| Age | Commit message (Collapse) | Author |
|---|
|
Reported-by: Jelte Fennema-Nio
Discussion: https://postgr.es/m/CAGECzQT4804OLOP+nDBxDpMw3Soq=g+fKOE7NryBHggy4GgEcg@mail.gmail.com
|
|
|
|
With a nod to PG 9.6.
Reported-by: jian he
Discussion: https://postgr.es/m/CACJufxEqs=EXZETwtaOooTFhZrtxvSWg8M2uPfzjNtS3wQ6Dzw@mail.gmail.com
|
|
Reported-by: Jelte Fennema-Nio
Discussion: https://postgr.es/m/CAGECzQSTBgTsDJPxOHWKo7106-YnnYQGzpzNJdis+xTKGUhu2g@mail.gmail.com
|
|
|
|
Reported-by: Jelte Fennema-Nio
Discussion: https://postgr.es/m/CAGECzQQj0r_JX38fa-_kepp9UaMzCcujRAYaJG2+fPks1b8MVg@mail.gmail.com
|
|
Also move ssl_groups to a more appropriate section.
Reported-by: Jacob Champion (ssl_groups item)
Discussion: https://postgr.es/m/CAOYmi+k_zpGaDOrwV46_j-O-a_hSWxcXM6h8vccq45Y28deP-g@mail.gmail.com
|
|
It's --auto-features not --auto_features.
Reported-by: Egor Chindyaskin <[email protected]>
Discussion: https://postgr.es/m/[email protected]
Discussion: https://postgr.es/m/[email protected]
Backpatch-through: 16
|
|
The extension_control_path setting (commit 4f7f7b03758) did not
support extensions that set a custom "directory" setting in their
control file. Very few extensions use that and during the discussion
on the previous commit it was suggested to maybe remove that
functionality. But a fix was easier than initially thought, so this
just adds that support. The fix is to use the control->control_dir as
a share dir to return the path of the extension script files.
To make this work more sensibly overall, the directory suffix
"extension" is no longer to be included in the extension_control_path
value. To quote the patch, it would be
-extension_control_path = '/usr/local/share/postgresql/extension:/home/my_project/share/extension:$system'
+extension_control_path = '/usr/local/share/postgresql:/home/my_project/share:$system'
During the initial patch, there was some discussion on which of these
two approaches would be better, and the committed patch was a 50/50
decision. But the support for the "directory" setting pushed it the
other way, and also it seems like many people didn't like the previous
behavior much.
Author: Matheus Alcantara <[email protected]>
Reviewed-by: Christoph Berg <[email protected]>
Reviewed-by: David E. Wheeler <[email protected]>
Discussion: https://www.postgresql.org/message-id/flat/aAi1VACxhjMhjFnb%40msg.df7cb.de#0cdf7b7d727cc593b029650daa3c4fbc
|
|
|
|
SQL "SET search_path = 'pg_catalog, pg_temp'" is silently equivalent to
"SET search_path = pg_temp, pg_catalog, "pg_catalog, pg_temp"" instead
of the intended "SET search_path = pg_catalog, pg_temp". (The intent
was a two-element search path. With the single quotes, it instead
specifies one element with a comma and a space in the middle of the
element.) In addition to the SET statement, this affects SET clauses of
CREATE FUNCTION, ALTER ROLE, and ALTER DATABASE. It does not affect the
set_config() SQL function.
Though the documentation did not show an insecure command, remove single
quotes that could entice a reader to write an insecure command.
Back-patch to v13 (all supported versions).
Reported-by: Sven Klemm <[email protected]>
Author: Sven Klemm <[email protected]>
Backpatch-through: 13
|
|
The variable is a bit magical in how it requires "postgresql" or
"pgsql" to be part of the path, and files end up in its "share" and
"lib" subdirectories. So mention all that and show an example of
setting "extension_control_path" and "dynamic_library_path" to use
those locations.
Author: David E. Wheeler <[email protected]>
Reviewed-by: Matheus Alcantara <[email protected]>
Reviewed-by: Christoph Berg <[email protected]>
Discussion: https://www.postgresql.org/message-id/[email protected]
|
|
The additional packaging footprint of the OAuth Curl dependency, as well
as the existence of libcurl in the address space even if OAuth isn't
ever used by a client, has raised some concerns. Split off this
dependency into a separate loadable module called libpq-oauth.
When configured using --with-libcurl, libpq.so searches for this new
module via dlopen(). End users may choose not to install the libpq-oauth
module, in which case the default flow is disabled.
