OSDN Git Service
Tom Lane [Tue, 18 Oct 2005 22:59:37 +0000 (22:59 +0000)]
Improve trace_sort code to also show the total memory or disk space used.
Per request from Marc.
Andrew Dunstan [Tue, 18 Oct 2005 22:53:54 +0000 (22:53 +0000)]
replace use of predefined perl vars $a and $b with $x and $y - per Greg Sabino Mullane
Tom Lane [Tue, 18 Oct 2005 21:43:33 +0000 (21:43 +0000)]
Add an entry to the discussion of regression test failures about the
possibility of a failure due to stack overflow when max_stack_depth is
not set properly for the platform.
Tom Lane [Tue, 18 Oct 2005 20:38:58 +0000 (20:38 +0000)]
Code review for regexp_replace patch. Improve documentation and comments,
fix problems with replacement-string backslashes that aren't followed by
one of the expected characters, avoid giving the impression that
replace_text_regexp() is meant to be called directly as a SQL function,
etc.
Tom Lane [Tue, 18 Oct 2005 17:13:14 +0000 (17:13 +0000)]
Code review for spi_query/spi_fetchrow patch: handle errors sanely,
avoid leaking memory. I would add a regression test for error handling
except it seems eval{} can't be used in unprivileged plperl :-(
Joe Conway [Tue, 18 Oct 2005 02:55:49 +0000 (02:55 +0000)]
When a cursor is opened using dblink_open, only start a transaction
if there isn't one already open. Upon dblink_close, only commit
the open transaction if it was started by dblink_open, and only
then when all cursors opened by dblink_open are closed. The transaction
accounting is done individually for all named connections, plus
the persistent unnamed connection.
Tom Lane [Tue, 18 Oct 2005 01:30:49 +0000 (01:30 +0000)]
Fix several contrib makefiles that failed in VPATH builds, particularly
when not using gcc (which has slightly nonstandard inclusion rules).
Tom Lane [Tue, 18 Oct 2005 01:06:24 +0000 (01:06 +0000)]
A few trivial code cleanups motivated by reading warnings generated
by a recent HP C compiler. Mostly, get rid of useless local variables
that are assigned to but never used.
Tom Lane [Mon, 17 Oct 2005 16:24:20 +0000 (16:24 +0000)]
Clean up libpq's pollution of application namespace by renaming the
exported routines of ip.c, md5.c, and fe-auth.c to begin with 'pg_'.
Also get rid of the vestigial fe_setauthsvc/fe_getauthsvc routines
altogether.
Tom Lane [Sun, 16 Oct 2005 21:22:12 +0000 (21:22 +0000)]
Add note that some versions of OS X require SHMMAX to be an exact multiple
of 4096. Also add comment explaining why we don't suggest using
/etc/sysctl.conf to avoid needing to edit /etc/rc.
Bruce Momjian [Sun, 16 Oct 2005 18:26:00 +0000 (18:26 +0000)]
Add space after description.
Euler Taveira de Oliveira
Bruce Momjian [Sat, 15 Oct 2005 21:27:19 +0000 (21:27 +0000)]
kerberos error message: localhost -> server hostname
Tom Lane [Sat, 15 Oct 2005 20:37:36 +0000 (20:37 +0000)]
Suppress warnings on platforms where fprintf is a macro (eg, recent
Fedora). This was already done by somebody for the core flex files,
but these contrib files seem to have been missed.
Tom Lane [Sat, 15 Oct 2005 20:28:59 +0000 (20:28 +0000)]
Fix bogus error test in get_ti_Oid().
Tom Lane [Sat, 15 Oct 2005 20:24:00 +0000 (20:24 +0000)]
Fix unportable struct initializations.
Neil Conway [Sat, 15 Oct 2005 20:15:48 +0000 (20:15 +0000)]
Remove a long comment from cvs.sgml -- AFAICS this is no longer useful,
or at any rate doesn't belong as a comment in a random SGML file.
Neil Conway [Sat, 15 Oct 2005 20:12:33 +0000 (20:12 +0000)]
Fix assorted typos in the documentation, and use American spelling
rather than British. Patch from Michael Fuhr.
