/*
* get_relation_info -
* Retrieves catalog information for a given relation.
*
* Given the Oid of the relation, return the following info into fields
* of the RelOptInfo struct:
*
* min_attr lowest valid AttrNumber
* max_attr highest valid AttrNumber
* indexlist list of IndexOptInfos for relation's indexes
* pages number of pages
* tuples number of tuples
*
* Also, initialize the attr_needed[] and attr_widths[] arrays. In most
* cases these are left as zeroes, but sometimes we need to compute attr
* widths here, and we may as well cache the results for costsize.c.
*
* If inhparent is true, all we need to do is set up the attr arrays:
* the RelOptInfo actually represents the appendrel formed by an inheritance
* tree, and so the parent rel's physical size and index information isn't
* important for it.
*/
void
get_relation_info(PlannerInfo *root, Oid relationObjectId, bool inhparent,
RelOptInfo *rel)
{
Index varno = rel->relid;
Relation relation;
bool hasindex;
List *indexinfos = NIL;
bool needs_longlock;
/*
* We need not lock the relation since it was already locked, either by
* the rewriter or when expand_inherited_rtentry() added it to the query's
* rangetable.
*/
relation = heap_open(relationObjectId, NoLock);
needs_longlock = rel_needs_long_lock(relationObjectId);
rel->min_attr = FirstLowInvalidHeapAttributeNumber + 1;
rel->max_attr = RelationGetNumberOfAttributes(relation);
Assert(rel->max_attr >= rel->min_attr);
rel->attr_needed = (Relids *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(Relids));
rel->attr_widths = (int32 *)
palloc0((rel->max_attr - rel->min_attr + 1) * sizeof(int32));
/*
* CDB: Get partitioning key info for distributed relation.
*/
rel->cdbpolicy = RelationGetPartitioningKey(relation);
/*
* Estimate relation size --- unless it's an inheritance parent, in which
* case the size will be computed later in set_append_rel_pathlist, and we
* must leave it zero for now to avoid bollixing the total_table_pages
* calculation.
*/
if (!inhparent)
{
cdb_estimate_rel_size
(
rel,
relation,
relation,
rel->attr_widths - rel->min_attr,
&rel->pages,
&rel->tuples,
&rel->cdb_default_stats_used
);
}
/*
* Make list of indexes. Ignore indexes on system catalogs if told to.
* Don't bother with indexes for an inheritance parent, either.
*/
if (inhparent ||
(IgnoreSystemIndexes && IsSystemClass(relation->rd_rel)))
hasindex = false;
else
hasindex = relation->rd_rel->relhasindex;
if (hasindex)
{
List *indexoidlist;
ListCell *l;
LOCKMODE lmode;
/* Warn if indexed table needs ANALYZE. */
if (rel->cdb_default_stats_used)
cdb_default_stats_warning_for_table(relation->rd_id);
indexoidlist = RelationGetIndexList(relation);
/*
* For each index, we get the same type of lock that the executor will
* need, and do not release it. This saves a couple of trips to the
* shared lock manager while not creating any real loss of
* concurrency, because no schema changes could be happening on the
* index while we hold lock on the parent rel, and neither lock type
* blocks any other kind of index operation.
*/
if (rel->relid == root->parse->resultRelation)
lmode = RowExclusiveLock;
else
lmode = AccessShareLock;
foreach(l, indexoidlist)
{
Oid indexoid = lfirst_oid(l);
Relation indexRelation;
Form_pg_index index;
IndexOptInfo *info;
int ncolumns;
int i;
int16 amorderstrategy;
/*
* Extract info from the relation descriptor for the index.
*/
indexRelation = index_open(indexoid, lmode);
index = indexRelation->rd_index;
/*
* Ignore invalid indexes, since they can't safely be used for
* queries. Note that this is OK because the data structure we
* are constructing is only used by the planner --- the executor
* still needs to insert into "invalid" indexes!
*/
if (!index->indisvalid)
{
index_close(indexRelation, NoLock);
continue;
}
info = makeNode(IndexOptInfo);
info->indexoid = index->indexrelid;
info->rel = rel;
info->ncolumns = ncolumns = index->indnatts;
/*
* Need to make opfamily and ordering arrays large enough to put
* a terminating 0 at the end of each one.
