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
Expose sequence page LSN via pg_get_sequence_data.
This patch enhances the pg_get_sequence_data function to include the
page-level LSN (Log Sequence Number) of the sequence. This additional
metadata will be used by upcoming patches to support synchronization
of sequences during logical replication
Fix Coverity issue reported in commit 2273fa32bce.
Coverity complains that the return value from gettuple_eval_partition
(stored in variable "datum") in a do..while loop in
WinGetFuncArgInPartition is overwritten when exiting the while
loop. This commit tries to fix the issue by changing the
gettu
Fix two typos in xlogstats.h and xlogstats.c
Issue found while browsing this area of the code, introduced and
copy-pasted around by 2258e76f90bf.
Backpatch-through: 15
Branch
--
REL_17_STABLE
Details
---
https://git.postgresql.org/pg/commitdiff/ede2f6b893219296d953177de11df4f43a593e81
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
pgstattuple: Improve reports generated for indexes (hash, gist, btree)
pgstattuple checks the state of the pages retrieved for gist and hash
using some check functions from each index AM, respectively
gistcheckpage() and _hash_checkpage(). When these are called, they
would fail when bumping on da
Cleanup VACUUM option processing error messages
The processing of the PARALLEL option for VACUUM was not quite
following what the DefElem code had intended. defGetInt32() already has
code to handle missing parameters and returns a perfectly good error
message for when that happens.
Here we get r
Fix lookups in pg_{clear,restore}_{attribute,relation}_stats().
Presently, these functions look up the relation's OID, lock it, and
then check privileges. Not only does this approach provide no
guarantee that the locked relation matches the arguments of the
lookup, but it also allows users to bri
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
dblink: Avoid locking relation before privilege check.
The present coding of dblink's get_rel_from_relname() predates the
introduction of RangeVarGetRelidExtended(), which provides a way to
check permissions before locking the relation. This commit adjusts
get_rel_from_relname() to use that funct
Allow private state in certain planner data structures.
Extension that make extensive use of planner hooks may want to
coordinate their efforts, for example to avoid duplicate computation,
but that's currently difficult because there's no really good way to
pass data between different hooks.
To m
Add pg_database_locale() to retrieve database default locale.
Reviewed-by: Peter Eisentraut
Discussion:
https://postgr.es/m/[email protected]
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/e533524b23b8dd504d38c09c9f84b3828
Add pg_iswxdigit(), useful for tsearch.
Reviewed-by: Peter Eisentraut
Discussion:
https://postgr.es/m/[email protected]
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/67a8b49e96caf0782b556521c8d6650e78f2d88e
Modified File
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
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
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
Allow role created by new test to log in on Windows.
We must tell init about each role name we plan to connect as,
else SSPI auth fails. Similar to previous patches such as
14793f471, 973542866.
Oversight in 208927e65, per buildfarm member drongo.
(Although that was back-patched to v13, the test
Allow role created by new test to log in on Windows.
We must tell init about each role name we plan to connect as,
else SSPI auth fails. Similar to previous patches such as
14793f471, 973542866.
Oversight in 208927e65, per buildfarm member drongo.
(Although that was back-patched to v13, the test
Allow role created by new test to log in on Windows.
We must tell init about each role name we plan to connect as,
else SSPI auth fails. Similar to previous patches such as
14793f471, 973542866.
Oversight in 208927e65, per buildfarm member drongo.
(Although that was back-patched to v13, the test
Allow role created by new test to log in on Windows.
We must tell init about each role name we plan to connect as,
else SSPI auth fails. Similar to previous patches such as
14793f471, 973542866.
Oversight in 208927e65, per buildfarm member drongo.
(Although that was back-patched to v13, the test
Add extension_state member to PlannedStmt.
Extensions can stash data computed at plan time into this list using
planner_shutdown_hook (or perhaps other mechanisms) and then access
it from any code that has access to the PlannedStmt (such as explain
hooks), allowing for extensible debugging and ins
Improve planner's width estimates for set operations
For UNION, EXCEPT and INTERSECT, we were not very good at estimating the
PathTarget.width for the set operation. Since the targetlist of the set
operation is made up of Vars with varno==0, this would result in
get_expr_width() applying a defaul
Implement Eager Aggregation
Eager aggregation is a query optimization technique that partially
pushes aggregation past a join, and finalizes it once all the
relations are joined. Eager aggregation may reduce the number of
input rows to the join and thus could result in a better overall plan.
