/*
* Build an empty SPGiST index in the initialization fork
*/
Datum
spgbuildempty(PG_FUNCTION_ARGS)
{
Relation index = (Relation) PG_GETARG_POINTER(0);
Page page;
/* Construct metapage. */
page = (Page) palloc(BLCKSZ);
SpGistInitMetapage(page);
/* Write the page. If archiving/streaming, XLOG it. */
smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_METAPAGE_BLKNO,
(char *) page, true);
if (XLogIsNeeded())
log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
SPGIST_METAPAGE_BLKNO, page);
/* Likewise for the root page. */
SpGistInitPage(page, SPGIST_LEAF);
smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_HEAD_BLKNO,
(char *) page, true);
if (XLogIsNeeded())
log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
SPGIST_HEAD_BLKNO, page);
/*
* An immediate sync is required even if we xlog'd the pages, because the
* writes did not go through shared buffers and therefore a concurrent
* checkpoint may have moved the redo pointer past our xlog record.
*/
smgrimmedsync(index->rd_smgr, INIT_FORKNUM);
PG_RETURN_VOID();
}
/*
* given a spool loaded by successive calls to _bt_spool,
* create an entire btree.
*/
void
_bt_leafbuild(BTSpool *btspool, BTSpool *btspool2)
{
BTWriteState wstate;
#ifdef BTREE_BUILD_STATS
if (log_btree_build_stats)
{
ShowUsage("BTREE BUILD (Spool) STATISTICS");
ResetUsage();
}
#endif /* BTREE_BUILD_STATS */
tuplesort_performsort(btspool->sortstate);
if (btspool2)
tuplesort_performsort(btspool2->sortstate);
wstate.heap = btspool->heap;
wstate.index = btspool->index;
/*
* We need to log index creation in WAL iff WAL archiving/streaming is
* enabled UNLESS the index isn't WAL-logged anyway.
*/
wstate.btws_use_wal = XLogIsNeeded() && RelationNeedsWAL(wstate.index);
/* reserve the metapage */
wstate.btws_pages_alloced = BTREE_METAPAGE + 1;
wstate.btws_pages_written = 0;
wstate.btws_zeropage = NULL; /* until needed */
_bt_load(&wstate, btspool, btspool2);
}
/*
* pg_create_restore_point: a named point for restore
*
* Permission checking for this function is managed through the normal
* GRANT system.
*/
Datum
pg_create_restore_point(PG_FUNCTION_ARGS)
{
text *restore_name = PG_GETARG_TEXT_P(0);
char *restore_name_str;
XLogRecPtr restorepoint;
if (RecoveryInProgress())
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
(errmsg("recovery is in progress"),
errhint("WAL control functions cannot be executed during recovery."))));
if (!XLogIsNeeded())
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("WAL level not sufficient for creating a restore point"),
errhint("wal_level must be set to \"replica\" or \"logical\" at server start.")));
restore_name_str = text_to_cstring(restore_name);
if (strlen(restore_name_str) >= MAXFNAMELEN)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("value too long for restore point (maximum %d characters)", MAXFNAMELEN - 1)));
restorepoint = XLogRestorePoint(restore_name_str);
/*
* As a convenience, return the WAL location of the restore point record
*/
PG_RETURN_LSN(restorepoint);
}
/*
* btbuildempty() -- build an empty btree index in the initialization fork
*/
Datum
btbuildempty(PG_FUNCTION_ARGS)
{
Relation index = (Relation) PG_GETARG_POINTER(0);
Page metapage;
/* Construct metapage. */
metapage = (Page) palloc(BLCKSZ);
_bt_initmetapage(metapage, P_NONE, 0);
/* Write the page. If archiving/streaming, XLOG it. */
smgrwrite(index->rd_smgr, INIT_FORKNUM, BTREE_METAPAGE,
(char *) metapage, true);
if (XLogIsNeeded())
log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
BTREE_METAPAGE, metapage);
/*
* An immediate sync is require even if we xlog'd the page, because the
* write did not go through shared_buffers and therefore a concurrent
* checkpoint may have move the redo pointer past our xlog record.
