Postgresql源码（17）数据库快照的生成（TODO）

10  11  12  13  14  15  16  17  18  19
s   r   r   r   s   r   s   r   r   r

xmin = 11
xmax = 16 + 1 = 17
xid = [11, 12, 13, 15]

Snapshot
GetSnapshotData(Snapshot snapshot)
{
	ProcArrayStruct *arrayP = procArray;
	TransactionId *other_xids = ProcGlobal->xids;
	TransactionId xmin;
	TransactionId xmax;
...
// 拿读锁访ProcArray
	LWLockAcquire(ProcArrayLock, LW_SHARED);

// 判断是否能复用快照，新增功能
	if (GetSnapshotDataReuse(snapshot))
	{
		LWLockRelease(ProcArrayLock);
		return snapshot;
	}

// 现在已经提交的最大事务ID
	latest_completed = ShmemVariableCache->latestCompletedXid;
// 获得当前事务ID
// PGPROC中保存了XID，为了降低CacheMiss会从ProcGlobal->xids中获取当前事务ID
// mypgxactoff是XID数组下标。
	mypgxactoff = MyProc->pgxactoff;
	myxid = other_xids[mypgxactoff];
	Assert(myxid == MyProc->xid);

// 最老的frozenxid： minimum datfrozenxid
	oldestxid = ShmemVariableCache->oldestXid;
	curXactCompletionCount = ShmemVariableCache->xactCompletionCount;

	/* xmax is always latestCompletedXid + 1 */
	xmax = XidFromFullTransactionId(latest_completed);
	TransactionIdAdvance(xmax);
	Assert(TransactionIdIsNormal(xmax));

	/* initialize xmin calculation with xmax */
	xmin = xmax;

	/* take own xid into account, saves a check inside the loop */
	if (TransactionIdIsNormal(myxid) && NormalTransactionIdPrecedes(myxid, xmin))
		xmin = myxid;

	snapshot->takenDuringRecovery = RecoveryInProgress();

	if (!snapshot->takenDuringRecovery)
	{
		int			numProcs = arrayP->numProcs;
		TransactionId *xip = snapshot->xip;
		int		   *pgprocnos = arrayP->pgprocnos;
		XidCacheStatus *subxidStates = ProcGlobal->subxidStates;
		uint8	   *allStatusFlags = ProcGlobal->statusFlags;

		/*
		 * First collect set of pgxactoff/xids that need to be included in the
		 * snapshot.
		 */
		for (int pgxactoff = 0; pgxactoff < numProcs; pgxactoff++)
		{
			/* Fetch xid just once - see GetNewTransactionId */
			TransactionId xid = UINT32_ACCESS_ONCE(other_xids[pgxactoff]);
			uint8		statusFlags;

			Assert(allProcs[arrayP->pgprocnos[pgxactoff]].pgxactoff == pgxactoff);

			/*
			 * If the transaction has no XID assigned, we can skip it; it
			 * won't have sub-XIDs either.
			 */
			if (likely(xid == InvalidTransactionId))
				continue;

			/*
			 * We don't include our own XIDs (if any) in the snapshot. It
			 * needs to be includeded in the xmin computation, but we did so
			 * outside the loop.
			 */
			if (pgxactoff == mypgxactoff)
				continue;

			/*
			 * The only way we are able to get here with a non-normal xid is
			 * during bootstrap - with this backend using
			 * BootstrapTransactionId. But the above test should filter that
			 * out.
			 */
			Assert(TransactionIdIsNormal(xid));

			/*
			 * If the XID is >= xmax, we can skip it; such transactions will
			 * be treated as running anyway (and any sub-XIDs will also be >=
			 * xmax).
			 */
			if (!NormalTransactionIdPrecedes(xid, xmax))
				continue;