In
pgbench: Fix error reporting in readCommandResponse().
pgbench uses readCommandResponse() to process server responses.
When readCommandResponse() encounters an error during a call to
PQgetResult() to fetch the current result, it attempts to report it
with an additional error message from PQerrorMe
ecpg: check return value of replace_variables()
The function returns false if it fails to allocate memory, so
make sure to check the return value in callsites.
Author: Aleksander Alekseev
Reviewed-by: Daniel Gustafsson
Discussion:
https://postgr.es/m/caj7c6tnpru8zxgdfn3pygy1tzo0bgszx+kkqw0z7zt
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
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:
Tidyup truncate_useless_pathkeys() function
This removes a few static functions and replaces them with 2 functions
which aim to be more reusable. The upper planner's pathkey requirements
can be simplified down to operations which require pathkeys in the same
order as the pathkeys for the given op
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
Fix issue with reading zero bytes in Gzip_read.
pg_dump expects a read request of zero bytes to be a no-op; see for
example ReadStr(). Gzip_read got this wrong and falsely supposed
that the resulting gzret == 0 indicated an error. We could complicate
that error-checking logic some more, but it s
Don't include execnodes.h in replication/conflict.h
... which silently propagates a lot of headers into many places
via pgstat.h, as evidenced by the variety of headers that this patch
needs to add to seemingly random places. Add a minimum of typedefs to
conflict.h to be able to remove execnodes.
Change reset_extra into a config_generic common field
This is not specific to the GUC parameter type, so it can be part of
the generic struct rather than the type-specific struct (like the
related "extra" field). This allows for some code simplifications.
Reviewed-by: Chao Li
Discussion:
https
Add test for pg_stat_reset_single_table_counters() on index
stats.sql is already doing some tests coverage on index statistics, by
retrieving for example idx_scan and friends in pg_stat_all_tables.
pg_stat_reset_single_table_counters() is supported for an index for a
long time, but the case was ne
Consistently handle tab delimiters for wait event names
Format validation and element extraction for intermediate line
strings were inconsistent in their handling of tab delimiters,
which resulted in an unclear error when multiple tab characters
were used as a delimiter. This fixes it by using ca
> On 22 Sep 2025, at 10:17, Daniel Gustafsson
> wrote:
>
> doc: Remove trailing whitespace in xref
>
> Remove stray whitespace in xref tag.
>
> This was found due to a regression in xmllint 2.15.0 which flagged
> this as an error, and at the time of this commit no fix for xmllint
> has shipped
Fix two typos in xlogstats.h and xlogstats.c
Issue found while browsing this area of the code, introduced and
copy-pasted around by 2258e76f90bf.
Backpatch-through: 15
Branch
--
REL_16_STABLE
Details
---
https://git.postgresql.org/pg/commitdiff/fa30f0cb06a184d13078832efc0052b9792de6f8
Fix two typos in xlogstats.h and xlogstats.c
Issue found while browsing this area of the code, introduced and
copy-pasted around by 2258e76f90bf.
Backpatch-through: 15
Branch
--
REL_15_STABLE
Details
---
https://git.postgresql.org/pg/commitdiff/5bc057d1f3afe6f6f0d902e3da89aa3770c79ceb
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
On Thu, Oct 16, 2025 at 2:03 PM Amit Langote wrote:
> Fix EPQ crash from missing partition directory in EState
>
> EvalPlanQualStart() failed to propagate es_partition_directory into
> the child EState used for EPQ rechecks. When execution time partition
> pruning ran during the EPQ scan, executor
Fix two comments in numeric.c
The comments at the top of numeric_int4_safe() and numeric_int8_safe()
mentioned respectively int4_numeric() and int8_numeric(). The intention
is to refer to numeric_int4() and numeric_int8().
Oversights in 4246a977bad6.
Reported-by: jian he
Discussion:
https://p
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
Revert "pg_createsubscriber: Add log message when no publications exist to
drop."
This reverts commit 74ac377d75135e02064fc4427bec401277b4f60c.