*/
smgrimmedsync(index->rd_smgr, INIT_FORKNUM);
PG_RETURN_VOID();
}
/*
* transientrel_startup --- executor startup
*/
static void
transientrel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
{
DR_transientrel *myState = (DR_transientrel *) self;
Relation transientrel;
transientrel = heap_open(myState->transientoid, NoLock);
/*
* Fill private fields of myState for use by later routines
*/
myState->transientrel = transientrel;
myState->output_cid = GetCurrentCommandId(true);
/*
* We can skip WAL-logging the insertions, unless PITR or streaming
* replication is in use. We can skip the FSM in any case.
*/
myState->hi_options = HEAP_INSERT_SKIP_FSM | HEAP_INSERT_FROZEN;
if (!XLogIsNeeded())
myState->hi_options |= HEAP_INSERT_SKIP_WAL;
myState->bistate = GetBulkInsertState();
/* Not using WAL requires smgr_targblock be initially invalid */
Assert(RelationGetTargetBlock(transientrel) == InvalidBlockNumber);
}
/*
* Build an empty SPGiST index in the initialization fork
*/
void
spgbuildempty(Relation index)
{
Page page;
/* Construct metapage. */
page = (Page) palloc(BLCKSZ);
SpGistInitMetapage(page);
/* Write the page. If archiving/streaming, XLOG it. */
PageSetChecksumInplace(page, SPGIST_METAPAGE_BLKNO);
smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_METAPAGE_BLKNO,
(char *) page, true);
if (XLogIsNeeded())
log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
SPGIST_METAPAGE_BLKNO, page, false);
/* Likewise for the root page. */
SpGistInitPage(page, SPGIST_LEAF);
PageSetChecksumInplace(page, SPGIST_ROOT_BLKNO);
smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_ROOT_BLKNO,
(char *) page, true);
if (XLogIsNeeded())
log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
SPGIST_ROOT_BLKNO, page, true);
/* Likewise for the null-tuples root page. */
SpGistInitPage(page, SPGIST_LEAF | SPGIST_NULLS);
PageSetChecksumInplace(page, SPGIST_NULL_BLKNO);
smgrwrite(index->rd_smgr, INIT_FORKNUM, SPGIST_NULL_BLKNO,
(char *) page, true);
if (XLogIsNeeded())
log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
SPGIST_NULL_BLKNO, page, true);
/*
* An immediate sync is required even if we xlog'd the pages, because the
* writes did not go through shared buffers and therefore a concurrent
* checkpoint may have moved the redo pointer past our xlog record.
*/
smgrimmedsync(index->rd_smgr, INIT_FORKNUM);
}
/*
* For Hot Standby we need to know the highest transaction id that will
* be removed by any change. VACUUM proceeds in a number of passes so
* we need to consider how each pass operates. The first phase runs
* heap_page_prune(), which can issue XLOG_HEAP2_CLEAN records as it
* progresses - these will have a latestRemovedXid on each record.
* In some cases this removes all of the tuples to be removed, though
* often we have dead tuples with index pointers so we must remember them
* for removal in phase 3. Index records for those rows are removed
* in phase 2 and index blocks do not have MVCC information attached.
* So before we can allow removal of any index tuples we need to issue
* a WAL record containing the latestRemovedXid of rows that will be
* removed in phase three. This allows recovery queries to block at the
* correct place, i.e. before phase two, rather than during phase three
* which would be after the rows have become inaccessible.
*/
static void
vacuum_log_cleanup_info(Relation rel, LVRelStats *vacrelstats)
{
/*
* Skip this for relations for which no WAL is to be written, or if we're
* not trying to support archive recovery.
*/
if (!RelationNeedsWAL(rel) || !XLogIsNeeded())
return;
/*
* No need to write the record at all unless it contains a valid value
*/
if (TransactionIdIsValid(vacrelstats->latestRemovedXid))
(void) log_heap_cleanup_info(rel->rd_node, vacrelstats->latestRemovedXid);
}
/*
* For Hot Standby we need to know the highest transaction id that will
* be removed by any change. VACUUM proceeds in a number of passes so
* we need to consider how each pass operates. The first phase runs
* heap_page_prune(), which can issue XLOG_HEAP2_CLEAN records as it
* progresses - these will have a latestRemovedXid on each record.
