Tom Lane [Wed, 24 Aug 2005 20:20:38 +0000 (20:20 +0000)]
Back off allow_nonpic_in_shlib for FreeBSD builds: only set it on i386.
This might be overly conservative, but we know it does not work on amd64.
Per buildfarm results.
Bruce Momjian [Wed, 24 Aug 2005 19:43:26 +0000 (19:43 +0000)]
Update:
< Currently, if a variable is commented out, it keeps the
< previous uncommented value until a server restarted.
> Currently, if a variable is commented out, it keeps the
> previous uncommented value until a server restarted.
> Logically, a reload should set the same values as a
> server restart.
Bruce Momjian [Wed, 24 Aug 2005 19:41:33 +0000 (19:41 +0000)]
Run spellchecker over release notes.
Bruce Momjian [Wed, 24 Aug 2005 19:34:34 +0000 (19:34 +0000)]
More beta1 cleanup.
Tom Lane [Wed, 24 Aug 2005 19:34:12 +0000 (19:34 +0000)]
Fix SHOW and RESET grammar to accept custom variable names.
Bruce Momjian [Wed, 24 Aug 2005 19:31:46 +0000 (19:31 +0000)]
Suggest markup items for the future.
Tom Lane [Wed, 24 Aug 2005 19:24:54 +0000 (19:24 +0000)]
Make the plperl regression tests pass in 'use_strict' mode, by adding
'my' where appropriate. Michael Fuhr
Bruce Momjian [Wed, 24 Aug 2005 19:24:20 +0000 (19:24 +0000)]
Update release notes for beta1.
Tom Lane [Wed, 24 Aug 2005 19:16:49 +0000 (19:16 +0000)]
Mention BEGIN { strict->import(); } as a substitute for 'use strict'
in plperl functions.
Tom Lane [Wed, 24 Aug 2005 19:06:28 +0000 (19:06 +0000)]
Get rid of inappropriate use of croak(). Per report from Michael Fuhr.
Tom Lane [Wed, 24 Aug 2005 18:56:07 +0000 (18:56 +0000)]
Adjust description of use_strict parameter. Some other minor editorial
cleanup.
Tom Lane [Wed, 24 Aug 2005 18:26:36 +0000 (18:26 +0000)]
Fix broken markup.
Tom Lane [Wed, 24 Aug 2005 18:16:58 +0000 (18:16 +0000)]
Fix up plperl 'use_strict' so that it can be enabled or disabled on the
fly. Fix problem with incompletely duplicated setup code. Andrew Dunstan,
from an idea of Michael Fuhr's.
Bruce Momjian [Wed, 24 Aug 2005 17:56:20 +0000 (17:56 +0000)]
Additem:
> * Add sleep() function, remove from regress.c
Tom Lane [Wed, 24 Aug 2005 17:50:00 +0000 (17:50 +0000)]
Add small hack to support use of Unicode-based locales on WIN32. This
is not adequately tested yet, but let's get it into beta1 so it can be
tested. Magnus Hagander and Tom Lane.
Tom Lane [Wed, 24 Aug 2005 17:38:35 +0000 (17:38 +0000)]
Fix ExecBRDeleteTriggers so that deletion is not suppressed when delete
triggers exist but are all disabled. Problem noted by Gavin Sherry in
original discussion of enable/disable trigger patch, but was never
addressed.
Tom Lane [Wed, 24 Aug 2005 17:24:19 +0000 (17:24 +0000)]
Add documentation for ALTER TABLE ENABLE/DISABLE TRIGGER.
Bruce Momjian [Wed, 24 Aug 2005 16:49:39 +0000 (16:49 +0000)]
Add:
> o Add sleep() to PL/PgSQL
Bruce Momjian [Wed, 24 Aug 2005 16:47:00 +0000 (16:47 +0000)]
Add to release notes.
Tom Lane [Wed, 24 Aug 2005 15:35:01 +0000 (15:35 +0000)]
Fix broken markup.
Bruce Momjian [Wed, 24 Aug 2005 14:35:26 +0000 (14:35 +0000)]
Update release notes.
Bruce Momjian [Wed, 24 Aug 2005 14:24:19 +0000 (14:24 +0000)]
Fix typo.
Bruce Momjian [Wed, 24 Aug 2005 14:05:37 +0000 (14:05 +0000)]
Mark "easy" items.
Jim C. Nasby
Bruce Momjian [Wed, 24 Aug 2005 14:00:36 +0000 (14:00 +0000)]
Update:
< o Do VACUUM FULL if table is nearly empty?
