aboutsummaryrefslogtreecommitdiff
path: root/src
Commit message (Collapse)AuthorAge
* Fix pg_dump for recent change removing separate RULE privilege.Tom Lane2006-09-08
| | | | | 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.
* Put back plan-time check for trying to apply SELECT FOR UPDATE/SHARETom Lane2006-09-08
| | | | | | 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 ...
* Tweak the behavior of log_duration as proposed by Guillaume Smet: ratherTom Lane2006-09-08
| | | | | | | 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 ↵Michael Meskes2006-09-08
| | | | removed it.
* Replaced complex tests with small ones.Michael Meskes2006-09-08
|
* More logic from complex/test* moved to their own testcases.Michael Meskes2006-09-08
|
* Clean up logging for extended-query-protocol operations, as per my recentTom Lane2006-09-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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.
* Update pgcvslog comments.Bruce Momjian2006-09-07
|
* Specify lo_write() to take a _const_ buffer, to match documentation.Bruce Momjian2006-09-07
|
* Changing a test case also changes the output that is expected.Michael Meskes2006-09-07
| | | | Float/Long aliasing doesn't work on all architecures.
* Removed one output because integer/double usage differMichael Meskes2006-09-07
|
* Update Emacs/vim editor info.Bruce Momjian2006-09-07
|
* Change processing of extended-Query mode so that an unnamed statementTom Lane2006-09-06
| | | | | | | | 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.
* Add interval division/multiplication regression tests.Bruce Momjian2006-09-06
| | | | Michael Glaesemann
* Get rid of the separate RULE privilege for tables: now only a table's ownerTom Lane2006-09-05
| | | | | | | | | | | | | 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
* Make Gen_fmgrtab.sh locale-proof. Per report from Marko Kreen andTom Lane2006-09-05
| | | | fix suggestion from Peter.
* Fix Intel compiler bug. Per discussionTeodor Sigaev2006-09-05
| | | | | 'GIN FailedAssertions on Itanium2 with Intel compiler' in pgsql-hackers, http://archives.postgresql.org/pgsql-hackers/2006-08/msg01914.php
* Lost some changes yet againMichael Meskes2006-09-05
|
* Started to cleanup complex tests.Michael Meskes2006-09-05
| | | | Added some interval checks to regression suite.
* Synced parser.Michael Meskes2006-09-05
| | | | | Fixed ecpglib trying to read one character after end-of-string. Fixed port number setting in regression suite.
* Fix imprecision from interval rounding of multiplication/division.Bruce Momjian2006-09-05
| | | | Bruce, Michael Glaesemann
* Fix information_schema.key_column_usage to show correct value ofTom Lane2006-09-04
| | | | | position_in_unique_constraint (column newly added per SQL2003). Greg Mullane
* Trivial patch to double vacuum speed on tables with no indexes (preventBruce Momjian2006-09-04
| | | | | | second scan of table). Gregory Stark
* Add MSVC build tools.Bruce Momjian2006-09-04
| | | | Magnus Hagander
* Disallow TRUNCATE when there are any pending after-trigger events forTom Lane2006-09-04
| | | | | | | 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' insteadBruce Momjian2006-09-04
| | | | | | | of 'S', and the views were not checking for table visibility with regards to temporary tables and sequences. Greg Sabino Mullane
* Remove trailing slash use in ecpg regression script; caused failures onBruce Momjian2006-09-04
| | | | some platforms.
* Change ILIKE to invoke lower() and then do plain LIKE comparison whenTom Lane2006-09-04
| | | | | | | 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 certificatePeter Eisentraut2006-09-04
| | | | Author: Victor Wagner <vitus@cryptocom.ru>
* Add missing gettext calls for some SSL errors.Peter Eisentraut2006-09-04
|
* Fix interval input parser so that fractional weeks and months areTom Lane2006-09-04
| | | | | | | 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
* Code review for UPDATE SET (columnlist) patch. Make it handle as muchTom Lane2006-09-03
| | | | | | 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.
* Suppress 'unused variable' warnings created by latest commit.Tom Lane2006-09-03
|
* Arrange for GetSnapshotData to copy live-subtransaction XIDs from theTom Lane2006-09-03
| | | | | | | | | | 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
* Synced parser.Michael Meskes2006-09-03
| | | | Added another regression test and fixed tcp test.
* Properly round months into days and into seconds for intervalBruce Momjian2006-09-03
| | | | | | | multiplication/division queries like select '41 mon 10:00:00'::interval / 10 as "pos". Report from Michael Glaesemann
* Revert FETCH/MOVE int64 patch. Was using incorrect checks forBruce Momjian2006-09-03
| | | | fetch/move in scan.l.
* Fix case where "PM" to_timestamp() mask was eating too many characters.Bruce Momjian2006-09-03
| | | | Report from Josh Tolley.
* Fix LLONG_MAX define used by new int64 FETCH/MOVE patch.Bruce Momjian2006-09-03
|
* Remove unnecessary copyObject() call in update (values) code.Bruce Momjian2006-09-03
|
* Make autovacuum behavior more agressive, per discussion on hackers listBruce Momjian2006-09-02
| | | | | | | --- 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.Bruce Momjian2006-09-02
|
* Change "superuser_reserved_connections" default to 3, because ofBruce Momjian2006-09-02
| | | | possible autovacuum use.
* Small code cleanup for recent UPDATE SET (values) patch.Bruce Momjian2006-09-02
|
* Add UPDATE tab SET ROW (col, ...) = (val, ...) for updatingBruce Momjian2006-09-02
| | | | | | multiple columns Susanne Ebrecht
* Change FETCH/MOVE to use int8.Bruce Momjian2006-09-02
| | | | Dhanaraj M
* Revert as not needed/inconsistent with SQL REINDEX:Bruce Momjian2006-09-02
| | | | | | Suppress some NOTICE messages from REINDEX command. Euler Taveira de Oliveira
* Remove GUC_REPORT for new "server_version_num" GUC variable. AddedBruce Momjian2006-09-02
| | | | overhead for every connection, per Tom.
* Apply a simple solution to the problem of making INSERT/UPDATE/DELETETom Lane2006-09-02
| | | | | | | | | | | | | | | 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 new variable "server_version_num", which is almost the same asBruce Momjian2006-09-02
| | | | | | | | "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
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-31 09:34:18 +0000