* In some cases this removes all of the tuples to be removed, though
* often we have dead tuples with index pointers so we must remember them
* for removal in phase 3. Index records for those rows are removed
* in phase 2 and index blocks do not have MVCC information attached.
* So before we can allow removal of any index tuples we need to issue
* a WAL record containing the latestRemovedXid of rows that will be
* removed in phase three. This allows recovery queries to block at the
* correct place, i.e. before phase two, rather than during phase three
* which would be after the rows have become inaccessible.
*/
static void
vacuum_log_cleanup_info(Relation rel, LVRelStats *vacrelstats)
{
/*
* No need to log changes for temp tables, they do not contain data
* visible on the standby server.
*/
if (rel->rd_istemp || !XLogIsNeeded())
return;
/*
* No need to write the record at all unless it contains a valid value
*/
if (TransactionIdIsValid(vacrelstats->latestRemovedXid))
(void) log_heap_cleanup_info(rel->rd_node, vacrelstats->latestRemovedXid);
}
/*
* given a spool loaded by successive calls to _bt_spool,
* create an entire btree.
*/
void
_bt_leafbuild(BTSpool *btspool, BTSpool *btspool2)
{
BTWriteState wstate;
#ifdef BTREE_BUILD_STATS
if (log_btree_build_stats)
{
ShowUsage("BTREE BUILD (Spool) STATISTICS");
ResetUsage();
}
#endif /* BTREE_BUILD_STATS */
tuplesort_performsort(btspool->sortstate);
if (btspool2)
tuplesort_performsort(btspool2->sortstate);
wstate.index = btspool->index;
/*
* We need to log index creation in WAL iff WAL archiving/streaming is
* enabled AND it's not a temp index.
*/
wstate.btws_use_wal = XLogIsNeeded() && !wstate.index->rd_istemp;
/*
* Write an XLOG UNLOGGED record if WAL-logging was skipped because WAL
* archiving is not enabled.
*/
if (!wstate.btws_use_wal && !wstate.index->rd_istemp)
{
char reason[NAMEDATALEN + 20];
snprintf(reason, sizeof(reason), "b-tree build on \"%s\"",
RelationGetRelationName(wstate.index));
XLogReportUnloggedStatement(reason);
}
/* reserve the metapage */
wstate.btws_pages_alloced = BTREE_METAPAGE + 1;
wstate.btws_pages_written = 0;
wstate.btws_zeropage = NULL; /* until needed */
_bt_load(&wstate, btspool, btspool2);
}
/*
* pg_create_restore_point: a named point for restore
*/
Datum
pg_create_restore_point(PG_FUNCTION_ARGS)
{
text *restore_name = PG_GETARG_TEXT_P(0);
char *restore_name_str;
XLogRecPtr restorepoint;
char location[MAXFNAMELEN];
if (!superuser())
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
(errmsg("must be superuser to create a restore point"))));
if (RecoveryInProgress())
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
(errmsg("recovery is in progress"),
errhint("WAL control functions cannot be executed during recovery."))));
if (!XLogIsNeeded())
ereport(ERROR,
(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
errmsg("WAL level not sufficient for creating a restore point"),
errhint("wal_level must be set to \"archive\" or \"hot_standby\" at server start.")));
restore_name_str = text_to_cstring(restore_name);
if (strlen(restore_name_str) >= MAXFNAMELEN)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("value too long for restore point (maximum %d characters)", MAXFNAMELEN - 1)));
restorepoint = XLogRestorePoint(restore_name_str);
/*
* As a convenience, return the WAL location of the restore point record
*/
snprintf(location, sizeof(location), "%X/%X",
restorepoint.xlogid, restorepoint.xrecoff);
PG_RETURN_TEXT_P(cstring_to_text(location));
}
/*
* btbuildempty() -- build an empty btree index in the initialization fork
*/
void
btbuildempty(Relation index)
{
Page metapage;
/* Construct metapage. */
metapage = (Page) palloc(BLCKSZ);
_bt_initmetapage(metapage, P_NONE, 0);
/* Write the page. If archiving/streaming, XLOG it. */
PageSetChecksumInplace(metapage, BTREE_METAPAGE);
smgrwrite(index->rd_smgr, INIT_FORKNUM, BTREE_METAPAGE,
(char *) metapage, true);
if (XLogIsNeeded())
log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
BTREE_METAPAGE, metapage, false);
/*
* An immediate sync is required even if we xlog'd the page, because the
* write did not go through shared_buffers and therefore a concurrent
* checkpoint may have moved the redo pointer past our xlog record.