The previous change contained a misconception about how publications
are cleaned up on the subscriber. The newly added log message could
confuse users,
Add helper for freeze determination to heap_page_prune_and_freeze
After scanning the line pointers on a heap page during the first phase
of vacuum, we use the information collected to decide whether to use
the assembled freeze plans.
Move this decision logic into a helper function to improve read
Add log_autoanalyze_min_duration
The log output functionality of log_autovacuum_min_duration applies to
both VACUUM and ANALYZE, so it is not possible to separate the VACUUM
and ANALYZE log output thresholds. Logs are likely to be output only for
VACUUM and not for ANALYZE.
Therefore, we decided
Optimize hex_encode() and hex_decode() using SIMD.
The hex_encode() and hex_decode() functions serve as the workhorses
for hexadecimal data for bytea's text format conversion functions,
and some workloads are sensitive to their performance. This commit
adds new implementations that use routines f
Fix comment in eager_aggregate.sql
The comment stated that eager aggregation is disabled by default,
which is no longer true. This patch removes that comment as well as
the related GUC set statement.
Reported-by: David Rowley
Discussion:
https://postgr.es/m/caaphdvr4ywpimr3rsgywjwv-u8xorqtakri
docs: Fix protocol version 3.2 message format of CancelRequest
Since protocol version 3.2 the CancelRequest does not have a fixed size
length anymore. The protocol docs still listed the length field to be a
constant number though. This fixes that.
Author: Jelte Fennema-Nio
Reported-by: Dmitry Ig
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 matching check in recovery test 042_low_level_backup
042_low_level_backup compared the result of a query two times with a
comparison operator based on an integer, while the result should be
compared with a string.
The outcome of the tests is currently not impacted by this change.
However, it
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
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:
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
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
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 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
Adjust new TAP test to work on macOS.
Seems Apple's version of "wc -l" puts spaces before the number.
(I wonder why the cfbot didn't find this.) While here, make
the failure case log what it got, to aid debugging future issues.
Per buildfarm.
Branch
--
master
Details
---
https://git.po
Use designated initializers for guc_tables
This makes the generating script simpler and the output easier to
read. In the future, it will make it easier to reorder and rearrange
the underlying C structures.
Reviewed-by: Chao Li
Discussion:
https://www.postgresql.org/message-id/flat/8fdfb91e-60
pg_regc_locale.c: rename some static functions.
Use the more specific prefix "regc_" rather than the generic prefix
"pg_".
A subsequent commit will create generic versions of some of these
functions that can be called from other modules.
Discussion:
https://postgr.es/m/0151ad01239e2cc7b31396443
Hi!
On 15.09.2022 06:52, John Naylor wrote:
On Thu, Sep 15, 2022 at 4:04 AM Andres Freund wrote:
The most general solution I can see would be
diff --git i/src/backend/common.mk w/src/backend/common.mk
index fa96a82b1a0..61861f5c7eb 100644
--- i/src/backend/common.mk
+++ w/src/backend/common.
Fix EPQ crash from missing partition directory in EState
EvalPlanQualStart() failed to propagate es_partition_directory into
the child EState used for EPQ rechecks. When execution time partition
pruning ran during the EPQ scan, executor code dereferenced a NULL
partition directory and crashed.
Pr
Fix matching check in recovery test 042_low_level_backup
042_low_level_backup compared the result of a query two times with a
comparison operator based on an integer, while the result should be
compared with a string.
The outcome of the tests is currently not impacted by this change.
However, it
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 determination of not-null constraint "locality" for inherited columns
It is possible to have a non-inherited not-null constraint on an
inherited column, but we were failing to preserve such constraints
during pg_upgrade where the source is 17 or older, because of a bug in
the pg_dump query for
Fix determination of not-null constraint "locality" for inherited columns
It is possible to have a non-inherited not-null constraint on an
inherited column, but we were failing to preserve such constraints
during pg_upgrade where the source is 17 or older, because of a bug in
the pg_dump query for
Fix determination of not-null constraint "locality" for inherited columns
It is possible to have a non-inherited not-null constraint on an
inherited column, but we were failing to preserve such constraints
during pg_upgrade where the source is 17 or older, because of a bug in
the pg_dump query for
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
Fix pg_dump sorting of foreign key constraints
Apparently, commit 04bc2c42f765 failed to notice that DO_FK_CONSTRAINT
objects require identical handling as DO_CONSTRAINT ones, which causes
some pg_upgrade tests in debug builds to fail spuriously. Add that.
