Commit Graph

23332 Commits

Author SHA1 Message Date
Bruce Momjian 3e6d1efa4a Add:
> * Research storing only active XIDs in subtransaction cache
2006-09-14 20:30:35 +00:00
Bruce Momjian a6e240a30f Add XML item.
>
> * Improve XML support
>
>   http://developer.postgresql.org/index.php/XML_Support
2006-09-14 18:10:38 +00:00
Bruce Momjian fa2801e361 Add description for variable-length header:
> 	  One idea is to store the header in network byte order (high bits
> 	  first), and read the high bits to determine the header length.
2006-09-14 17:34:14 +00:00
Bruce Momjian 536316aa42 Add recent ICU URL:
>   http://archives.postgresql.org/pgsql-hackers/2006-09/msg00662.php
2006-09-14 17:14:53 +00:00
Bruce Momjian 7f75537cd7 Update TODO items:
< 	o Store disk pages with no alignment/padding?
>
> 	  This involves having the user-specified order of columns
> 	  be different from the physical order.  SELECT * would
> 	  need to reorder the physical values to match the
> 	  user-specified ordering.
>
> 	o Store disk pages with no alignment/padding?
>
> 	  This necessitates adding CPU-required padding when moving
> 	  rows from disk to memory.
>
>
> 	  http://archives.postgresql.org/pgsql-hackers/2006-09/msg00848.php
>
2006-09-14 17:11:51 +00:00
Bruce Momjian 9256b84e61 For release notes checklist, add UTF8 URL. 2006-09-14 16:55:43 +00:00
Bruce Momjian 4f7b0fb103 In release notes checklist, add URL for HTML non-ASCII escapes, mention
UTF8 escapes.
2006-09-14 16:51:39 +00:00
Teodor Sigaev e25c3e84b6 Fix SGML markup 2006-09-14 13:40:28 +00:00
Teodor Sigaev deb66e013c Improve error message. Per discussion
http://archives.postgresql.org/pgsql-general/2006-09/msg00186.php
2006-09-14 11:26:49 +00:00
Teodor Sigaev 0ca9907ce4 GIN documentation and slightly improving GiST docs.
Thanks to  Christopher Kings-Lynne <chris.kingslynne@gmail.com> for
initial version and Jeff Davis <pgsql@j-davis.com> for inspection
2006-09-14 11:16:27 +00:00
Michael Meskes 4eef745fb1 Cygwin systems seem to have a different error message when trying to connect to port 0. Let's try port 20 instead. 2006-09-14 08:46:58 +00:00
Michael Meskes 0f0d6765ce Added missing constuctor/destructor for interval and date. 2006-09-14 08:02:38 +00:00
Tom Lane f8fe328c24 Some small editorialization on the description of CREATE INDEX
CONCURRENTLY.  Greg Stark, some further tweaks by me.
2006-09-13 23:42:26 +00:00
Tom Lane 0b4bf8537f Make logging of extended-protocol commands a bit more consistent, per
discussion with Guillaume Smet.
2006-09-13 21:59:04 +00:00
Tom Lane 33d3ad4657 Code review for patch to avoid second scan when vacuuming index-less
table: avoid invoking LockBufferForCleanup without need, put out the
same log message we would have before, minor code beautification.
2006-09-13 17:47:08 +00:00
Tatsuo Ishii ea21eea6a8 Change "tps" to "scale" to avoid confusion
Fix bug with handling default scaling factor in the default
scenarios
2006-09-13 00:39:19 +00:00
Bruce Momjian 500da222f1 Add David Fetter:
> * David is David Fetter <david@fetter.org>
2006-09-12 21:02:43 +00:00
Teodor Sigaev 67e7f0ab34 Add uninstall script 2006-09-12 16:11:44 +00:00
Tom Lane d3f54c7907 Spell readme file's name correctly, per buildfarm reports. 2006-09-12 14:47:24 +00:00
Peter Eisentraut e79380e5ae Small fix for the README install for contrib/sslinfo.
Dave Page
2006-09-12 11:46:11 +00:00
Michael Meskes 9c356a6b3e Seems this wasn't committed originally 2006-09-12 09:09:31 +00:00
Tom Lane 568b80168f Move set_pglocale_pgservice() from path.c to exec.c, so that pulling in
path.c does not in itself force linking of both exec.c and libintl.
Should fix current ecpglib build failure on pickier platforms.
