OSDN Git Service
Tom Lane [Tue, 19 Sep 2006 17:22:42 +0000 (17:22 +0000)]
Fix broken markup.
Tom Lane [Tue, 19 Sep 2006 15:36:08 +0000 (15:36 +0000)]
Fix shared library creation to work properly on AIX. Albe Laurenz
Neil Conway [Tue, 19 Sep 2006 15:18:41 +0000 (15:18 +0000)]
Minor additions and typo fixes for the backup documentation. Patch from
Simon Riggs, minor editorialization by Neil Conway.
Bruce Momjian [Tue, 19 Sep 2006 02:25:13 +0000 (02:25 +0000)]
More 8.2 release item reordering.
Bruce Momjian [Tue, 19 Sep 2006 02:08:30 +0000 (02:08 +0000)]
Reorder 8.2 release note items more logically.
Bruce Momjian [Tue, 19 Sep 2006 00:57:07 +0000 (00:57 +0000)]
Update migration changes, more cleanups.
Bruce Momjian [Mon, 18 Sep 2006 23:19:50 +0000 (23:19 +0000)]
Properly mention in the release notes that fillfactor controls both heap
and indexes. Other cleanups.
Bruce Momjian [Mon, 18 Sep 2006 23:01:43 +0000 (23:01 +0000)]
Wrap long lines in 8.2 release notes.
Bruce Momjian [Mon, 18 Sep 2006 22:43:16 +0000 (22:43 +0000)]
Updates from Jim Nasby.
Tom Lane [Mon, 18 Sep 2006 22:40:40 +0000 (22:40 +0000)]
Add built-in userlock manipulation functions to replace the former
contrib functionality. Along the way, remove the USER_LOCKS configuration
symbol, since it no longer makes any sense to try to compile that out.
No user documentation yet ... mmoncure has promised to write some.
Thanks to Abhijit Menon-Sen for creating a first draft to work from.
Bruce Momjian [Mon, 18 Sep 2006 21:45:10 +0000 (21:45 +0000)]
Move 8.2 release documentation into SGML.
Neil Conway [Mon, 18 Sep 2006 21:19:29 +0000 (21:19 +0000)]
Make the order of the CASCADE and RESTRICT keywords in the DROP OWNED
syntax summary consistent with the other SQL reference pages. Patch
from Euler Taveira de Oliveira.
Tom Lane [Mon, 18 Sep 2006 19:54:01 +0000 (19:54 +0000)]
Documentation for VALUES lists. Joe Conway and Tom Lane
Bruce Momjian [Mon, 18 Sep 2006 16:24:07 +0000 (16:24 +0000)]
Add URL for commenting postgresql.conf:
> http://archives.postgresql.org/pgsql-hackers/2006-09/msg01481.php
Bruce Momjian [Mon, 18 Sep 2006 16:22:32 +0000 (16:22 +0000)]
Add URL for UUID:
>
> http://archives.postgresql.org/pgsql-patches/2006-09/msg00209.php
>
Tom Lane [Mon, 18 Sep 2006 16:04:04 +0000 (16:04 +0000)]
Fix problems with column name list of CREATE TABLE AS being applied to
the input query's target list too soon, causing it to affect processing
of ORDER BY in the input query.
Bruce Momjian [Mon, 18 Sep 2006 15:52:23 +0000 (15:52 +0000)]
Add item:
>
> * Set client encoding based on the client operating system encoding
>
> Currently client_encoding is set in postgresql.conf, which
> defaults to the server encoding.
Bruce Momjian [Mon, 18 Sep 2006 14:56:19 +0000 (14:56 +0000)]
Add URL to UPDATE unique index case x=x+1:
<
> http://archives.postgresql.org/pgsql-hackers/2006-09/msg01458.php
Teodor Sigaev [Mon, 18 Sep 2006 12:11:36 +0000 (12:11 +0000)]
Improve wordings by David Fuhry <dfuhry@cs.kent.edu>
Tom Lane [Mon, 18 Sep 2006 00:52:14 +0000 (00:52 +0000)]
Fix CREATE TABLE ... AS VALUES ... to work rather than Assert'ing;
oversight in original implementation of VALUES. Also fix an oversight
in recent addition of options to CREATE TABLE AS: they weren't getting
propagated if the query was a set-operation such as UNION.