*/
smgrimmedsync(index->rd_smgr, INIT_FORKNUM);
}
/*
* intorel_startup --- executor startup
*/
static void
intorel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
{
DR_intorel *myState = (DR_intorel *) self;
IntoClause *into = myState->into;
bool is_matview;
char relkind;
CreateStmt *create;
Oid intoRelationId;
Relation intoRelationDesc;
RangeTblEntry *rte;
Datum toast_options;
ListCell *lc;
int attnum;
static char *validnsps[] = HEAP_RELOPT_NAMESPACES;
Assert(into != NULL); /* else somebody forgot to set it */
/* This code supports both CREATE TABLE AS and CREATE MATERIALIZED VIEW */
is_matview = (into->viewQuery != NULL);
relkind = is_matview ? RELKIND_MATVIEW : RELKIND_RELATION;
/*
* Create the target relation by faking up a CREATE TABLE parsetree and
* passing it to DefineRelation.
*/
create = makeNode(CreateStmt);
create->relation = into->rel;
create->tableElts = NIL; /* will fill below */
create->inhRelations = NIL;
create->ofTypename = NULL;
create->constraints = NIL;
create->options = into->options;
create->oncommit = into->onCommit;
create->tablespacename = into->tableSpaceName;
create->if_not_exists = false;
/*
* Build column definitions using "pre-cooked" type and collation info. If
* a column name list was specified in CREATE TABLE AS, override the
* column names derived from the query. (Too few column names are OK, too
* many are not.)
*/
lc = list_head(into->colNames);
for (attnum = 0; attnum < typeinfo->natts; attnum++)
{
Form_pg_attribute attribute = typeinfo->attrs[attnum];
ColumnDef *col = makeNode(ColumnDef);
TypeName *coltype = makeNode(TypeName);
if (lc)
{
col->colname = strVal(lfirst(lc));
lc = lnext(lc);
}
else
col->colname = NameStr(attribute->attname);
col->typeName = coltype;
col->inhcount = 0;
col->is_local = true;
col->is_not_null = false;
col->is_from_type = false;
col->storage = 0;
col->raw_default = NULL;
col->cooked_default = NULL;
col->collClause = NULL;
col->collOid = attribute->attcollation;
col->constraints = NIL;
col->fdwoptions = NIL;
coltype->names = NIL;
coltype->typeOid = attribute->atttypid;
coltype->setof = false;
coltype->pct_type = false;
coltype->typmods = NIL;
coltype->typemod = attribute->atttypmod;
coltype->arrayBounds = NIL;
coltype->location = -1;
/*
* It's possible that the column is of a collatable type but the
* collation could not be resolved, so double-check. (We must check
* this here because DefineRelation would adopt the type's default
* collation rather than complaining.)
*/
if (!OidIsValid(col->collOid) &&
type_is_collatable(coltype->typeOid))
ereport(ERROR,
(errcode(ERRCODE_INDETERMINATE_COLLATION),
errmsg("no collation was derived for column \"%s\" with collatable type %s",
col->colname, format_type_be(coltype->typeOid)),
errhint("Use the COLLATE clause to set the collation explicitly.")));
create->tableElts = lappend(create->tableElts, col);
}
if (lc != NULL)
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("too many column names were specified")));
/*
* Actually create the target table
*/
intoRelationId = DefineRelation(create, relkind, InvalidOid);
/*
* If necessary, create a TOAST table for the target table. Note that
* AlterTableCreateToastTable ends with CommandCounterIncrement(), so that
* the TOAST table will be visible for insertion.