Tom Lane [Sat, 15 Oct 2005 19:47:09 +0000 (19:47 +0000)]
Fix thinko in pg_read_file: testing for negative result is not the way
to determine whether fread() failed.
Tom Lane [Sat, 15 Oct 2005 17:59:38 +0000 (17:59 +0000)]
Update 'supported platforms' list with current buildfarm results.
Bruce Momjian [Sat, 15 Oct 2005 15:29:24 +0000 (15:29 +0000)]
Fix kerberos description: localhost -> server hostname.
Bruce Momjian [Sat, 15 Oct 2005 02:49:52 +0000 (02:49 +0000)]
Standard pgindent run for 8.1.
Bruce Momjian [Sat, 15 Oct 2005 02:14:22 +0000 (02:14 +0000)]
Update pgindent typedef list.
Neil Conway [Sat, 15 Oct 2005 01:47:12 +0000 (01:47 +0000)]
Merge some user-submitted suggestions for improvement into the
documentation. Mostly add some <xref>s, fix a few typos, and
document that zlib is required in the installation docs.
Alvaro Herrera [Sat, 15 Oct 2005 01:15:33 +0000 (01:15 +0000)]
Fix typo.
Tom Lane [Fri, 14 Oct 2005 20:53:56 +0000 (20:53 +0000)]
Fix syslog bug: if any messages are emitted to write_syslog before
the facility has been set, the facility gets set to LOCAL0 and cannot
be changed later. This seems reasonably plausible to happen, particularly
at higher debug log levels, though I am not certain it explains Han Holl's
recent report. Easiest fix is to teach the code how to change the value
on-the-fly, which is nicer anyway. I made the settings PGC_SIGHUP to
conform with log_destination.
Andrew Dunstan [Fri, 14 Oct 2005 20:48:18 +0000 (20:48 +0000)]
fix nonsensical summary row on example
Tom Lane [Fri, 14 Oct 2005 16:41:02 +0000 (16:41 +0000)]
Pass a strdup'd ident string to openlog(), to ensure that reallocation
of GUC memory doesn't cause us to start emitting a bogus ident string.
Per report from Han Holl. Also some trivial code cleanup in write_syslog.
Bruce Momjian [Fri, 14 Oct 2005 11:47:57 +0000 (11:47 +0000)]
Allow times of 24:00:00 to match rounding behavior:
regression=# select '23:59:59.9'::time(0);
time
----------
24:00:00
(1 row)
This is bad because:
regression=# select '24:00:00'::time(0);
ERROR: date/time field value out of range: "24:00:00"
The last example now works.
Tom Lane [Thu, 13 Oct 2005 23:41:07 +0000 (23:41 +0000)]
Add documentation mentioning that there are separate regression tests
for the PL languages and for contrib.
Tom Lane [Thu, 13 Oct 2005 23:26:00 +0000 (23:26 +0000)]
Improve documentation about CREATEROLE privilege.
Bruce Momjian [Thu, 13 Oct 2005 23:22:11 +0000 (23:22 +0000)]
Fix uppercase TRUE/FALSE that are WIN32 stuffl.
Bruce Momjian [Thu, 13 Oct 2005 23:12:04 +0000 (23:12 +0000)]
Update regression output for new prepare transaction error messages.
Bruce Momjian [Thu, 13 Oct 2005 22:57:27 +0000 (22:57 +0000)]
Make stack_base_ptr non-static, for PL/Java.
Bruce Momjian [Thu, 13 Oct 2005 22:55:55 +0000 (22:55 +0000)]
This makes the error messages for PREPARE TRANSACTION, COMMIT PREPARED
etc. match the docs, which talk about "transaction identifier" not
"gid" or "global transaction identifier".
Steve Woodcock
Bruce Momjian [Thu, 13 Oct 2005 22:55:19 +0000 (22:55 +0000)]
Update krb_server_name to document that a missing entry defaults to
'localhost'.
Improve kerberos error message.
