git.postgresql.org Git - postgresql.git/log
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.
Not all C compilers understand the "//" comment in this test case, so I removed it.
Replaced complex tests with small ones.
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ドル
DETAIL: parameters: 1ドル = 'joe''s place'
LOG: statement: execute <unnamed>: SELECT * FROM test1 WHERE i = 1ドル::int4
DETAIL: parameters: 1ドル = '2'
and log_min_duration_statement = 0 results in
LOG: duration: 2.431 ms parse <unnamed>: SELECT * FROM test1 WHERE t = 1ドル
LOG: duration: 2.335 ms bind <unnamed> to <unnamed>: SELECT * FROM test1 WHERE t = 1ドル
DETAIL: parameters: 1ドル = 'joe''s place'
LOG: duration: 0.394 ms execute <unnamed>: SELECT * FROM test1 WHERE t = 1ドル
DETAIL: parameters: 1ドル = 'joe''s place'
LOG: duration: 1.251 ms parse <unnamed>: SELECT * FROM test1 WHERE i = 1ドル::int4
LOG: duration: 0.566 ms bind <unnamed> to <unnamed>: SELECT * FROM test1 WHERE i = 1ドル::int4
DETAIL: parameters: 1ドル = '2'
LOG: duration: 0.173 ms execute <unnamed>: SELECT * FROM test1 WHERE i = 1ドル::int4
DETAIL: parameters: 1ドル = '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.
Update pgcvslog comments.
Specify lo_write() to take a _const_ buffer, to match documentation.
Changing a test case also changes the output that is expected.
Float/Long aliasing doesn't work on all architecures.
Removed one output because integer/double usage differ
HTLM cleanup.
Update Emacs/vim editor info.
Update emacs info for FAQ_DEV.
Andrew Dunstan
Add XML documentation.
Update tools directory name.
Tom Lane [Wed, 6 Sep 2006 20:40:48 +0000 (20:40 +0000)]
Change processing of extended-Query mode so that an unnamed statement
that has parameters is always planned afresh for each Bind command,
treating the parameter values as constants in the planner. This removes
the performance penalty formerly often paid for using out-of-line
parameters --- with this definition, the planner can do constant folding,
LIKE optimization, etc. After a suggestion by Andrew@supernews.
Tom Lane [Wed, 6 Sep 2006 18:30:17 +0000 (18:30 +0000)]
Be more wary about which LIBS elements to pull into sslinfo link.
Per buildfarm results.
Fix compiler warnings on 64-bit boxes: difference between
pointers are int64, but warnings are emitted for position info in
error messages in parser, so, just cast it to int32
Add interval division/multiplication regression tests.
Michael Glaesemann
Tom Lane [Tue, 5 Sep 2006 23:15:02 +0000 (23:15 +0000)]
Fix sslinfo so it builds on Darwin.
Tom Lane [Tue, 5 Sep 2006 23:07:16 +0000 (23:07 +0000)]
Silence compiler warning about signed vs unsigned chars.
Tom Lane [Tue, 5 Sep 2006 23:02:28 +0000 (23:02 +0000)]
Silence compiler warnings about incompatible function pointer types.
Tom Lane [Tue, 5 Sep 2006 21:26:48 +0000 (21:26 +0000)]
Remove pgcrypto functions that were deprecated and slated for removal.
Marko Kreen
Tom Lane [Tue, 5 Sep 2006 21:08:36 +0000 (21:08 +0000)]
Get rid of the separate RULE privilege for tables: now only a table's owner
can create or modify rules for the table. Do setRuleCheckAsUser() while
loading rules into the relcache, rather than when defining a rule. This
ensures that permission checks for tables referenced in a rule are done with
respect to the current owner of the rule's table, whereas formerly ALTER TABLE
OWNER would fail to update the permission checking for associated rules.
