mirrors/postgres
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
21,774 Commits 37 Branches 632 Tags
Commit Graph

21774 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Bruce Momjian
6d41b144e9 Add: 
>
> 	* Allow SERIAL sequences to inherit permissions from the base table?
 2006-01-05 17:47:53 +00:00
Bruce Momjian
9a47ad1d20 Add logging control TODO.detail. 2006-01-05 17:28:45 +00:00
Bruce Momjian
db6cb1a9a9 Update: 
<   stable logging probably can not have indexes.  [wallog]
>   stable logging probably can not have indexes.  [walcontrol]
 2006-01-05 16:39:54 +00:00
Bruce Momjian
ac9e14d064 Update wording: 
<   STABLE | DEFAULT ].  [wallog]
>   STABLE | DEFAULT ].  Tables using non-default logging should not use
>   referential integrity with default-logging tables, and tables using
>   stable logging probably can not have indexes.  [wallog]
 2006-01-05 16:35:19 +00:00
Bruce Momjian
e7893db5cf Update wording: 
<   the table. Another option is to avoid transaction logging entirely
<   and truncate or drop the table on crash recovery.  These should be
<   implemented using ALTER TABLE, e.g. ALTER TABLE PERSISTENCE [ DROP |
<   TRUNCATE | STABLE | DEFAULT ].  [wallog]
>   the table.  This would affect COPY, and perhaps INSERT/UPDATE too.
>   Another option is to avoid transaction logging entirely and truncate
>   or drop the table on crash recovery.  These should be implemented
>   using ALTER TABLE, e.g. ALTER TABLE PERSISTENCE [ DROP | TRUNCATE |
>   STABLE | DEFAULT ].  [wallog]
 2006-01-05 16:26:49 +00:00
Bruce Momjian
1b736817d0 Add: 
>
> * Allow control over which tables are WAL-logged
>
>   Allow tables to bypass WAL writes and just fsync() dirty pages on
>   commit.  To do this, only a single writer can modify the table, and
>   writes must happen only on new pages.  Readers can continue accessing
>   the table. Another option is to avoid transaction logging entirely
>   and truncate or drop the table on crash recovery.  These should be
>   implemented using ALTER TABLE, e.g. ALTER TABLE PERSISTENCE [ DROP |
>   TRUNCATE | STABLE | DEFAULT ].  [wallog]
 2006-01-05 16:23:48 +00:00
Bruce Momjian
33cd2706ad Update x86 Solaris documenation ideas. 2006-01-05 15:56:54 +00:00
Bruce Momjian
449c8af127 Add compile flags sample. 2006-01-05 15:31:23 +00:00
Bruce Momjian
04236bb296 New pgcrypto item wording. 2006-01-05 15:19:05 +00:00
Bruce Momjian
3002492fc7 Update item: 
< * %Remove behavior of postmaster -o after making postmaster/postgres
<   flags unique
> * %Remove behavior of postmaster -o
 2006-01-05 15:13:32 +00:00
Bruce Momjian
8b2b1d87f8 Wording improvements. 2006-01-05 15:12:36 +00:00
Bruce Momjian
1c59af06db Improve markup. 2006-01-05 14:53:47 +00:00
Peter Eisentraut
86c23a6eb2 Make all command-line options of postmaster and postgres the same. See 
http://archives.postgresql.org/pgsql-hackers/2006-01/msg00151.php for the
complete plan.
 2006-01-05 10:07:46 +00:00
Bruce Momjian
4e1712ea54 Update release notes for 8.1.X, 8.0.X, 7.4.X, and 7.3.X. 2006-01-05 05:15:50 +00:00
Bruce Momjian
0dc43870ae Update version number. 2006-01-05 03:55:13 +00:00
Bruce Momjian
9be5beb918 Done: 
> * -Remove BeOS and QNX-specific code
 2006-01-05 03:02:03 +00:00
Bruce Momjian
44f9021223 Remove BEOS port. 2006-01-05 03:01:38 +00:00
Bruce Momjian
6f84b2da75 Remove QNX file. 2006-01-05 02:43:38 +00:00
Bruce Momjian
a1675649e4 Remove QNX port. 2006-01-05 01:56:30 +00:00
Tom Lane
349f40b2c2 Rearrange backend startup sequence so that ShmemIndexLock can become 
an LWLock instead of a spinlock.  This hardly matters on Unix machines
but should improve startup performance on Windows (or any port using
EXEC_BACKEND).  Per previous discussion.
 2006-01-04 21:06:32 +00:00
Tom Lane
e0078ea22d Fix another case in which autovacuum would fail while analyzing 
expressional indexes.  Per report from Brian Hirt.
 2006-01-04 19:16:24 +00:00
Tom Lane
507e07e277 There is a signedness bug in Openwall gen_salt code that pgcrypto uses. 
This makes the salt space for md5 and xdes algorithms a lot smaller than
it should be.