*/
info->indexkeys = (int *) palloc(sizeof(int) * ncolumns);
info->opfamily = (Oid *) palloc0(sizeof(Oid) * (ncolumns + 1));
info->ordering = (Oid *) palloc0(sizeof(Oid) * (ncolumns + 1));
for (i = 0; i < ncolumns; i++)
{
info->opfamily[i] = indexRelation->rd_opfamily[i];
info->indexkeys[i] = index->indkey.values[i];
}
info->relam = indexRelation->rd_rel->relam;
info->amcostestimate = indexRelation->rd_am->amcostestimate;
info->amoptionalkey = indexRelation->rd_am->amoptionalkey;
/*
* Fetch the ordering operators associated with the index, if any.
*/
amorderstrategy = indexRelation->rd_am->amorderstrategy;
if (amorderstrategy > 0)
{
int oprindex = amorderstrategy - 1;
/*
* Index AM must have a fixed set of strategies for it to
* make sense to specify amorderstrategy, so we need not
* allow the case amstrategies == 0.
*/
Assert(oprindex < indexRelation->rd_am->amstrategies);
for (i = 0; i < ncolumns; i++)
{
info->ordering[i] = indexRelation->rd_operator[oprindex];
oprindex += indexRelation->rd_am->amstrategies;
}
}
/*
* Fetch the index expressions and predicate, if any. We must
* modify the copies we obtain from the relcache to have the
* correct varno for the parent relation, so that they match up
* correctly against qual clauses.
*/
info->indexprs = RelationGetIndexExpressions(indexRelation);
info->indpred = RelationGetIndexPredicate(indexRelation);
if (info->indexprs && varno != 1)
ChangeVarNodes((Node *) info->indexprs, 1, varno, 0);
if (info->indpred && varno != 1)
ChangeVarNodes((Node *) info->indpred, 1, varno, 0);
info->predOK = false; /* set later in indxpath.c */
info->unique = index->indisunique;
/*
* Estimate the index size. If it's not a partial index, we lock
* the number-of-tuples estimate to equal the parent table; if it
* is partial then we have to use the same methods as we would for
* a table, except we can be sure that the index is not larger
* than the table.
*/
cdb_estimate_rel_size(rel,
relation,
indexRelation,
NULL,
&info->pages,
&info->tuples,
&info->cdb_default_stats_used);
if (!info->indpred ||
info->tuples > rel->tuples)
info->tuples = rel->tuples;
if (info->cdb_default_stats_used &&
!rel->cdb_default_stats_used)
cdb_default_stats_warning_for_index(relation->rd_id, indexoid);
index_close(indexRelation, needs_longlock ? NoLock : lmode);
indexinfos = lcons(info, indexinfos);
}
list_free(indexoidlist);
}
/*
* Primary entry point for VACUUM and ANALYZE commands.
*
* options is a bitmask of VacuumOption flags, indicating what to do.
*
* relid, if not InvalidOid, indicate the relation to process; otherwise,
* the RangeVar is used. (The latter must always be passed, because it's
* used for error messages.)
*
* params contains a set of parameters that can be used to customize the
* behavior.
*
* va_cols is a list of columns to analyze, or NIL to process them all.
*
* bstrategy is normally given as NULL, but in autovacuum it can be passed
* in to use the same buffer strategy object across multiple vacuum() calls.
*
* isTopLevel should be passed down from ProcessUtility.
*
* It is the caller's responsibility that all parameters are allocated in a
* memory context that will not disappear at transaction commit.
*/
void
vacuum(int options, RangeVar *relation, Oid relid, VacuumParams *params,
List *va_cols, BufferAccessStrategy bstrategy, bool isTopLevel)
{
// TODO :: Peloton Changes
// Disabled vacuumming in Postgres
if(false){
const char *stmttype;
volatile bool in_outer_xact,
use_own_xacts;
List *relations;
static bool in_vacuum = false;
Assert(params != NULL);
stmttype = (options & VACOPT_VACUUM) ? "VACUUM" : "ANALYZE";
/*
* We cannot run VACUUM inside a user transaction block; if we were inside
* a transaction, then our commit- and start-transaction-command calls
* would not have the intended effect! There are numerous other subtle
* dependencies on this, too.
*
* ANALYZE (without VACUUM) can run either way.