> o Suggest VACUUM FULL if a table is nearly empty
Bruce Momjian [Wed, 24 Aug 2005 13:57:27 +0000 (13:57 +0000)]
Add explaination:
>
> Currently, if a variable is commented out, it keeps the
> previous uncommented value until a server restarted.
>
Michael Meskes [Wed, 24 Aug 2005 10:34:19 +0000 (10:34 +0000)]
- Check for NULL before checking whether argument is an array.
- Remove stary character from string quoting.
- Fixed check to report missing varchar pointer implementation.
Bruce Momjian [Wed, 24 Aug 2005 03:47:11 +0000 (03:47 +0000)]
Remove periods on bullet items.
Bruce Momjian [Tue, 23 Aug 2005 23:51:18 +0000 (23:51 +0000)]
Mark item as complete, add another:
< * Allow triggers to be disabled [trigger]
> * -Allow triggers to be disabled [trigger]
> * Allow triggers to be disabled in only the current session.
< Currently the only way to disable triggers is to modify the system
< tables.
> This is currently possible by starting a multi-statement transaction,
> modifying the system tables, performing the desired SQL, restoring the
> system tables, and committing the transaction. ALTER TABLE ...
> TRIGGER requires a table lock so it is not idea for this usage.
Bruce Momjian [Tue, 23 Aug 2005 23:31:52 +0000 (23:31 +0000)]
Release note cleanups.
Tom Lane [Tue, 23 Aug 2005 22:40:47 +0000 (22:40 +0000)]
Add ALTER TABLE ENABLE/DISABLE TRIGGER commands. Change pg_dump to
use these instead of its previous hack of changing pg_class.reltriggers.
Documentation is lacking, will add that later.
Patch by Satoshi Nagayasu, review and some extra work by Tom Lane.
Bruce Momjian [Tue, 23 Aug 2005 21:25:56 +0000 (21:25 +0000)]
Update pgcrypto items.
Bruce Momjian [Tue, 23 Aug 2005 21:17:15 +0000 (21:17 +0000)]
Update ALTER OWNER description.
Bruce Momjian [Tue, 23 Aug 2005 21:11:22 +0000 (21:11 +0000)]
Add new file for win32 threading.
Bruce Momjian [Tue, 23 Aug 2005 21:02:05 +0000 (21:02 +0000)]
The attached patch updates the thread test program to run stand-alone on
Windows. The test itself is bypassed in configure as discussed, and
libpq has been updated appropriately to allow it to build in thread-safe
mode.
Dave Page
Bruce Momjian [Tue, 23 Aug 2005 20:51:27 +0000 (20:51 +0000)]
Fix function name.
Tom Lane [Tue, 23 Aug 2005 20:49:47 +0000 (20:49 +0000)]
Clean up some very old and crufty code for TID scan planning. Not much
functional difference really, but make use of stuff added to the planner
since this code was touched last.
Bruce Momjian [Tue, 23 Aug 2005 20:48:47 +0000 (20:48 +0000)]
Back out incorrect commit.
Bruce Momjian [Tue, 23 Aug 2005 20:45:11 +0000 (20:45 +0000)]
Fix function name.
Bruce Momjian [Tue, 23 Aug 2005 19:44:58 +0000 (19:44 +0000)]
Update release notes.
Bruce Momjian [Tue, 23 Aug 2005 14:54:06 +0000 (14:54 +0000)]
More release note updates.
Tom Lane [Tue, 23 Aug 2005 13:31:11 +0000 (13:31 +0000)]
Fix broken lrand48() implementation, per Merlin Moncure.
Bruce Momjian [Tue, 23 Aug 2005 12:47:30 +0000 (12:47 +0000)]
Release note updates.
Bruce Momjian [Tue, 23 Aug 2005 12:46:35 +0000 (12:46 +0000)]
Release note updates.
Bruce Momjian [Tue, 23 Aug 2005 12:14:33 +0000 (12:14 +0000)]
Avoid bullets in subparagraphs.
Bruce Momjian [Tue, 23 Aug 2005 11:59:09 +0000 (11:59 +0000)]
Fix markup for para.
Bruce Momjian [Tue, 23 Aug 2005 11:53:33 +0000 (11:53 +0000)]
Adjust SGML so major feature items are all not in a single subparagraph.
Bruce Momjian [Tue, 23 Aug 2005 11:32:33 +0000 (11:32 +0000)]
Update release notes from community comments.
Bruce Momjian [Tue, 23 Aug 2005 02:57:07 +0000 (02:57 +0000)]
Update release notes for 8.1.
