database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-09 22:41:56 +03:00
Code Activity

Fix multiple crasher bugs in partitioned-table replication logic.

Browse Source 
apply_handle_tuple_routing(), having detected and reported that
the tuple it needed to update didn't exist, tried to update that
tuple anyway, leading to a null-pointer dereference.

logicalrep_partition_open() failed to ensure that the
LogicalRepPartMapEntry it built for a partition was fully
independent of that for the partition root, leading to
trouble if the root entry was later freed or rebuilt.

Meanwhile, on the publisher's side, pgoutput_change() sometimes
attempted to apply execute_attr_map_tuple() to a NULL tuple.

The first of these was reported by Sergey Bernikov in bug #17055;
I found the other two while developing some test cases for this
sadly under-tested code.

Diagnosis and patch for the first issue by Amit Langote; patches
for the others by me; new test cases by me.  Back-patch to v13
where this logic came in.

Discussion: https://postgr.es/m/17055-9ba800ec8522668b@postgresql.org
This commit is contained in:
Tom Lane
2021-06-11 16:12:36 -04:00
parent 4efcf47053
commit ab55d742eb
5 changed files with 146 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/backend/replication/logical/relation.c
View File

@ -620,7 +620,9 @@ logicalrep_partmap_init(void)
* logicalrep_partition_open
*
* Returned entry reuses most of the values of the root table's entry, save
* the attribute map, which can be different for the partition.
* the attribute map, which can be different for the partition. However,
* we must physically copy all the data, in case the root table's entry
* gets freed/rebuilt.
*
* Note there's no logicalrep_partition_close, because the caller closes the
* component relation.
@ -656,7 +658,7 @@ logicalrep_partition_open(LogicalRepRelMapEntry *root,
part_entry->partoid = partOid;
/* Remote relation is used as-is from the root entry. */
/* Remote relation is copied as-is from the root entry. */
entry = &part_entry->relmapentry;
entry->remoterel.remoteid = remoterel->remoteid;
entry->remoterel.nspname = pstrdup(remoterel->nspname);
@ -699,7 +701,12 @@ logicalrep_partition_open(LogicalRepRelMapEntry *root,
}
}
else
entry->attrmap = attrmap;
{
/* Lacking copy_attmap, do this the hard way. */
entry->attrmap = make_attrmap(attrmap->maplen);
memcpy(entry->attrmap->attnums, attrmap->attnums,
attrmap->maplen * sizeof(AttrNumber));
}
entry->updatable = root->updatable;

48
src/backend/replication/logical/worker.c
View File

@ -1477,12 +1477,13 @@ apply_handle_update_internal(ApplyExecutionData *edata,
else
{
/*
* The tuple to be updated could not be found.
* The tuple to be updated could not be found. Do nothing except for
* emitting a log message.
*
* TODO what to do here, change the log level to LOG perhaps?
* XXX should this be promoted to ereport(LOG) perhaps?
*/
elog(DEBUG1,
"logical replication did not find row for update "
"logical replication did not find row to be updated "
"in replication target relation \"%s\"",
RelationGetRelationName(localrel));
}
@ -1589,9 +1590,14 @@ apply_handle_delete_internal(ApplyExecutionData *edata,
}
else
{
/* The tuple to be deleted could not be found. */
/*
* The tuple to be deleted could not be found. Do nothing except for
* emitting a log message.
*
* XXX should this be promoted to ereport(LOG) perhaps?
*/
elog(DEBUG1,
"logical replication did not find row for delete "
"logical replication did not find row to be deleted "
"in replication target relation \"%s\"",
RelationGetRelationName(localrel));
}
@ -1728,30 +1734,30 @@ apply_handle_tuple_routing(ApplyExecutionData *edata,
found = FindReplTupleInLocalRel(estate, partrel,
&part_entry->remoterel,
remoteslot_part, &localslot);
oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
if (found)
{
/* Apply the update. */
slot_modify_data(remoteslot_part, localslot,
part_entry,
newtup);
MemoryContextSwitchTo(oldctx);
}
else
if (!found)
{
/*
* The tuple to be updated could not be found.
* The tuple to be updated could not be found. Do nothing
* except for emitting a log message.
*
* TODO what to do here, change the log level to LOG
* perhaps?
* XXX should this be promoted to ereport(LOG) perhaps?
*/
elog(DEBUG1,
"logical replication did not find row for update "
"in replication target relation \"%s\"",
"logical replication did not find row to be updated "
"in replication target relation's partition \"%s\"",
RelationGetRelationName(partrel));
return;
}
/*
* Apply the update to the local tuple, putting the result in
* remoteslot_part.
*/
oldctx = MemoryContextSwitchTo(GetPerTupleMemoryContext(estate));
slot_modify_data(remoteslot_part, localslot, part_entry,
newtup);
MemoryContextSwitchTo(oldctx);
/*
* Does the updated tuple still satisfy the current
* partition's constraint?

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

@ -612,8 +612,11 @@ pgoutput_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn,
/* Convert tuples if needed. */
if (relentry->map)
{
oldtuple = execute_attr_map_tuple(oldtuple, relentry->map);
newtuple = execute_attr_map_tuple(newtuple, relentry->map);
if (oldtuple)
oldtuple = execute_attr_map_tuple(oldtuple,
relentry->map);
newtuple = execute_attr_map_tuple(newtuple,
relentry->map);
}
}