Removal of separate RULE privilege is needed to prevent various scenarios
in which a grantee of RULE privilege could effectively have any privilege
of the table owner. For backwards compatibility, GRANT/REVOKE RULE is still
accepted, but it doesn't do anything. Per discussion here:
http://archives.postgresql.org/pgsql-hackers/2006-04/msg01138.php
Tom Lane [Tue, 5 Sep 2006 19:18:13 +0000 (19:18 +0000)]
Make Gen_fmgrtab.sh locale-proof. Per report from Marko Kreen and
fix suggestion from Peter.
Fix markup and license.
Fix Intel compiler bug. Per discussion
'GIN FailedAssertions on Itanium2 with Intel compiler' in pgsql-hackers,
http://archives.postgresql.org/pgsql-hackers/2006-08/msg01914.php
Add hstore contrib module.
Per discussion
http://archives.postgresql.org/pgsql-hackers/2006-08/msg01409.php
Tom Lane [Tue, 5 Sep 2006 17:20:29 +0000 (17:20 +0000)]
Remove contrib modules that have been migrated to pgfoundry: adddepend,
dbase, dbmirror, fulltextindex, mac, userlock; or abandoned: mSQL-interface,
tips.
Lost some changes yet again
Started to cleanup complex tests.
Added some interval checks to regression suite.
Synced parser.
Fixed ecpglib trying to read one character after end-of-string.
Fixed port number setting in regression suite.
Remove GIN documentation
Christopher Kings-Lynne
Fix imprecision from interval rounding of multiplication/division.
Bruce, Michael Glaesemann
Update Japanese FAQ.
Jun Kuwamura
Tom Lane [Mon, 4 Sep 2006 23:13:01 +0000 (23:13 +0000)]
Fix information_schema.key_column_usage to show correct value of
position_in_unique_constraint (column newly added per SQL2003).
Greg Mullane
Tom Lane [Mon, 4 Sep 2006 22:22:36 +0000 (22:22 +0000)]
Bring sslinfo Makefile up to speed for VPATH and pgxs builds.
Update setseed() documentation.
Update LDAP installation wording.
Albe Laurenz
Trivial patch to double vacuum speed on tables with no indexes (prevent
second scan of table).
Gregory Stark
Add MSVC build tools.
Magnus Hagander
Tom Lane [Mon, 4 Sep 2006 21:15:56 +0000 (21:15 +0000)]
Disallow TRUNCATE when there are any pending after-trigger events for
the target relation(s). There might be some cases where we could discard
the pending event instead, but for the moment a conservative approach
seems sufficient. Per report from Markus Schiltknecht and subsequent
discussion.
Sequences were not being shown due to the use of lowercase 's' instead
of 'S', and the views were not checking for table visibility with
regards to temporary tables and sequences.
Greg Sabino Mullane
Add GIN documentation.
Christopher Kings-Lynne
Mention paremeterized queries do not work with partial indexes.
Simon Riggs
Remove trailing slash use in ecpg regression script; caused failures on
some platforms.
Tom Lane [Mon, 4 Sep 2006 18:32:55 +0000 (18:32 +0000)]
Change ILIKE to invoke lower() and then do plain LIKE comparison when
working in a multibyte encoding. This fixes the problems exhibited in
bug #1931 and other reports of ILIKE misbehavior in UTF8 encoding.
It's a pretty grotty solution though --- should rethink how to do it
after we install better locale support, someday.
sslinfo contrib module - information about current SSL certificate
Author: Victor Wagner <vitus@cryptocom.ru>
Add missing gettext calls for some SSL errors.
Update Japanese readme for pgstattuple.
Tom Lane [Mon, 4 Sep 2006 02:03:04 +0000 (02:03 +0000)]
Clean up some leftover problems in pgstattuple: remove unwanted and
unportable elog(NOTICE) report, fix install/uninstall sequence.
Itagaki Takahiro
Tom Lane [Mon, 4 Sep 2006 01:26:28 +0000 (01:26 +0000)]
Fix interval input parser so that fractional weeks and months are
cascaded first to days and only what is leftover into seconds. This
seems to satisfy the principle of least surprise given the general
conversion to three-part interval values --- it was an oversight that
these cases weren't dealt with in 8.1. Michael Glaesemann
Tom Lane [Sun, 3 Sep 2006 22:37:06 +0000 (22:37 +0000)]
Code review for UPDATE SET (columnlist) patch. Make it handle as much
of the syntax as this fundamentally dead-end approach can, in particular
combinations of single and multi column assignments. Improve rather
inadequate documentation and provide some regression tests.
