to replica identity <literal>FULL</literal>, which means the entire row becomes
the key. When replica identity <literal>FULL</literal> is specified,
indexes can be used on the subscriber side for searching the rows. Candidate
- indexes must be btree, non-partial, and the leftmost index field must be a
- column (not an expression) that references the published table column. These
- restrictions on the non-unique index properties adhere to some of the
+ indexes must be btree or hash, non-partial, and the leftmost index field must
+ be a column (not an expression) that references the published table column.
+ These restrictions on the non-unique index properties adhere to some of the
restrictions that are enforced for primary keys. If there are no such
suitable indexes, the search on the subscriber side can be very inefficient,
therefore replica identity <literal>FULL</literal> should only be used as a
#include "access/tableam.h"
#include "access/transam.h"
#include "access/xact.h"
+#include "catalog/pg_am_d.h"
#include "commands/trigger.h"
#include "executor/executor.h"
#include "executor/nodeModifyTable.h"
static bool tuples_equal(TupleTableSlot *slot1, TupleTableSlot *slot2,
TypeCacheEntry **eq);
+/*
+ * Returns the fixed strategy number, if any, of the equality operator for the
+ * given index access method, otherwise, InvalidStrategy.
+ *
+ * Currently, only Btree and Hash indexes are supported. The other index access
+ * methods don't have a fixed strategy for equality operation - instead, the
+ * support routines of each operator class interpret the strategy numbers
+ * according to the operator class's definition.
+ */
+StrategyNumber
+get_equal_strategy_number_for_am(Oid am)
+{
+ int ret;
+
+ switch (am)
+ {
+ case BTREE_AM_OID:
+ ret = BTEqualStrategyNumber;
+ break;
+ case HASH_AM_OID:
+ ret = HTEqualStrategyNumber;
+ break;
+ default:
+ /* XXX: Only Btree and Hash indexes are supported */
+ ret = InvalidStrategy;
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * Return the appropriate strategy number which corresponds to the equality
+ * operator.
+ */
+static StrategyNumber
+get_equal_strategy_number(Oid opclass)
+{
+ Oid am = get_opclass_method(opclass);
+
+ return get_equal_strategy_number_for_am(am);
+}
+
/*
* Setup a ScanKey for a search in the relation 'rel' for a tuple 'key' that
* is setup to match 'rel' (*NOT* idxrel!).
Oid opfamily;
RegProcedure regop;
int table_attno = indkey->values[index_attoff];
+ StrategyNumber eq_strategy;
if (!AttributeNumberIsValid(table_attno))
{
*/
optype = get_opclass_input_type(opclass->values[index_attoff]);
opfamily = get_opclass_family(opclass->values[index_attoff]);
+ eq_strategy = get_equal_strategy_number(opclass->values[index_attoff]);
operator = get_opfamily_member(opfamily, optype,
optype,
- BTEqualStrategyNumber);
+ eq_strategy);
+
if (!OidIsValid(operator))
elog(ERROR, "missing operator %d(%u,%u) in opfamily %u",
- BTEqualStrategyNumber, optype, optype, opfamily);
+ eq_strategy, optype, optype, opfamily);
regop = get_opcode(operator);
/* Initialize the scankey. */
ScanKeyInit(&skey[skey_attoff],
index_attoff + 1,
- BTEqualStrategyNumber,
+ eq_strategy,
regop,
searchslot->tts_values[table_attno - 1]);
#include "postgres.h"
+#ifdef USE_ASSERT_CHECKING
+#include "access/amapi.h"
+#endif
#include "access/genam.h"
#include "access/table.h"
#include "catalog/namespace.h"
/*
* Returns the oid of an index that can be used by the apply worker to scan
- * the relation. The index must be btree, non-partial, and the leftmost
+ * the relation. The index must be btree or hash, non-partial, and the leftmost
* field must be a column (not an expression) that references the remote
* relation column. These limitations help to keep the index scan similar
* to PK/RI index scans.
* compare the tuples for non-PK/RI index scans. See
* RelationFindReplTupleByIndex().
*
- * XXX: There are no fundamental problems for supporting non-btree indexes.
- * We mostly need to relax the limitations in RelationFindReplTupleByIndex().
- * For partial indexes, the required changes are likely to be larger. If
- * none of the tuples satisfy the expression for the index scan, we fall-back
- * to sequential execution, which might not be a good idea in some cases.
+ * XXX: See IsIndexUsableForReplicaIdentityFull() to know the challenges in
+ * supporting indexes other than btree and hash. For partial indexes, the
+ * required changes are likely to be larger. If none of the tuples satisfy
+ * the expression for the index scan, we fall-back to sequential execution,
+ * which might not be a good idea in some cases.
*
* We expect to call this function when REPLICA IDENTITY FULL is defined for
* the remote relation.
/*
* Returns true if the index is usable for replica identity full. For details,
* see FindUsableIndexForReplicaIdentityFull.
+ *
+ * Currently, only Btree and Hash indexes can be returned as usable. This
+ * is due to following reasons:
+ *
+ * 1) Other index access methods don't have a fixed strategy for equality
+ * operation. Refer get_equal_strategy_number_for_am().
+ *
+ * 2) For indexes other than PK and REPLICA IDENTITY, we need to match the
+ * local and remote tuples. The equality routine tuples_equal() cannot accept
+ * a datatype (e.g. point or box) that does not have a default operator class
+ * for Btree or Hash.
+ *
+ * XXX: Note that BRIN and GIN indexes do not implement "amgettuple" which
+ * will be used later to fetch the tuples. See RelationFindReplTupleByIndex().
