mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-08-31 05:07:21 +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
249 lines
11 KiB
Plaintext
249 lines
11 KiB
Plaintext
CREATE EXTENSION pgstattuple;
|
|
--
|
|
-- It's difficult to come up with platform-independent test cases for
|
|
-- the pgstattuple functions, but the results for empty tables and
|
|
-- indexes should be that.
|
|
--
|
|
create table test (a int primary key, b int[]);
|
|
select * from pgstattuple('test');
|
|
table_len | tuple_count | tuple_len | tuple_percent | dead_tuple_count | dead_tuple_len | dead_tuple_percent | free_space | free_percent
|
|
-----------+-------------+-----------+---------------+------------------+----------------+--------------------+------------+--------------
|
|
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0
|
|
(1 row)
|
|
|
|
select * from pgstattuple('test'::text);
|
|
table_len | tuple_count | tuple_len | tuple_percent | dead_tuple_count | dead_tuple_len | dead_tuple_percent | free_space | free_percent
|
|
-----------+-------------+-----------+---------------+------------------+----------------+--------------------+------------+--------------
|
|
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0
|
|
(1 row)
|
|
|
|
select * from pgstattuple('test'::name);
|
|
table_len | tuple_count | tuple_len | tuple_percent | dead_tuple_count | dead_tuple_len | dead_tuple_percent | free_space | free_percent
|
|
-----------+-------------+-----------+---------------+------------------+----------------+--------------------+------------+--------------
|
|
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0
|
|
(1 row)
|
|
|
|
select * from pgstattuple('test'::regclass);
|
|
table_len | tuple_count | tuple_len | tuple_percent | dead_tuple_count | dead_tuple_len | dead_tuple_percent | free_space | free_percent
|
|
-----------+-------------+-----------+---------------+------------------+----------------+--------------------+------------+--------------
|
|
0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0
|
|
(1 row)
|
|
|
|
select pgstattuple(oid) from pg_class where relname = 'test';
|
|
pgstattuple
|
|
---------------------
|
|
(0,0,0,0,0,0,0,0,0)
|
|
(1 row)
|
|
|
|
select pgstattuple(relname) from pg_class where relname = 'test';
|
|
pgstattuple
|
|
---------------------
|
|
(0,0,0,0,0,0,0,0,0)
|
|
(1 row)
|
|
|
|
select version, tree_level,
|
|
index_size / current_setting('block_size')::int as index_size,
|
|
root_block_no, internal_pages, leaf_pages, empty_pages, deleted_pages,
|
|
avg_leaf_density, leaf_fragmentation
|
|
from pgstatindex('test_pkey');
|
|
version | tree_level | index_size | root_block_no | internal_pages | leaf_pages | empty_pages | deleted_pages | avg_leaf_density | leaf_fragmentation
|
|
---------+------------+------------+---------------+----------------+------------+-------------+---------------+------------------+--------------------
|
|
4 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | NaN | NaN
|
|
(1 row)
|
|
|
|
select version, tree_level,
|
|
index_size / current_setting('block_size')::int as index_size,
|
|
root_block_no, internal_pages, leaf_pages, empty_pages, deleted_pages,
|
|
avg_leaf_density, leaf_fragmentation
|
|
from pgstatindex('test_pkey'::text);
|
|
version | tree_level | index_size | root_block_no | internal_pages | leaf_pages | empty_pages | deleted_pages | avg_leaf_density | leaf_fragmentation
|
|
---------+------------+------------+---------------+----------------+------------+-------------+---------------+------------------+--------------------
|
|
4 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | NaN | NaN
|
|
(1 row)
|
|
|
|
