bk commit into 5.1 tree (stewart:1.2314) BUG#19148

[Stewart Smith]

Below is the list of changes that have just been committed into a local
5.1 repository of stewart. When stewart does a push these changes will
be propagated to the main repository and, within 24 hours after the
push, to the public repository.
For information on how to access the public repository
see http://dev.mysql.com/doc/mysql/en/installing-source-tree.html

ChangeSet@stripped, 2006-10-18 18:19:16+10:00, stewart@willster.(none) +4 -0
  Bug #19148  	Backup causes cluster down if _really_ early abort happens
  
  Early abort, failing to allocate buffers, would go down the abort track and
   end up trying to sendDropTriggers (as the standard stop backup does). 
  However, it is possible to not have any tables yet defined in the backup 
  (due to allocating buffers is before this). Simple check in sendDropTrig 
  (and continue to next step). Files may be open, so we continue to close them.
  
  Also updated ERROR_Codes (and added one to test this bug).

  storage/ndb/src/kernel/blocks/ERROR_codes.txt@stripped, 2006-10-18 18:19:14+10:00, stewart@willster.(none) +6 -1
    update BACKUP error insert codes to reflect current reality.

  storage/ndb/src/kernel/blocks/backup/Backup.cpp@stripped, 2006-10-18 18:19:14+10:00, stewart@willster.(none) +32 -10
    Allow for early abort when no tables have been included in backup.
    
    Allow for abort when file records have been seized but not yet allocated
    to specific uses (is the case when buffer allocation fails)

  storage/ndb/src/kernel/blocks/backup/Backup.hpp@stripped, 2006-10-18 18:19:14+10:00, stewart@willster.(none) +1 -0
    initialize BackupRecord file Ptrs

  storage/ndb/test/src/NdbBackup.cpp@stripped, 2006-10-18 18:19:14+10:00, stewart@willster.(none) +4 -2
    Add extra failure codes for buffer allocation failure in backup

# This is a BitKeeper patch.  What follows are the unified diffs for the
# set of deltas contained in the patch.  The rest of the patch, the part
# that BitKeeper cares about, is below these diffs.
# User:	stewart
# Host:	willster.(none)
# Root:	/home/stewart/Documents/MySQL/5.1/bug19148

--- 1.27/storage/ndb/src/kernel/blocks/ERROR_codes.txt	2006-10-18 18:19:22 +10:00
+++ 1.28/storage/ndb/src/kernel/blocks/ERROR_codes.txt	2006-10-18 18:19:22 +10:00
@@ -8,7 +8,7 @@
 Next DBDIH 7178
 Next DBTC 8038
 Next CMVMI 9000
-Next BACKUP 10022
+Next BACKUP 10036
 Next DBUTIL 11002
 Next DBTUX 12008
 Next SUMA 13001
@@ -411,6 +411,11 @@
 10028: Abort backup by error at reception of BACKUP_FRAGMENT_CONF at master (code 305)
 10029: Abort backup by error at reception of FSAPPENDCONF in slave (FileOrScanError = 5)
 10030: Simulate buffer full from trigger execution => abort backup
+10031: Error 331 for dictCommitTableMutex_locked
+10032: backup checkscan
+10033: backup checkscan
+10034: define backup reply error
+10035: Fail to allocate buffers
 
 11001: Send UTIL_SEQUENCE_REF (in master)
 

--- 1.54/storage/ndb/src/kernel/blocks/backup/Backup.cpp	2006-10-18 18:19:22 +10:00
+++ 1.55/storage/ndb/src/kernel/blocks/backup/Backup.cpp	2006-10-18 18:19:22 +10:00
@@ -2004,7 +2004,15 @@
 
   if (ptr.p->slaveData.dropTrig.tableId == RNIL) {
     jam();
-    ptr.p->tables.first(tabPtr);
+    if(ptr.p->tables.count())
+      ptr.p->tables.first(tabPtr);
+    else
+    {
+      // Early abort, go to close files
+      jam();
+      closeFiles(signal, ptr);
+      return;
+    }
   } else {
     jam();
     ndbrequire(findTable(ptr, tabPtr, ptr.p->slaveData.dropTrig.tableId));
@@ -2105,8 +2113,11 @@
   BackupRecordPtr ptr;
   c_backupPool.getPtr(ptr, ptrI);
 