For static applications using libpq.a, the libpq-oauth staticlib is a
mandatory link-time dependency for --with-libcurl builds. libpq.pc has
been updated accordingly.
The default flow relies on some libpq internals. Some of these can be
safely duplicated (such as the SIGPIPE handlers), but others need to be
shared between libpq and libpq-oauth for thread-safety. To avoid
exporting these internals to all libpq clients forever, these
dependencies are instead injected from the libpq side via an
initialization function. This also lets libpq communicate the offsets of
PGconn struct members to libpq-oauth, so that we can function without
crashing if the module on the search path came from a different build of
Postgres. (A minor-version upgrade could swap the libpq-oauth module out
from under a long-running libpq client before it does its first load of
the OAuth flow.)
This ABI is considered "private". The module has no SONAME or version
symlinks, and it's named libpq-oauth-<major>.so to avoid mixing and
matching across Postgres versions. (Future improvements may promote this
"OAuth flow plugin" to a first-class concept, at which point we would
need a public API to replace this anyway.)
Additionally, NLS support for error messages in b3f0be788a was
incomplete, because the new error macros weren't being scanned by
xgettext. Fix that now.
Per request from Tom Lane and Bruce Momjian. Based on an initial patch
by Daniel Gustafsson, who also contributed docs changes. The "bare"
dlopen() concept came from Thomas Munro. Many people reviewed the design
and implementation; thank you!
Co-authored-by: Daniel Gustafsson <[email protected]>
Reviewed-by: Andres Freund <[email protected]>
Reviewed-by: Christoph Berg <[email protected]>
Reviewed-by: Daniel Gustafsson <[email protected]>
Reviewed-by: Jelte Fennema-Nio <[email protected]>
Reviewed-by: Peter Eisentraut <[email protected]>
Reviewed-by: Wolfgang Walther <[email protected]>
Discussion: https://postgr.es/m/641687.1742360249%40sss.pgh.pa.us
|
|
Oversight in commit cb45dc3afb.
Reported-by: Erik Rijkers <[email protected]>
Reviewed-by: Fujii Masao <[email protected]>
Discussion: https://postgr.es/m/7b856277-62ad-80f0-36e1-a134ec3c9cab%40xs4all.nl
|
|
Add a documentation warning to ts_headline() pointing out that, when
working with untrusted input documents, the output is not guaranteed
to be safe for direct inclusion in web pages. This is because, while
it does remove some XML tags from the input, it doesn't remove all
HTML markup, and so the result may be unsafe (e.g., it might permit
XSS attacks).
To guard against that, all HTML markup should be removed from the
input, making it plain text, or the output should be passed through an
HTML sanitizer.
In addition, document precisely what the default text search parser
recognises as valid XML tags, since that's what determines which XML
tags ts_headline() will remove.
Reported-by: Richard Neill <[email protected]>
Author: Dean Rasheed <[email protected]>
Reviewed-by: Noah Misch <[email protected]>
Backpatch-through: 13
|
|
Further improvement for commit 11bd8318602. That commit confused
identity and generated columns; fix that. Also, virtual generated
columns have since been added; add more details about that. Also some
small rewordings and reformattings to further improve clarity.
Reviewed-by: Robert Treat <[email protected]>
Discussion: https://postgr.es/m/[email protected]
|
|
30a6ed0ce4b has added four attributes to pg_stat_all_tables to track the
cumulative time spent in [auto]vacuum and [auto]analyze. It was not
mentioned that the vacuum cost-based delays are included in these
numbers, which could be confusing now that the delays are included in
the vacuum progress view (bb8dff9995f2).
This commit adds an extra note about this matter.
Reported-by: Magnus Hagander <[email protected]>
Author: Bertrand Drouvot <[email protected]>
Discussion: https://postgr.es/m/CABUevEz9v1ZNToPyD98JnWDGZgG=SmPZKkSNzU9hXQ-nGTQF0g@mail.gmail.com
|
|
Oversight in commit bb8dff9995.
|
|
Since pg_upgrade does not transfer the cumulative statistics used
to trigger autovacuum and autoanalyze, the server may take much
longer than expected to process them post-upgrade. Currently, we
recommend analyzing only relations for which optimizer statistics
were not transferred by using the --analyze-in-stages and
--missing-stats-only options. This commit appends another
recommendation to analyze all relations to update the relevant
cumulative statistics by using the --analyze-only option. This is
similar to the recommendation for pg_stat_reset().