Tom Lane [Thu, 13 Oct 2005 22:44:51 +0000 (22:44 +0000)]
Update documentation to reflect the new ALTER OWNER rules for all
affected types of objects.
Tom Lane [Thu, 13 Oct 2005 21:43:43 +0000 (21:43 +0000)]
Describe the behavior of the SQL_ASCII encoding more accurately.
Tom Lane [Thu, 13 Oct 2005 21:09:38 +0000 (21:09 +0000)]
Adjust the discussion of triggers to more clearly guide people in the
direction of writing triggers in a procedural language, rather than C.
Per discussion.
Bruce Momjian [Thu, 13 Oct 2005 20:58:42 +0000 (20:58 +0000)]
The patch updates the documentation to reflect the fact that higher values
of client_min_messages (fatal + panic) are valid and also fixes a slight
issue with how psql tried to display error messages that aren't sent to
the client.
We often tell people to ignore errors in response to requests for things
like "drop if exists", but there's no good way to completely hide this
without upping client_min_messages past ERROR. When running a file like
SET client_min_messages TO 'FATAL';
DROP TABLE doesntexist;
with "psql -f filename" you get an error prefix of
"psql:/home/username/filename:3" even though there is no error message to
prefix because it isn't sent to the client.
Kris Jurka
Bruce Momjian [Thu, 13 Oct 2005 20:40:04 +0000 (20:40 +0000)]
Enable threaded python builds on freebsd5, per report from Jim C. Nasby
Peter Eisentraut [Thu, 13 Oct 2005 20:10:03 +0000 (20:10 +0000)]
Turn off list of tables, figures, and examples.
Tom Lane [Thu, 13 Oct 2005 17:58:44 +0000 (17:58 +0000)]
Go back to emitting path names with forward slashes on Windows.
I'm not clear on what the double-backslash idea was intended to fix,
but it breaks at least mingw GNU Make. Per report from Thomas Hallgren.
Bruce Momjian [Thu, 13 Oct 2005 17:57:57 +0000 (17:57 +0000)]
Back out this because of fear of changing error strings:
This makes the error messages for PREPARE TRANSACTION, COMMIT PREPARED
etc. match the docs, which talk about "transaction identifier" not
"gid" or "global transaction identifier".
Steve Woodcock
Bruce Momjian [Thu, 13 Oct 2005 17:57:17 +0000 (17:57 +0000)]
This makes the error messages for PREPARE TRANSACTION, COMMIT PREPARED
etc. match the docs, which talk about "transaction identifier" not
"gid" or "global transaction identifier".
Steve Woodcock
Bruce Momjian [Thu, 13 Oct 2005 17:55:18 +0000 (17:55 +0000)]
Rewording, use the more common multi-threaded/single-threaded.
Bruce Momjian [Thu, 13 Oct 2005 17:46:18 +0000 (17:46 +0000)]
Clarify causes of possible mismatch between Win32 libraries and
applications that use FILE pointers.
Bruce Momjian [Thu, 13 Oct 2005 17:32:42 +0000 (17:32 +0000)]
Some additional doc changes based around compression of page images in
WAL and the interaction of the new full_page_writes parameter with PITR.
The too-small WAL first sect1 has been merged with the one following
sect1 for clarity.
Some minor comments have been made in the WAL config section also.
Passes SGML make and proofread for typos.
Files changed:
patching file doc/src/sgml/backup.sgml
patching file doc/src/sgml/config.sgml
patching file doc/src/sgml/wal.sgml
Simon Riggs
Bruce Momjian [Thu, 13 Oct 2005 16:10:14 +0000 (16:10 +0000)]
Mark xslt_process() as volatile.
Bruce Momjian [Thu, 13 Oct 2005 15:37:14 +0000 (15:37 +0000)]
Use get_progname() in backend main.c, rather than port-specific hack
that is too fragile.
Tom Lane [Thu, 13 Oct 2005 15:34:19 +0000 (15:34 +0000)]
Fix small oversight in recent patch to add more CREATE-FUNCTION-time
syntax checking to plpgsql: check_sql_expr() wasn't being called by
make_select_stmt(), so that there was no SQL syntax check for SELECT
statements.
