1 files changed, 462 insertions, 0 deletions
diff --git a/src/backend/catalog/storage.c b/src/backend/catalog/storage.c
new file mode 100644
index 00000000000..c8187d511c9
--- /dev/null
+++ b/src/backend/catalog/storage.c
@@ -0,0 +1,462 @@
+/*-------------------------------------------------------------------------
+ *
+ * storage.c
+ *	  code to create and destroy physical storage for relations
+ *
+ * Portions Copyright (c) 1996-2008, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ *
+ * IDENTIFICATION
+ *	  $PostgreSQL: pgsql/src/backend/catalog/storage.c,v 1.1 2008/11/19 10:34:51 heikki Exp $
+ *
+ * NOTES
+ *	  Some of this code used to be in storage/smgr/smgr.c, and the
+ *	  function names still reflect that.
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+
+#include "access/xact.h"
+#include "access/xlogutils.h"
+#include "catalog/catalog.h"
+#include "catalog/storage.h"
+#include "storage/freespace.h"
+#include "storage/smgr.h"
+#include "utils/memutils.h"
+#include "utils/rel.h"
+
+/*
+ * We keep a list of all relations (represented as RelFileNode values)
+ * that have been created or deleted in the current transaction.  When
+ * a relation is created, we create the physical file immediately, but
+ * remember it so that we can delete the file again if the current
+ * transaction is aborted.	Conversely, a deletion request is NOT
+ * executed immediately, but is just entered in the list.  When and if
+ * the transaction commits, we can delete the physical file.
+ *
+ * To handle subtransactions, every entry is marked with its transaction
+ * nesting level.  At subtransaction commit, we reassign the subtransaction's
+ * entries to the parent nesting level.  At subtransaction abort, we can
+ * immediately execute the abort-time actions for all entries of the current
+ * nesting level.
+ *
+ * NOTE: the list is kept in TopMemoryContext to be sure it won't disappear
+ * unbetimes.  It'd probably be OK to keep it in TopTransactionContext,
+ * but I'm being paranoid.
+ */
+
+typedef struct PendingRelDelete
+{
+	RelFileNode relnode;		/* relation that may need to be deleted */
+	bool		isTemp;			/* is it a temporary relation? */
+	bool		atCommit;		/* T=delete at commit; F=delete at abort */
+	int			nestLevel;		/* xact nesting level of request */
+	struct PendingRelDelete *next;		/* linked-list link */
+} PendingRelDelete;
+
+static PendingRelDelete *pendingDeletes = NULL; /* head of linked list */
+
+/*
+ * Declarations for smgr-related XLOG records
+ *
+ * Note: we log file creation and truncation here, but logging of deletion
+ * actions is handled by xact.c, because it is part of transaction commit.
+ */
+
+/* XLOG gives us high 4 bits */
+#define XLOG_SMGR_CREATE	0x10
+#define XLOG_SMGR_TRUNCATE	0x20
+
+typedef struct xl_smgr_create
+{
+	RelFileNode rnode;
+} xl_smgr_create;
+
+typedef struct xl_smgr_truncate
+{
+	BlockNumber blkno;
+	RelFileNode rnode;
+} xl_smgr_truncate;
+
+
+/*
+ * RelationCreateStorage
+ *		Create physical storage for a relation.
+ *
+ * Create the underlying disk file storage for the relation. This only
+ * creates the main fork; additional forks are created lazily by the
+ * modules that need them.
+ *
+ * This function is transactional. The creation is WAL-logged, and if the
+ * transaction aborts later on, the storage will be destroyed.
+ */
+void
+RelationCreateStorage(RelFileNode rnode, bool istemp)
+{
+	PendingRelDelete *pending;
+	XLogRecPtr	lsn;
+	XLogRecData rdata;
+	xl_smgr_create xlrec;
+	SMgrRelation srel;
+
+	srel = smgropen(rnode);
+	smgrcreate(srel, MAIN_FORKNUM, false);
+
+	if (istemp)
+	{
+		/*
+		 * Make an XLOG entry showing the file creation.  If we abort, the file
+		 * will be dropped at abort time.