Tom Lane [Sun, 17 Sep 2006 22:50:31 +0000 (22:50 +0000)]
Change ANALYZE to take ShareUpdateExclusiveLock not AccessShareLock on
the table being analyzed. This prevents two ANALYZEs from running
concurrently on the same table and possibly suffering concurrent-update
failures while trying to store their results into pg_statistic. The
downside is that a database-wide ANALYZE executed within a transaction
block will hold ShareUpdateExclusiveLock on many tables simultaneously,
which could lead to concurrency issues or even deadlock against another
such ANALYZE. However, this seems a corner case of less importance
than getting unexpected errors from a foreground ANALYZE when autovacuum
elects to analyze the same table concurrently. Per discussion.
Tom Lane [Sun, 17 Sep 2006 22:16:22 +0000 (22:16 +0000)]
Marginal cleanup in arrangements for ensuring StrategyHintVacuum is cleared
after an error during VACUUM. We have a PG_TRY block anyway around the only
call sites, so just reset it in the CATCH clause instead of having
AtEOXact_Buffers blindly do it during xact end. I think the old code was
actively wrong for the case of a failure during ANALYZE inside a
subtransaction --- the flag wouldn't get cleared until main transaction end.
Probably not worth back-patching though.
Bruce Momjian [Sat, 16 Sep 2006 22:06:54 +0000 (22:06 +0000)]
Update TODO for short header versions:
< o Reorder physical storage order to reduce padding?
<
< This involves having the user-specified order of columns
< be different from the physical order. SELECT * would
< need to reorder the physical values to match the
< user-specified ordering.
<
< o Store disk pages with no alignment/padding?
<
< This necessitates adding CPU-required padding when moving
< rows from disk to memory.
<
< One idea is to store the header in network byte order (high bits
< first), and read the high bits to determine the header length.
< http://archives.postgresql.org/pgsql-hackers/2006-09/msg00848.php
> One idea is to create zero-or-one-byte-header versions
> of varlena data types. In involves setting the high-bit and
> 0-127 length in the single-byte header, or clear the high bit
> and store the 7-bit ASCII value in the rest of the byte.
> The small-header versions have no alignment requirements.
> http://archives.postgresql.org/pgsql-hackers/2006-09/msg01372.php
Tom Lane [Sat, 16 Sep 2006 20:14:34 +0000 (20:14 +0000)]
Rename the recently-added pg_timezonenames view to pg_timezone_abbrevs,
and create a new view pg_timezone_names that provides information about
the zones known in the 'zic' database. Magnus Hagander, with some
additional work by Tom Lane.
Tom Lane [Sat, 16 Sep 2006 17:21:03 +0000 (17:21 +0000)]
Update timezone data files to release 2006k of the zic database.
Tom Lane [Sat, 16 Sep 2006 16:18:11 +0000 (16:18 +0000)]
Rename xml_valid() to xml_is_well_formed(), but provide a temporary
alias with the old name for backwards compatibility. Per discussion,
the old name is actively wrong because validity and well-formedness
have different meanings in XML.
Tom Lane [Sat, 16 Sep 2006 13:35:49 +0000 (13:35 +0000)]
Define errcode as __msvc_errcode not __vc_errcode for MSVC builds,
per Magnus.
Tom Lane [Sat, 16 Sep 2006 13:31:40 +0000 (13:31 +0000)]
Fix some more uses of str[n]casecmp that should be pg_str[n]casecmp.
Bruce Momjian [Sat, 16 Sep 2006 00:30:20 +0000 (00:30 +0000)]
Remove emacs info from footer of SGML files.
Bruce Momjian [Fri, 15 Sep 2006 22:02:21 +0000 (22:02 +0000)]
Document Warm Standby for High Availability
Includes sample standby script.
Simon Riggs
Bruce Momjian [Fri, 15 Sep 2006 21:55:07 +0000 (21:55 +0000)]
Document WAL recovery now uses checkpoints.
Simon Riggs
Tom Lane [Fri, 15 Sep 2006 21:42:02 +0000 (21:42 +0000)]
Several fixes for MSVC build scripts, from Magnus.