Bruce Momjian [Thu, 13 Oct 2005 14:58:33 +0000 (14:58 +0000)]
Change xpath_table() and xslt_process() from IMMUTABLE to STABLE.
Bruce Momjian [Thu, 13 Oct 2005 14:44:58 +0000 (14:44 +0000)]
Fix capitalization of example.
Neil Conway [Thu, 13 Oct 2005 06:24:05 +0000 (06:24 +0000)]
Remove an antiquated comment.
Neil Conway [Thu, 13 Oct 2005 06:17:34 +0000 (06:17 +0000)]
Add a comment describing the requirement that pointers into shared memory
that is protected by a spinlock must be volatile, per recent discussion.
Bruce Momjian [Thu, 13 Oct 2005 02:23:12 +0000 (02:23 +0000)]
Update trigger demo to reflect new trigger ordering.
Bruce Momjian [Thu, 13 Oct 2005 02:00:09 +0000 (02:00 +0000)]
Remove extra <para>
Bruce Momjian [Thu, 13 Oct 2005 01:23:49 +0000 (01:23 +0000)]
Update:
> * Prevent PQfnumber() from lowercasing unquoted the column name
>
> PQfnumber() should never have been doing lowercasing, but historically
> it has so we need a way to prevent it
>
Tom Lane [Thu, 13 Oct 2005 00:06:46 +0000 (00:06 +0000)]
Don't try to remove duplicate OR-subclauses in create_bitmap_subplan and
make_restrictinfo_from_bitmapqual. The likelihood of finding duplicates
seems much less than in the AND-subclause case, and the cost much higher,
because OR lists with hundreds or even thousands of subclauses are not
uncommon. Per discussion with Ilia Kantor and andrew@supernews.
Tom Lane [Wed, 12 Oct 2005 23:19:22 +0000 (23:19 +0000)]
Fix spelling error, per Michael Fuhr.
Bruce Momjian [Wed, 12 Oct 2005 22:39:35 +0000 (22:39 +0000)]
Remove item:
< * Prevent libpq's PQfnumber() from lowercasing the column name
<
< One idea is to lowercase all identifiers except those that are
< surrounded by quotes.
<
Tom Lane [Wed, 12 Oct 2005 17:18:03 +0000 (17:18 +0000)]
Fix longstanding bug found by Atsushi Ogawa: _bt_check_unique would mark
the wrong buffer dirty when trying to kill a dead index entry that's on
a page after the one it started on. No risk of data corruption, just
inefficiency, but still a bug.
Tom Lane [Wed, 12 Oct 2005 16:55:59 +0000 (16:55 +0000)]
Fix another recently-changed place that was messing with spinlock-
protected data structures and not using a volatile pointer for same.
Tom Lane [Wed, 12 Oct 2005 16:45:14 +0000 (16:45 +0000)]
Do all accesses to shared buffer headers through volatile-qualified
pointers, to ensure that compilers won't rearrange accesses to occur
while we're not holding the buffer header spinlock. It's probably
not necessary to mark volatile in every single place in bufmgr.c,
but better safe than sorry. Per trouble report from Kevin Grittner.
Bruce Momjian [Wed, 12 Oct 2005 14:28:33 +0000 (14:28 +0000)]
Add warning about plperl nested named subroutines
Andrew Dunstan
Bruce Momjian [Wed, 12 Oct 2005 14:06:46 +0000 (14:06 +0000)]
No longer needed:
<
< * Add code to detect an SMP machine and handle spinlocks accordingly
< from distributted.net, http://www1.distributed.net/source,
< in client/common/cpucheck.cpp
<
< On SMP machines, it is possible that locks might be released shortly,
< while on non-SMP machines, the backend should sleep so the process
< holding the lock can complete and release it.