Author: Álvaro Herrera
Backpatch-throu
Fix pg_dump sorting of foreign key constraints
Apparently, commit 04bc2c42f765 failed to notice that DO_FK_CONSTRAINT
objects require identical handling as DO_CONSTRAINT ones, which causes
some pg_upgrade tests in debug builds to fail spuriously. Add that.
Author: Álvaro Herrera
Backpatch-throu
Fix pg_dump sorting of foreign key constraints
Apparently, commit 04bc2c42f765 failed to notice that DO_FK_CONSTRAINT
objects require identical handling as DO_CONSTRAINT ones, which causes
some pg_upgrade tests in debug builds to fail spuriously. Add that.
Author: Álvaro Herrera
Backpatch-throu
Assign each subquery a unique name prior to planning it.
Previously, subqueries were given names only after they were planned,
which makes it difficult to use information from a previous execution of
the query to guide future planning. If, for example, you knew something
about how you want "InitPl
Remove preprocessor guards from injection points
When defining an injection point there is no need to wrap the definition
with USE_INJECTION_POINT guards, the INJECTION_POINT macro is available
in all builds. Remove to make the code consistent.
Author: Hayato Kuroda
Reviewed-by: Michael Paquier
Fix pg_dump sorting of foreign key constraints
Apparently, commit 04bc2c42f765 failed to notice that DO_FK_CONSTRAINT
objects require identical handling as DO_CONSTRAINT ones, which causes
some pg_upgrade tests in debug builds to fail spuriously. Add that.
Author: Álvaro Herrera
Backpatch-throu
Fix pg_dump sorting of foreign key constraints
Apparently, commit 04bc2c42f765 failed to notice that DO_FK_CONSTRAINT
objects require identical handling as DO_CONSTRAINT ones, which causes
some pg_upgrade tests in debug builds to fail spuriously. Add that.
Author: Álvaro Herrera
Backpatch-throu
Fix pg_dump sorting of foreign key constraints
Apparently, commit 04bc2c42f765 failed to notice that DO_FK_CONSTRAINT
objects require identical handling as DO_CONSTRAINT ones, which causes
some pg_upgrade tests in debug builds to fail spuriously. Add that.
Author: Álvaro Herrera
Backpatch-throu
Fix pg_dump sorting of foreign key constraints
Apparently, commit 04bc2c42f765 failed to notice that DO_FK_CONSTRAINT
objects require identical handling as DO_CONSTRAINT ones, which causes
some pg_upgrade tests in debug builds to fail spuriously. Add that.
Author: Álvaro Herrera
Backpatch-throu
Use ereport rather than elog in WinCheckAndInitializeNullTreatment.
Previously WinCheckAndInitializeNullTreatment() used elog() to emit an
error message. ereport() should be used instead because it's a
user-facing error. Also use existing get_func_name() to get a
function's name, rather than own i
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 LOCK_TIMEOUT handling during parallel apply.
Previously, the parallel apply worker used SIGINT to receive a graceful
shutdown signal from the leader apply worker. However, SIGINT is also used
by the LOCK_TIMEOUT handler to trigger a query-cancel interrupt. This
overlap caused the parallel appl
Align the data block sizes of pg_dump's various compression modes.
After commit fe8192a95, compress_zstd.c tends to produce data block
sizes around 128K, and we don't really have any control over that
unless we want to overrule ZSTD_CStreamOutSize(). Which seems like
a bad idea. But let's try to
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
Add stats_reset to pg_stat_all_{tables,indexes} and related views
It is possible to call pg_stat_reset_single_table_counters() on a
relation (index or table) but the reset time was missing from the system
views showing their statistics.
This commit adds the reset time as an attribute of pg_stat_a
Override log_error_verbosity to "default" in test 009_log_temp_files
Per report from buildfarm member prion. The CI does not use this
parameter, and this buildfarm member sets log_error_verbosity to
"verbose". This would generate extra LOCATION entries in the logs,
causing the regexps of the tes
dbase_redo: Fix Valgrind-reported memory leak
Introduced by my (Álvaro's) commit 9e4f914b5eba, which was itself
backpatched to pg10, though only pg15 and up contain the problem
because of commit 9c08aea6a309.