Tom Lane [Sun, 3 Sep 2006 22:23:58 +0000 (22:23 +0000)]
Remove duplicated index entry.
Tom Lane [Sun, 3 Sep 2006 22:15:32 +0000 (22:15 +0000)]
Fix broken markup.
Tom Lane [Sun, 3 Sep 2006 19:30:43 +0000 (19:30 +0000)]
Suppress 'unused variable' warnings created by latest commit.
Tom Lane [Sun, 3 Sep 2006 19:06:15 +0000 (19:06 +0000)]
Fix non-improvement of description of archive_timeout. archive_command
is only invoked on completed WAL segments, period --- there's no 'by
default' about it.
Tom Lane [Sun, 3 Sep 2006 15:59:39 +0000 (15:59 +0000)]
Arrange for GetSnapshotData to copy live-subtransaction XIDs from the
PGPROC array into snapshots, and use this information to avoid visits
to pg_subtrans in HeapTupleSatisfiesSnapshot. This appears to solve
the pg_subtrans-related context swap storm problem that's been reported
by several people for 8.1. While at it, modify GetSnapshotData to not
take an exclusive lock on ProcArrayLock, as closer analysis shows that
shared lock is always sufficient.
Itagaki Takahiro and Tom Lane
Remove:
< * Change LIMIT/OFFSET and FETCH/MOVE to use int8
Synced parser.
Added another regression test and fixed tcp test.
Properly round months into days and into seconds for interval
multiplication/division queries like select '41 mon 10:00:00'::interval
/ 10 as "pos".
Report from Michael Glaesemann
Reverted:
< * -Change LIMIT/OFFSET and FETCH/MOVE to use int8
> * Change LIMIT/OFFSET and FETCH/MOVE to use int8
Revert FETCH/MOVE int64 patch. Was using incorrect checks for
fetch/move in scan.l.
Update predicate locking text.
Fix case where "PM" to_timestamp() mask was eating too many characters.
Report from Josh Tolley.
Fix LLONG_MAX define used by new int64 FETCH/MOVE patch.
Remove unnecessary copyObject() call in update (values) code.
Add:
> * Simplify ability to create partitioned tables
>
> This would allow creation of partitioned tables without requiring
> creation of rules for INSERT/UPDATE/DELETE, and constraints for
> rapid partition selection. Options could include range and hash
> partition selection.
>
> * Allow auto-selection of partitioned tables for min/max() operations
Make autovacuum behavior more agressive, per discussion on hackers list
--- was part of autovacuum default 'on' patch that was reverted, but we
want this part.
Peter Eisentraut
Update postgresql.conf line for default superuser_reserved_connections.
Change "superuser_reserved_connections" default to 3, because of
possible autovacuum use.
Add URL for autovacuum default:
>
> http://archives.postgresql.org/pgsql-hackers/2006-08/msg01852.php
Use '' rather than \' for literal single quotes in strings in
/contrib/tsearch2.
Teodor Sigaev
Wording improvements for archive_timeout.
Joe Conway [Sat, 2 Sep 2006 21:11:15 +0000 (21:11 +0000)]
Added async query capability. Original patch by
Kai Londenberg, modified by Joe Conway
Small code cleanup for recent UPDATE SET (values) patch.
Add UPDATE tab SET ROW (col, ...) = (val, ...) for updating
multiple columns
Susanne Ebrecht
Update:
< Last updated: Sat Sep 2 08:31:04 EDT 2006
> Last updated: Sat Sep 2 16:31:46 EDT 2006
< o Allow UPDATE tab SET ROW (col, ...) = (...) for updating multiple
< columns
> o -Allow UPDATE tab SET ROW (col, ...) = (val, ...) for updating
> multiple columns
> o Allow UPDATE tab SET ROW (col, ...) = (SELECT...)
< A subselect can also be used as the value source.
