mirror of
https://github.com/postgres/postgres.git
synced 2025-05-12 16:21:30 +03:00
068674f4ab
When creating and initializing a logical slot, the restart_lsn is set to the latest WAL insertion point (or the latest replay point on standbys). Subsequently, WAL records are decoded from that point to find the start point for extracting changes in the DecodingContextFindStartpoint() function. Since the initial restart_lsn could be in the middle of a transaction, the start point must be a consistent point where we won't see the data for partial transactions. Previously, when not building a full snapshot, serialized snapshots were restored, and the SnapBuild jumps to the consistent state even while finding the start point. Consequently, the slot's restart_lsn and confirmed_flush could be set to the middle of a transaction. This could lead to various unexpected consequences. Specifically, there were reports of logical decoding decoding partial transactions, and assertion failures occurred because only subtransactions were decoded without decoding their top-level transaction until decoding the commit record. To resolve this issue, the changes prevent restoring the serialized snapshot and jumping to the consistent state while finding the start point. On v17 and HEAD, a flag indicating whether snapshot restores should be skipped has been added to the SnapBuild struct, and SNAPBUILD_VERSION has been bumpded. On backbranches, the flag is stored in the LogicalDecodingContext instead, preserving on-disk compatibility. Backpatch to all supported versions. Reported-by: Drew Callahan Reviewed-by: Amit Kapila, Hayato Kuroda Discussion: https://postgr.es/m/2444AA15-D21B-4CCE-8052-52C7C2DAFE5C%40amazon.com Backpatch-through: 12
47 lines
2.1 KiB
Ruby
47 lines
2.1 KiB
Ruby
# Test that a slot creation skips to restore serialized snapshot to reach
|
|
# the consistent state.
|
|
|
|
setup
|
|
{
|
|
DROP TABLE IF EXISTS tbl;
|
|
CREATE TABLE tbl (val1 integer);
|
|
}
|
|
|
|
teardown
|
|
{
|
|
DROP TABLE tbl;
|
|
SELECT 'stop' FROM pg_drop_replication_slot('slot0');
|
|
SELECT 'stop' FROM pg_drop_replication_slot('slot1');
|
|
}
|
|
|
|
session "s0"
|
|
setup { SET synchronous_commit = on; }
|
|
step "s0_init" { SELECT 'init' FROM pg_create_logical_replication_slot('slot0', 'test_decoding'); }
|
|
step "s0_begin" { BEGIN; }
|
|
step "s0_insert1" { INSERT INTO tbl VALUES (1); }
|
|
step "s0_insert2" { INSERT INTO tbl VALUES (2); }
|
|
step "s0_commit" { COMMIT; }
|
|
|
|
session "s1"
|
|
setup { SET synchronous_commit = on; }
|
|
step "s1_init" { SELECT 'init' FROM pg_create_logical_replication_slot('slot1', 'test_decoding'); }
|
|
step "s1_get_changes_slot0" { SELECT data FROM pg_logical_slot_get_changes('slot0', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
|
|
step "s1_get_changes_slot1" { SELECT data FROM pg_logical_slot_get_changes('slot1', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
|
|
|
|
session "s2"
|
|
setup { SET synchronous_commit = on ;}
|
|
step "s2_checkpoint" { CHECKPOINT; }
|
|
step "s2_get_changes_slot0" { SELECT data FROM pg_logical_slot_get_changes('slot0', NULL, NULL, 'skip-empty-xacts', '1', 'include-xids', '0'); }
|
|
|
|
|
|
# While 'slot1' creation by "s1_init" waits for s0-transaction to commit, the
|
|
# RUNNING_XACTS record is written by "s2_checkpoint" and "s2_get_changes_slot1"
|
|
# serializes consistent snapshots to the disk at LSNs where are before
|
|
# s0-transaction's commit. After s0-transaction commits, "s1_init" resumes but
|
|
# must not restore any serialized snapshots and will reach the consistent state
|
|
# when decoding a RUNNING_XACT record generated after s0-transaction's commit.
|
|
# We check if the get_changes on 'slot1' will not return any s0-transaction's
|
|
# changes as its confirmed_flush_lsn will be after the s0-transaction's commit
|
|
# record.
|
|
permutation "s0_init" "s0_begin" "s0_insert1" "s1_init" "s2_checkpoint" "s2_get_changes_slot0" "s0_insert2" "s0_commit" "s1_get_changes_slot0" "s1_get_changes_slot1"
|