Reported-by: Christoph Berg <[email protected]>
Reviewed-by: Christoph Berg <[email protected]>
Discussion: https://postgr.es/m/aAfxfKC82B9NvJDj%40msg.df7cb.de
|
|
The current ordering strategy for these pages is to list the short
options in alphabetical order followed by the long options in
alphabetical order. If an option has both a short variant and a
long variant, the short variant takes precedence. This commit
moves a few recently added options to match this style. We should
probably adjust all pages and --help output to list the long and
short options in one combined alphabetical list (with the long
variants taking precedence), but that is a much larger change, so
it is left as a future exercise.
Oversights in commits a5cf808be5, 1fd1bd8710, and bde2fb797a.
Reviewed-by: Álvaro Herrera <[email protected]>
Reviewed-by: Peter Eisentraut <[email protected]>
Discussion: https://postgr.es/m/aBFBtsltgu3-IU1d%40nathan
|
|
This fixes comment and docs typos as well as a small documentation
change to make it clearer. Found via post-commit review.
Author: Rahila Syed <[email protected]>
Reviewed-by: Daniel Gustafsson <[email protected]>
Discussion: https://postgr.es/m/CAH2L28vt16C9xTuK+K7QZvtA3kCNWXOEiT=gEekUw3Xxp9LVQw@mail.gmail.com
|
|
This reverts commit 38da053463bef32adf563ddee5277d16d2b6c5af, which
attempted to preserve our ability to start with only 60 semaphores.
Subsequent changes (particularly 55b454d0e) have put that idea pretty
much permanently out of reach: people wishing to use Postgres v18 on
OpenBSD or NetBSD will have no choice but to increase those platforms'
default values of SEMMNI and SEMMNS.
Hence, revert 38da05346's changes in SEMAS_PER_SET and the minimum
tested value of max_connections. Adjust a comment from the subsequent
patch 6d0154196, and tweak the wording in runtime.sgml to make it
clear that changing SEMMNI/SEMMNS is no longer even a little bit
optional on these platforms.
Although 38da05346 was later back-patched into v17, leave that branch
alone: it's still capable of starting with 60 semaphores, and there's
no reason to break that.
Author: Tom Lane <[email protected]>
Reviewed-by: Nathan Bossart <[email protected]>
Discussion: https://postgr.es/m/[email protected]
Discussion: https://postgr.es/m/[email protected]
|
|
Python 3.2 is no longer tested by the buildfarm, and there are only a
handful of buildfarm animals running versions older than 3.6, which
itself went end-of-life in 2021. Python 3.6.8 is the default version
shipped in RHEL8, so that seems like a reasonable baseline for PG18.
Now that we use the Python Limited API as of 0793ab810, older versions
of Python should continue functioning for users of PL/Python in
particular, so soften the language from "required" to "supported".
Wording by Tom Lane. Separate from the review of the patch itself,
several people provided input on the choice of cutoff: Christoph Berg,
Devrim Gündüz, Florents Tselai, Jelte Fennema-Nio, and Renan Alves
Fonseca. Thank you!
Suggested-by: Tom Lane <[email protected]>
Reviewed-by: Peter Eisentraut <[email protected]>
Discussion: https://postgr.es/m/16098.1745079444%40sss.pgh.pa.us
|
|
Reported-by: Andres Freund
Discussion: https://postgr.es/m/5yqochswkulckuzzrwgv2nqdrfh4k4coc4uwq4lvgzkfwnbjbd@46igbiwjabn2
|
|
|
|
Add a comment character before a line annotation, so that the query
can be used as presented.
Reported-by: Yaroslav Saburov <[email protected]>
Author: Euler Taveira <[email protected]>
Reviewed-by: Robert Treat <[email protected]>
Discussion: https://www.postgresql.org/message-id/flat/174393459040.678.17810152410419444783%40wrigleys.postgresql.org
|
|
Author: Peter Smith <[email protected]>
Reviewed-by: David G. Johnston <[email protected]>
Reviewed-by: Amit Kapila <[email protected]>
Discussion: https://postgr.es/m/CAHut+PtnjLiNFFh-3f9cXH0wnwqjdkTjQNbVmZdZ1y+zKt_PPg@mail.gmail.com
|
|
|
|
Previously, config.sgml included secondary index terms for
max_replication_slots and max_active_replication_origins. These are
no longer necessary, as each parameter now has a single distinct index entry.