Tom Lane [Fri, 15 Sep 2006 21:35:30 +0000 (21:35 +0000)]
Fix some uses of str[n]casecmp that should be pg_str[n]casecmp.
Tom Lane [Fri, 15 Sep 2006 21:34:23 +0000 (21:34 +0000)]
Fix some uses of str[n]casecmp that should be pg_str[n]casecmp,
per Magnus.
Tom Lane [Fri, 15 Sep 2006 21:28:08 +0000 (21:28 +0000)]
Remove WINLDAPAPI decoration from ldap_start_tls_sA typedef, per Magnus.
Tom Lane [Fri, 15 Sep 2006 16:39:32 +0000 (16:39 +0000)]
Improve confusing comment for HeapTupleSatisfiesNow, per gripe from Greg Stark.
Bruce Momjian [Thu, 14 Sep 2006 23:21:47 +0000 (23:21 +0000)]
Make postgresql.conf.sample match the initdb defaults. This fixes
comment alignment on most systems.
Tom Lane [Thu, 14 Sep 2006 22:05:06 +0000 (22:05 +0000)]
Add a couple of information functions to support direct checks on whether
a schema is our own temp schema or another backend's temp schema, and use
these in place of some former kluges in information_schema. Per my
proposal of yesterday.
Bruce Momjian [Thu, 14 Sep 2006 21:44:08 +0000 (21:44 +0000)]
Seems no one wants this:
< * -Allow PREPARE to automatically determine parameter types based on the SQL
< statement (Neil)
Bruce Momjian [Thu, 14 Sep 2006 21:41:29 +0000 (21:41 +0000)]
Done:
< * -Allow protocol-level BIND parameter values to be logged, if text mode
> * -Allow protocol-level BIND parameter values to be logged
Bruce Momjian [Thu, 14 Sep 2006 21:37:04 +0000 (21:37 +0000)]
Not done yet:
< o -Allow commenting of variables in postgresql.conf to restore them
> o Allow commenting of variables in postgresql.conf to restore them
Tom Lane [Thu, 14 Sep 2006 21:15:07 +0000 (21:15 +0000)]
Fix missing markup.
Bruce Momjian [Thu, 14 Sep 2006 20:50:51 +0000 (20:50 +0000)]
Remove sslinfo copyright with author permission, keep author attribution.
Victor Wagner
Bruce Momjian [Thu, 14 Sep 2006 20:46:10 +0000 (20:46 +0000)]
Remove:
< * Research storing only active XIDs in subtransaction cache
Bruce Momjian [Thu, 14 Sep 2006 20:30:35 +0000 (20:30 +0000)]
Add:
> * Research storing only active XIDs in subtransaction cache
Bruce Momjian [Thu, 14 Sep 2006 18:10:38 +0000 (18:10 +0000)]
Add XML item.
>
> * Improve XML support
>
> http://developer.postgresql.org/index.php/XML_Support
Bruce Momjian [Thu, 14 Sep 2006 17:34:14 +0000 (17:34 +0000)]
Add description for variable-length header:
> One idea is to store the header in network byte order (high bits
> first), and read the high bits to determine the header length.
Bruce Momjian [Thu, 14 Sep 2006 17:14:53 +0000 (17:14 +0000)]
Add recent ICU URL:
> http://archives.postgresql.org/pgsql-hackers/2006-09/msg00662.php
Bruce Momjian [Thu, 14 Sep 2006 17:11:51 +0000 (17:11 +0000)]
Update TODO items:
< o Store disk pages with no alignment/padding?
>
> This involves having the user-specified order of columns
> be different from the physical order. SELECT * would
> need to reorder the physical values to match the
> user-specified ordering.
>
> o Store disk pages with no alignment/padding?
>
> This necessitates adding CPU-required padding when moving
> rows from disk to memory.
>
>
> http://archives.postgresql.org/pgsql-hackers/2006-09/msg00848.php
>
Bruce Momjian [Thu, 14 Sep 2006 16:55:43 +0000 (16:55 +0000)]
For release notes checklist, add UTF8 URL.
Bruce Momjian [Thu, 14 Sep 2006 16:51:39 +0000 (16:51 +0000)]
In release notes checklist, add URL for HTML non-ASCII escapes, mention
UTF8 escapes.