			/*
			 * Skip over backends doing logical decoding which manages xmin
			 * separately (check below) and ones running LAZY VACUUM.
			 */
			statusFlags = allStatusFlags[pgxactoff];
			if (statusFlags & (PROC_IN_LOGICAL_DECODING | PROC_IN_VACUUM))
				continue;

			if (NormalTransactionIdPrecedes(xid, xmin))
				xmin = xid;

			/* Add XID to snapshot. */
			xip[count++] = xid;

			/*
			 * Save subtransaction XIDs if possible (if we've already
			 * overflowed, there's no point).  Note that the subxact XIDs must
			 * be later than their parent, so no need to check them against
			 * xmin.  We could filter against xmax, but it seems better not to
			 * do that much work while holding the ProcArrayLock.
			 *
			 * The other backend can add more subxids concurrently, but cannot
			 * remove any.  Hence it's important to fetch nxids just once.
			 * Should be safe to use memcpy, though.  (We needn't worry about
			 * missing any xids added concurrently, because they must postdate
			 * xmax.)
			 *
			 * Again, our own XIDs are not included in the snapshot.
			 */
			if (!suboverflowed)
			{

				if (subxidStates[pgxactoff].overflowed)
					suboverflowed = true;
				else
				{
					int			nsubxids = subxidStates[pgxactoff].count;

					if (nsubxids > 0)
					{
						int			pgprocno = pgprocnos[pgxactoff];
						PGPROC	   *proc = &allProcs[pgprocno];

						pg_read_barrier();	/* pairs with GetNewTransactionId */

						memcpy(snapshot->subxip + subcount,
							   (void *) proc->subxids.xids,
							   nsubxids * sizeof(TransactionId));
						subcount += nsubxids;
					}
				}
			}
		}
	}
	else
	{
		/*
		 * We're in hot standby, so get XIDs from KnownAssignedXids.
		 *
		 * We store all xids directly into subxip[]. Here's why:
		 *
		 * In recovery we don't know which xids are top-level and which are
		 * subxacts, a design choice that greatly simplifies xid processing.
		 *
		 * It seems like we would want to try to put xids into xip[] only, but
		 * that is fairly small. We would either need to make that bigger or
		 * to increase the rate at which we WAL-log xid assignment; neither is
		 * an appealing choice.
		 *
		 * We could try to store xids into xip[] first and then into subxip[]
		 * if there are too many xids. That only works if the snapshot doesn't
		 * overflow because we do not search subxip[] in that case. A simpler
		 * way is to just store all xids in the subxact array because this is
		 * by far the bigger array. We just leave the xip array empty.
		 *
		 * Either way we need to change the way XidInMVCCSnapshot() works
		 * depending upon when the snapshot was taken, or change normal
		 * snapshot processing so it matches.
		 *
		 * Note: It is possible for recovery to end before we finish taking
		 * the snapshot, and for newly assigned transaction ids to be added to
		 * the ProcArray.  xmax cannot change while we hold ProcArrayLock, so
		 * those newly added transaction ids would be filtered away, so we
		 * need not be concerned about them.
		 */
		subcount = KnownAssignedXidsGetAndSetXmin(snapshot->subxip, &xmin,
												  xmax);

		if (TransactionIdPrecedesOrEquals(xmin, procArray->lastOverflowedXid))
			suboverflowed = true;
	}


	/*
	 * Fetch into local variable while ProcArrayLock is held - the
	 * LWLockRelease below is a barrier, ensuring this happens inside the
	 * lock.
	 */
	replication_slot_xmin = procArray->replication_slot_xmin;
	replication_slot_catalog_xmin = procArray->replication_slot_catalog_xmin;

	if (!TransactionIdIsValid(MyProc->xmin))
		MyProc->xmin = TransactionXmin = xmin;

	LWLockRelease(ProcArrayLock);

	/* maintain state for GlobalVis* */
	{
		TransactionId def_vis_xid;
		TransactionId def_vis_xid_data;
		FullTransactionId def_vis_fxid;
		FullTransactionId def_vis_fxid_data;
		FullTransactionId oldestfxid;