select version, tree_level,
|
|
index_size / current_setting('block_size')::int as index_size,
|
|
root_block_no, internal_pages, leaf_pages, empty_pages, deleted_pages,
|
|
avg_leaf_density, leaf_fragmentation
|
|
from pgstatindex('test_pkey'::name);
|
|
version | tree_level | index_size | root_block_no | internal_pages | leaf_pages | empty_pages | deleted_pages | avg_leaf_density | leaf_fragmentation
|
|
---------+------------+------------+---------------+----------------+------------+-------------+---------------+------------------+--------------------
|
|
4 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | NaN | NaN
|
|
(1 row)
|
|
|
|
select version, tree_level,
|
|
index_size / current_setting('block_size')::int as index_size,
|
|
root_block_no, internal_pages, leaf_pages, empty_pages, deleted_pages,
|
|
avg_leaf_density, leaf_fragmentation
|
|
from pgstatindex('test_pkey'::regclass);
|
|
version | tree_level | index_size | root_block_no | internal_pages | leaf_pages | empty_pages | deleted_pages | avg_leaf_density | leaf_fragmentation
|
|
---------+------------+------------+---------------+----------------+------------+-------------+---------------+------------------+--------------------
|
|
4 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | NaN | NaN
|
|
(1 row)
|
|
|
|
select pg_relpages('test');
|
|
pg_relpages
|
|
-------------
|
|
0
|
|
(1 row)
|
|
|
|
select pg_relpages('test_pkey');
|
|
pg_relpages
|
|
-------------
|
|
1
|
|
(1 row)
|
|
|
|
select pg_relpages('test_pkey'::text);
|
|
pg_relpages
|
|
-------------
|
|
1
|
|
(1 row)
|
|
|
|
select pg_relpages('test_pkey'::name);
|
|
pg_relpages
|
|
-------------
|
|
1
|
|
(1 row)
|
|
|
|
select pg_relpages('test_pkey'::regclass);
|
|
pg_relpages
|
|
-------------
|
|
1
|
|
(1 row)
|
|
|
|
select pg_relpages(oid) from pg_class where relname = 'test_pkey';
|
|
pg_relpages
|
|
-------------
|
|
1
|
|
(1 row)
|
|
|
|
select pg_relpages(relname) from pg_class where relname = 'test_pkey';
|
|
pg_relpages
|
|
-------------
|
|
1
|
|
(1 row)
|
|
|
|
create index test_ginidx on test using gin (b);
|
|
select * from pgstatginindex('test_ginidx');
|
|
version | pending_pages | pending_tuples
|
|
---------+---------------+----------------
|
|
2 | 0 | 0
|
|
(1 row)
|
|
|
|
create index test_hashidx on test using hash (b);
|
|
select * from pgstathashindex('test_hashidx');
|
|
version | bucket_pages | overflow_pages | bitmap_pages | unused_pages | live_items | dead_items | free_percent
|
|
---------+--------------+----------------+--------------+--------------+------------+------------+--------------
|
|
4 | 4 | 0 | 1 | 0 | 0 | 0 | 100
|
|
(1 row)
|
|
|
|
-- these should error with the wrong type
|
|
select pgstatginindex('test_pkey');
|
|
ERROR: relation "test_pkey" is not a GIN index
|
|
select pgstathashindex('test_pkey');
|
|
ERROR: relation "test_pkey" is not a hash index
|
|
select pgstatindex('test_ginidx');
|
|
ERROR: relation "test_ginidx" is not a btree index
|
|
select pgstathashindex('test_ginidx');
|
|
ERROR: relation "test_ginidx" is not a hash index
|
|
select pgstatindex('test_hashidx');
|
|
ERROR: relation "test_hashidx" is not a btree index
|
|
select pgstatginindex('test_hashidx');
|
|
ERROR: relation "test_hashidx" is not a GIN index
|
|
-- check that using any of these functions with unsupported relations will fail
|
|
create table test_partitioned (a int) partition by range (a);
|
|
create index test_partitioned_index on test_partitioned(a);
|
|
-- these should all fail
|
|
select pgstattuple('test_partitioned');
|
|
ERROR: "test_partitioned" (partitioned table) is not supported
|
|
select pgstattuple('test_partitioned_index');
|
|
