Add pg_iswalpha() and related functions.
Per-character pg_locale_t APIs. Useful for tsearch parsing and
potentially other places.
Significant overlap with the regc_wc_isalpha() and related functions
in regc_pg_locale.c, but this change leaves those intact for
now.
Discussion:
https://postgr.es/
Fix lookup code for REINDEX INDEX.
This commit adjusts RangeVarCallbackForReindexIndex() to handle an
extremely unlikely race condition involving concurrent OID reuse.
In short, if REINDEX INDEX is executed at the same time that the
index is re-created with the same name and OID but a different
pa
John Naylor writes:
> On Wed, Oct 15, 2025 at 2:49 PM Anton A. Melnikov
> wrote:
>> Maybe backpatch [2] to all supported versions not just 16+?
> That only changed src/backend/common.mk, so that's not going to affect
> contrib. I looked, and contrib/contrib-global.mk doesn't have any
> extra *.b
Fix reset of incorrect hash iterator in GROUPING SETS queries
This fixes an unlikely issue when fetching GROUPING SET results from
their internally stored hash tables. It was possible in rare cases that
the hash iterator would be set up incorrectly which could result in a
crash.
This was introdu
bufmgr: fewer calls to BufferDescriptorGetContentLock
We're planning to merge buffer content locks into BufferDesc.state. To reduce
the size of that patch, centralize calls to BufferDescriptorGetContentLock().
The biggest part of the change is in assertions, by introducing
BufferIsLockedByMe[InMo
Improve ReadRecentBuffer() scalability
While testing a new potential use for ReadRecentBuffer(), Andres
reported that it scales badly when called concurrently for the same
buffer by many backends. Instead of a naive (but wrong) coding with
PinBuffer(), it used the spinlock, so that it could be ca
Fix incorrect message-printing in win32security.c.
log_error() would probably fail completely if used, and would
certainly print garbage for anything that needed to be interpolated
into the message, because it was failing to use the correct printing
subroutine for a va_list argument.
This bug lik
pgbench: Fix assertion failure with retriable errors in pipeline mode.
When running pgbench with --verbose-errors option and a custom script that
triggered retriable errors (e.g., serialization errors) in pipeline mode,
an assertion failure could occur:
Assertion failed: (sql_script[st->use_f
Fix redefinition of typedef RangeVar.
Commit c8af5019be added a forward declaration for this typedef that
caused redefinitions, which are not valid in C99.
Per buildfarm members longfin and sifaka.
Discussion: https://postgr.es/m/aO_fzfnKVXMd_RUM%40nathan
Backpatch-through: 18 only
Branch
-
Fix EvalPlanQual handling of foreign/custom joins in ExecScanFetch.
If inside an EPQ recheck, ExecScanFetch would run the recheck method
function for foreign/custom joins even if they aren't descendant nodes
in the EPQ recheck plan tree, which is problematic at least in the
foreign-join case, beca
plpython: Remove support for major version conflict detection
This essentially reverts commit 866566a690b, which installed
safeguards against loading plpython2 and plpython3 into the same
process. We don't support plpython2 anymore, so this is obsolete.
The Python and PL/Python initialization no
Use SOCK_ERRNO[_SET] in fe-secure-gssapi.c.
On Windows, this code did not handle error conditions correctly at
all, since it looked at "errno" which is not used for socket-related
errors on that platform. This resulted, for example, in failure
to connect to a PostgreSQL server with GSSAPI enabled
Fix version number calculation for data folder flush in pg_combinebackup
The version number calculated by read_pg_version_file() is multiplied
once by 1, to be able to do comparisons based on PG_VERSION_NUM or
equivalents with a minor version included. However, the version number
given sync_p
pg_createsubscriber: Use new routine to retrieve data of PG_VERSION
pg_createsubscriber is documented as requiring the same major version as
the target clusters. Attempting to use this tool on a cluster where the
control file version read does not match with the version compiled with
would lead t
Fix access-to-already-freed-memory issue in pgoutput.