*/
CommandCounterIncrement();
/* parse and validate reloptions for the toast table */
toast_options = transformRelOptions((Datum) 0,
create->options,
"toast",
validnsps,
true, false);
(void) heap_reloptions(RELKIND_TOASTVALUE, toast_options, true);
AlterTableCreateToastTable(intoRelationId, toast_options);
/* Create the "view" part of a materialized view. */
if (is_matview)
{
/* StoreViewQuery scribbles on tree, so make a copy */
Query *query = (Query *) copyObject(into->viewQuery);
StoreViewQuery(intoRelationId, query, false);
CommandCounterIncrement();
}
/*
* Finally we can open the target table
*/
intoRelationDesc = heap_open(intoRelationId, AccessExclusiveLock);
/*
* Check INSERT permission on the constructed table.
*
* XXX: It would arguably make sense to skip this check if into->skipData
* is true.
*/
rte = makeNode(RangeTblEntry);
rte->rtekind = RTE_RELATION;
rte->relid = intoRelationId;
rte->relkind = relkind;
rte->requiredPerms = ACL_INSERT;
for (attnum = 1; attnum <= intoRelationDesc->rd_att->natts; attnum++)
rte->modifiedCols = bms_add_member(rte->modifiedCols,
attnum - FirstLowInvalidHeapAttributeNumber);
ExecCheckRTPerms(list_make1(rte), true);
/*
* Tentatively mark the target as populated, if it's a matview and we're
* going to fill it; otherwise, no change needed.
*/
if (is_matview && !into->skipData)
SetMatViewPopulatedState(intoRelationDesc, true);
/*
* Fill private fields of myState for use by later routines
*/
myState->rel = intoRelationDesc;
myState->output_cid = GetCurrentCommandId(true);
/*
* We can skip WAL-logging the insertions, unless PITR or streaming
* replication is in use. We can skip the FSM in any case.
*/
myState->hi_options = HEAP_INSERT_SKIP_FSM |
(XLogIsNeeded() ? 0 : HEAP_INSERT_SKIP_WAL);
myState->bistate = GetBulkInsertState();
/* Not using WAL requires smgr_targblock be initially invalid */
Assert(RelationGetTargetBlock(intoRelationDesc) == InvalidBlockNumber);
}
static void
_bt_mergebuild(Spooler *self, BTSpool *btspool)
{
Relation heapRel = self->relinfo->ri_RelationDesc;
BTWriteState wstate;
BTReader reader;
bool merge;
Assert(btspool->index->rd_index->indisvalid);
tuplesort_performsort(btspool->sortstate);
wstate.index = btspool->index;
/*
* We need to log index creation in WAL iff WAL archiving is enabled AND
* it's not a temp index.
*/
#if PG_VERSION_NUM >= 90000
wstate.btws_use_wal = self->use_wal &&
XLogIsNeeded() && !RELATION_IS_LOCAL(wstate.index);
#else
wstate.btws_use_wal = self->use_wal &&
XLogArchivingActive() && !RELATION_IS_LOCAL(wstate.index);
#endif
/* reserve the metapage */
wstate.btws_pages_alloced = BTREE_METAPAGE + 1;
wstate.btws_pages_written = 0;
wstate.btws_zeropage = NULL; /* until needed */
/*
* Flush dirty buffers so that we will read the index files directly
* in order to get pre-existing data. We must acquire AccessExclusiveLock
* for the target table for calling FlushRelationBuffer().
*/
LockRelation(wstate.index, AccessExclusiveLock);
FlushRelationBuffers(wstate.index);
BULKLOAD_PROFILE(&prof_flush);
merge = BTReaderInit(&reader, wstate.index);
elog(DEBUG1, "pg_bulkload: build \"%s\" %s merge (%s wal)",
RelationGetRelationName(wstate.index),
merge ? "with" : "without",
wstate.btws_use_wal ? "with" : "without");
/* Assign a new file node. */
RelationSetNewRelfilenode(wstate.index, InvalidTransactionId);
if (merge || (btspool->isunique && self->max_dup_errors > 0))
{
/* Merge two streams into the new file node that we assigned. */
BULKLOAD_PROFILE_PUSH();
_bt_mergeload(self, &wstate, btspool, &reader, heapRel);
BULKLOAD_PROFILE_POP();
BULKLOAD_PROFILE(&prof_merge);
}
else
{
/* Fast path for newly created index. */
_bt_load(&wstate, btspool, NULL);
BULKLOAD_PROFILE(&prof_index);
}
BTReaderTerm(&reader);
}