Bruce Momjian [Wed, 12 Oct 2005 13:41:08 +0000 (13:41 +0000)]
Rearrange:
< o %Add dumping of comments on composite type columns
< o %Add dumping of comments on index columns
< o Stop dumping CASCADE on DROP TYPE commands in clean mode
> o %Add dumping of comments on index columns and composite type columns
604a603
> o Stop dumping CASCADE on DROP TYPE commands in clean mode
Bruce Momjian [Wed, 12 Oct 2005 13:39:51 +0000 (13:39 +0000)]
Done:
< o %Replace crude DELETE FROM method of pg_dumpall --clean for
< cleaning of roles with separate DROP commands
608a607
>
Bruce Momjian [Wed, 12 Oct 2005 13:39:21 +0000 (13:39 +0000)]
Add:
<
> o Allow pg_dump --clean to drop roles that own objects or have
> privileges
Peter Eisentraut [Wed, 12 Oct 2005 09:45:29 +0000 (09:45 +0000)]
Update keywords table for 8.1.
Bruce Momjian [Wed, 12 Oct 2005 03:26:38 +0000 (03:26 +0000)]
Add description:
< * Prevent libpq's PQfnumber() from lowercasing the column name?
> * Prevent libpq's PQfnumber() from lowercasing the column name
>
> One idea is to lowercase all identifiers except those that are
> surrounded by quotes.
>
Bruce Momjian [Wed, 12 Oct 2005 02:57:42 +0000 (02:57 +0000)]
Add:
> o Add options like pg_restore -l and -L to pg_dump
Bruce Momjian [Tue, 11 Oct 2005 23:55:10 +0000 (23:55 +0000)]
Add:
> o Allow selection of individual object(s) of all types, not just
> tables
> o In a selective dump, allow dumping of an object and all its
> dependencies
PostgreSQL Daemon [Tue, 11 Oct 2005 23:27:46 +0000 (23:27 +0000)]
must commit *after* autoconf, not before
PostgreSQL Daemon [Tue, 11 Oct 2005 23:26:43 +0000 (23:26 +0000)]
update to beta3 before tagging ...
Neil Conway [Tue, 11 Oct 2005 22:58:15 +0000 (22:58 +0000)]
Fix typo in sample pg_hba.conf; per IRC report from Bernhard Neuhauser.
Tom Lane [Tue, 11 Oct 2005 21:17:11 +0000 (21:17 +0000)]
Release notes up to date as of today.
Tom Lane [Tue, 11 Oct 2005 20:41:32 +0000 (20:41 +0000)]
Add infrastructure for making spins_per_delay variable depending on
whether we seem to be running in a uniprocessor or multiprocessor.
The adjustment rules could probably still use further tweaking, but
I'm convinced this should be a win overall.
Tom Lane [Tue, 11 Oct 2005 20:01:30 +0000 (20:01 +0000)]
Don't use a non-locked pre-test of the spinlock on x86_64 machines.
The pre-test has been shown to be a big loss on Opterons and at best a
wash on EM64T.
Tom Lane [Tue, 11 Oct 2005 17:27:14 +0000 (17:27 +0000)]
Document that get_attstatsslot/free_attstatsslot only need to be passed
valid type information if they are asked to fetch the values part of a
pg_statistic slot; these arguments are unneeded if fetching only the
numbers part. Use this to save a catcache lookup in btcostestimate,
which is looking like a bit of a hotspot in recent profiling. Not a
big savings, but since it's essentially free, might as well do it.
Tom Lane [Tue, 11 Oct 2005 16:44:40 +0000 (16:44 +0000)]
Fix oversight in 8.0 modification of RestrictInfo data structures.
A RestrictInfo representing an OR clause now contains two versions of
the contained expression, one with sub-RestrictInfos and one without.
clause_selectivity() should descend to the version with sub-RestrictInfos
so that it has a chance of caching its results for the OR's sub-clauses.
Failing to do so resulted in redundant planner effort.
Tom Lane [Mon, 10 Oct 2005 22:29:48 +0000 (22:29 +0000)]
Remove the DELETEs from pg_shadow and pg_group that pg_dumpall used to
emit when given the --clean option, in favor of individual DROP ROLE
commands. The old technique could not possibly work in 8.1, and was
never a very good idea anyway IMHO. The DROP ROLE approach has the
defect that the DROPs will fail for roles that own objects or have
privileges, but perhaps we can improve that later.
