f1ea98a797
The GiST sorted build currently chooses split points according to the only page space utilization. That may lead to higher non-leaf keys overlap and, in turn, slower search query answers. This commit makes the sorted build use the opclass's picksplit method. Once four pages at the level are accumulated, the picksplit method is applied until each split partition fits the page. Some of our split algorithms could show significant performance degradation while processing 4-times more data at once. But those opclasses haven't received the sorted build support and shouldn't receive it before their split algorithms are improved. Discussion: https://postgr.es/m/CAHqSB9jqtS94e9%3D0vxqQX5dxQA89N95UKyz-%3DA7Y%2B_YJt%2BVW5A%40mail.gmail.com Author: Aliaksandr Kalenik, Sergei Shoulbakov, Andrey Borodin Reviewed-by: Björn Harrtell, Darafei Praliaskouski, Andres Freund Reviewed-by: Alexander Korotkov
68 lines
2.8 KiB
Plaintext
68 lines
2.8 KiB
Plaintext
-- The gist_page_opaque_info() function prints the page's LSN. Normally,
|
|
-- that's constant 1 (GistBuildLSN) on every page of a freshly built GiST
|
|
-- index. But with wal_level=minimal, the whole relation is dumped to WAL at
|
|
-- the end of the transaction if it's smaller than wal_skip_threshold, which
|
|
-- updates the LSNs. Wrap the tests on gist_page_opaque_info() in the
|
|
-- same transaction with the CREATE INDEX so that we see the LSNs before
|
|
-- they are possibly overwritten at end of transaction.
|
|
BEGIN;
|
|
-- Create a test table and GiST index.
|
|
CREATE TABLE test_gist AS SELECT point(i,i) p, i::text t FROM
|
|
generate_series(1,1000) i;
|
|
CREATE INDEX test_gist_idx ON test_gist USING gist (p);
|
|
-- Page 0 is the root, the rest are leaf pages
|
|
SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 0));
|
|
lsn | nsn | rightlink | flags
|
|
-----+-----+------------+-------
|
|
0/1 | 0/0 | 4294967295 | {}
|
|
(1 row)
|
|
|
|
SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 1));
|
|
lsn | nsn | rightlink | flags
|
|
-----+-----+------------+--------
|
|
0/1 | 0/0 | 4294967295 | {leaf}
|
|
(1 row)
|
|
|
|
SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist_idx', 2));
|
|
lsn | nsn | rightlink | flags
|
|
-----+-----+-----------+--------
|
|
0/1 | 0/0 | 1 | {leaf}
|
|
(1 row)
|
|
|
|
COMMIT;
|
|
SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 0), 'test_gist_idx');
|
|
itemoffset | ctid | itemlen | dead | keys
|
|
------------+-----------+---------+------+-------------------
|
|
1 | (1,65535) | 40 | f | (p)=((185,185))
|
|
2 | (2,65535) | 40 | f | (p)=((370,370))
|
|
3 | (3,65535) | 40 | f | (p)=((555,555))
|
|
4 | (4,65535) | 40 | f | (p)=((740,740))
|
|
5 | (5,65535) | 40 | f | (p)=((870,870))
|
|
6 | (6,65535) | 40 | f | (p)=((1000,1000))
|
|
(6 rows)
|
|
|
|
SELECT * FROM gist_page_items(get_raw_page('test_gist_idx', 1), 'test_gist_idx') LIMIT 5;
|
|
itemoffset | ctid | itemlen | dead | keys
|
|
------------+-------+---------+------+-------------
|
|
1 | (0,1) | 40 | f | (p)=((1,1))
|
|
2 | (0,2) | 40 | f | (p)=((2,2))
|
|
3 | (0,3) | 40 | f | (p)=((3,3))
|
|
4 | (0,4) | 40 | f | (p)=((4,4))
|
|
5 | (0,5) | 40 | f | (p)=((5,5))
|
|
(5 rows)
|
|
|
|
-- gist_page_items_bytea prints the raw key data as a bytea. The output of that is
|
|
-- platform-dependent (endianess), so omit the actual key data from the output.
|
|
SELECT itemoffset, ctid, itemlen FROM gist_page_items_bytea(get_raw_page('test_gist_idx', 0));
|
|
itemoffset | ctid | itemlen
|
|
------------+-----------+---------
|
|
1 | (1,65535) | 40
|
|
2 | (2,65535) | 40
|
|
3 | (3,65535) | 40
|
|
4 | (4,65535) | 40
|
|
5 | (5,65535) | 40
|
|
6 | (6,65535) | 40
|
|
(6 rows)
|
|
|
|
DROP TABLE test_gist;
|