*/
if (options & VACOPT_VACUUM)
{
PreventTransactionChain(isTopLevel, stmttype);
in_outer_xact = false;
}
else
in_outer_xact = IsInTransactionChain(isTopLevel);
/*
* Due to static variables vac_context, anl_context and vac_strategy,
* vacuum() is not reentrant. This matters when VACUUM FULL or ANALYZE
* calls a hostile index expression that itself calls ANALYZE.
*/
if (in_vacuum)
elog(ERROR, "%s cannot be executed from VACUUM or ANALYZE", stmttype);
/*
* Send info about dead objects to the statistics collector, unless we are
* in autovacuum --- autovacuum.c does this for itself.
*/
if ((options & VACOPT_VACUUM) && !IsAutoVacuumWorkerProcess())
pgstat_vacuum_stat();
/*
* Create special memory context for cross-transaction storage.
*
* Since it is a child of PortalContext, it will go away eventually even
* if we suffer an error; there's no need for special abort cleanup logic.
*/
vac_context = AllocSetContextCreate(PortalContext,
"Vacuum",
ALLOCSET_DEFAULT_MINSIZE,
ALLOCSET_DEFAULT_INITSIZE,
ALLOCSET_DEFAULT_MAXSIZE);
/*
* If caller didn't give us a buffer strategy object, make one in the
* cross-transaction memory context.
*/
if (bstrategy == NULL)
{
MemoryContext old_context = MemoryContextSwitchTo(vac_context);
bstrategy = GetAccessStrategy(BAS_VACUUM);
MemoryContextSwitchTo(old_context);
}
vac_strategy = bstrategy;
/*
* Build list of relations to process, unless caller gave us one. (If we
* build one, we put it in vac_context for safekeeping.)
*/
relations = get_rel_oids(relid, relation);
/*
* Decide whether we need to start/commit our own transactions.
*
* For VACUUM (with or without ANALYZE): always do so, so that we can
* release locks as soon as possible. (We could possibly use the outer
* transaction for a one-table VACUUM, but handling TOAST tables would be
* problematic.)
*
* For ANALYZE (no VACUUM): if inside a transaction block, we cannot
* start/commit our own transactions. Also, there's no need to do so if
* only processing one relation. For multiple relations when not within a
* transaction block, and also in an autovacuum worker, use own
* transactions so we can release locks sooner.
*/
if (options & VACOPT_VACUUM)
use_own_xacts = true;
else
{
Assert(options & VACOPT_ANALYZE);
if (IsAutoVacuumWorkerProcess())
use_own_xacts = true;
else if (in_outer_xact)
use_own_xacts = false;
else if (list_length(relations) > 1)
use_own_xacts = true;
else
use_own_xacts = false;
}
/*
* vacuum_rel expects to be entered with no transaction active; it will
* start and commit its own transaction. But we are called by an SQL
* command, and so we are executing inside a transaction already. We
* commit the transaction started in PostgresMain() here, and start
* another one before exiting to match the commit waiting for us back in
* PostgresMain().
*/
if (use_own_xacts)
{
Assert(!in_outer_xact);
/* ActiveSnapshot is not set by autovacuum */
if (ActiveSnapshotSet())
PopActiveSnapshot();
/* matches the StartTransaction in PostgresMain() */
CommitTransactionCommand();
}
/* Turn vacuum cost accounting on or off */
PG_TRY();
{
ListCell *cur;
in_vacuum = true;
VacuumCostActive = (VacuumCostDelay > 0);
VacuumCostBalance = 0;
VacuumPageHit = 0;
VacuumPageMiss = 0;
VacuumPageDirty = 0;
/*
* Loop to process each selected relation.
*/
foreach(cur, relations)
{
Oid relid = lfirst_oid(cur);
if (options & VACOPT_VACUUM)
{
if (!vacuum_rel(relid, relation, options, params))
continue;
}
if (options & VACOPT_ANALYZE)
{
/*
* If using separate xacts, start one for analyze. Otherwise,
* we can use the outer transaction.
*/
if (use_own_xacts)
{
StartTransactionCommand();
/* functions in indexes may want a snapshot set */
PushActiveSnapshot(GetTransactionSnapshot());
}
analyze_rel(relid, relation, options, params,
va_cols, in_outer_xact, vac_strategy);
if (use_own_xacts)
{
PopActiveSnapshot();
CommitTransactionCommand();
}
}
}
}
PG_CATCH();
{
in_vacuum = false;
VacuumCostActive = false;
PG_RE_THROW();
}
PG_END_TRY();
in_vacuum = false;
VacuumCostActive = false;
/*
* Finish up processing.