Teodor Sigaev [Thu, 14 Sep 2006 13:40:28 +0000 (13:40 +0000)]
Fix SGML markup
Teodor Sigaev [Thu, 14 Sep 2006 11:26:49 +0000 (11:26 +0000)]
Improve error message. Per discussion
http://archives.postgresql.org/pgsql-general/2006-09/msg00186.php
Teodor Sigaev [Thu, 14 Sep 2006 11:16:27 +0000 (11:16 +0000)]
GIN documentation and slightly improving GiST docs.
Thanks to Christopher Kings-Lynne <chris.kingslynne@gmail.com> for
initial version and Jeff Davis <pgsql@j-davis.com> for inspection
Michael Meskes [Thu, 14 Sep 2006 08:46:58 +0000 (08:46 +0000)]
Cygwin systems seem to have a different error message when trying to connect to port 0. Let's try port 20 instead.
Michael Meskes [Thu, 14 Sep 2006 08:02:38 +0000 (08:02 +0000)]
Added missing constuctor/destructor for interval and date.
Tom Lane [Wed, 13 Sep 2006 23:42:26 +0000 (23:42 +0000)]
Some small editorialization on the description of CREATE INDEX
CONCURRENTLY. Greg Stark, some further tweaks by me.
Tom Lane [Wed, 13 Sep 2006 21:59:04 +0000 (21:59 +0000)]
Make logging of extended-protocol commands a bit more consistent, per
discussion with Guillaume Smet.
Tom Lane [Wed, 13 Sep 2006 17:47:08 +0000 (17:47 +0000)]
Code review for patch to avoid second scan when vacuuming index-less
table: avoid invoking LockBufferForCleanup without need, put out the
same log message we would have before, minor code beautification.
Tatsuo Ishii [Wed, 13 Sep 2006 00:39:19 +0000 (00:39 +0000)]
Change "tps" to "scale" to avoid confusion
Fix bug with handling default scaling factor in the default
scenarios
Bruce Momjian [Tue, 12 Sep 2006 21:02:43 +0000 (21:02 +0000)]
Add David Fetter:
> * David is David Fetter <david@fetter.org>
Teodor Sigaev [Tue, 12 Sep 2006 16:11:44 +0000 (16:11 +0000)]
Add uninstall script
Tom Lane [Tue, 12 Sep 2006 14:47:24 +0000 (14:47 +0000)]
Spell readme file's name correctly, per buildfarm reports.
Peter Eisentraut [Tue, 12 Sep 2006 11:46:11 +0000 (11:46 +0000)]
Small fix for the README install for contrib/sslinfo.
Dave Page
Michael Meskes [Tue, 12 Sep 2006 09:09:31 +0000 (09:09 +0000)]
Seems this wasn't committed originally
Tom Lane [Mon, 11 Sep 2006 20:10:30 +0000 (20:10 +0000)]
Move set_pglocale_pgservice() from path.c to exec.c, so that pulling in
path.c does not in itself force linking of both exec.c and libintl.
Should fix current ecpglib build failure on pickier platforms.
Tom Lane [Mon, 11 Sep 2006 15:30:32 +0000 (15:30 +0000)]
Move xml2's PG_MODULE_MAGIC block to the right source file, per Michael Fuhr.
Tom Lane [Mon, 11 Sep 2006 15:14:46 +0000 (15:14 +0000)]
Rename the uninstall scripts for contrib/lo and contrib/tsearch2 to
match the convention that foo's uninstall script is uninstall_foo.sql.
Also, stop installing lo_test.sql, which really ought to be made into
a regression test anyway (though it's unclear how to avoid a dependency
on the current OID counter...)
Tom Lane [Mon, 11 Sep 2006 13:35:08 +0000 (13:35 +0000)]
Add LDAP_LIBS_FE to $(libpq) for static or AIX linking, per Albe Laurenz.
Tom Lane [Mon, 11 Sep 2006 02:50:07 +0000 (02:50 +0000)]
Ooops, forgot to update ecpg comparison files to match
source-code change.