While pgoutput caches relation synchronization information in
RelationSyncCache that resides in CacheMemoryContext, each entry's
information (such as row filter expressions and column lists) is
stored in the entry's private memory context (entr
Generate EUC_CN mappings from gb18030-2022.ucm
In the wake of cfa6cd292, EUC_CN was the only encoding that used
gb-18030-2000.xml to generate the .map files. Since EUC_CN is a subset
of GB18030, we can easily use the same UCM file. This allows deleting
the XML file from our repository.
Author: Ch
injection_points: Enable entry count in its variable-sized stats
This serves as coverage for the tracking of entry count added by
7bd2975fa92b as built-in variable-sized stats kinds have no need for it,
at least not yet.
A new function, called injection_points_stats_count(), is added to the
modul
Fix incorrect and inconsistent comments in tableam.h and heapam.c.
This commit corrects several issues in function comments:
* The parameter "rel" was incorrectly referred to as "relation" in the comments
for table_tuple_delete(), table_tuple_update(), and table_tuple_lock().
* In table_tuple_
test_bitmapset: Simplify code of the module
Two macros are added in this module, to cut duplicated patterns:
- PG_ARG_GETBITMAPSET(), for input argument handling, with knowledge
about NULL.
- PG_RETURN_BITMAPSET_AS_TEXT(), that generates a text result from a
Bitmapset.
These changes limit the cod
Add planner_setup_hook and planner_shutdown_hook.
These hooks allow plugins to get control at the earliest point at
which the PlannerGlobal object is fully initialized, and then just
before it gets destroyed. This is useful in combination with the
extendable plan state facilities (see extendplan.h
Remove block information from description of some WAL records for GIN
The WAL records XLOG_GIN_INSERT and XLOG_GIN_VACUUM_DATA_LEAF_PAGE
included some information about the blocks added to the record.
This information is already provided by XLogRecGetBlockRefInfo() with
much more details about th
test_bitmapset: Expand more the test coverage
This commit expands the set of tests added by 00c3d87a5cab, to bring the
coverage of bitmapset.c close to 100% by addressing a lot of corner
cases (most of these relate to word counts and reallocations).
Some of the functions of this module also have
Fix privilege checks for pg_prewarm() on indexes.
pg_prewarm() currently checks for SELECT privileges on the target
relation. However, indexes do not have access rights of their own,
so a role may be denied permission to prewarm an index despite
having the SELECT privilege on its parent table. T
Don't include execnodes.h in brin.h or gin.h
These headers don't need execnodes.h for anything. I think they never
have.
Discussion: https://postgr.es/m/[email protected]
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/1b6f61bd89889f70465600
pg_createsubscriber: Fix matching check in TAP test
040_pg_createsubscriber has been calling safe_psql(), that returns the
result of a SQL query, with ok() without checking the result generated
(in this case 't', for a number of publications).
The outcome of the tests is currently not impacted by
Replace defunct URL with stable archive.org URL in rbtree.c
The URL for "Sorting and Searching Algorithms: A Cookbook"
by Thomas Niemann has started returning 404, and since we
refer to the page for license terms this replaces the now
defunct link with one to the copy on archive.org.
Author: Chao
Remove duplicated log related to slot creation in pg_createsubscriber
The creation of a replication slot done in a specific database on a
publisher was logged twice, with the second log not mentioning the
database where the slot creation happened. This commit removes the
information logged after
Fix access-to-already-freed-memory issue in pgoutput.
While pgoutput caches relation synchronization information in
RelationSyncCache that resides in CacheMemoryContext, each entry's
information (such as row filter expressions and column lists) is
stored in the entry's private memory context (entr
Remove partColsUpdated.
This information appears to have been unused since commit
c5b7ba4e67. We could not find any references in third-party code,
either.
Reviewed-by: Chao Li
Reviewed-by: Tom Lane
Reviewed-by: Michael Paquier
Discussion: https://postgr.es/m/aO_CyFRpbVMtgJWM%40nathan
Branch
Fix internal error from CollateExpr in SQL/JSON DEFAULT expressions
SQL/JSON functions such as JSON_VALUE could fail with "unrecognized
node type" errors when a DEFAULT clause contained an explicit COLLATE
expression. That happened because assign_collations_walker() could
invoke exprSetCollation()
Fix EvalPlanQual handling of foreign/custom joins in ExecScanFetch.