2006-09-11 20:10:30 +00:00
Tom Lane 7ce2ff2d22 Move xml2's PG_MODULE_MAGIC block to the right source file, per Michael Fuhr. 2006-09-11 15:30:32 +00:00
Tom Lane 41dcc65c0e Rename the uninstall scripts for contrib/lo and contrib/tsearch2 to
match the convention that foo's uninstall script is uninstall_foo.sql.
Also, stop installing lo_test.sql, which really ought to be made into
a regression test anyway (though it's unclear how to avoid a dependency
on the current OID counter...)
2006-09-11 15:14:46 +00:00
Tom Lane 0bdc18d5d1 Add LDAP_LIBS_FE to $(libpq) for static or AIX linking, per Albe Laurenz. 2006-09-11 13:35:08 +00:00
Tom Lane bb87c7b551 Ooops, forgot to update ecpg comparison files to match
source-code change.
2006-09-11 02:50:07 +00:00
Tom Lane 9fc4c6b20b Fix omissions in contrib uninstall scripts. Michael Fuhr 2006-09-11 02:10:26 +00:00
Tom Lane 1d0b7e71e3 Fix unportable usage complained of by icc. Per buildfarm results. 2006-09-11 01:41:35 +00:00
Bruce Momjian d18768867e Remove unnecessary brace pair. 2006-09-10 23:33:22 +00:00
Bruce Momjian 94cf48d72b Back out patch added during 8.2.X development:
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).
2006-09-10 22:54:47 +00:00
Bruce Momjian a80b1b4bfc Add items:
< * Research storing disk pages with no alignment/padding
> * Consider ways of storing rows more compactly on disk
>
> 	o Store disk pages with no alignment/padding?
> 	o Reorder physical storage order to reduce padding?
> 	o Support a smaller header for short variable-length fields?
> 	o Reduce the row header size?
2006-09-10 22:20:01 +00:00
Tom Lane 4ee24cbb55 Install a cleaner solution to the AIX libpq linking problem, as per
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.
2006-09-10 22:07:02 +00:00
Tom Lane 723af8e67a Fix dblink build for --enable-nls or --enable-openssl on AIX.
Per Chris Browne.
2006-09-10 21:38:26 +00:00
Tom Lane 17c371fe82 Remove unhelpful/misleading advice about how to use SPI_saveplan().
Per gripe from Jack Orenstein.
2006-09-10 20:56:42 +00:00
Tom Lane 5e08e49637 contrib/isn updates from Jeremy Kronuz. 2006-09-10 20:45:17 +00:00
Tom Lane f5b4d9a9e0 If we're going to advertise the array overlap/containment operators,
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.
2006-09-10 20:14:20 +00:00
Tom Lane 69b7c99265 Add missing documentation for new anyarray-overlap operator. 2006-09-10 19:03:57 +00:00
Tom Lane 684ad6a92f Rename contrib contains/contained-by operators to @> and <@, per discussion. 2006-09-10 17:36:52 +00:00
Tom Lane ba920e1c91 Rename contains/contained-by operators to @> and <@, per discussion that
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.
2006-09-10 00:29:35 +00:00
Tom Lane 9cea5a82f8 Remove reference to contrib/mac, which isn't there anymore. 2006-09-09 18:45:37 +00:00
Tom Lane dff84dc762 Add contrib/isn module for ISBN/ISSN/EAN13/etc product numbers, and
remove the old isbn_issn module which is about to be obsoleted by EAN13.
contrib/isn is by Germán Méndez Bravo.  Our thanks to Garrett A. Wollman
for having written the original isbn_issn module.
2006-09-09 04:07:52 +00:00
Tom Lane 42c17a6bb0 Revise OpenLDAP configuration and linking to work on more platforms
than before.  Albe Laurenz (but editorialized heavily by me, so if it
doesn't work it's my fault).
2006-09-09 03:15:40 +00:00
Tom Lane bf6b92d6e0 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.
2006-09-08 18:05:35 +00:00
Tom Lane d09e79deb9 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 ...
2006-09-08 17:49:13 +00:00
Tom Lane b59d31c215 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.
2006-09-08 15:55:53 +00:00
Michael Meskes 0b33c56297 Not all C compilers understand the "//" comment in this test case, so I removed it. 2006-09-08 14:58:27 +00:00
Michael Meskes 460f46816a Replaced complex tests with small ones. 2006-09-08 13:32:29 +00:00
Michael Meskes 52a013bea8 More logic from complex/test* moved to their own testcases. 2006-09-08 09:03:40 +00:00
Tom Lane 893632be4e 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
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.
2006-09-07 22:52:01 +00:00
Bruce Momjian b6eab50ce4 Update pgcvslog comments. 2006-09-07 18:13:56 +00:00