mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-08-28 16:47:20 +02:00
Make nbtree treat all index tuples as having a heap TID attribute. Index searches can distinguish duplicates by heap TID, since heap TID is always guaranteed to be unique. This general approach has numerous benefits for performance, and is prerequisite to teaching VACUUM to perform "retail index tuple deletion". Naively adding a new attribute to every pivot tuple has unacceptable overhead (it bloats internal pages), so suffix truncation of pivot tuples is added. This will usually truncate away the "extra" heap TID attribute from pivot tuples during a leaf page split, and may also truncate away additional user attributes. This can increase fan-out, especially in a multi-column index. Truncation can only occur at the attribute granularity, which isn't particularly effective, but works well enough for now. A future patch may add support for truncating "within" text attributes by generating truncated key values using new opclass infrastructure. Only new indexes (BTREE_VERSION 4 indexes) will have insertions that treat heap TID as a tiebreaker attribute, or will have pivot tuples undergo suffix truncation during a leaf page split (on-disk compatibility with versions 2 and 3 is preserved). Upgrades to version 4 cannot be performed on-the-fly, unlike upgrades from version 2 to version 3. contrib/amcheck continues to work with version 2 and 3 indexes, while also enforcing stricter invariants when verifying version 4 indexes. These stricter invariants are the same invariants described by "3.1.12 Sequencing" from the Lehman and Yao paper. A later patch will enhance the logic used by nbtree to pick a split point. This patch is likely to negatively impact performance without smarter choices around the precise point to split leaf pages at. Making these two mostly-distinct sets of enhancements into distinct commits seems like it might clarify their design, even though neither commit is particularly useful on its own. The maximum allowed size of new tuples is reduced by an amount equal to the space required to store an extra MAXALIGN()'d TID in a new high key during leaf page splits. The user-facing definition of the "1/3 of a page" restriction is already imprecise, and so does not need to be revised. However, there should be a compatibility note in the v12 release notes. Author: Peter Geoghegan Reviewed-By: Heikki Linnakangas, Alexander Korotkov Discussion: https://postgr.es/m/CAH2-WzkVb0Kom=R+88fDFb=JSxZMFvbHVC6Mn9LJ2n=X=kS-Uw@mail.gmail.com
173 lines
5.7 KiB
Plaintext
173 lines
5.7 KiB
Plaintext
CREATE TABLE bttest_a(id int8);
|
|
CREATE TABLE bttest_b(id int8);
|
|
CREATE TABLE bttest_multi(id int8, data int8);
|
|
CREATE TABLE delete_test_table (a bigint, b bigint, c bigint, d bigint);
|
|
-- Stabalize tests
|
|
ALTER TABLE bttest_a SET (autovacuum_enabled = false);
|
|
ALTER TABLE bttest_b SET (autovacuum_enabled = false);
|
|
ALTER TABLE bttest_multi SET (autovacuum_enabled = false);
|
|
ALTER TABLE delete_test_table SET (autovacuum_enabled = false);
|
|
INSERT INTO bttest_a SELECT * FROM generate_series(1, 100000);
|
|
INSERT INTO bttest_b SELECT * FROM generate_series(100000, 1, -1);
|
|
INSERT INTO bttest_multi SELECT i, i%2 FROM generate_series(1, 100000) as i;
|
|
CREATE INDEX bttest_a_idx ON bttest_a USING btree (id);
|
|
CREATE INDEX bttest_b_idx ON bttest_b USING btree (id);
|
|
CREATE UNIQUE INDEX bttest_multi_idx ON bttest_multi
|
|
USING btree (id) INCLUDE (data);
|
|
CREATE ROLE bttest_role;
|
|
-- verify permissions are checked (error due to function not callable)
|
|
SET ROLE bttest_role;
|
|
SELECT bt_index_check('bttest_a_idx'::regclass);
|
|
ERROR: permission denied for function bt_index_check
|
|
SELECT bt_index_parent_check('bttest_a_idx'::regclass);
|
|
ERROR: permission denied for function bt_index_parent_check
|
|
RESET ROLE;
|
|
-- we, intentionally, don't check relation permissions - it's useful
|
|
-- to run this cluster-wide with a restricted account, and as tested
|
|
-- above explicit permission has to be granted for that.
|
|
GRANT EXECUTE ON FUNCTION bt_index_check(regclass) TO bttest_role;
|
|
GRANT EXECUTE ON FUNCTION bt_index_parent_check(regclass) TO bttest_role;
|
|
GRANT EXECUTE ON FUNCTION bt_index_check(regclass, boolean) TO bttest_role;
|
|
GRANT EXECUTE ON FUNCTION bt_index_parent_check(regclass, boolean) TO bttest_role;
|
|
SET ROLE bttest_role;
|
|
SELECT bt_index_check('bttest_a_idx');
|
|
bt_index_check
|
|
----------------
|
|
|
|
(1 row)
|
|
|
|
SELECT bt_index_parent_check('bttest_a_idx');
|
|
bt_index_parent_check
|
|
-----------------------
|
|
|
|
(1 row)
|
|
|
|
RESET ROLE;
|
|
-- verify plain tables are rejected (error)
|
|
SELECT bt_index_check('bttest_a');
|
|
ERROR: "bttest_a" is not an index
|
|
SELECT bt_index_parent_check('bttest_a');
|
|
ERROR: "bttest_a" is not an index
|
|
-- verify non-existing indexes are rejected (error)
|
|
SELECT bt_index_check(17);
|
|
ERROR: could not open relation with OID 17
|
|
SELECT bt_index_parent_check(17);
|
|
ERROR: could not open relation with OID 17
|
|
-- verify wrong index types are rejected (error)
|
|
BEGIN;
|
|
CREATE INDEX bttest_a_brin_idx ON bttest_a USING brin(id);
|
|
SELECT bt_index_parent_check('bttest_a_brin_idx');
|
|
ERROR: only B-Tree indexes are supported as targets for verification
|
|
DETAIL: Relation "bttest_a_brin_idx" is not a B-Tree index.
