aboutsummaryrefslogtreecommitdiff
path: root/src/backend/utils
Commit message (Collapse)AuthorAge
...
* Make postgresql.conf.sample match the initdb defaults. This fixesBruce Momjian2006-09-14
| | | | comment alignment on most systems.
* 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).
* 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.
* 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.
* 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 imprecision from interval rounding of multiplication/division.Bruce Momjian2006-09-05
| | | | Bruce, Michael Glaesemann
* 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.
* 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
* 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
* 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
* Fix case where "PM" to_timestamp() mask was eating too many characters.Bruce Momjian2006-09-03
| | | | Report from Josh Tolley.
* 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.
* Remove GUC_REPORT for new "server_version_num" GUC variable. AddedBruce Momjian2006-09-02
| | | | overhead for every connection, per Tom.
* 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
* Repair interpretation of GB as MB.Peter Eisentraut2006-08-31
|
* Revert change to turn autovacuum on by default.Peter Eisentraut2006-08-29
|
* Now bind displays prepare as detail, and execute displays prepare andBruce Momjian2006-08-29
| | | | | | | | | | optionally bind. I re-added the "statement:" label so people will understand why the line is being printed (it is log_*statement behavior). Use single quotes for bind values, instead of double quotes, and double literal single quotes in bind values (and document that). I also made use of the DETAIL line to have much cleaner output.
* Turn autovacuum on by default. (stats_row_level is also on by default.)Peter Eisentraut2006-08-28
| | | | Threshold and scale factor are cut in half for more aggressive behavior.
* Add some notes about why it's not a bug that RI_FKey_check callsTom Lane2006-08-27
| | | | | HeapTupleSatisfiesItself without doing LockBuffer first. This code is a bit fragile, but AFAICS it's not actually broken.
* Add the ability to create indexes 'concurrently', that is, withoutTom Lane2006-08-25
| | | | | blocking concurrent writes to the table. Greg Stark, with a little help from Tom Lane.
* In new "invalid byte sequence" error hint, call it "error", notBruce Momjian2006-08-22
| | | | "failure".
* Add hint for "invalid byte sequence for encoding" error message,Bruce Momjian2006-08-22
| | | | suggesting review of client_encoding.
* Minor code rearrangement to save a few cycles in RI_FKey_check whenTom Lane2006-08-21
| | | | | the subject tuple is already deleted: we need not open the pk_rel until after we check that.
* Fix all known problems with pg_dump's handling of serial sequencesTom Lane2006-08-21
| | | | | | | | | | | | | | | | | | | | | by abandoning the idea that it should say SERIAL in the dump. Instead, dump serial sequences and column defaults just like regular ones. Add a new backend command ALTER SEQUENCE OWNED BY to let pg_dump recreate the sequence-to-column dependency that was formerly created "behind the scenes" by SERIAL. This restores SERIAL to being truly "just a macro" consisting of component operations that can be stated explicitly in SQL. Furthermore, the new command allows sequence ownership to be reassigned, so that old mistakes can be cleaned up. Also, downgrade the OWNED-BY dependency from INTERNAL to AUTO, since there is no longer any very compelling argument why the sequence couldn't be dropped while keeping the column. (This forces initdb, to be sure the right kinds of dependencies are in there.) Along the way, add checks to prevent ALTER OWNER or SET SCHEMA on an owned sequence; you can now only do this indirectly by changing the owning table's owner or schema. This is an oversight in previous releases, but probably not worth back-patching.
* Add a 'waiting' column to pg_stat_activity to carry the same informationTom Lane2006-08-19
| | | | | | | that ps_status provides by appending 'waiting' to the PS display. This completes the project of making it feasible to turn off process title updates and instead rely on pg_stat_activity. Per my suggestion a few weeks ago.
* Implement archive_timeout feature to force xlog file switches to occur no moreTom Lane2006-08-17
| | | | | | | | | | | than N seconds apart. This allows a simple, if not very high performance, means of guaranteeing that a PITR archive is no more than N seconds behind real time. Also make pg_current_xlog_location return the WAL Write pointer, add pg_current_xlog_insert_location to return the Insert pointer, and fix pg_xlogfile_name_offset to return its results as a two-element record instead of a smashed-together string, as per recent discussion. Simon Riggs
* Seems some C compilers think 'restrict' is a fully reserved word.Tom Lane2006-08-16
| | | | Per buildfarm results from warthog.
* Add a hack so that get_type_io_data() can work from bootstrap.c'sTom Lane2006-08-15
| | | | | | internal TypInfo table in bootstrap mode. This allows array_in and array_out to be used during early bootstrap, which eliminates the former obstacle to giving OUT parameters to built-in functions.
* Add server support for "plugin" libraries that can be used for add-on tasksTom Lane2006-08-15
| | | | | | | | | | | | | | | | | | such as debugging and performance measurement. This consists of two features: a table of "rendezvous variables" that allows separately-loaded shared libraries to communicate, and a new GUC setting "local_preload_libraries" that allows libraries to be loaded into specific sessions without explicit cooperation from the client application. To make local_preload_libraries as flexible as possible, we do not restrict its use to superusers; instead, it is restricted to load only libraries stored in $libdir/plugins/. The existing LOAD command has also been modified to allow non-superusers to LOAD libraries stored in this directory. This patch also renames the existing GUC variable preload_libraries to shared_preload_libraries (after a suggestion by Simon Riggs) and does some code refactoring in dfmgr.c to improve clarity. Korry Douglas, with a little help from Tom Lane.