The secondary index terms were originally useful because
max_active_replication_origins was part of max_replication_slots,
and separate index entries helped users locate each setting. However,
commit 04ff636cbce split them into independent parameters,
making the secondary terms redundant.
This commit removes the unnecessary secondary index entries to
simplify the documentation.
Author: Fujii Masao <[email protected]>
Reviewed-by: Euler Taveira <[email protected]>
Reviewed-by: Robert Treat <[email protected]>
Discussion: https://postgr.es/m/[email protected]
|
|
|
|
All the injection points used in the tree have relied on an implied
rule: their names should be made of lower-case characters, with dashes
between the words used.
This commit adds a light mention about that in the docs, encouraging the
practice.
Author: Hayato Kuroda <[email protected]>
Reviewed-by: Aleksander Alekseev <[email protected]>
Discussion: https://postgr.es/m/OSCPR01MB14966E14C1378DEE51FB7B7C5F5B32@OSCPR01MB14966.jpnprd01.prod.outlook.com
Backpatch-through: 17
|
|
The previous text was a little clumsy. Here we improve that.
Author: David Rowley <[email protected]>
Reported-by: Noboru Saito <[email protected]>
Reviewed-by: David G. Johnston <[email protected]>
Discussion: https://postgr.es/m/CAAM3qnJtv5YbjpwDfVOYN2gZ9zGSLFM1UGJgptSXmwfifOZJFQ@mail.gmail.com
Backpatch-through: 13
|
|
* Use <symbol> tags for CONNECTION_* #defines
We were using an inconsistent mix of <literal> and sometimes <function>
tags.
* Use <application> tag for libpq
There was a mix of <literal> and <productname>
Also fix a whitespace issue.
None of these seem critical enough mistakes to backpatch.
Author: Noboru Saito <[email protected]>
Discussion: https://postgr.es/m/CAAM3qnJtv5YbjpwDfVOYN2gZ9zGSLFM1UGJgptSXmwfifOZJFQ@mail.gmail.com
|
|
Author: Noboru Saito <[email protected]>
Discussion: https://postgr.es/m/CAAM3qnJtv5YbjpwDfVOYN2gZ9zGSLFM1UGJgptSXmwfifOZJFQ@mail.gmail.com
Backpatch-through: 17
|
|
Commit d9e03864b6b changed the memory context level numbers shown by
pg_log_backend_memory_contexts() to be 1-based. However, the example in
the documentation was not updated and still used 0-based numbering.
This commit updates the example to match the current 1-based output.
Author: Fujii Masao <[email protected]>
Reviewed-by: David Rowley <[email protected]>
Discussion: https://postgr.es/m/[email protected]
|
|
The large majority of these have been introduced by recent commits done
in the v18 development cycle.
Author: Alexander Lakhin <[email protected]>
Discussion: https://postgr.es/m/[email protected]
|
|
Backpatch to 17, where the line was added.
Reported by Noboru Saito while he was working on translating the file
into Japanese.
Discussion: https://postgr.es/m/20250417.203047.1321297410457834775.ishii%40postgresql.org
Reported-by: Noboru Saito <[email protected]>
Reviewed-by: Daniel Gustafs <[email protected]>
Backpatch-through: 17
|
|
This fixes a set of typos introduced during the v18 development
cycle.
Author: Daniel Gustafsson <[email protected]>
Reviewed-by: Laurenz Albe <[email protected]>
Discussion: https://postgr.es/m/[email protected]
|
|
Previously, a space was missing between "<option>--exclude-schema</option>"
and "for" in the pg_restore documentation. This commit fixes the typo by
adding the missing whitespace.
Back-patch to v17 where the typo was added.
Author: Lele Gaifax <[email protected]>
Reviewed-by: Fujii Masao <[email protected]>
Discussion: https://postgr.es/m/[email protected]
Backpatch-through: 17
|
|
Per the precedent set by 04539e73f, adjust article prefixes for "SQL" to
use "an" consistently rather than "a", i.e., "an es-que-ell" rather than
"a sequel".
Both of these are new to v18. Also see b1b13d2b5, d866f0374 and
7bdd489d3.
|
|
Add a paragraph break per suggestion from David G. Johnston.
Use a consistent voice for all the different parameter
descriptions, and fix a couple of grammatical issues.
Reported-by: Igor Korot <[email protected]>
Co-authored-by: "David G. Johnston" <[email protected]>
Co-authored-by: Tom Lane <[email protected]>
Discussion: https://postgr.es/m/CA+FnnTz=EW1VQRpWB9J+G-NSchrPFcw4nR7d0JqzEK9jWKB35A@mail.gmail.com
|
|
This fixes typos in docs and comments introduced during the v18
development cycle, to keep them from ending up in backbranches.
