aboutsummaryrefslogtreecommitdiff
path: root/src
Commit message (Collapse)AuthorAge
* Add built-in userlock manipulation functions to replace the formerTom Lane2006-09-18
| | | | | | | 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.
* Fix problems with column name list of CREATE TABLE AS being applied toTom Lane2006-09-18
| | | | | the input query's target list too soon, causing it to affect processing of ORDER BY in the input query.
* Fix CREATE TABLE ... AS VALUES ... to work rather than Assert'ing;Tom Lane2006-09-18
| | | | | | 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.
* Change ANALYZE to take ShareUpdateExclusiveLock not AccessShareLock onTom Lane2006-09-17
| | | | | | | | | | | | 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.
* Marginal cleanup in arrangements for ensuring StrategyHintVacuum is clearedTom Lane2006-09-17
| | | | | | | | | 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.
* Rename the recently-added pg_timezonenames view to pg_timezone_abbrevs,Tom Lane2006-09-16
| | | | | | 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.
* Update timezone data files to release 2006k of the zic database.Tom Lane2006-09-16
|
* Define errcode as __msvc_errcode not __vc_errcode for MSVC builds,Tom Lane2006-09-16
| | | | per Magnus.
* Several fixes for MSVC build scripts, from Magnus.Tom Lane2006-09-15
|
* Fix some uses of str[n]casecmp that should be pg_str[n]casecmp,Tom Lane2006-09-15
| | | | per Magnus.
* Remove WINLDAPAPI decoration from ldap_start_tls_sA typedef, per Magnus.Tom Lane2006-09-15
|
* Improve confusing comment for HeapTupleSatisfiesNow, per gripe from Greg Stark.Tom Lane2006-09-15
|
* Make postgresql.conf.sample match the initdb defaults. This fixesBruce Momjian2006-09-14
| | | | comment alignment on most systems.
* Add a couple of information functions to support direct checks on whetherTom Lane2006-09-14
| | | | | | 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.
* Improve error message. Per discussionTeodor Sigaev2006-09-14
| | | | http://archives.postgresql.org/pgsql-general/2006-09/msg00186.php
* Cygwin systems seem to have a different error message when trying to connect ↵Michael Meskes2006-09-14
| | | | to port 0. Let's try port 20 instead.
* Added missing constuctor/destructor for interval and date.Michael Meskes2006-09-14
|
* Make logging of extended-protocol commands a bit more consistent, perTom Lane2006-09-13
| | | | discussion with Guillaume Smet.
* Code review for patch to avoid second scan when vacuuming index-lessTom Lane2006-09-13
| | | | | table: avoid invoking LockBufferForCleanup without need, put out the same log message we would have before, minor code beautification.
* Seems this wasn't committed originallyMichael Meskes2006-09-12
|
* Move set_pglocale_pgservice() from path.c to exec.c, so that pulling inTom Lane2006-09-11
| | | | | path.c does not in itself force linking of both exec.c and libintl. Should fix current ecpglib build failure on pickier platforms.
* Add LDAP_LIBS_FE to $(libpq) for static or AIX linking, per Albe Laurenz.Tom Lane2006-09-11
|
* Ooops, forgot to update ecpg comparison files to matchTom Lane2006-09-11
| | | | source-code change.
* Fix unportable usage complained of by icc. Per buildfarm results.Tom Lane2006-09-11
|
* Remove unnecessary brace pair.Bruce Momjian2006-09-10
|
* Back out patch added during 8.2.X development:Bruce Momjian2006-09-10
| | | | | | | 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).
* Install a cleaner solution to the AIX libpq linking problem, as perTom Lane2006-09-10
| | | | | | | 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.
* If we're going to advertise the array overlap/containment operators,Tom Lane2006-09-10
| | | | | | 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.
* Rename contains/contained-by operators to @> and <@, per discussion thatTom Lane2006-09-10
| | | | | | | | 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.
* Revise OpenLDAP configuration and linking to work on more platformsTom Lane2006-09-09
| | | | | than before. Albe Laurenz (but editorialized heavily by me, so if it doesn't work it's my fault).
* 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.
generated by cgit v1.2.3 (git 2.25.1) at 2025-06-24 18:32:46 +0000