PostgreSQL備機checkpoint

? 數據庫異常關閉時，數據庫關閉時來不及或者沒機會做checkpoint，則需要從上一個一致性檢查的開始恢復。

? ? PostgreSQL備機checkpoint是不能產生checkpoint WAL的，因為如果寫這樣類型的checkpoint的話，就會將接收的WAL打亂，那么日志將混亂，回放會出問題。

? ? 那么問題來了，備機支持checkpoint嗎？他的checkpoint怎么做的？

? ? PostgreSQL為了縮短恢復時間，備機上也支持checkpoint，即CreateRestartPoint。但是其pg_control文件的checkpoint記錄的位點是從主機傳過來WAL里面的checkpoint記錄位置。

1、備機回放

StartupXLOG
    do{
        ...
        RmgrTable[record->xl_rmid].rm_redo(xlogreader);//回放
        ...
        record = ReadRecord(xlogreader, InvalidXLogRecPtr, LOG, false);//讀取一個xlog
    } while (record != NULL);

2、回放函數

void
xlog_redo(XLogReaderState *record)
{
    ...
    else if (info == XLOG_CHECKPOINT_SHUTDOWN){
        ...
        memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
        ...
        RecoveryRestartPoint(&checkPoint);
    }else if (info == XLOG_CHECKPOINT_ONLINE){
        ...
        memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
        ...
        RecoveryRestartPoint(&checkPoint);
    }
    ...
}

3、RecoveryRestartPoint

static void
RecoveryRestartPoint(const CheckPoint *checkPoint)
{
    ...
    SpinLockAcquire(&XLogCtl->info_lck);
    XLogCtl->lastCheckPointRecPtr = ReadRecPtr;//ReadRecPtr為讀取checkpoint記錄后的位置
    XLogCtl->lastCheckPointEndPtr = EndRecPtr;
    XLogCtl->lastCheckPoint = *checkPoint;
    SpinLockRelease(&XLogCtl->info_lck);
}

4、ReadRecPtr賦值

ReadRecord
    for (;;)
    {
        char       *errormsg;

        record = XLogReadRecord(xlogreader, RecPtr, &errormsg);
        ReadRecPtr = xlogreader->ReadRecPtr;
        EndRecPtr = xlogreader->EndRecPtr;
        ...
    }

5、備機createcheckpoint

bool
CreateRestartPoint(int flags)
{

    LWLockAcquire(CheckpointLock, LW_EXCLUSIVE);

    /* Get a local copy of the last safe checkpoint record. */
    SpinLockAcquire(&XLogCtl->info_lck);
    lastCheckPointRecPtr = XLogCtl->lastCheckPointRecPtr;//checkpoint的位置來自XLogCtl->lastCheckPointRecPtr
    lastCheckPointEndPtr = XLogCtl->lastCheckPointEndPtr;
    lastCheckPoint = XLogCtl->lastCheckPoint;
    SpinLockRelease(&XLogCtl->info_lck);

    ...

    if (XLogRecPtrIsInvalid(lastCheckPointRecPtr) || lastCheckPoint.redo <= ControlFile->checkPointCopy.redo){
        //回放了最后一個checkpoint記錄后，備機再次手動執行checkpoint命令
        UpdateMinRecoveryPoint(InvalidXLogRecPtr, true);
        if (flags & CHECKPOINT_IS_SHUTDOWN){
            LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
            ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY;
            ControlFile->time = (pg_time_t) time(NULL);
            UpdateControlFile();
            LWLockRelease(ControlFileLock);
        }
        LWLockRelease(CheckpointLock);
        return false;
    }
    ...
    LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
    if (ControlFile->state == DB_IN_ARCHIVE_RECOVERY && ControlFile->checkPointCopy.redo < lastCheckPoint.redo){
        ControlFile->prevCheckPoint = ControlFile->checkPoint;
        ControlFile->checkPoint = lastCheckPointRecPtr;//checkpoint的位置
        ControlFile->checkPointCopy = lastCheckPoint;
        ControlFile->time = (pg_time_t) time(NULL);
        ...
        if (flags & CHECKPOINT_IS_SHUTDOWN)
            ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY;
        UpdateControlFile();
    }
    ...

    return true;
}

6、備機shutdown

void
ShutdownXLOG(int code, Datum arg)
{
    /*
     * Signal walsenders to move to stopping state.
     */
    WalSndInitStopping();

    /*
     * Wait for WAL senders to be in stopping state.  This prevents commands
     * from writing new WAL.
     */
    WalSndWaitStopping();

    if (RecoveryInProgress())//備機寫checkpoint
        CreateRestartPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE);
    else
    {
        /*
         * If archiving is enabled, rotate the last XLOG file so that all the
         * remaining records are archived (postmaster wakes up the archiver
         * process one more time at the end of shutdown). The checkpoint
         * record will go to the next XLOG file and won't be archived (yet).
         */
        if (XLogArchivingActive() && XLogArchiveCommandSet())
            RequestXLogSwitch(false);

        CreateCheckPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE);
    }
    ShutdownCLOG();
    ShutdownCommitTs();
    ShutdownSUBTRANS();
    ShutdownMultiXact();
}

7、總結

PostgreSQL備庫也可以寫檢查點，目的是避免每次重啟備庫都需要從上一個檢查點（由主庫產生，在WAL中回放出來的）APPLY后面所有的WAL。但是他記錄的checkpoint位點是從主庫傳過來的。這樣的話就有問題了，如果主機很長時間都沒有做checkpoint了，備機即使正常關閉，重啟時，也會從上一個checkpoint開始恢復，這樣也會恢復很長時間；并且多次重啟也需要從上一次checkpoint開始重復恢復。