*/
if (use_own_xacts)
{
/* here, we are not in a transaction */
/*
* This matches the CommitTransaction waiting for us in
* PostgresMain().
*/
StartTransactionCommand();
}
if ((options & VACOPT_VACUUM) && !IsAutoVacuumWorkerProcess())
{
/*
* Update pg_database.datfrozenxid, and truncate pg_clog if possible.
* (autovacuum.c does this for itself.)
*/
vac_update_datfrozenxid();
}
/*
* Clean up working storage --- note we must do this after
* StartTransactionCommand, else we might be trying to delete the active
* context!
*/
MemoryContextDelete(vac_context);
vac_context = NULL;
}
/*
* ErrorIfNotSupportedConstraint run checks related to unique index / exclude
* constraints.
*
* Forbid UNIQUE, PRIMARY KEY, or EXCLUDE constraints on append partitioned
* tables, since currently there is no way of enforcing uniqueness for
* overlapping shards.
*
* Similarly, do not allow such constraints if they do not include partition
* column. This check is important for two reasons:
* i. First, currently Citus does not enforce uniqueness constraint on multiple
* shards.
* ii. Second, INSERT INTO .. ON CONFLICT (i.e., UPSERT) queries can be executed
* with no further check for constraints.
*/
static void
ErrorIfNotSupportedConstraint(Relation relation, char distributionMethod,
Var *distributionColumn, uint32 colocationId)
{
char *relationName = RelationGetRelationName(relation);
List *indexOidList = RelationGetIndexList(relation);
ListCell *indexOidCell = NULL;
foreach(indexOidCell, indexOidList)
{
Oid indexOid = lfirst_oid(indexOidCell);
Relation indexDesc = index_open(indexOid, RowExclusiveLock);
IndexInfo *indexInfo = NULL;
AttrNumber *attributeNumberArray = NULL;
bool hasDistributionColumn = false;
int attributeCount = 0;
int attributeIndex = 0;
/* extract index key information from the index's pg_index info */
indexInfo = BuildIndexInfo(indexDesc);
/* only check unique indexes and exclusion constraints. */
if (indexInfo->ii_Unique == false && indexInfo->ii_ExclusionOps == NULL)
{
index_close(indexDesc, NoLock);
continue;
}
/*
* Citus cannot enforce uniqueness/exclusion constraints with overlapping shards.
* Thus, emit a warning for unique indexes and exclusion constraints on
* append partitioned tables.
*/
if (distributionMethod == DISTRIBUTE_BY_APPEND)
{
ereport(WARNING, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("table \"%s\" has a UNIQUE or EXCLUDE constraint",
relationName),
errdetail("UNIQUE constraints, EXCLUDE constraints, "
"and PRIMARY KEYs on "
"append-partitioned tables cannot be enforced."),
errhint("Consider using hash partitioning.")));
}
attributeCount = indexInfo->ii_NumIndexAttrs;
attributeNumberArray = indexInfo->ii_KeyAttrNumbers;
for (attributeIndex = 0; attributeIndex < attributeCount; attributeIndex++)
{
AttrNumber attributeNumber = attributeNumberArray[attributeIndex];
bool uniqueConstraint = false;
bool exclusionConstraintWithEquality = false;
if (distributionColumn->varattno != attributeNumber)
{
continue;
}
uniqueConstraint = indexInfo->ii_Unique;
exclusionConstraintWithEquality = (indexInfo->ii_ExclusionOps != NULL &&
OperatorImplementsEquality(
indexInfo->ii_ExclusionOps[
attributeIndex]));
if (uniqueConstraint || exclusionConstraintWithEquality)
{
hasDistributionColumn = true;
break;
}
}
if (!hasDistributionColumn)
{
ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot distribute relation: \"%s\"",
relationName),
errdetail("Distributed relations cannot have UNIQUE, "
"EXCLUDE, or PRIMARY KEY constraints that do not "
"include the partition column (with an equality "
"operator if EXCLUDE).")));
}
index_close(indexDesc, NoLock);
}
