mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-08-23 21:17:18 +02:00
8af2565248
The new facility makes it easier to optimize bulk loading, as the logic for buffering, WAL-logging, and syncing the relation only needs to be implemented once. It's also less error-prone: We have had a number of bugs in how a relation is fsync'd - or not - at the end of a bulk loading operation. By centralizing that logic to one place, we only need to write it correctly once. The new facility is faster for small relations: Instead of of calling smgrimmedsync(), we register the fsync to happen at next checkpoint, which avoids the fsync latency. That can make a big difference if you are e.g. restoring a schema-only dump with lots of relations. It is also slightly more efficient with large relations, as the WAL logging is performed multiple pages at a time. That avoids some WAL header overhead. The sorted GiST index build did that already, this moves the buffering to the new facility. The changes to pageinspect GiST test needs an explanation: Before this patch, the sorted GiST index build set the LSN on every page to the special GistBuildLSN value, not the LSN of the WAL record, even though they were WAL-logged. There was no particular need for it, it just happened naturally when we wrote out the pages before WAL-logging them. Now we WAL-log the pages first, like in B-tree build, so the pages are stamped with the record's real LSN. When the build is not WAL-logged, we still use GistBuildLSN. To make the test output predictable, use an unlogged index. Reviewed-by: Andres Freund Discussion: https://www.postgresql.org/message-id/30e8f366-58b3-b239-c521-422122dd5150%40iki.fi
126 lines
4.9 KiB
Plaintext
126 lines
4.9 KiB
Plaintext
-- The gist_page_opaque_info() function prints the page's LSN.
|
|
-- Use an unlogged index, so that the LSN is predictable.
|
|
CREATE UNLOGGED 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)
|
|
|
|
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),(1,1)")
|
|
2 | (2,65535) | 40 | f | (p)=("(370,370),(186,186)")
|
|
3 | (3,65535) | 40 | f | (p)=("(555,555),(371,371)")
|
|
4 | (4,65535) | 40 | f | (p)=("(740,740),(556,556)")
|
|
5 | (5,65535) | 40 | f | (p)=("(870,870),(741,741)")
|
|
6 | (6,65535) | 40 | f | (p)=("(1000,1000),(871,871)")
|
|
(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),(1,1)")
|
|
2 | (0,2) | 40 | f | (p)=("(2,2),(2,2)")
|
|
3 | (0,3) | 40 | f | (p)=("(3,3),(3,3)")
|
|
4 | (0,4) | 40 | f | (p)=("(4,4),(4,4)")
|
|
5 | (0,5) | 40 | f | (p)=("(5,5),(5,5)")
|
|
(5 rows)
|
|
|
|
-- gist_page_items_bytea prints the raw key data as a bytea. The output of that is
|
|
-- platform-dependent (endianness), 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)
|
|
|
|
-- Suppress the DETAIL message, to allow the tests to work across various
|
|
-- page sizes and architectures.
|
|
\set VERBOSITY terse
|
|
-- Failures with non-GiST index.
|
|
CREATE INDEX test_gist_btree on test_gist(t);
|
|
SELECT gist_page_items(get_raw_page('test_gist_btree', 0), 'test_gist_btree');
|
|
ERROR: "test_gist_btree" is not a GiST index
|
|
SELECT gist_page_items(get_raw_page('test_gist_btree', 0), 'test_gist_idx');
|
|
ERROR: input page is not a valid GiST page
|
|
-- Failure with various modes.
|
|
-- invalid page size
|
|
SELECT gist_page_items_bytea('aaa'::bytea);
|
|
ERROR: invalid page size
|
|
SELECT gist_page_items('aaa'::bytea, 'test_gist_idx'::regclass);
|
|
ERROR: invalid page size
|
|
SELECT gist_page_opaque_info('aaa'::bytea);
|
|
ERROR: invalid page size
|
|
-- invalid special area size
|
|
SELECT * FROM gist_page_opaque_info(get_raw_page('test_gist', 0));
|
|
ERROR: input page is not a valid GiST page
|
|
SELECT gist_page_items_bytea(get_raw_page('test_gist', 0));
|
|
ERROR: input page is not a valid GiST page
|
|
SELECT gist_page_items_bytea(get_raw_page('test_gist_btree', 0));
|
|
ERROR: input page is not a valid GiST page
|
|
\set VERBOSITY default
|
|
-- Tests with all-zero pages.
|
|
SHOW block_size \gset
|
|
SELECT gist_page_items_bytea(decode(repeat('00', :block_size), 'hex'));
|
|
gist_page_items_bytea
|
|
-----------------------
|
|
(0 rows)
|
|
|
|
SELECT gist_page_items(decode(repeat('00', :block_size), 'hex'), 'test_gist_idx'::regclass);
|
|
gist_page_items
|
|
-----------------
|
|
(0 rows)
|
|
|
|
SELECT gist_page_opaque_info(decode(repeat('00', :block_size), 'hex'));
|
|
gist_page_opaque_info
|
|
-----------------------
|
|
|
|
(1 row)
|
|
|
|
-- Test gist_page_items with included columns.
|
|
-- Non-leaf pages contain only the key attributes, and leaf pages contain
|
|
-- the included attributes.
|
|
ALTER TABLE test_gist ADD COLUMN i int DEFAULT NULL;
|
|
CREATE INDEX test_gist_idx_inc ON test_gist
|
|
USING gist (p) INCLUDE (t, i);
|
|
-- Mask the value of the key attribute to avoid alignment issues.
|
|
SELECT regexp_replace(keys, '\(p\)=\("(.*?)"\)', '(p)=("<val>")') AS keys_nonleaf_1
|
|
FROM gist_page_items(get_raw_page('test_gist_idx_inc', 0), 'test_gist_idx_inc')
|
|
WHERE itemoffset = 1;
|
|
keys_nonleaf_1
|
|
----------------
|
|
(p)=("<val>")
|
|
(1 row)
|
|
|
|
SELECT keys AS keys_leaf_1
|
|
FROM gist_page_items(get_raw_page('test_gist_idx_inc', 1), 'test_gist_idx_inc')
|
|
WHERE itemoffset = 1;
|
|
keys_leaf_1
|
|
------------------------------------------------------
|
|
(p) INCLUDE (t, i)=("(1,1),(1,1)") INCLUDE (1, null)
|
|
(1 row)
|
|
|
|
DROP TABLE test_gist;
|