This isn't a particularly significant leak, but given the fix is
trivial, we might as we
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
bufmgr: Don't lock buffer header in StrategyGetBuffer()
Previously StrategyGetBuffer() acquired the buffer header spinlock for every
buffer, whether it was reusable or not. If reusable, it'd be returned, with
the lock held, to GetVictimBuffer(), which then would pin the buffer with
PinBuffer_Locke
Avoid unnecessary GinFormTuple() calls for incompressible posting lists.
Previously, we attempted to form a posting list tuple even when
ginCompressPostingList() failed to compress the posting list due to
its size. While there was no functional failure, it always wasted one
GinFormTuple() call whe
dbase_redo: Fix Valgrind-reported memory leak
Introduced by my (Álvaro's) commit 9e4f914b5eba, which was itself
backpatched to pg10, though only pg15 and up contain the problem
because of commit 9c08aea6a309.
This isn't a particularly significant leak, but given the fix is
trivial, we might as we
Fix issue with reading zero bytes in Gzip_read.
pg_dump expects a read request of zero bytes to be a no-op; see for
example ReadStr(). Gzip_read got this wrong and falsely supposed
that the resulting gzret == 0 indicated an error. We could complicate
that error-checking logic some more, but it s
Stamp 18.0.
Branch
--
REL_18_STABLE
Details
---
https://git.postgresql.org/pg/commitdiff/3d6a828938a5fa0444275d3d2f67b64ec3199eb7
Modified Files
--
configure| 18 +-
configure.ac | 2 +-
meson.build | 2 +-
3 files changed, 11 insertions(+), 11 deletions(-
Correct prune WAL record opcode name in comment
f83d709760d8 incorrectly refers to a XLOG_HEAP2_PRUNE_FREEZE WAL record
opcode. No such code exists. The relevant opcodes are
XLOG_HEAP2_PRUNE_ON_ACCESS, XLOG_HEAP2_PRUNE_VACUUM_SCAN, and
XLOG_HEAP2_PRUNE_VACUUM_CLEANUP. Correct it.
Author: Melanie
Remove unused nbtree array advancement variable.
Remove a variable that is no longer in use following commit 9a2e2a28.
It's not immediately clear why there were no compiler warnings about
this oversight.
Author: Peter Geoghegan
Backpatch-through: 18
Branch
--
REL_18_STABLE
Details
---
Add mem_exceeded_count column to pg_stat_replication_slots.
This commit introduces a new column mem_exceeded_count to the
pg_stat_replication_slots view. This counter tracks how often the
memory used by logical decoding exceeds the logical_decoding_work_mem
limit. The new statistic helps users det
Add support for tracking of entry count in pgstats
Stats kinds can set a new option called "track_entry_count" (disabled by
default, available for variable-numbered stats) that will make pgstats
track the number of entries that exist in its shared hashtable.
As there is only one code path where a
Inline TransactionIdFollows/Precedes[OrEquals]()
These functions appeared prominently in a profile of a patch that sets
the visibility map on-access. Inline them to remove call overhead and
make them cheaper to use in hot paths.
Author: Melanie Plageman
Reviewed-by: Kirill Reshke
Reviewed-by: A
Remove unnecessary include of "utils/fmgroids.h"
In initsplan.c, no macros for built-in function OIDs are used, so this
include is unnecessary and can be removed. This was my oversight in
commit 8e1185910.
Discussion:
https://postgr.es/m/CAMbWs4_-sag-cAKrLJ+X+5njL1=oudk=+KfLmsLZ5a2jckn=k...@mai
Use bms_add_members() instead of bms_union() when possible
bms_union() causes a new set to be allocated. What this caller needs is
members added to an existing set. bms_add_members() is the tool for
that job.
This is just a matter of fixing an inefficiency due to surplus memory
allocations. No
Fix incorrect targetlist in dummy UNIONs
The prior code, added in 03d40e4b5 attempted to use the targetlist of the
first UNION child when all UNION children were proven as dummy rels.
That's not going to work when some operation atop of the Result node must
find target entries within the Result's
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
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
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
1 - 100 of 141 matches
Mail list logo