-  ndbout << "ERROR DROPPING TRIGGER: " << ref->getConf()->getTriggerId();
-  ndbout << " Err: " << (Uint32)ref->getErrorCode() << endl << endl;
+  if(ref->getConf()->getTriggerId() != -1)
+  {
+    ndbout << "ERROR DROPPING TRIGGER: " << ref->getConf()->getTriggerId();
+    ndbout << " Err: " << (Uint32)ref->getErrorCode() << endl << endl;
+  }
 
   dropTrigReply(signal, ptr);
 }
@@ -2538,8 +2549,9 @@
     files[i].p->filePointer = RNIL;
     files[i].p->m_flags = 0;
     files[i].p->errorCode = 0;
-    
-    if(files[i].p->pages.seize(noOfPages[i]) == false) {
+
+    if(ERROR_INSERTED(10035) || files[i].p->pages.seize(noOfPages[i]) == false)
+    {
       jam();
       DEBUG_OUT("Failed to seize " << noOfPages[i] << " pages");
       defineBackupRef(signal, ptr, DefineBackupRef::FailedToAllocateBuffers);
@@ -4451,14 +4463,24 @@
   }
   
   jam();
-  BackupFilePtr filePtr;
-  ptr.p->files.getPtr(filePtr, ptr.p->logFilePtr);
-  
+
   StopBackupConf* conf = (StopBackupConf*)signal->getDataPtrSend();
   conf->backupId = ptr.p->backupId;
   conf->backupPtr = ptr.i;
-  conf->noOfLogBytes = filePtr.p->operation.noOfBytes;
-  conf->noOfLogRecords = filePtr.p->operation.noOfRecords;
+
+  BackupFilePtr filePtr;
+  if(ptr.p->logFilePtr != RNIL)
+  {
+    ptr.p->files.getPtr(filePtr, ptr.p->logFilePtr);
+    conf->noOfLogBytes= filePtr.p->operation.noOfBytes;
+    conf->noOfLogRecords= filePtr.p->operation.noOfRecords;
+  }
+  else
+  {
+    conf->noOfLogBytes= 0;
+    conf->noOfLogRecords= 0;
+  }
+
   sendSignal(ptr.p->masterRef, GSN_STOP_BACKUP_CONF, signal,
 	     StopBackupConf::SignalLength, JBB);
   

--- 1.24/storage/ndb/src/kernel/blocks/backup/Backup.hpp	2006-10-18 18:19:22 +10:00
+++ 1.25/storage/ndb/src/kernel/blocks/backup/Backup.hpp	2006-10-18 18:19:22 +10:00
@@ -427,6 +427,7 @@
       : slaveState(b, validSlaveTransitions, validSlaveTransitionsCount,1)
       , tables(tp), triggers(trp), files(bp)
       , masterData(b), backup(b)
+      , ctlFilePtr(RNIL), logFilePtr(RNIL), dataFilePtr(RNIL)
       {
       }
     

--- 1.26/storage/ndb/test/src/NdbBackup.cpp	2006-10-18 18:19:22 +10:00
+++ 1.27/storage/ndb/test/src/NdbBackup.cpp	2006-10-18 18:19:22 +10:00
@@ -350,7 +350,8 @@
 FailS_codes[] = {
   10025,
   10027,
-  10033
+  10033,
+  10035
 };
 
 int
@@ -362,7 +363,8 @@
   10027,
   10028,
   10031,
-  10033
+  10033,
+  10035
 };
 
 int