+		 */
+		xlrec.rnode = rnode;
+
+		rdata.data = (char *) &xlrec;
+		rdata.len = sizeof(xlrec);
+		rdata.buffer = InvalidBuffer;
+		rdata.next = NULL;
+
+		lsn = XLogInsert(RM_SMGR_ID, XLOG_SMGR_CREATE, &rdata);
+	}
+
+	/* Add the relation to the list of stuff to delete at abort */
+	pending = (PendingRelDelete *)
+		MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+	pending->relnode = rnode;
+	pending->isTemp = istemp;
+	pending->atCommit = false;	/* delete if abort */
+	pending->nestLevel = GetCurrentTransactionNestLevel();
+	pending->next = pendingDeletes;
+	pendingDeletes = pending;
+}
+
+/*
+ * RelationDropStorage
+ *		Schedule unlinking of physical storage at transaction commit.
+ */
+void
+RelationDropStorage(Relation rel)
+{
+	PendingRelDelete *pending;
+
+	/* Add the relation to the list of stuff to delete at commit */
+	pending = (PendingRelDelete *)
+		MemoryContextAlloc(TopMemoryContext, sizeof(PendingRelDelete));
+	pending->relnode = rel->rd_node;
+	pending->isTemp = rel->rd_istemp;
+	pending->atCommit = true;	/* delete if commit */
+	pending->nestLevel = GetCurrentTransactionNestLevel();
+	pending->next = pendingDeletes;
+	pendingDeletes = pending;
+
+	/*
+	 * NOTE: if the relation was created in this transaction, it will now be
+	 * present in the pending-delete list twice, once with atCommit true and
+	 * once with atCommit false.  Hence, it will be physically deleted at end
+	 * of xact in either case (and the other entry will be ignored by
+	 * smgrDoPendingDeletes, so no error will occur).  We could instead remove
+	 * the existing list entry and delete the physical file immediately, but
+	 * for now I'll keep the logic simple.
+	 */
+
+	RelationCloseSmgr(rel);
+}
+
+/*
+ * RelationTruncate
+ *		Physically truncate a relation to the specified number of blocks.
+ *
+ * This includes getting rid of any buffers for the blocks that are to be
+ * dropped. If 'fsm' is true, the FSM of the relation is truncated as well.
+ */
+void
+RelationTruncate(Relation rel, BlockNumber nblocks)
+{
+	bool fsm;
+
+	/* Open it at the smgr level if not already done */
+	RelationOpenSmgr(rel);
+
+	/* Make sure rd_targblock isn't pointing somewhere past end */
+	rel->rd_targblock = InvalidBlockNumber;
+
+	/* Truncate the FSM first if it exists */
+	fsm = smgrexists(rel->rd_smgr, FSM_FORKNUM);
+	if (fsm)
+		FreeSpaceMapTruncateRel(rel, nblocks);
+
+	/*
+	 * We WAL-log the truncation before actually truncating, which
+	 * means trouble if the truncation fails. If we then crash, the WAL
+	 * replay likely isn't going to succeed in the truncation either, and
+	 * cause a PANIC. It's tempting to put a critical section here, but
+	 * that cure would be worse than the disease. It would turn a usually
+	 * harmless failure to truncate, that could spell trouble at WAL replay,
+	 * into a certain PANIC.
+	 */
+	if (rel->rd_istemp)
+	{
+		/*
+		 * Make an XLOG entry showing the file truncation.
+		 */
+		XLogRecPtr	lsn;
+		XLogRecData rdata;
+		xl_smgr_truncate xlrec;
+
+		xlrec.blkno = nblocks;
+		xlrec.rnode = rel->rd_node;
+
+		rdata.data = (char *) &xlrec;
+		rdata.len = sizeof(xlrec);
+		rdata.buffer = InvalidBuffer;
+		rdata.next = NULL;
+
+		lsn = XLogInsert(RM_SMGR_ID, XLOG_SMGR_TRUNCATE, &rdata);
+
+		/*
+		 * Flush, because otherwise the truncation of the main relation
+		 * might hit the disk before the WAL record of truncating the
+		 * FSM is flushed. If we crashed during that window, we'd be
+		 * left with a truncated heap, but the FSM would still contain
+		 * entries for the non-existent heap pages.