Tom Lane [Mon, 11 Sep 2006 02:10:26 +0000 (02:10 +0000)]
Fix omissions in contrib uninstall scripts. Michael Fuhr
Tom Lane [Mon, 11 Sep 2006 01:41:35 +0000 (01:41 +0000)]
Fix unportable usage complained of by icc. Per buildfarm results.
Bruce Momjian [Sun, 10 Sep 2006 23:33:22 +0000 (23:33 +0000)]
Remove unnecessary brace pair.
Bruce Momjian [Sun, 10 Sep 2006 22:54:47 +0000 (22:54 +0000)]
Back out patch added during 8.2.X development:
Allow to_char() "D" format specifiers for interval/time.
It doesn't work, and I doubt it is useful enough to fix ("D" = day of
week).
Bruce Momjian [Sun, 10 Sep 2006 22:20:01 +0000 (22:20 +0000)]
Add items:
< * Research storing disk pages with no alignment/padding
> * Consider ways of storing rows more compactly on disk
>
> o Store disk pages with no alignment/padding?
> o Reorder physical storage order to reduce padding?
> o Support a smaller header for short variable-length fields?
> o Reduce the row header size?
Tom Lane [Sun, 10 Sep 2006 22:07:02 +0000 (22:07 +0000)]
Install a cleaner solution to the AIX libpq linking problem, as per
an earlier discussion. Centralize assumptions about what libpq depends
on in one place in Makefile.global. I am unconvinced that this list
is complete, but since ecpg seems to have gotten along with just these
entries, we'll try it this way and see what happens.
Tom Lane [Sun, 10 Sep 2006 21:38:26 +0000 (21:38 +0000)]
Fix dblink build for --enable-nls or --enable-openssl on AIX.
Per Chris Browne.
Tom Lane [Sun, 10 Sep 2006 20:56:42 +0000 (20:56 +0000)]
Remove unhelpful/misleading advice about how to use SPI_saveplan().
Per gripe from Jack Orenstein.
Tom Lane [Sun, 10 Sep 2006 20:45:17 +0000 (20:45 +0000)]
contrib/isn updates from Jeremy Kronuz.
Tom Lane [Sun, 10 Sep 2006 20:14:20 +0000 (20:14 +0000)]
If we're going to advertise the array overlap/containment operators,
we probably should make them work reliably for all arrays. Fix code
to handle NULLs and multidimensional arrays, move it into arrayfuncs.c.
GIN is still restricted to indexing arrays with no null elements, however.
Tom Lane [Sun, 10 Sep 2006 19:03:57 +0000 (19:03 +0000)]
Add missing documentation for new anyarray-overlap operator.
Tom Lane [Sun, 10 Sep 2006 17:36:52 +0000 (17:36 +0000)]
Rename contrib contains/contained-by operators to @> and <@, per discussion.
Tom Lane [Sun, 10 Sep 2006 00:29:35 +0000 (00:29 +0000)]
Rename contains/contained-by operators to @> and <@, per discussion that
agreed these symbols are less easily confused. I made new pg_operator
entries (with new OIDs) for the old names, so as to provide backward
compatibility while making it pretty easy to remove the old names in
some future release cycle. This commit only touches the core datatypes,
contrib will be fixed separately.
Tom Lane [Sat, 9 Sep 2006 18:45:37 +0000 (18:45 +0000)]
Remove reference to contrib/mac, which isn't there anymore.
Tom Lane [Sat, 9 Sep 2006 04:07:52 +0000 (04:07 +0000)]
Add contrib/isn module for ISBN/ISSN/EAN13/etc product numbers, and
remove the old isbn_issn module which is about to be obsoleted by EAN13.
contrib/isn is by Germán Méndez Bravo. Our thanks to Garrett A. Wollman
for having written the original isbn_issn module.
Tom Lane [Sat, 9 Sep 2006 03:15:40 +0000 (03:15 +0000)]
Revise OpenLDAP configuration and linking to work on more platforms
than before. Albe Laurenz (but editorialized heavily by me, so if it
doesn't work it's my fault).
Tom Lane [Fri, 8 Sep 2006 18:05:35 +0000 (18:05 +0000)]
Fix pg_dump for recent change removing separate RULE privilege.
I had thought this code could be left alone, but I was wrong: as-is
it's failing to recognize when to use ALL for table privileges in 8.2.
