aboutsummaryrefslogtreecommitdiff
path: root/src
Commit message (Collapse)AuthorAge
* Work around bug in strxfmt() but in MS VS2005.Bruce Momjian2006-07-26
| | | | William ZHANG
* When a GUC string variable is not set, print the empty string (in SHOW etc.),Peter Eisentraut2006-07-26
| | | | | | not "unset". An "unset" state doesn't really exist; all variables behave like an empty string value if the string being pointed to has not been initialized.
* Convert effective_cache_size to an integer, for better integration withPeter Eisentraut2006-07-26
| | | | upcoming units feature.
* Change LIMIT/OFFSET to use int8Bruce Momjian2006-07-26
| | | | Dhanaraj M
* Modify btree to delete known-dead index entries without an actual VACUUM.Tom Lane2006-07-25
| | | | | | | | | | When we are about to split an index page to do an insertion, first look to see if any entries marked LP_DELETE exist on the page, and if so remove them to try to make enough space for the desired insert. This should reduce index bloat in heavily-updated tables, although of course you still need VACUUM eventually to clean up the heap. Junji Teramoto
* Add missing @OVERRIDE to 'India' config file, per Michael Fuhr.Tom Lane2006-07-25
| | | | Add $PostgreSQL$ lines for CVS identity, too.
* Remove hard-wired lists of timezone abbreviations in favor of providingTom Lane2006-07-25
| | | | | | | | | configuration files that can be altered by a DBA. The australian_timezones GUC setting disappears, replaced by a timezone_abbreviations setting (set this to 'Australia' to get the effect of australian_timezones). The list of zone names defined by default has undergone a bit of cleanup, too. Documentation still needs some work --- in particular, should we fix Table B-4, or just get rid of it? Joachim Wieland, with some editorializing by moi.
* Use correct ifdef test for cygwin, namely __CYGWIN__ (note underscores).Andrew Dunstan2006-07-25
|
* Make the order of operations in PostmasterMain a bit saner ... someTom Lane2006-07-25
| | | | recent patches had added stuff in rather random spots.
* DTrace support, with a small initial set of probesPeter Eisentraut2006-07-24
| | | | by Robert Lor
* Mark postgresql.conf entries that require server restart; some minorPeter Eisentraut2006-07-24
| | | | editing and reformatting.
* Remove dubious and redundant (we think) setting of libdir in PATH for non ↵Andrew Dunstan2006-07-24
| | | | temp-install case.
* Add a fudge factor to genericcostestimate() to prevent the planner fromTom Lane2006-07-24
| | | | | | | thinking that indexes of different sizes are equally attractive. Per gripe from Jim Nasby. (I remain unconvinced that there's such a problem in existing releases, but CVS HEAD definitely has got a problem because of its new count-only-leaf-pages approach to indexscan costing.)
* Convert the lock manager to use the new dynahash.c support for partitionedTom Lane2006-07-23
| | | | | hash tables, instead of the previous kluge involving multiple hash tables. This partially undoes my patch of last December.
* Fix oversight in sizing of shared buffer lookup hashtable. BecauseTom Lane2006-07-23
| | | | | | | | | BufferAlloc tries to insert a new mapping entry before deleting the old one for a buffer, we have a transient need for more than NBuffers entries --- one more in 8.1, and as many as NUM_BUFFER_PARTITIONS more in CVS HEAD. In theory this could lead to an "out of shared memory" failure if shmem had already been completely claimed by the time the extra entries were needed.
* Split the buffer mapping table into multiple separately lockableTom Lane2006-07-23
| | | | | partitions, as per discussion. Passes functionality checks, but I don't have any performance data yet.
* Add support to dynahash.c for partitioning shared hashtables accordingTom Lane2006-07-22
| | | | | | to the low-order bits of the entry hash value. Also make some incidental cleanups in the dynahash API, such as not exporting the hash header structs to the world.
* Hmm, seems --disable-spinlocks has been broken for awhile and nobodyTom Lane2006-07-22
| | | | | noticed. Fix SpinlockSemas() to report the correct count considering that PG 8.1 adds a spinlock to each shared-buffer header.
* In the recent changes to make the planner account better for cacheTom Lane2006-07-22
| | | | | | | effects in a nestloop inner indexscan, I had only dealt with plain index scans and the index portion of bitmap scans. But there will be cache benefits for the heap accesses of bitmap scans too, so fix cost_bitmap_heap_scan() to account for that.
* Add libdir to PATH for Cygwin as well as WIN32 - should fix buildfarm eel.Andrew Dunstan2006-07-22
|
* For automatic dependency tracking, replace our sed hackery with the GCC-Peter Eisentraut2006-07-21
| | | | | | -built-in mechanism through the -MP flag. Adjust the file extensions to look more like Automake practice. This frees up the .d suffix for use by DTrace.
* Add the full set of comparison functions for type TID, including a btreeTom Lane2006-07-21
| | | | | | | | opclass. This is not so much because anyone's likely to create an index on TID, as that sorting TIDs can be useful. Also added max and min aggregates while at it, so that one can investigate the clusteredness of a table with queries like SELECT min(ctid), max(ctid) FROM tab WHERE ... Greg Stark and Tom Lane
* Ah, I finally realize why Magnus wanted to add a --bindir option toTom Lane2006-07-21
| | | | | | | | | pg_regress: there's no other way to cope with testing a relocated installation. Seems better to call it --psqldir though, since the only thing we need to find in that case is psql. It'd be better if we could use find_other_exec, but that's not happening unless we are willing to install pg_regress alongside psql, which seems unlikely to happen.
* As a stopgap to get the Windows buildfarm members running again, hot-wireTom Lane2006-07-20
| | | | | | the check on diff's exit status to check for literally 0 or 1. Someone should look into why WIFEXITED/WEXITSTATUS don't work for this, but I've spent more than enough time on it already.