+		 */
+		if (fsm)
+			XLogFlush(lsn);
+	}
+
+	/* Do the real work */
+	smgrtruncate(rel->rd_smgr, MAIN_FORKNUM, nblocks, rel->rd_istemp);
+}
+
+/*
+ *	smgrDoPendingDeletes() -- Take care of relation deletes at end of xact.
+ *
+ * This also runs when aborting a subxact; we want to clean up a failed
+ * subxact immediately.
+ */
+void
+smgrDoPendingDeletes(bool isCommit)
+{
+	int			nestLevel = GetCurrentTransactionNestLevel();
+	PendingRelDelete *pending;
+	PendingRelDelete *prev;
+	PendingRelDelete *next;
+
+	prev = NULL;
+	for (pending = pendingDeletes; pending != NULL; pending = next)
+	{
+		next = pending->next;
+		if (pending->nestLevel < nestLevel)
+		{
+			/* outer-level entries should not be processed yet */
+			prev = pending;
+		}
+		else
+		{
+			/* unlink list entry first, so we don't retry on failure */
+			if (prev)
+				prev->next = next;
+			else
+				pendingDeletes = next;
+			/* do deletion if called for */
+			if (pending->atCommit == isCommit)
+			{
+				int i;
+
+				/* schedule unlinking old files */
+				SMgrRelation srel;
+
+				srel = smgropen(pending->relnode);
+				for (i = 0; i <= MAX_FORKNUM; i++)
+				{
+					if (smgrexists(srel, i))
+						smgrdounlink(srel,
+									 i,
+									 pending->isTemp,
+									 false);
+				}
+				smgrclose(srel);
+			}
+			/* must explicitly free the list entry */
+			pfree(pending);
+			/* prev does not change */
+		}
+	}
+}
+
+/*
+ * smgrGetPendingDeletes() -- Get a list of relations to be deleted.
+ *
+ * The return value is the number of relations scheduled for termination.
+ * *ptr is set to point to a freshly-palloc'd array of RelFileNodes.
+ * If there are no relations to be deleted, *ptr is set to NULL.
+ *
+ * If haveNonTemp isn't NULL, the bool it points to gets set to true if
+ * there is any non-temp table pending to be deleted; false if not.
+ *
+ * Note that the list does not include anything scheduled for termination
+ * by upper-level transactions.
+ */
+int
+smgrGetPendingDeletes(bool forCommit, RelFileNode **ptr, bool *haveNonTemp)
+{
+	int			nestLevel = GetCurrentTransactionNestLevel();
+	int			nrels;
+	RelFileNode *rptr;
+	PendingRelDelete *pending;
+
+	nrels = 0;
+	if (haveNonTemp)
+		*haveNonTemp = false;
+	for (pending = pendingDeletes; pending != NULL; pending = pending->next)
+	{
+		if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit)
+			nrels++;
+	}
+	if (nrels == 0)
+	{
+		*ptr = NULL;
+		return 0;
+	}
+	rptr = (RelFileNode *) palloc(nrels * sizeof(RelFileNode));
+	*ptr = rptr;
+	for (pending = pendingDeletes; pending != NULL; pending = pending->next)
+	{
+		if (pending->nestLevel >= nestLevel && pending->atCommit == forCommit)
+		{
+			*rptr = pending->relnode;
+			rptr++;
+		}
+		if (haveNonTemp && !pending->isTemp)
+			*haveNonTemp = true;
+	}
+	return nrels;
+}
+
+/*
+ *	PostPrepare_smgr -- Clean up after a successful PREPARE
+ *
+ * What we have to do here is throw away the in-memory state about pending
+ * relation deletes.  It's all been recorded in the 2PC state file and
+ * it's no longer smgr's job to worry about it.