* Fix oversight in initial implementation of PORTAL_ONE_RETURNING mode: weTom Lane2006-08-14
| | | | | | | | | | cannot assume that there's exactly one Query in the Portal, as we can for ONE_SELECT mode, because non-SELECT queries might have extra queries added during rule rewrites. Fix things up so that we'll use ONE_RETURNING mode when a Portal contains one primary (canSetTag) query and that query has a RETURNING list. This appears to be a second showstopper reason for running the Portal to completion before we start to hand anything back --- we want to be sure that the rule-added queries get run too.
* Remove hash_destroy calls in hash_create's failure paths. As noted byTom Lane2006-08-14
| | | | | | | a Coverity warning, these are risky since the hashtable isn't necessarily fully set up yet. They're unnecessary anyway: a deletable hashtable should be in a memory context that will be cleared following elog(ERROR). Per report from Martijn van Oosterhout.
* Revert (again) GUC patch to return commented fields to their defaultBruce Momjian2006-08-14
| | | | values, due to concern about the patch.
* Fix recent guc comment-to-default patch for custom variables.Bruce Momjian2006-08-13
|
* Recommit patch to allow commented GUC variables to return to theirBruce Momjian2006-08-13
| | | | default values.
* Re-apply guc cleanup patch, with memory allocation bugs fixed.Bruce Momjian2006-08-13
|
* Back out patch to reorganize guc processing. Was causing regressionBruce Momjian2006-08-12
| | | | failures.
* Back out patch that allowed commented guc variables to return to theirBruce Momjian2006-08-12
| | | | default values. Was causing regression failures.
* Add INSERT/UPDATE/DELETE RETURNING, with basic docs and regression tests.Tom Lane2006-08-12
| | | | | | | | plpgsql support to come later. Along the way, convert execMain's SELECT INTO support into a DestReceiver, in order to eliminate some ugly special cases. Jonah Harris and Tom Lane
* Allow commenting of variables in postgresql.conf to restore them toBruce Momjian2006-08-11
| | | | | | defaults. Zdenek Kotala
* Refactor GUC set_config_option function:Bruce Momjian2006-08-11
| | | | | | | | | | | | | | | | | | The main reason for refactoring was that set_config_option() was too overloaded function and its behavior did not consistent. Old version of set_config_function hides some messages. For example if you type: tcp_port = 5432.1 then old implementation ignore this error without any message to log file in the signal context (configuration reload). Main problem was that semantic analysis of postgresql.conf is not perform in the ProcessConfigFile function, but in the set_config_options *after* context check. This skipped check for variables with PG_POSTMASTER context. There was request from Joachim Wieland to add more messages about ignored changes in the config file as well. Zdenek Kotala
* Add a feature for automatic initialization and finalization of dynamicallyTom Lane2006-08-08
| | | | | | | | | loaded libraries: call functions _PG_init() and _PG_fini() if the library defines such symbols. Hence we no longer need to specify an initialization function in preload_libraries: we can assume that the library used the _PG_init() convention, instead. This removes one source of pilot error in use of preloaded libraries. Original patch by Ralf Engelschall, preload_libraries changes by me.
* For protocol-level prepare/bind/execute:Bruce Momjian2006-08-08
| | | | | | | | o print user name for all o print portal name if defined for all o print query for all o reduce log_statement header to single keyword o print bind parameters as DETAIL if text mode
* Fix domain_in() bug exhibited by Darcy Buskermolen. The idea of an EStateTom Lane2006-08-04
| | | | | | | | | | | | | that's shorter-lived than the expression state being evaluated in it really doesn't work :-( --- we end up with fn_extra caches getting deleted while still in use. Rather than abandon the notion of caching expression state across domain_in calls altogether, I chose to make domain_in a bit cozier with ExprContext. All we really need for evaluating variable-free expressions is an ExprContext, not an EState, so I invented the notion of a "standalone" ExprContext. domain_in can prevent resource leakages by doing a ReScanExprContext on this rather than having to free it entirely; so we can make the ExprContext have the same lifespan (and particularly the same per_query memory context) as the expression state structs.
* Move 'ddl' right after 'none' in postgresql.conf. It used to be betweenBruce Momjian2006-08-02
| | | | | 'mod' and 'all', which is not the right order. SGML documentation order was correct. Report from Chander Ganesan.
* Add support for multi-row VALUES clauses as part of INSERT statementsJoe Conway2006-08-02
| | | | | | (e.g. "INSERT ... VALUES (...), (...), ...") and elsewhere as allowed by the spec. (e.g. similar to a FROM clause subselect). initdb required. Joe Conway and Tom Lane.
* Change the relation_open protocol so that we obtain lock on a relationTom Lane2006-07-31
| | | | | | | | | | | | (table or index) before trying to open its relcache entry. This fixes race conditions in which someone else commits a change to the relation's catalog entries while we are in process of doing relcache load. Problems of that ilk have been reported sporadically for years, but it was not really practical to fix until recently --- for instance, the recent addition of WAL-log support for in-place updates helped. Along the way, remove pg_am.amconcurrent: all AMs are now expected to support concurrent update.
* Adjust initialization sequence for timezone_abbreviations so thatTom Lane2006-07-29
| | | | | | | | | it's handled just about like timezone; in particular, don't try to read anything during InitializeGUCOptions. Should solve current startup failure on Windows, and avoid wasted cycles if a nondefault setting is specified in postgresql.conf too. Possibly we need to think about a more general solution for handling 'expensive to set' GUC options.
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-03 02:12:55 +0000