*/
bool
IsIndexUsableForReplicaIdentityFull(IndexInfo *indexInfo)
{
- bool is_btree = (indexInfo->ii_Am == BTREE_AM_OID);
- bool is_partial = (indexInfo->ii_Predicate != NIL);
- bool is_only_on_expression = IsIndexOnlyOnExpression(indexInfo);
+ /* Ensure that the index access method has a valid equal strategy */
+ if (get_equal_strategy_number_for_am(indexInfo->ii_Am) == InvalidStrategy)
+ return false;
+ if (indexInfo->ii_Predicate != NIL)
+ return false;
+ if (IsIndexOnlyOnExpression(indexInfo))
+ return false;
+
+#ifdef USE_ASSERT_CHECKING
+ {
+ IndexAmRoutine *amroutine;
- return is_btree && !is_partial && !is_only_on_expression;
+ /* The given index access method must implement amgettuple. */
+ amroutine = GetIndexAmRoutineByAmId(indexInfo->ii_Am, false);
+ Assert(amroutine->amgettuple != NULL);
+ }
+#endif
+
+ return true;
}
/*
return true;
}
+/*
+ * get_opclass_method
+ *
+ * Returns the OID of the index access method the opclass belongs to.
+ */
+Oid
+get_opclass_method(Oid opclass)
+{
+ HeapTuple tp;
+ Form_pg_opclass cla_tup;
+ Oid result;
+
+ tp = SearchSysCache1(CLAOID, ObjectIdGetDatum(opclass));
+ if (!HeapTupleIsValid(tp))
+ elog(ERROR, "cache lookup failed for opclass %u", opclass);
+ cla_tup = (Form_pg_opclass) GETSTRUCT(tp);
+
+ result = cla_tup->opcmethod;
+ ReleaseSysCache(tp);
+ return result;
+}
+
/* ---------- OPERATOR CACHE ---------- */
/*
/*
* prototypes from functions in execReplication.c
*/
+extern StrategyNumber get_equal_strategy_number_for_am(Oid am);
extern bool RelationFindReplTupleByIndex(Relation rel, Oid idxoid,
LockTupleMode lockmode,
TupleTableSlot *searchslot,
extern Oid get_opclass_input_type(Oid opclass);
extern bool get_opclass_opfamily_and_input_type(Oid opclass,
Oid *opfamily, Oid *opcintype);
+extern Oid get_opclass_method(Oid opclass);
extern RegProcedure get_opcode(Oid opno);
extern char *get_opname(Oid opno);
extern Oid get_op_rettype(Oid opno);
# data
# =============================================================================
+# =============================================================================
+# Testcase start: Subscription can use hash index
+#
+
+# create tables on pub and sub
+$node_publisher->safe_psql('postgres',
+ "CREATE TABLE test_replica_id_full (x int, y text)");
+$node_publisher->safe_psql('postgres',
+ "ALTER TABLE test_replica_id_full REPLICA IDENTITY FULL");
+$node_subscriber->safe_psql('postgres',
+ "CREATE TABLE test_replica_id_full (x int, y text)");
+$node_subscriber->safe_psql('postgres',
+ "CREATE INDEX test_replica_id_full_idx ON test_replica_id_full USING HASH (x)");
+
+# insert some initial data
+$node_publisher->safe_psql('postgres',
+ "INSERT INTO test_replica_id_full SELECT i, (i%10)::text FROM generate_series(0,10) i"
+);
+
+# create pub/sub
+$node_publisher->safe_psql('postgres',
+ "CREATE PUBLICATION tap_pub_rep_full FOR TABLE test_replica_id_full");
+$node_subscriber->safe_psql('postgres',
+ "CREATE SUBSCRIPTION tap_sub_rep_full CONNECTION '$publisher_connstr application_name=$appname' PUBLICATION tap_pub_rep_full"
+);
+
+# wait for initial table synchronization to finish
+$node_subscriber->wait_for_subscription_sync($node_publisher, $appname);
+
+# delete 2 rows
+$node_publisher->safe_psql('postgres',
+ "DELETE FROM test_replica_id_full WHERE x IN (5, 6)");
+
+# update 2 rows
+$node_publisher->safe_psql('postgres',
+ "UPDATE test_replica_id_full SET x = 100, y = '200' WHERE x IN (1, 2)");
+
+# wait until the index is used on the subscriber
+$node_publisher->wait_for_catchup($appname);
+$node_subscriber->poll_query_until('postgres',
+ q{select (idx_scan = 4) from pg_stat_all_indexes where indexrelname = 'test_replica_id_full_idx';}
+ )
+ or die
+ "Timed out while waiting for check subscriber tap_sub_rep_full deletes 2 rows and updates 2 rows via index";
+
+# make sure that the subscriber has the correct data after the UPDATE
+$result = $node_subscriber->safe_psql('postgres',
+ "select count(*) from test_replica_id_full WHERE (x = 100 and y = '200')"
+);
+is($result, qq(2),
+ 'ensure subscriber has the correct data at the end of the test');
+
+# make sure that the subscriber has the correct data after the first DELETE
+$result = $node_subscriber->safe_psql('postgres',
+ "select count(*) from test_replica_id_full where x in (5, 6)");
+is($result, qq(0),
+ 'ensure subscriber has the correct data at the end of the test');
+
+# cleanup pub
+$node_publisher->safe_psql('postgres', "DROP PUBLICATION tap_pub_rep_full");
+$node_publisher->safe_psql('postgres', "DROP TABLE test_replica_id_full");
+# cleanup sub
+$node_subscriber->safe_psql('postgres', "DROP SUBSCRIPTION tap_sub_rep_full");
+$node_subscriber->safe_psql('postgres', "DROP TABLE test_replica_id_full");
+
+# Testcase end: Subscription can use hash index
+# =============================================================================
+
$node_subscriber->stop('fast');
$node_publisher->stop('fast');
projects / users / rhaas / postgres.git / commitdiff