Tom Lane [Tue, 23 Aug 2005 01:41:30 +0000 (01:41 +0000)]
Fix wrong dependency on owner created by ALTER OPCLASS OWNER.
Per Alvaro.
Bruce Momjian [Tue, 23 Aug 2005 01:22:53 +0000 (01:22 +0000)]
Fix SGML sect1-3 alignment in the 8.0.X series.
Tom Lane [Mon, 22 Aug 2005 23:59:04 +0000 (23:59 +0000)]
Rewrite gather-write patch into something less obviously bolted on
after the fact. Fix bug with incorrect test for whether we are at end
of logfile segment. Arrange for writes triggered by XLogInsert's
is-cache-more-than-half-full test to synchronize with the cache boundaries,
so that in long transactions we tend to write alternating halves of the
cache rather than randomly chosen portions of it; this saves one more
write syscall per cache load.
Bruce Momjian [Mon, 22 Aug 2005 21:32:01 +0000 (21:32 +0000)]
Update documentation that non-super users can now do ALTER OWNER.
Bruce Momjian [Mon, 22 Aug 2005 20:25:03 +0000 (20:25 +0000)]
Back out incorrect use of E'' escape addition.
Tom Lane [Mon, 22 Aug 2005 19:40:37 +0000 (19:40 +0000)]
Cause ALTER INDEX OWNER to generate a warning and do nothing, rather than
erroring out as it has done for the last couple weeks. Document that this
form is now ignored because indexes can't usefully have different owners
from their parent tables. Fix pg_dump to not generate ALTER OWNER commands
for indexes.
Tom Lane [Mon, 22 Aug 2005 17:38:20 +0000 (17:38 +0000)]
Fix unwanted denial of ALTER OWNER rights to superusers. There was some
discussion of getting around this by relaxing the checks made for regular
users, but I'm disinclined to toy with the security model right now,
so just special-case it for superusers where needed.
Bruce Momjian [Mon, 22 Aug 2005 17:35:03 +0000 (17:35 +0000)]
enable_constraint_exclusion => constraint_exclusion
Also improve wording.
Bruce Momjian [Mon, 22 Aug 2005 16:59:47 +0000 (16:59 +0000)]
Improve xid wraparound message (the server isn't really shut down, just
not accepting queries).
errmsg("database is not accepting queries to avoid
wraparound data loss in database \"%s\"",
errhint("Stop the postmaster and use a standalone
backend to VACUUM database \"%s\".",
Tom Lane [Mon, 22 Aug 2005 16:27:36 +0000 (16:27 +0000)]
Use an initdb-time test to see if the local version of getaddrinfo()
chokes on IPv6 addresses, and comment out the IPv6 entry in the default
pg_hba.conf if so. Per Andrew Dunstan.
Tom Lane [Mon, 22 Aug 2005 00:41:28 +0000 (00:41 +0000)]
Fix some inconsistent choices of datatypes in xlog.c. Make buffer
indexes all be int, rather than variously int, uint16 and uint32;
add some casts where necessary to support large buffer arrays.
Tom Lane [Sun, 21 Aug 2005 03:39:37 +0000 (03:39 +0000)]
Minor GUC cleanups: document krb_server_hostname and custom_variable_classes
in postgresql.conf.sample, mark custom_variable_classes as SIGHUP not
POSTMASTER to agree with the documentation (I can't see a reason it has
to be POSTMASTER so I think the docs are right).
Bruce Momjian [Sun, 21 Aug 2005 01:04:45 +0000 (01:04 +0000)]
Add:
> * Fix problems with wrong runtime encoding conversion for NLS message files
Tom Lane [Sat, 20 Aug 2005 23:45:08 +0000 (23:45 +0000)]
Seems that the childXids list would be better based on Oid lists than
integer lists.
Tom Lane [Sat, 20 Aug 2005 23:26:37 +0000 (23:26 +0000)]
Convert the arithmetic for shared memory size calculation from 'int'
to 'Size' (that is, size_t), and install overflow detection checks in it.
This allows us to remove the former arbitrary restrictions on NBuffers
etc. It won't make any difference in a 32-bit machine, but in a 64-bit
machine you could theoretically have terabytes of shared buffers.
(How efficiently we could manage 'em remains to be seen.) Similarly,
num_temp_buffers, work_mem, and maintenance_work_mem can be set above
2Gb on a 64-bit machine. Original patch from Koichi Suzuki, additional
work by moi.