ERROR: "test_partitioned_index" (partitioned index) is not supported
|
|
select pgstattuple_approx('test_partitioned');
|
|
ERROR: "test_partitioned" is not a table or materialized view
|
|
select pg_relpages('test_partitioned');
|
|
ERROR: "test_partitioned" is not a table, index, materialized view, sequence, or TOAST table
|
|
select pgstatindex('test_partitioned');
|
|
ERROR: relation "test_partitioned" is not a btree index
|
|
select pgstatginindex('test_partitioned');
|
|
ERROR: relation "test_partitioned" is not a GIN index
|
|
select pgstathashindex('test_partitioned');
|
|
ERROR: "test_partitioned" is not an index
|
|
create view test_view as select 1;
|
|
-- these should all fail
|
|
select pgstattuple('test_view');
|
|
ERROR: "test_view" (view) is not supported
|
|
select pgstattuple_approx('test_view');
|
|
ERROR: "test_view" is not a table or materialized view
|
|
select pg_relpages('test_view');
|
|
ERROR: "test_view" is not a table, index, materialized view, sequence, or TOAST table
|
|
select pgstatindex('test_view');
|
|
ERROR: relation "test_view" is not a btree index
|
|
select pgstatginindex('test_view');
|
|
ERROR: relation "test_view" is not a GIN index
|
|
select pgstathashindex('test_view');
|
|
ERROR: "test_view" is not an index
|
|
create foreign data wrapper dummy;
|
|
create server dummy_server foreign data wrapper dummy;
|
|
create foreign table test_foreign_table () server dummy_server;
|
|
-- these should all fail
|
|
select pgstattuple('test_foreign_table');
|
|
ERROR: "test_foreign_table" (foreign table) is not supported
|
|
select pgstattuple_approx('test_foreign_table');
|
|
ERROR: "test_foreign_table" is not a table or materialized view
|
|
select pg_relpages('test_foreign_table');
|
|
ERROR: "test_foreign_table" is not a table, index, materialized view, sequence, or TOAST table
|
|
select pgstatindex('test_foreign_table');
|
|
ERROR: relation "test_foreign_table" is not a btree index
|
|
select pgstatginindex('test_foreign_table');
|
|
ERROR: relation "test_foreign_table" is not a GIN index
|
|
select pgstathashindex('test_foreign_table');
|
|
ERROR: "test_foreign_table" is not an index
|
|
-- a partition of a partitioned table should work though
|
|
create table test_partition partition of test_partitioned for values from (1) to (100);
|
|
select pgstattuple('test_partition');
|
|
pgstattuple
|
|
---------------------
|
|
(0,0,0,0,0,0,0,0,0)
|
|
(1 row)
|
|
|
|
select pgstattuple_approx('test_partition');
|
|
pgstattuple_approx
|
|
-----------------------
|
|
(0,0,0,0,0,0,0,0,0,0)
|
|
(1 row)
|
|
|
|
select pg_relpages('test_partition');
|
|
pg_relpages
|
|
-------------
|
|
0
|
|
(1 row)
|
|
|
|
-- not for the index calls though, of course
|
|
select pgstatindex('test_partition');
|
|
ERROR: relation "test_partition" is not a btree index
|
|
select pgstatginindex('test_partition');
|
|
ERROR: relation "test_partition" is not a GIN index
|
|
select pgstathashindex('test_partition');
|
|
ERROR: "test_partition" is not an index
|
|
-- an actual index of a partitioned table should work though
|
|
create index test_partition_idx on test_partition(a);
|
|
create index test_partition_hash_idx on test_partition using hash (a);
|
|
-- these should work
|
|
select pgstatindex('test_partition_idx');
|
|
pgstatindex
|
|
------------------------------
|
|
(4,0,8192,0,0,0,0,0,NaN,NaN)
|
|
(1 row)
|
|
|
|
select pgstathashindex('test_partition_hash_idx');
|
|
pgstathashindex
|
|
---------------------
|
|
(4,8,0,1,0,0,0,100)
|
|
(1 row)
|
|
|
|
drop table test_partitioned;
|
|
drop view test_view;
|
|
drop foreign table test_foreign_table;
|
|
drop server dummy_server;
|
|
drop foreign data wrapper dummy;
|