* Make pg_config location overridable for pgxs builds.Peter Eisentraut2006-07-20
|
* Print out diff status code when we think there's a hard failure.Tom Lane2006-07-20
| | | | May help in debugging behavior on Windows.
* Suppress unused-variable compiler warning, per Andrew Dunstan.Tom Lane2006-07-20
|
* Fix pg_regress.c to report tests in a parallel group when they finish,Tom Lane2006-07-20
| | | | | | not when they're started. This mimics a subtle point of the behavior of the old shell script, and gives better feedback when watching the tests.
* Make pg_regress.c get paths from pg_config_paths.h, instead of -DTom Lane2006-07-20
| | | | | switches passed from the Makefile. This looks like it will fix problem with virtual vs real paths under msys.
* Don't try to truncate multixact SLRU files in checkpoints done during xlogTom Lane2006-07-20
| | | | | | | | | | | recovery. In the first place, it doesn't work because slru's latest_page_number isn't set up yet (this is why we've been hearing reports of strange "apparent wraparound" log messages during crash recovery, but only from people who'd managed to advance their next-mxact counters some considerable distance from 0). In the second place, it seems a bit unwise to be throwing away data during crash recovery anwyway. This latter consideration convinces me to just disable truncation during recovery, rather than computing latest_page_number and pushing ahead.
* Adjust spawn_process() to avoid unnecessary overhead processes: we canTom Lane2006-07-19
| | | | | | just exec instead of creating a subprocess. This reduces process usage from four processes per parallel test to two. I have no idea whether a comparable optimization is possible or useful in the Windows port.
* Update WIN32 quoting roles documentation.Bruce Momjian2006-07-19
|
* Adjust pg_regress to print out the exact string given to system() whenTom Lane2006-07-19
| | | | | 'make install' or 'initdb' fails. Also minor simplification of fgets() usage --- fgets guarantees a trailing null anyway.
* Add WIN32 compile suggestion to pginclude README.Bruce Momjian2006-07-19
|
* kill() is declared in <signal.h> per Single Unix Spec.Tom Lane2006-07-19
|
* Tweak command quoting for Windows (I'd forgotten about SYSTEMQUOTE).Tom Lane2006-07-19
|
* Remove unnecessary inclusion of libpq into pg_regress --- overlyTom Lane2006-07-19
| | | | enthusiastic copy and paste ...
* Rewrite pg_regress as a C program instead of a shell script.Tom Lane2006-07-19
| | | | | | | This allows it to be used on Windows without installing mingw (though you do still need 'diff'), and opens the door to future improvements such as message localization. Magnus Hagander and Tom Lane.
* copydir() and rmtree() need to use lstat, not stat, to behave as expectedTom Lane2006-07-18
| | | | with symlinks. Noted while trying to use rmtree in new C-code pg_regress.
* The Win32 DEF files that are generated for libpq contain the attributeBruce Momjian2006-07-18
| | | | | | | | "DESCRIPTION", which is actually only allowed for device drivers. The compilers ignore it with a warning - if we remove them, we get rid of the warning. Magnus Hagander
* Add pginclude testing ideas.Bruce Momjian2006-07-18
|
* Mark a few functions as static or NOT_USED.Bruce Momjian2006-07-18
|
* Make pg_regress a tad simpler and more general-purpose by removing itsTom Lane2006-07-18
| | | | | | | | code to forcibly drop regressuser[1-4] and regressgroup[1-2]. Instead, let the privileges.sql test do that for itself (this is made easy by the recent addition of DROP ROLE IF EXISTS). Per a recent patch proposed by Joachim Wieland --- the rest of his patch is superseded by the rewrite into C, but this is a good idea we should adopt.
* Mention dependency problems caused by pgrminclude on include files.Bruce Momjian2006-07-17
|
* Improve psql's \df slash command to include the argument names and modesNeil Conway2006-07-17
| | | | | (OUT or INOUT) of the function. Patch from David Fetter, editorialization by Neil Conway.
* Include libpq/pqcomm.h to ensure we have correct knowledge ofTom Lane2006-07-16
| | | | HAVE_STRUCT_SOCKADDR_STORAGE_SS_LEN. Per results of pgcheckdefines.
* In a Windows backend, don't build src/port/pgsleep.c's version ofTom Lane2006-07-16
| | | | | | | | pg_usleep at all. Instead call the replacement function in port/win32/signal.c by that name. Avoids tricky macro-redefinition logic and suppresses a compiler warning; furthermore it ensures that no one can accidentally use the non-signal-aware version of pg_usleep in a Windows backend.
* Ensure that we retry rather than erroring out when send() or recv() returnTom Lane2006-07-16
| | | | | | | | | | | | EINTR; the stats code was failing to do this and so were a couple of places in the postmaster. The stats code assumed that recv() could not return EINTR if a preceding select() showed the socket to be read-ready, but this is demonstrably false with our Windows implementation of recv(), and it may not be the case on all Unix variants either. I think this explains the intermittent stats regression test failures we've been seeing, as well as reports of stats collector instability under high load on Windows. Backpatch as far as 8.0.
* Fix a few places where $Id$ and $Header$ CVS tags had crept into theTom Lane2006-07-16
| | | | source tree. They should all be $PostgreSQL$ of course.
* Fix lack of repeat-inclusion guard in win32 substitute sys/socket.h.Tom Lane2006-07-16
| | | | | | | I think this explains the 'implicit declaration of function gai_strerror' warnings visible in the current buildfarm report from snake: if sys/socket.h is included again after getaddrinfo.h, the file would merrily undefine the gai_strerror macro.
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-04 21:30:13 +0000