Tom Lane [Sat, 20 Aug 2005 19:19:21 +0000 (19:19 +0000)]
Invoke mksafefunc and mkunsafefunc with :: decoration. This seems a good
idea on consistency grounds, whether or not it really fixes bug #1831.
Michael Fuhr
Tatsuo Ishii [Sat, 20 Aug 2005 01:29:27 +0000 (01:29 +0000)]
Make GetMultiXactIdMembers() a public function.
Tatsuo Ishii [Sat, 20 Aug 2005 01:26:36 +0000 (01:26 +0000)]
Add BackendXidGetPid().
Tom Lane [Sat, 20 Aug 2005 00:40:32 +0000 (00:40 +0000)]
Repair problems with VACUUM destroying t_ctid chains too soon, and with
insufficient paranoia in code that follows t_ctid links. (We must do both
because even with VACUUM doing it properly, the intermediate state with
a dangling t_ctid link is visible concurrently during lazy VACUUM, and
could be seen afterwards if either type of VACUUM crashes partway through.)
Also try to improve documentation about what's going on. Patch is a bit
bulky because passing the XMAX information around required changing the
APIs of some low-level heapam.c routines, but it's not conceptually very
complicated. Per trouble report from Teodor and subsequent analysis.
This needs to be back-patched, but I'll do that after 8.1 beta is out.
Bruce Momjian [Fri, 19 Aug 2005 18:58:18 +0000 (18:58 +0000)]
Fix LRU/ALL description mismatch for GUC parameter.
Bruce Momjian [Fri, 19 Aug 2005 01:55:18 +0000 (01:55 +0000)]
Consistently align comments in postgresql.conf, move some slightly to
the right to stand out.
Tom Lane [Thu, 18 Aug 2005 21:34:20 +0000 (21:34 +0000)]
Update some obsolete comments --- code is using t_self now, not t_ctid.
Tom Lane [Thu, 18 Aug 2005 17:51:12 +0000 (17:51 +0000)]
Fix up LIMIT/OFFSET planning so that we cope with non-constant LIMIT
or OFFSET clauses by using estimate_expression_value(). The main advantage
of this is that if the expression is a Param and we have a value for the
Param, we'll use that value rather than defaulting. Also, fix some
thinkos in the logic for combining LIMIT/OFFSET with an externally
supplied tuple fraction (this covers cases like EXISTS(...LIMIT...)).
And make sure the results of all this are shown by EXPLAIN. Per a
gripe from Merlin Moncure.
Bruce Momjian [Thu, 18 Aug 2005 14:14:31 +0000 (14:14 +0000)]
Add:
> o Remove unnecessary abstractions in pg_dump source code
Bruce Momjian [Thu, 18 Aug 2005 13:43:08 +0000 (13:43 +0000)]
Add hint for to_char(interval) invalid format specifications.
Bruce Momjian [Thu, 18 Aug 2005 04:42:41 +0000 (04:42 +0000)]
Done:
> * -Prevent to_char() on interval from returning meaningless values
Bruce Momjian [Thu, 18 Aug 2005 04:37:08 +0000 (04:37 +0000)]
Fix to_char(interval) to return proper year and century values.
Fix to_char(interval) to return large year/month/day/hour values that
are larger than possible timestamp values.
Prevent to_char(interval) format specifications that make no sense, like
Month.
Clean up formatting.c code to more logically handle return lengths.
Tom Lane [Wed, 17 Aug 2005 22:14:34 +0000 (22:14 +0000)]
Avoid an Assert failure if OuterUserId hasn't been set yet during
AbortTransaction. This can happen if a backend's InitPostgres transaction
fails (eg, because the given username is invalid). Per Alvaro.
Bruce Momjian [Wed, 17 Aug 2005 22:06:53 +0000 (22:06 +0000)]
More formatting.c cleanups.
Bruce Momjian [Wed, 17 Aug 2005 21:54:50 +0000 (21:54 +0000)]
Small cleanup.
Bruce Momjian [Wed, 17 Aug 2005 21:47:55 +0000 (21:47 +0000)]
Adjust to_char/from_char code to use boolean "is_to_char" rather than
integer with flags.
Tom Lane [Wed, 17 Aug 2005 20:20:10 +0000 (20:20 +0000)]
Remove unnecessary configure test for inet_ntop(), per Andrew Dunstan.
Tom Lane [Wed, 17 Aug 2005 19:45:51 +0000 (19:45 +0000)]
Fix declaration of dumpacl, per Alvaro.