If inside an EPQ recheck, ExecScanFetch would run the recheck method
function for foreign/custom joins even if they aren't descendant nodes
in the EPQ recheck plan tree, which is problematic at least in the
foreign-join case, beca
pg_createsubscriber: Add log message when no publications exist to drop.
When specifying --clean=publication to pg_createsubscriber, it drops
all existing publications with a log message "dropping all existing
publications in database "testdb"". Add a new log message "no
publications found" when t
Fix incorrect message-printing in win32security.c.
log_error() would probably fail completely if used, and would
certainly print garbage for anything that needed to be interpolated
into the message, because it was failing to use the correct printing
subroutine for a va_list argument.
This bug lik
Remove overzealous _bt_killitems assertion.
An assertion in _bt_killitems expected the scan's currPos state to
contain a valid LSN, saved from when currPos's page was initially read.
The assertion failed to account for the fact that even logged relations
can have leaf pages with an invalid LSN whe
Fix reset of incorrect hash iterator in GROUPING SETS queries
This fixes an unlikely issue when fetching GROUPING SET results from
their internally stored hash tables. It was possible in rare cases that
the hash iterator would be set up incorrectly which could result in a
crash.
This was introdu
Improve TAP tests by replacing ok() with better Test::More functions
Transpose the changes made by commit fabb33b35 in 002_pg_dump.pl
into its recently-created clone 006_pg_dump_compress.pl.
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/a6113dc1dae009a3d9a634d2fcc
Remove state.tmp when failing to save a replication slot
An error happening while a slot data is saved on disk in
SaveSlotToPath() could cause a state.tmp file (temporary file holding
the slot state data, renamed to its permanent name at the end of the
function) to remain around after it has been
Fix StatisticsObjIsVisibleExt() for pg_temp.
Neighbor get_statistics_object_oid() ignores objects in pg_temp, as has
been the standard for non-relation, non-type namespace searches since
CVE-2007-2138. Hence, most operations that name a statistics object
correctly decline to map an unqualified na
Avoid uninitialized-variable warnings from older compilers.
Some of the buildfarm is still unhappy with WinGetFuncArgInPartition
even after 2273fa32b. While it seems to be just very old compilers,
we can suppress the warnings and arguably make the code more readable
by not initializing these vari
Fix privilege checks for pg_prewarm() on indexes.
pg_prewarm() currently checks for SELECT privileges on the target
relation. However, indexes do not have access rights of their own,
so a role may be denied permission to prewarm an index despite
having the SELECT privilege on its parent table. T
Fix privilege checks for pg_prewarm() on indexes.
pg_prewarm() currently checks for SELECT privileges on the target
relation. However, indexes do not have access rights of their own,
so a role may be denied permission to prewarm an index despite
having the SELECT privilege on its parent table. T
Fix privilege checks for pg_prewarm() on indexes.
pg_prewarm() currently checks for SELECT privileges on the target
relation. However, indexes do not have access rights of their own,
so a role may be denied permission to prewarm an index despite
having the SELECT privilege on its parent table. T
Fix privilege checks for pg_prewarm() on indexes.
pg_prewarm() currently checks for SELECT privileges on the target
relation. However, indexes do not have access rights of their own,
so a role may be denied permission to prewarm an index despite
having the SELECT privilege on its parent table. T
Fix privilege checks for pg_prewarm() on indexes.
pg_prewarm() currently checks for SELECT privileges on the target
relation. However, indexes do not have access rights of their own,
so a role may be denied permission to prewarm an index despite
having the SELECT privilege on its parent table. T
Bump XLOG_PAGE_MAGIC after xl_heap_prune change
add323da40a6 altered xl_heap_prune, changing the WAL format, but
neglected to bump XLOG_PAGE_MAGIC. Do so now.
Author: Melanie Plageman
Reported-by: Kirill Reshke
Reported-by: Michael Paquier
Discussion: https://postgr.es/m/aO3Gw6hCAZFUd5ab%40paq
Use SOCK_ERRNO[_SET] in fe-secure-gssapi.c.
On Windows, this code did not handle error conditions correctly at
all, since it looked at "errno" which is not used for socket-related
errors on that platform. This resulted, for example, in failure
to connect to a PostgreSQL server with GSSAPI enabled
Remove unused data_bufsz from DecodedBkpBlock struct.