Tom Lane [Mon, 10 Oct 2005 20:02:20 +0000 (20:02 +0000)]
Use a safer order of operations in dropdb(): rollbackable operations,
ie removing shared-dependency entries, should happen before non-rollbackable
ones. That way a failure during the rollbackable part doesn't leave us
with inconsistent state.
Peter Eisentraut [Mon, 10 Oct 2005 19:41:27 +0000 (19:41 +0000)]
Document the process to update translations.
Peter Eisentraut [Mon, 10 Oct 2005 19:36:36 +0000 (19:36 +0000)]
Translation update
Tom Lane [Mon, 10 Oct 2005 18:49:04 +0000 (18:49 +0000)]
Fix the problem of GRANTs creating "dangling" privileges not directly
traceable to grant options. As per my earlier proposal, a GRANT made by
a role member has to be recorded as being granted by the role that actually
holds the grant option, and not the member.
Tom Lane [Mon, 10 Oct 2005 01:34:00 +0000 (01:34 +0000)]
<limits.h> is now needed here, for INT_MAX. Per Michael Fuhr.
Tom Lane [Sun, 9 Oct 2005 17:21:47 +0000 (17:21 +0000)]
Fix (hopefully for the last time) problems with datetime values displaying
like '23:59:60' because of fractional-second roundoff problems. Trying
to control this upstream of the actual display code was hopeless; the right
way is to explicitly round fractional seconds in the display code and then
refigure the results if the fraction rounds up to 1. Per bug #1927.
Tom Lane [Sat, 8 Oct 2005 20:27:25 +0000 (20:27 +0000)]
Fix a thinko in description of krb_server_hostname.
Tom Lane [Sat, 8 Oct 2005 20:08:19 +0000 (20:08 +0000)]
Fix up grammar in variable description string.
Tom Lane [Sat, 8 Oct 2005 19:32:58 +0000 (19:32 +0000)]
Fix Kerberos authentication in wake of virtual-hosts changes --- need
to call krb5_sname_to_principal() always. Also, use krb_srvname rather
than the hardwired string 'postgres' as the appl_version string in the
krb5_sendauth/recvauth calls, to avoid breaking compatibility with PG
8.0. Magnus Hagander
Bruce Momjian [Sat, 8 Oct 2005 16:10:38 +0000 (16:10 +0000)]
Remove unnecessary ABORT commands in dblink regression tests.
Bruce Momjian [Sat, 8 Oct 2005 12:18:48 +0000 (12:18 +0000)]
Cosmetic improvements to dblink.
Bruce Momjian [Sat, 8 Oct 2005 12:12:29 +0000 (12:12 +0000)]
Cosmetic changes to dblink.
Bruce Momjian [Sat, 8 Oct 2005 11:33:45 +0000 (11:33 +0000)]
Cosmetic changes to dblink.
Bruce Momjian [Sat, 8 Oct 2005 02:39:27 +0000 (02:39 +0000)]
Add spacing around operators.
Tom Lane [Fri, 7 Oct 2005 21:42:38 +0000 (21:42 +0000)]
Fix LWLockAssign() so that it can safely be executed after postmaster
initialization. Add spinlocking, fix EXEC_BACKEND unsafeness.
Bruce Momjian [Fri, 7 Oct 2005 20:26:41 +0000 (20:26 +0000)]
Minor parentheses cleanup.
Bruce Momjian [Fri, 7 Oct 2005 20:13:16 +0000 (20:13 +0000)]
Add spaces around operator.
Tom Lane [Fri, 7 Oct 2005 20:11:03 +0000 (20:11 +0000)]
Allocate a few extra LWLocks for possible use by add-on modules.
Per request from Marc Munro.
Tom Lane [Fri, 7 Oct 2005 19:59:34 +0000 (19:59 +0000)]
Marginal performance improvement in aclmask(): don't bother with
testing ownership if the caller isn't interested in any GOPTION bits
(which is the common case). It did not matter in 8.0 where the ownership
test was just a trivial equality test, but it matters now.