Tom Lane [Fri, 8 Sep 2006 17:49:13 +0000 (17:49 +0000)]
Put back plan-time check for trying to apply SELECT FOR UPDATE/SHARE
to a relation on the nullable side of an outer join. I had removed
this during the outer join planning rewrite a few months ago ... I think
I intended to put it somewhere else, but forgot ...
Tom Lane [Fri, 8 Sep 2006 15:55:53 +0000 (15:55 +0000)]
Tweak the behavior of log_duration as proposed by Guillaume Smet: rather
than being equivalent to setting log_min_duration_statement to zero, this
option now forces logging of all query durations, but doesn't force logging
of query text. Also, add duration logging coverage for fastpath function
calls.
Michael Meskes [Fri, 8 Sep 2006 14:58:27 +0000 (14:58 +0000)]
Not all C compilers understand the "//" comment in this test case, so I removed it.
Michael Meskes [Fri, 8 Sep 2006 13:32:29 +0000 (13:32 +0000)]
Replaced complex tests with small ones.
Michael Meskes [Fri, 8 Sep 2006 09:03:40 +0000 (09:03 +0000)]
More logic from complex/test* moved to their own testcases.
Tom Lane [Thu, 7 Sep 2006 22:52:01 +0000 (22:52 +0000)]
Clean up logging for extended-query-protocol operations, as per my recent
proposal. Parameter logging works even for binary-format parameters, and
logging overhead is avoided when disabled.
log_statement = all output for the src/test/examples/testlibpq3.c example
now looks like
LOG: statement: execute <unnamed>: SELECT * FROM test1 WHERE t = $1
DETAIL: parameters: $1 = 'joe''s place'
LOG: statement: execute <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
DETAIL: parameters: $1 = '2'
and log_min_duration_statement = 0 results in
LOG: duration: 2.431 ms parse <unnamed>: SELECT * FROM test1 WHERE t = $1
LOG: duration: 2.335 ms bind <unnamed> to <unnamed>: SELECT * FROM test1 WHERE t = $1
DETAIL: parameters: $1 = 'joe''s place'
LOG: duration: 0.394 ms execute <unnamed>: SELECT * FROM test1 WHERE t = $1
DETAIL: parameters: $1 = 'joe''s place'
LOG: duration: 1.251 ms parse <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
LOG: duration: 0.566 ms bind <unnamed> to <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
DETAIL: parameters: $1 = '2'
LOG: duration: 0.173 ms execute <unnamed>: SELECT * FROM test1 WHERE i = $1::int4
DETAIL: parameters: $1 = '2'
(This example demonstrates the folly of ignoring parse/bind steps for duration
logging purposes, BTW.)
Along the way, create a less ad-hoc mechanism for determining which commands
are logged by log_statement = mod and log_statement = ddl. The former coding
was actually missing quite a few things that look like ddl to me, and it
did not handle EXECUTE or extended query protocol correctly at all.
This commit does not do anything about the question of whether log_duration
should be removed or made less redundant with log_min_duration_statement.
Bruce Momjian [Thu, 7 Sep 2006 18:13:56 +0000 (18:13 +0000)]
Update pgcvslog comments.
Bruce Momjian [Thu, 7 Sep 2006 15:37:25 +0000 (15:37 +0000)]
Specify lo_write() to take a _const_ buffer, to match documentation.
Michael Meskes [Thu, 7 Sep 2006 11:18:47 +0000 (11:18 +0000)]
Changing a test case also changes the output that is expected.
Float/Long aliasing doesn't work on all architecures.
Michael Meskes [Thu, 7 Sep 2006 08:15:58 +0000 (08:15 +0000)]
Removed one output because integer/double usage differ
Bruce Momjian [Thu, 7 Sep 2006 00:12:20 +0000 (00:12 +0000)]
HTLM cleanup.
Bruce Momjian [Thu, 7 Sep 2006 00:10:46 +0000 (00:10 +0000)]
Update Emacs/vim editor info.
Bruce Momjian [Thu, 7 Sep 2006 00:08:43 +0000 (00:08 +0000)]
Update emacs info for FAQ_DEV.
Andrew Dunstan