|
|
ROLLBACK;
|
|
-- normal check outside of xact
|
|
SELECT bt_index_check('bttest_a_idx');
|
|
bt_index_check
|
|
----------------
|
|
|
|
(1 row)
|
|
|
|
-- more expansive tests
|
|
SELECT bt_index_check('bttest_a_idx', true);
|
|
bt_index_check
|
|
----------------
|
|
|
|
(1 row)
|
|
|
|
SELECT bt_index_parent_check('bttest_b_idx', true);
|
|
bt_index_parent_check
|
|
-----------------------
|
|
|
|
(1 row)
|
|
|
|
BEGIN;
|
|
SELECT bt_index_check('bttest_a_idx');
|
|
bt_index_check
|
|
----------------
|
|
|
|
(1 row)
|
|
|
|
SELECT bt_index_parent_check('bttest_b_idx');
|
|
bt_index_parent_check
|
|
-----------------------
|
|
|
|
(1 row)
|
|
|
|
-- make sure we don't have any leftover locks
|
|
SELECT * FROM pg_locks
|
|
WHERE relation = ANY(ARRAY['bttest_a', 'bttest_a_idx', 'bttest_b', 'bttest_b_idx']::regclass[])
|
|
AND pid = pg_backend_pid();
|
|
locktype | database | relation | page | tuple | virtualxid | transactionid | classid | objid | objsubid | virtualtransaction | pid | mode | granted | fastpath
|
|
----------+----------+----------+------+-------+------------+---------------+---------+-------+----------+--------------------+-----+------+---------+----------
|
|
(0 rows)
|
|
|
|
COMMIT;
|
|
-- normal check outside of xact for index with included columns
|
|
SELECT bt_index_check('bttest_multi_idx');
|
|
bt_index_check
|
|
----------------
|
|
|
|
(1 row)
|
|
|
|
-- more expansive test for index with included columns
|
|
SELECT bt_index_parent_check('bttest_multi_idx', true);
|
|
bt_index_parent_check
|
|
-----------------------
|
|
|
|
(1 row)
|
|
|
|
-- repeat expansive test for index built using insertions
|
|
TRUNCATE bttest_multi;
|
|
INSERT INTO bttest_multi SELECT i, i%2 FROM generate_series(1, 100000) as i;
|
|
SELECT bt_index_parent_check('bttest_multi_idx', true);
|
|
bt_index_parent_check
|
|
-----------------------
|
|
|
|
(1 row)
|
|
|
|
--
|
|
-- Test for multilevel page deletion/downlink present checks
|
|
--
|
|
INSERT INTO delete_test_table SELECT i, 1, 2, 3 FROM generate_series(1,80000) i;
|
|
ALTER TABLE delete_test_table ADD PRIMARY KEY (a,b,c,d);
|
|
-- Delete many entries, and vacuum. This causes page deletions.
|
|
DELETE FROM delete_test_table WHERE a > 40000;
|
|
VACUUM delete_test_table;
|
|
-- Delete most entries, and vacuum, deleting internal pages and creating "fast
|
|
-- root"
|
|
DELETE FROM delete_test_table WHERE a < 79990;
|
|
VACUUM delete_test_table;
|
|
SELECT bt_index_parent_check('delete_test_table_pkey', true);
|
|
bt_index_parent_check
|
|
-----------------------
|
|
|
|
(1 row)
|
|
|
|
--
|
|
-- BUG #15597: must not assume consistent input toasting state when forming
|
|
-- tuple. Bloom filter must fingerprint normalized index tuple representation.
|
|
--
|
|
CREATE TABLE toast_bug(buggy text);
|
|
ALTER TABLE toast_bug ALTER COLUMN buggy SET STORAGE plain;
|
|
-- pg_attribute entry for toasty.buggy will have plain storage:
|
|
CREATE INDEX toasty ON toast_bug(buggy);
|
|
-- Whereas pg_attribute entry for toast_bug.buggy now has extended storage:
|
|
ALTER TABLE toast_bug ALTER COLUMN buggy SET STORAGE extended;
|
|
-- Insert compressible heap tuple (comfortably exceeds TOAST_TUPLE_THRESHOLD):
|
|
INSERT INTO toast_bug SELECT repeat('a', 2200);
|
|
-- Should not get false positive report of corruption:
|
|
SELECT bt_index_check('toasty', true);
|
|
bt_index_check
|
|
----------------
|
|
|
|
(1 row)
|
|
|
|
-- cleanup
|
|
DROP TABLE bttest_a;
|
|
DROP TABLE bttest_b;
|
|
DROP TABLE bttest_multi;
|
|
DROP TABLE delete_test_table;
|
|
DROP TABLE toast_bug;
|
|
DROP OWNED BY bttest_role; -- permissions
|
|
DROP ROLE bttest_role;
|