		/*
		 * Converting oldestXid is only safe when xid horizon cannot advance,
		 * i.e. holding locks. While we don't hold the lock anymore, all the
		 * necessary data has been gathered with lock held.
		 */
		oldestfxid = FullXidRelativeTo(latest_completed, oldestxid);

		/* apply vacuum_defer_cleanup_age */
		def_vis_xid_data =
			TransactionIdRetreatedBy(xmin, vacuum_defer_cleanup_age);

		/* Check whether there's a replication slot requiring an older xmin. */
		def_vis_xid_data =
			TransactionIdOlder(def_vis_xid_data, replication_slot_xmin);

		/*
		 * Rows in non-shared, non-catalog tables possibly could be vacuumed
		 * if older than this xid.
		 */
		def_vis_xid = def_vis_xid_data;

		/*
		 * Check whether there's a replication slot requiring an older catalog
		 * xmin.
		 */
		def_vis_xid =
			TransactionIdOlder(replication_slot_catalog_xmin, def_vis_xid);

		def_vis_fxid = FullXidRelativeTo(latest_completed, def_vis_xid);
		def_vis_fxid_data = FullXidRelativeTo(latest_completed, def_vis_xid_data);

		/*
		 * Check if we can increase upper bound. As a previous
		 * GlobalVisUpdate() might have computed more aggressive values, don't
		 * overwrite them if so.
		 */
		GlobalVisSharedRels.definitely_needed =
			FullTransactionIdNewer(def_vis_fxid,
								   GlobalVisSharedRels.definitely_needed);
		GlobalVisCatalogRels.definitely_needed =
			FullTransactionIdNewer(def_vis_fxid,
								   GlobalVisCatalogRels.definitely_needed);
		GlobalVisDataRels.definitely_needed =
			FullTransactionIdNewer(def_vis_fxid_data,
								   GlobalVisDataRels.definitely_needed);
		/* See temp_oldest_nonremovable computation in ComputeXidHorizons() */
		if (TransactionIdIsNormal(myxid))
			GlobalVisTempRels.definitely_needed =
				FullXidRelativeTo(latest_completed, myxid);
		else
		{
			GlobalVisTempRels.definitely_needed = latest_completed;
			FullTransactionIdAdvance(&GlobalVisTempRels.definitely_needed);
		}

		/*
		 * Check if we know that we can initialize or increase the lower
		 * bound. Currently the only cheap way to do so is to use
		 * ShmemVariableCache->oldestXid as input.
		 *
		 * We should definitely be able to do better. We could e.g. put a
		 * global lower bound value into ShmemVariableCache.
		 */
		GlobalVisSharedRels.maybe_needed =
			FullTransactionIdNewer(GlobalVisSharedRels.maybe_needed,
								   oldestfxid);
		GlobalVisCatalogRels.maybe_needed =
			FullTransactionIdNewer(GlobalVisCatalogRels.maybe_needed,
								   oldestfxid);
		GlobalVisDataRels.maybe_needed =
			FullTransactionIdNewer(GlobalVisDataRels.maybe_needed,
								   oldestfxid);
		/* accurate value known */
		GlobalVisTempRels.maybe_needed = GlobalVisTempRels.definitely_needed;
	}

	RecentXmin = xmin;
	Assert(TransactionIdPrecedesOrEquals(TransactionXmin, RecentXmin));

	snapshot->xmin = xmin;
	snapshot->xmax = xmax;
	snapshot->xcnt = count;
	snapshot->subxcnt = subcount;
	snapshot->suboverflowed = suboverflowed;
	snapshot->snapXactCompletionCount = curXactCompletionCount;

	snapshot->curcid = GetCurrentCommandId(false);

	/*
	 * This is a new snapshot, so set both refcounts are zero, and mark it as
	 * not copied in persistent memory.
	 */
	snapshot->active_count = 0;
	snapshot->regd_count = 0;
	snapshot->copied = false;

	GetSnapshotDataInitOldSnapshot(snapshot);

	return snapshot;
}