Author: Jacob Brazeal <[email protected]>
Reviewed-by: Daniel Gustafsson <[email protected]>
Discussion: https://postgr.es/m/CA+COZaCgGua25f2hSrjrDLJcJJAHkwoKgTTqUy-wyL1=64JNjw@mail.gmail.com
|
|
Oversight in commit 1495eff7bd.
|
|
It's been twenty years since we generated constraint names that
look like "$N". So this advice about double-quoting such names
is well past its sell-by date, and now it merely seems confusing.
Reported-by: Yaroslav Saburov <[email protected]>
Author: "David G. Johnston" <[email protected]>
Discussion: https://postgr.es/m/[email protected]
Backpatch-through: 13
|
|
Author: Peter Smith <[email protected]>
Reviewed-by: Amit Kapila <[email protected]>
Discussion: https://postgr.es/m/CAHut+PsmSCQ-ENSDQ0YOUcsgzT=GG-E9jyXBvxd51A_dMXH5XA@mail.gmail.com
|
|
It's weird to have the core regression tests depending on contrib
code, and coverage testing shows that those test queries add nothing
to the core-code coverage of the core tests. So pull those test bits
out and put them into ordinary test scripts inside contrib/spi/,
making that more like other contrib modules.
Aside from being structurally nicer, anything we can take out of the
core tests (which are executed multiple times per check-world run)
and put into tests executed only once should be a win. It doesn't
look like this change will buy a whole lot of milliseconds, but a
cycle saved is a cycle earned.
Also, there is some discussion around possibly removing refint and/or
autoinc altogether. I don't know if that will happen, but we'd
certainly need to decouple them from the core tests to do so.
The tests for autoinc were quite intertwined with the undocumented
"ttdummy" trigger in regress.c. That made the tests very hard to
understand and contributed nothing to autoinc's testing either.
So I just deleted ttdummy and rewrote the autoinc tests without it.
I realized while doing this that the description of autoinc in
the SGML docs is not a great description of what the function
actually does, so the patch includes some updates to those docs.
Author: Tom Lane <[email protected]>
Reviewed-by: Heikki Linnakangas <[email protected]>
Discussion: https://postgr.es/m/[email protected]
|
|
The page_num was defined as integer, which should be sufficient for the
near future (with 4K pages it's 8TB). But it's virtually free to return
bigint, and get a wider range. This was agreed on the thread, but I
forgot to tweak this in ba2a3c2302f1.
While at it, make the data types in CREATE VIEW a bit more consistent.
Discussion: https://postgr.es/m/CAKZiRmxh6KWo0aqRqvmcoaX2jUxZYb4kGp3N%3Dq1w%2BDiH-696Xw%40mail.gmail.co
|
|
The code in pg_get_shmem_allocations_numa() returned 'size' as int64,
but the docs said int32.
Report and fix by Noriyoshi Shinoda.
Reported-by: Noriyoshi Shinoda <[email protected]>
Discussion: https://postgr.es/m/DM4PR84MB1734308EB741A6ECFF040C27EEAA2@DM4PR84MB1734.NAMPRD84.PROD.OUTLOOK.COM
|
|
Typo in previous commit.
|
|
It can be set to either COPY (the default) or CLONE if the system
supports it. CLONE causes callers of copydir(), currently CREATE
DATABASE ... STRATEGY=FILE_COPY and ALTER DATABASE ... SET TABLESPACE =
..., to use copy_file_range (Linux, FreeBSD) or copyfile (macOS) to copy
files instead of a read-write loop over the contents.
CLONE gives the kernel the opportunity to share block ranges on
copy-on-write file systems and push copying down to storage on others,
depending on configuration. On some systems CLONE can be used to clone
large databases quickly with CREATE DATABASE ... TEMPLATE=source
STRATEGY=FILE_COPY.
Other operating systems could be supported; patches welcome.
Co-authored-by: Nazir Bilal Yavuz <[email protected]>
Reviewed-by: Robert Haas <[email protected]>
Reviewed-by: Ranier Vilela <[email protected]>
Discussion: https://postgr.es/m/CA%2BhUKGLM%2Bt%2BSwBU-cHeMUXJCOgBxSHLGZutV5zCwY4qrCcE02w%40mail.gmail.com
|