Author: Mikhail Gribkov
Reviewed-by: Nazir Bilal Yavuz
Discussion:
https://postgr.es/m/CAMEv5_sxuaiAfSy1ZyN%3D7UGbHg3C10cwHhEk8nXEjiCsBVs4vQ%40mail.gmail.com
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/fd5
Improve description of some WAL records for GIN
The following information is added in the description of some GIN
records:
- In INSERT_LISTPAGE, the number of tuples and the right link block.
- In UPDATE_META_PAGE, the number of tuples, the previous tail block,
and the right link block.
- In SPLIT
bufmgr: Fix valgrind checking for buffers pinned in StrategyGetBuffer()
In 5e899859287 I made StrategyGetBuffer() pin buffers with a single CAS,
instead of using PinBuffer_Locked(). Unfortunately I missed that
PinBuffer_Locked() marked the page as defined for valgrind.
Fix this oversight by centr
Fix update-po for the PGXS case
The original formulation failed to take into account the fact that for
the PGXS case, the source dir is not $(top_srcdir), so it ended up not
doing anything. Handle it explicitly.
Author: Ryo Matsumura
Reviewed-by: Bryan Green
Backpatch-through: 13
Discussion:
Fix update-po for the PGXS case
The original formulation failed to take into account the fact that for
the PGXS case, the source dir is not $(top_srcdir), so it ended up not
doing anything. Handle it explicitly.
Author: Ryo Matsumura
Reviewed-by: Bryan Green
Backpatch-through: 13
Discussion:
Fix hashjoin memory balancing logic
Commit a1b4f289beec improved the hashjoin sizing to also consider the
memory used by BufFiles for batches. The code however had multiple
issues, making it ineffective or not working as expected in some cases.
* The amount of memory needed by buffers was calcula
Fix hashjoin memory balancing logic
Commit a1b4f289beec improved the hashjoin sizing to also consider the
memory used by BufFiles for batches. The code however had multiple
issues, making it ineffective or not working as expected in some cases.
* The amount of memory needed by buffers was calcula
Add more TAP test coverage for pg_dump.
Add a test case to cover pg_dump with --compress=none. This
brings the coverage of compress_none.c up from about 64% to 90%,
in particular covering the new code added in a previous patch.
Include compression of toc.dat in manually-compressed test cases.
We
Use SOCK_ERRNO[_SET] in fe-secure-gssapi.c.
On Windows, this code did not handle error conditions correctly at
all, since it looked at "errno" which is not used for socket-related
errors on that platform. This resulted, for example, in failure
to connect to a PostgreSQL server with GSSAPI enabled
Doc: clarify n_distinct_inherited setting
There was some confusion around how to adjust the n_distinct estimates
for partitioned tables. Here we try and clarify that
n_distinct_inherited needs to be adjusted rather than n_distinct.
Also fix some slightly misleading text which was talking about t
pg_createsubscriber: Fix matching check in TAP test
040_pg_createsubscriber has been calling safe_psql(), that returns the
result of a SQL query, with ok() without checking the result generated
(in this case 't', for a number of publications).
The outcome of the tests is currently not impacted by
Use SOCK_ERRNO[_SET] in fe-secure-gssapi.c.
On Windows, this code did not handle error conditions correctly at
all, since it looked at "errno" which is not used for socket-related
errors on that platform. This resulted, for example, in failure
to connect to a PostgreSQL server with GSSAPI enabled
Avoid warnings in tests when openssl binary isn't available
The SSL tests for pg_stat_ssl tries to exactly match the serial
from the certificate by extracting it with the openssl binary.
If that fails due to the binary not being available, a fallback
match is used, but the attempt to execute a mis
Make some use of anonymous unions [DSM registry].
Make some use of anonymous unions, which are allowed as of C11, as
examples and encouragement for future code, and to test compilers.
This commit changes the DSMRegistryEntry struct.