Bruce Momjian [Wed, 17 Aug 2005 03:50:59 +0000 (03:50 +0000)]
Fix FSM warning to mention increasing max_fsm_pages. Was incorrectly
max_fsm_relations.
Bruce Momjian [Wed, 17 Aug 2005 01:45:20 +0000 (01:45 +0000)]
Minor cleanup.
Bruce Momjian [Tue, 16 Aug 2005 19:29:38 +0000 (19:29 +0000)]
Update comments.
Bruce Momjian [Tue, 16 Aug 2005 19:23:31 +0000 (19:23 +0000)]
Improve comment.
Bruce Momjian [Tue, 16 Aug 2005 17:46:57 +0000 (17:46 +0000)]
Update pgcvslog comment on how to find branch start time.
Run autoconf/autoheader in case someone forgot in the past.
Tom Lane [Tue, 16 Aug 2005 00:48:12 +0000 (00:48 +0000)]
Reject operator names >= NAMEDATALEN characters. These will not work
anyway, and in assert-enabled builds you are likely to get an assertion
failure. Backpatch as far as 7.3; 7.2 seems not to have the problem.
Bruce Momjian [Mon, 15 Aug 2005 23:00:14 +0000 (23:00 +0000)]
Rename pg_stat_file columns to be more consistent. Split apart change
and creation columns to behave for Unix or Win32.
Tom Lane [Mon, 15 Aug 2005 21:50:15 +0000 (21:50 +0000)]
Clean up recent patch for PL handler functions in pg_catalog: the patch
caused PL languages and handlers to be dumped ALWAYS, even in the face
of contrary --schema or --table switches. Adopt a slightly saner
definition.
Tom Lane [Mon, 15 Aug 2005 21:02:26 +0000 (21:02 +0000)]
Make createlang and droplang proof against weird search_path settings
by forcing search_path to be just pg_catalog.
Tom Lane [Mon, 15 Aug 2005 19:40:20 +0000 (19:40 +0000)]
array_in() and array_recv() need to be more paranoid about validating
their OID parameter. It was possible to crash the backend with
select array_in('{123}',0,0); because that would bypass the needed step
of initializing the workspace. These seem to be the only two places
with a problem, though (record_in and record_recv don't have the issue,
and the other array functions aren't depending on user-supplied input).
Back-patch as far as 7.4; 7.3 does not have the bug.
Tom Lane [Mon, 15 Aug 2005 19:05:16 +0000 (19:05 +0000)]
int_array_enum function should be using fcinfo->flinfo->fn_extra for
working state, not fcinfo->context. Silly oversight on my part in last
go-round of fixes.
Tom Lane [Mon, 15 Aug 2005 16:25:19 +0000 (16:25 +0000)]
Allow the pgstat views to show toast tables as well as regular tables
(the stats system has always collected this info, but the views were
filtering it out). Modify autovacuum so that over-threshold activity
in a toast table can trigger a VACUUM of the parent table, even if the
parent didn't appear to need vacuuming itself. Per discussion a month
or so back about "short, wide tables".
Tom Lane [Mon, 15 Aug 2005 02:40:36 +0000 (02:40 +0000)]
Clean up some stray remaining references to pg_shadow, pg_user, pg_group.
Tom Lane [Mon, 15 Aug 2005 02:36:30 +0000 (02:36 +0000)]
Change pg_dump to use pg_roles instead of pg_user on 8.1 and up,
so that it will correctly dump owners of objects owned by non-login roles.
Tom Lane [Sun, 14 Aug 2005 23:35:38 +0000 (23:35 +0000)]
Update administrator's guide chapters for ROLEs patch.
Peter Eisentraut [Sun, 14 Aug 2005 22:19:50 +0000 (22:19 +0000)]
Change standard_compliant_strings to standard_conforming_strings.
Tom Lane [Sun, 14 Aug 2005 20:16:03 +0000 (20:16 +0000)]
Update the createuser utility for the ROLEs world. Alvaro Herrera
Tom Lane [Sun, 14 Aug 2005 19:20:45 +0000 (19:20 +0000)]
Fix psql's \d commands to use pg_roles instead of pg_user, so that
they don't miss owners that are NOLOGIN.
Tom Lane [Sun, 14 Aug 2005 18:49:30 +0000 (18:49 +0000)]
Fix up tab completion for ROLEs and add some more completion logic for
other stuff; change \du and \dg to be role-aware (Stefan Kaltenbrunner).
Also make tab completion fetch the list of GUC variables from pg_settings
instead of having a hard-wired copy of the list (Tom Lane).