+ */
+void
+PostPrepare_smgr(void)
+{
+	PendingRelDelete *pending;
+	PendingRelDelete *next;
+
+	for (pending = pendingDeletes; pending != NULL; pending = next)
+	{
+		next = pending->next;
+		pendingDeletes = next;
+		/* must explicitly free the list entry */
+		pfree(pending);
+	}
+}
+
+
+/*
+ * AtSubCommit_smgr() --- Take care of subtransaction commit.
+ *
+ * Reassign all items in the pending-deletes list to the parent transaction.
+ */
+void
+AtSubCommit_smgr(void)
+{
+	int			nestLevel = GetCurrentTransactionNestLevel();
+	PendingRelDelete *pending;
+
+	for (pending = pendingDeletes; pending != NULL; pending = pending->next)
+	{
+		if (pending->nestLevel >= nestLevel)
+			pending->nestLevel = nestLevel - 1;
+	}
+}
+
+/*
+ * AtSubAbort_smgr() --- Take care of subtransaction abort.
+ *
+ * Delete created relations and forget about deleted relations.
+ * We can execute these operations immediately because we know this
+ * subtransaction will not commit.
+ */
+void
+AtSubAbort_smgr(void)
+{
+	smgrDoPendingDeletes(false);
+}
+
+void
+smgr_redo(XLogRecPtr lsn, XLogRecord *record)
+{
+	uint8		info = record->xl_info & ~XLR_INFO_MASK;
+
+	if (info == XLOG_SMGR_CREATE)
+	{
+		xl_smgr_create *xlrec = (xl_smgr_create *) XLogRecGetData(record);
+		SMgrRelation reln;
+
+		reln = smgropen(xlrec->rnode);
+		smgrcreate(reln, MAIN_FORKNUM, true);
+	}
+	else if (info == XLOG_SMGR_TRUNCATE)
+	{
+		xl_smgr_truncate *xlrec = (xl_smgr_truncate *) XLogRecGetData(record);
+		SMgrRelation reln;
+
+		reln = smgropen(xlrec->rnode);
+
+		/*
+		 * Forcibly create relation if it doesn't exist (which suggests that
+		 * it was dropped somewhere later in the WAL sequence).  As in
+		 * XLogOpenRelation, we prefer to recreate the rel and replay the log
+		 * as best we can until the drop is seen.
+		 */
+		smgrcreate(reln, MAIN_FORKNUM, true);
+
+		smgrtruncate(reln, MAIN_FORKNUM, xlrec->blkno, false);
+
+		/* Also tell xlogutils.c about it */
+		XLogTruncateRelation(xlrec->rnode, MAIN_FORKNUM, xlrec->blkno);
+ 
+		/* Truncate FSM too */
+		if (smgrexists(reln, FSM_FORKNUM))
+		{
+			Relation rel = CreateFakeRelcacheEntry(xlrec->rnode);
+			FreeSpaceMapTruncateRel(rel, xlrec->blkno);
+			FreeFakeRelcacheEntry(rel);
+		}
+
+	}
+	else
+		elog(PANIC, "smgr_redo: unknown op code %u", info);
+}
+
+void
+smgr_desc(StringInfo buf, uint8 xl_info, char *rec)
+{
+	uint8		info = xl_info & ~XLR_INFO_MASK;
+
+	if (info == XLOG_SMGR_CREATE)
+	{
+		xl_smgr_create *xlrec = (xl_smgr_create *) rec;
+		char *path = relpath(xlrec->rnode, MAIN_FORKNUM);
+
+		appendStringInfo(buf, "file create: %s", path);
+		pfree(path);
+	}
+	else if (info == XLOG_SMGR_TRUNCATE)
+	{
+		xl_smgr_truncate *xlrec = (xl_smgr_truncate *) rec;
+		char *path = relpath(xlrec->rnode, MAIN_FORKNUM);
+
+		appendStringInfo(buf, "file truncate: %s to %u blocks", path,
+						 xlrec->blkno);
+		pfree(path);
+	}
+	else
+		appendStringInfo(buf, "UNKNOWN");
+}