Change FETCH/MOVE to use int8.
Dhanaraj M
Revert as not needed/inconsistent with SQL REINDEX:
Suppress some NOTICE messages from REINDEX command.
Euler Taveira de Oliveira
Remove GUC_REPORT for new "server_version_num" GUC variable. Added
overhead for every connection, per Tom.
Tom Lane [Sat, 2 Sep 2006 17:06:52 +0000 (17:06 +0000)]
Apply a simple solution to the problem of making INSERT/UPDATE/DELETE
RETURNING play nice with views/rules. To wit, have the rule rewriter
rewrite any RETURNING clause found in a rule to produce what the rule's
triggering query asked for in its RETURNING clause, in particular drop
the RETURNING clause if no RETURNING in the triggering query. This
leaves the responsibility for knowing how to produce the view's output
columns on the rule author, without requiring any fundamental changes
in rule semantics such as adding new rule event types would do. The
initial implementation constrains things to ensure that there is
exactly one, unconditionally invoked RETURNING clause among the rules
for an event --- later we might be able to relax that, but for a post
feature freeze fix it seems better to minimize how much invention we do.
Per gripe from Jaime Casanova.
Add functions to /contrib/pgstattuple that show index statistics and
index page contents.
Satoshi Nagayasu
Add new variable "server_version_num", which is almost the same as
"server_version" but uses the handy PG_VERSION_NUM which allows apps to
do things like if ($version >= 80200) without having to parse apart the
value of server_version themselves.
Greg Sabino Mullane greg@turnstep.com
Update wording:
< o -Allow PL/python to composite types and result sets
> o -Allow PL/python to return composite types and result sets
Allow PL/python to return composite types and result sets
Sven Suursoho
Done:
o -Allow PL/python to composite types and result sets
Suppress some NOTICE messages from REINDEX command.
Euler Taveira de Oliveira
Tom Lane [2006年8月31日 17:31:33 +0000 (17:31 +0000)]
Clean up rather sloppy fix in HEAD for the ancient bug that CREATE CONVERSION
didn't create a dependency from the new conversion to its schema. Back-patch
to all supported releases.
Repair interpretation of GB as MB.
Attibution addition: Add Karel Zak also for COPY SELECT.
Correct attibution:
COPY SELECT work done by Zoltan Boszormenyi
Done:
< Last updated: Tue Aug 29 12:21:52 EDT 2006
> Last updated: Wed Aug 30 20:34:28 EDT 2006
< o Allow COPY (SELECT ...) TO 'filename'
<
< COPY should also be able to output views using COPY (SELECT
< * FROM view) TO 'filename' internally.
< http://archives.postgresql.org/pgsql-patches/2005-09/msg00148.php
> o -Allow COPY (SELECT ...) TO 'filename'
Tom Lane [2006年8月30日 23:34:22 +0000 (23:34 +0000)]
Extend COPY to support COPY (SELECT ...) TO ...
Bernd Helmle
Update logging of prepare/execute syntax, per comments from Guillaume Smet.
Tom Lane [2006年8月30日 18:06:27 +0000 (18:06 +0000)]
Fix things so that fopen's, not only open's, pass FILE_SHARE_DELETE
and other special flags on Windows. May fix intermittent 'Permission
denied' errors. Magnus Hagander
Tom Lane [2006年8月29日 22:48:55 +0000 (22:48 +0000)]
Dept. of second thoughts: if query fails part way through, shut down
the pager before reporting the error.
Tom Lane [2006年8月29日 22:25:08 +0000 (22:25 +0000)]
Create a FETCH_COUNT parameter that causes psql to execute SELECT-like
queries via a cursor, fetching a limited number of rows at a time and
therefore not risking exhausting memory. A disadvantage of the scheme
is that 'aligned' output mode will align each group of rows independently
leading to odd-looking output, but all the other output formats work
reasonably well. Chris Mair, with some additional hacking by moi.
Separate prepared statement and bind parameters with comma.
Fix printing of NULL bind parameters, use "NULL".
This is the main PostgreSQL git repository.
RSS
Atom