Marko Kreen
 2006-01-03 23:46:24 +00:00
Joe Conway
925952603d When the remote query result has a different number of columns 
than the local query specifies (e.g. in the FROM clause),
throw an ERROR (instead of crashing). Fix for bug #2129 reported
by Akio Iwaasa.
 2006-01-03 23:45:52 +00:00
Tom Lane
71ad8e2077 Fix incorrect treatment of RL_PROMPT_START_IGNORE/RL_PROMPT_END_IGNORE, 
per http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=343616 via Martin Pitt.
 2006-01-03 23:32:30 +00:00
Tom Lane
41ec930d7c Add checks to verify that a plpgsql function returning a rowtype is actually 
returning the rowtype it's supposed to return.  Per reports from David Niblett
and Michael Fuhr.
 2006-01-03 22:48:10 +00:00
Bruce Momjian
75bb2b611d Assume select() might modify struct timeout, so remove previous 
optimization.
 2006-01-03 19:54:08 +00:00
Bruce Momjian
447450df71 Use setitimer() for stats file write, rather than do a gettimeofday() 
call for every stats packet read to adjust select() timeout.  Other
stylistic improvements.
 2006-01-03 16:42:17 +00:00
Tom Lane
fd924b2988 Don't assume that LC_MESSAGES is always available on WIN32. Per Magnus. 2006-01-02 20:25:45 +00:00
Tom Lane
499f4d5e1e Reset flex state in a way that works for both flex 2.5.4 and 2.5.31. 2006-01-02 19:55:25 +00:00
Andrew Dunstan
14d6c9fe6f Remove the nexus between trial_buffs and trial_conns, and don't test shared buffers lower than or equal to a value we already know is good, but use that value instead. This will make it easier to adjust the trial values and/or formulae in future if necessary. 2006-01-02 16:45:12 +00:00
Bruce Momjian
bb1bba8eca Remove unnecessary assignment, per Tom. 2006-01-02 03:30:41 +00:00
Bruce Momjian
9625b18493 Change if (!(x || y)) construct with if (!x && !y), for clarity. 2006-01-02 00:58:00 +00:00
Tom Lane
fc6da31ae1 Rewrite ProcessConfigFile() to avoid misbehavior at EOF, as per report 
from Andrus Moor.  The former state-machine-style coding wasn't actually
doing much except obscuring the control flow, and it didn't extend
readily to fix this case, so I just took it out.  Also, add a
YY_FLUSH_BUFFER call to ensure the lexer is reset correctly if the
previous scan failed partway through the file.
 2006-01-01 19:52:40 +00:00
Neil Conway
0898033b1e Remove DOS line endings ("\r\n") from several .po files. DOS line endings 
are inconsistent with the rest of the .po files, and apparently cause
problems for Sun's cc. Per report on IRC from "bitvector2".
 2006-01-01 10:13:56 +00:00
Neil Conway
c20a9f25af Trim an obsolete comment: it is no longer relevant that "SELECT" was 
formerly "RETRIEVE", and so forth.
 2006-01-01 01:41:42 +00:00
Tom Lane
bcb26d74cb Clean up initdb's code for selecting max_connections and shared_buffers 
a little bit, and set the minimum buffers-per-connection ratio to 10 not
5.  I folded the two test routines into one to counteract the illusion
that the tests can be twiddled independently, and added some documentation
pointing out the necessary connection between the sets of values tested.
Fixes strange choices of parameters that I noticed CVS tip making on
Darwin with Apple's undersized default SHMMAX.
 2005-12-31 23:50:59 +00:00
Bruce Momjian
dbf53e6345 Rename variable to cmd_str. 2005-12-31 19:39:11 +00:00
Bruce Momjian
ba3e1cb8c2 Rename variable 'what' to 'stat_msg'. 2005-12-31 17:46:19 +00:00
Bruce Momjian
206499d2fb Prefix client-side prepare with '[protocol]' rather than '[client]'. 2005-12-31 16:50:44 +00:00
Bruce Momjian
a8a93f72c5 Rename send_rfq to send_ready_for_query. 2005-12-30 23:49:48 +00:00
Bruce Momjian
c86be11ddc Mmark client-side prepare/bind/execute statements with "[client]" so 
they can be easily distinguished from SQL commands.
 2005-12-30 22:55:20 +00:00
Bruce Momjian
12af9cdff4 Add support for Solaris x86_64 using Sun's compiler. 
Pierre Girard
 2005-12-30 21:43:41 +00:00
Tom Lane
c876d965f5 Repair EXPLAIN failure when trying to display a plan condition that involves 
selection of a field from the result of a function returning RECORD.
I believe this case is new in 8.1; it's due to the addition of OUT parameters.
Per example from Michael Fuhr.
 2005-12-30 18:34:22 +00:00
Bruce Momjian
7211ff7d32 Add: 
> * Make CLUSTER preserve recently-dead tuples per MVCC requirements
 2005-12-30 03:24:58 +00:00
Peter Eisentraut
810530020f Disallow setting ssl = on if SSL is not compiled in. 2005-12-30 00:13:50 +00:00
Neil Conway
edafb4f037 Index: src/pl/plpython/plpython.c 
===================================================================
RCS file: /Users/neilc/postgres/cvs_root/pgsql/src/pl/plpython/plpython.c,v
retrieving revision 1.67
diff -c -r1.67 plpython.c
*** src/pl/plpython/plpython.c	26 Dec 2005 04:28:48 -0000	1.67
--- src/pl/plpython/plpython.c	29 Dec 2005 16:54:57 -0000
***************
*** 2,8 ****
   * plpython.c - python as a procedural language for PostgreSQL
   *
   * This software is copyright by Andrew Bosma
!  * but is really shameless cribbed from pltcl.c by Jan Weick, and
   * plperl.c by Mark Hollomon.
   *
   * The author hereby grants permission to use, copy, modify,
--- 2,8 ----
   * plpython.c - python as a procedural language for PostgreSQL
   *
   * This software is copyright by Andrew Bosma
!  * but is really shamelessly cribbed from pltcl.c by Jan Wieck, and
   * plperl.c by Mark Hollomon.
   *
   * The author hereby grants permission to use, copy, modify,
***************
*** 1996,2002 ****
  	int			i,
  				rv;
  	PLyPlanObject *plan;
- 	char	   *nulls;
  	MemoryContext oldcontext;