Reviewed-by: Peter Eisentraut
Discussion: https://postgr.es/m/
Stop creating constraints during DETACH CONCURRENTLY
Commit 71f4c8c6f74b (which implemented DETACH CONCURRENTLY) added code
to create a separate table constraint when a table is detached
concurrently, identical to the partition constraint, on the theory that
such a constraint was needed in case th
Englishify comment wording
Switch to using the English word here rather than using a verbified
function name.
The full word still fits within a single comment line, so it's probably
better just to use that instead of trying to shorten it, which might
cause confusion.
Author: Rafia Sabih
Discuss
Fix typo in pgstat_relation.c header comment
Looks like a copy and paste error from pgstat_function.c
Author: Bertrand Drouvot
Discussion:
https://postgr.es/m/[email protected]
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdif
Fix incorrect message-printing in win32security.c.
log_error() would probably fail completely if used, and would
certainly print garbage for anything that needed to be interpolated
into the message, because it was failing to use the correct printing
subroutine for a va_list argument.
This bug lik
Fix StatisticsObjIsVisibleExt() for pg_temp.
Neighbor get_statistics_object_oid() ignores objects in pg_temp, as has
been the standard for non-relation, non-type namespace searches since
CVE-2007-2138. Hence, most operations that name a statistics object
correctly decline to map an unqualified na
Keep track of what RTIs a Result node is scanning.
Result nodes now include an RTI set, which is only non-NULL when they
have no subplan, and is taken from the relid set of the RelOptInfo that
the Result is generating. ExplainPreScanNode now takes notice of these
RTIs, which means that a few thing
Stop creating constraints during DETACH CONCURRENTLY
Commit 71f4c8c6f74b (which implemented DETACH CONCURRENTLY) added code
to create a separate table constraint when a table is detached
concurrently, identical to the partition constraint, on the theory that
such a constraint was needed in case th
Fix EvalPlanQual handling of foreign/custom joins in ExecScanFetch.
If inside an EPQ recheck, ExecScanFetch would run the recheck method
function for foreign/custom joins even if they aren't descendant nodes
in the EPQ recheck plan tree, which is problematic at least in the
foreign-join case, beca
Remove overzealous _bt_killitems assertion.
An assertion in _bt_killitems expected the scan's currPos state to
contain a valid LSN, saved from when currPos's page was initially read.
The assertion failed to account for the fact that even logged relations
can have leaf pages with an invalid LSN whe
Doc: clarify n_distinct_inherited setting
There was some confusion around how to adjust the n_distinct estimates
for partitioned tables. Here we try and clarify that
n_distinct_inherited needs to be adjusted rather than n_distinct.
Also fix some slightly misleading text which was talking about t
Remove overzealous _bt_killitems assertion.
An assertion in _bt_killitems expected the scan's currPos state to
contain a valid LSN, saved from when currPos's page was initially read.
The assertion failed to account for the fact that even logged relations
can have leaf pages with an invalid LSN whe
Improve TAP tests by replacing ok() with better Test::More functions
The TAP tests whose ok() calls are changed in this commit were relying
on perl operators, rather than equivalents available in Test::More. For
example, rather than the following:
ok($data =~ qr/expr/m, "expr matching");
ok($data
doc: Clarify when backend_xmin in pg_stat_replication can be NULL.
Improve the documentation of pg_stat_replication to explain when
the backend_xmin column becomes NULL. This happens when
a replication slot is used (the xmin is then shown in pg_replication_slots)
or when hot_standby_feedback is di
Fix access-to-already-freed-memory issue in pgoutput.
While pgoutput caches relation synchronization information in
RelationSyncCache that resides in CacheMemoryContext, each entry's
information (such as row filter expressions and column lists) is
stored in the entry's private memory context (entr
Make some use of anonymous unions [reorderbuffer xact_time]
Make some use of anonymous unions, which are allowed as of C11, as
examples and encouragement for future code, and to test compilers.
This commit changes the ReorderBufferTXN struct.
Reviewed-by: Chao Li
Discussion:
https://www.postgr
Remove unused parameter from find_window_run_conditions()
... and check_and_push_window_quals().
Similar to 4be9024d5, but it seems there was yet another unused
parameter.
Author: Matheus Alcantara
Discussion: https://postgr.es/m/[email protected]
Branch
--
master
Detai
76 matches
Mail list logo
