database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-12 21:01:52 +03:00
Code Activity

Fix possibility of logical decoding partial transaction changes.

Browse Source 
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
This commit is contained in:
Masahiko Sawada
2024-07-11 22:48:23 +09:00
parent c194de0713
commit bb19b70081
7 changed files with 122 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/backend/replication/logical/logical.c
View File

@ -152,6 +152,7 @@ StartupDecodingContext(List *output_plugin_options,
TransactionId xmin_horizon,
bool need_full_snapshot,
bool fast_forward,
bool in_create,
XLogReaderRoutine *xl_routine,
LogicalOutputPluginWriterPrepareWrite prepare_write,
LogicalOutputPluginWriterWrite do_write,
@ -212,7 +213,7 @@ StartupDecodingContext(List *output_plugin_options,
ctx->reorder = ReorderBufferAllocate();
ctx->snapshot_builder =
AllocateSnapshotBuilder(ctx->reorder, xmin_horizon, start_lsn,
need_full_snapshot, slot->data.two_phase_at);
need_full_snapshot, in_create, slot->data.two_phase_at);
ctx->reorder->private_data = ctx;
@ -438,7 +439,7 @@ CreateInitDecodingContext(const char *plugin,
ReplicationSlotSave();
ctx = StartupDecodingContext(NIL, restart_lsn, xmin_horizon,
need_full_snapshot, false,
need_full_snapshot, false, true,
xl_routine, prepare_write, do_write,
update_progress);
@ -592,7 +593,7 @@ CreateDecodingContext(XLogRecPtr start_lsn,
ctx = StartupDecodingContext(output_plugin_options,
start_lsn, InvalidTransactionId, false,
fast_forward, xl_routine, prepare_write,
fast_forward, false, xl_routine, prepare_write,
do_write, update_progress);
/* call output plugin initialization callback */

29
src/backend/replication/logical/snapbuild.c
View File

@ -189,6 +189,14 @@ struct SnapBuild
/* Indicates if we are building full snapshot or just catalog one. */
bool building_full_snapshot;
/*
* Indicates if we are using the snapshot builder for the creation of a
* logical replication slot. If it's true, the start point for decoding
* changes is not determined yet. So we skip snapshot restores to properly
* find the start point. See SnapBuildFindSnapshot() for details.
*/
bool in_slot_creation;
/*
* Snapshot that's valid to see the catalog state seen at this moment.
*/
@ -317,6 +325,7 @@ AllocateSnapshotBuilder(ReorderBuffer *reorder,
TransactionId xmin_horizon,
XLogRecPtr start_lsn,
bool need_full_snapshot,
bool in_slot_creation,
XLogRecPtr two_phase_at)
{
MemoryContext context;
@ -347,6 +356,7 @@ AllocateSnapshotBuilder(ReorderBuffer *reorder,
builder->initial_xmin_horizon = xmin_horizon;
builder->start_decoding_at = start_lsn;
builder->in_slot_creation = in_slot_creation;
builder->building_full_snapshot = need_full_snapshot;
builder->two_phase_at = two_phase_at;
@ -1327,10 +1337,12 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
* state while waiting on c)'s sub-states.
*
* b) This (in a previous run) or another decoding slot serialized a
* snapshot to disk that we can use. Can't use this method for the
* initial snapshot when slot is being created and needs full snapshot
* for export or direct use, as that snapshot will only contain catalog
* modifying transactions.
* snapshot to disk that we can use. Can't use this method while finding
* the start point for decoding changes as the restart LSN would be an
* arbitrary LSN but we need to find the start point to extract changes
* where we won't see the data for partial transactions. Also, we cannot
* use this method when a slot needs a full snapshot for export or direct
* use, as that snapshot will only contain catalog modifying transactions.
*
* c) First incrementally build a snapshot for catalog tuples
* (BUILDING_SNAPSHOT), that requires all, already in-progress,
@ -1395,8 +1407,13 @@ SnapBuildFindSnapshot(SnapBuild *builder, XLogRecPtr lsn, xl_running_xacts *runn
return false;
}
/* b) valid on disk state and not building full snapshot */
/*
* b) valid on disk state and while neither building full snapshot nor
* creating a slot.
*/
else if (!builder->building_full_snapshot &&
!builder->in_slot_creation &&
SnapBuildRestore(builder, lsn))
{
/* there won't be any state to cleanup */
@ -1580,7 +1597,7 @@ typedef struct SnapBuildOnDisk
offsetof(SnapBuildOnDisk, version)
#define SNAPBUILD_MAGIC 0x51A1E001
#define SNAPBUILD_VERSION 5
#define SNAPBUILD_VERSION 6
/*
* Store/Load a snapshot from disk, depending on the snapshot builder's state.