  	if (list != NULL)
--- 1996,2001 ----
***************
*** 2018,2024 ****
  	if (nargs != plan->nargs)
  	{
  		char	   *sv;
-
  		PyObject   *so = PyObject_Str(list);

  		if (!so)
--- 2017,2022 ----
***************
*** 2036,2048 ****
  	oldcontext = CurrentMemoryContext;
  	PG_TRY();
  	{
! 		nulls = palloc(nargs * sizeof(char));

  		for (i = 0; i < nargs; i++)
  		{
  			PyObject   *elem,
  					   *so;
- 			char	   *sv;

  			elem = PySequence_GetItem(list, i);
  			if (elem != Py_None)
--- 2034,2045 ----
  	oldcontext = CurrentMemoryContext;
  	PG_TRY();
  	{
! 		char	   *nulls = palloc(nargs * sizeof(char));

  		for (i = 0; i < nargs; i++)
  		{
  			PyObject   *elem,
  					   *so;

  			elem = PySequence_GetItem(list, i);
  			if (elem != Py_None)
***************
*** 2051,2070 ****
  				if (!so)
  					PLy_elog(ERROR, "function \"%s\" could not execute plan",
  							 PLy_procedure_name(PLy_curr_procedure));
! 				sv = PyString_AsString(so);

! 				/*
! 				 * FIXME -- if this elogs, we have Python reference leak
! 				 */
! 				plan->values[i] =
! 					FunctionCall3(&(plan->args[i].out.d.typfunc),
! 								  CStringGetDatum(sv),
! 							ObjectIdGetDatum(plan->args[i].out.d.typioparam),
! 								  Int32GetDatum(-1));

! 				Py_DECREF(so);
! 				Py_DECREF(elem);

  				nulls[i] = ' ';
  			}
  			else
--- 2048,2073 ----
  				if (!so)
  					PLy_elog(ERROR, "function \"%s\" could not execute plan",
  							 PLy_procedure_name(PLy_curr_procedure));
! 				Py_DECREF(elem);

! 				PG_TRY();
! 				{
! 					char *sv = PyString_AsString(so);

! 					plan->values[i] =
! 						FunctionCall3(&(plan->args[i].out.d.typfunc),
! 									  CStringGetDatum(sv),
! 								ObjectIdGetDatum(plan->args[i].out.d.typioparam),
! 									  Int32GetDatum(-1));
! 				}
! 				PG_CATCH();
! 				{
! 					Py_DECREF(so);
! 					PG_RE_THROW();
! 				}
! 				PG_END_TRY();

+ 				Py_DECREF(so);
  				nulls[i] = ' ';
  			}
  			else
 2005-12-29 21:47:32 +00:00
Tom Lane
195f164228 Get rid of the SpinLockAcquire/SpinLockAcquire_NoHoldoff distinction 
in favor of having just one set of macros that don't do HOLD/RESUME_INTERRUPTS
(hence, these correspond to the old SpinLockAcquire_NoHoldoff case).
Given our coding rules for spinlock use, there is no reason to allow
CHECK_FOR_INTERRUPTS to be done while holding a spinlock, and also there
is no situation where ImmediateInterruptOK will be true while holding a
spinlock.  Therefore doing HOLD/RESUME_INTERRUPTS while taking/releasing a
spinlock is just a waste of cycles.  Qingqing Zhou and Tom Lane.
 2005-12-29 18:08:05 +00:00
Bruce Momjian
e135d9631b Update: 
< * Add missing rtree optimizer selectivity
> * Improve selectivity functions for geometric operators
 2005-12-29 16:45:11 +00:00
Andrew Dunstan
eb29d89ffd Move declaration of check_function_bodies to where the perl headers 
haven't had a chance to mangle the definition of DLLIMPORT (thanks again, perl guys).
 2005-12-29 14:28:31 +00:00
Neil Conway
12119188fe Revert some careless search-and-replace: "ADD" in comment text should 
not be replaced with "ADD_P".
 2005-12-29 04:53:18 +00:00