  fprintf(out, " backupPtr: %d backupId: %d nodeId: %d errorCode: %d\n",

	  sig->backupPtr, sig->backupId, sig->nodeId, sig->errorCode);

  return true;

}

ndb/src/kernel/blocks/backup/Backup.cpp

+616 −876

File changed.

Preview size limit exceeded, changes collapsed.

ndb/src/kernel/blocks/backup/Backup.hpp

+15 −21
Original line number Diff line number Diff line
@@ -232,6 +232,7 @@ public: 
     */

    bool newScan();

    bool scanConf(Uint32 noOfOps, Uint32 opLen);

    bool closeScan();

    

    /**

     * Per record
@@ -330,7 +331,7 @@ public: 
    

    Uint8 fileOpened;

    Uint8 fileRunning;

    Uint8 fileDone;

    Uint8 fileClosing;

    Uint8 scanRunning;

  }; 

  typedef Ptr<BackupFile> BackupFilePtr;
@@ -403,13 +404,11 @@ public: 
		 ArrayPool<TriggerRecord> & trp) 

      : slaveState(b, validSlaveTransitions, validSlaveTransitionsCount,1)

      , tables(tp), triggers(trp), files(bp), pages(pp)

      , masterData(b, validMasterTransitions, validMasterTransitionsCount)

	, backup(b)

      , masterData(b), backup(b)

      {

      closingFiles    = false;

      okToCleanMaster = true;

      }

    

    Uint32 m_gsn;

    CompoundState slaveState; 

    

    Uint32 clientRef;
@@ -420,9 +419,6 @@ public: 
    Uint32 errorCode;

    NdbNodeBitmask nodes;

    

    bool okToCleanMaster;

    bool closingFiles;



    Uint64 noOfBytes;

    Uint64 noOfRecords;

    Uint64 noOfLogBytes;
@@ -444,15 +440,13 @@ public: 
    SimpleProperties props;// Used for (un)packing backup request

    

    struct MasterData {

      MasterData(Backup & b, const State valid[], Uint32 count) 

	: state(b, valid, count, 0) 

      MasterData(Backup & b) 

	{

	}

      MutexHandle2<BACKUP_DEFINE_MUTEX> m_defineBackupMutex;

      MutexHandle2<DICT_COMMIT_TABLE_MUTEX> m_dictCommitTableMutex;



      Uint32 gsn;

      CompoundState state;

      SignalCounter sendCounter;

      Uint32 errorCode;

      struct {
@@ -557,6 +551,7 @@ public: 
  void stopBackupReply(Signal* signal, BackupRecordPtr ptr, Uint32 nodeId);

  

  void defineBackupRef(Signal*, BackupRecordPtr, Uint32 errCode = 0);

  void backupFragmentRef(Signal * signal, BackupFilePtr filePtr);



  void nextFragment(Signal*, BackupRecordPtr);
@@ -578,14 +573,14 @@ public: 
  void sendAbortBackupOrd(Signal* signal, BackupRecordPtr ptr, Uint32 errCode);

  void sendAbortBackupOrdSlave(Signal* signal, BackupRecordPtr ptr, 

			       Uint32 errCode);

  void masterAbort(Signal*, BackupRecordPtr ptr, bool controlledAbort);

  void masterAbort(Signal*, BackupRecordPtr ptr);

  void masterSendAbortBackup(Signal*, BackupRecordPtr ptr);

  void slaveAbort(Signal*, BackupRecordPtr ptr);

  

  void abortFile(Signal* signal, BackupRecordPtr ptr, BackupFilePtr filePtr);

  void abortFileHook(Signal* signal, BackupFilePtr filePtr, bool scanDone);

  

  bool verifyNodesAlive(const NdbNodeBitmask& aNodeBitMask);

  bool verifyNodesAlive(BackupRecordPtr, const NdbNodeBitmask& aNodeBitMask);

  bool checkAbort(BackupRecordPtr ptr);

  void checkNodeFail(Signal* signal,

		     BackupRecordPtr ptr,
@@ -603,9 +598,8 @@ public: 
  void sendBackupRef(BlockReference ref, Signal *signal,

		     Uint32 senderData, Uint32 errorCode);

  void dumpUsedResources();

  void cleanupMasterResources(BackupRecordPtr ptr);

  void cleanupSlaveResources(BackupRecordPtr ptr);

  void cleanupFinalResources(BackupRecordPtr ptr);

  void cleanup(Signal*, BackupRecordPtr ptr);

  void abort_scan(Signal*, BackupRecordPtr ptr);

  void removeBackup(Signal*, BackupRecordPtr ptr);



  void sendSTTORRY(Signal*);