OSDN Git Service
Bruce Momjian [Wed, 2 Aug 2006 21:48:43 +0000 (21:48 +0000)]
Move 'ddl' right after 'none' in postgresql.conf. It used to be between
'mod' and 'all', which is not the right order. SGML documentation order
was correct. Report from Chander Ganesan.
Bruce Momjian [Wed, 2 Aug 2006 21:43:43 +0000 (21:43 +0000)]
Fix logic to prevent pg_dump from dumping system schemas; bug introduced
in recent -t/-n/-T/-N patch.
Small style cleanups.
Andrew Dunstan [Wed, 2 Aug 2006 19:02:34 +0000 (19:02 +0000)]
remove extraneous space after -L flag.
Tom Lane [Wed, 2 Aug 2006 18:58:21 +0000 (18:58 +0000)]
Arrange for ValuesScan to keep per-sublist expression eval state in a
temporary context that can be reset when advancing to the next sublist.
This is faster and more thorough at recovering space than the previous
method; moreover it will do the right thing if something in the sublist
tries to register an expression context callback.
Tom Lane [Wed, 2 Aug 2006 16:29:49 +0000 (16:29 +0000)]
Fix documentation error: GRANT/REVOKE for roles only accept role names
as grantees, not PUBLIC ... and you can't say GROUP either. Noted by
Brian Hurt.
Michael Meskes [Wed, 2 Aug 2006 14:19:14 +0000 (14:19 +0000)]
And finally the Makefiles
Tom Lane [Wed, 2 Aug 2006 14:14:22 +0000 (14:14 +0000)]
Wups, got the test for contain_vars_of_level-not-needed wrong in
transformInsertStmt: the target table is already in p_rtable at that point.
Michael Meskes [Wed, 2 Aug 2006 14:14:04 +0000 (14:14 +0000)]
Hopefully that's it. The remaining files for ecpg regression tests.
Tom Lane [Wed, 2 Aug 2006 13:58:52 +0000 (13:58 +0000)]
Add a HINT per suggestion from Michael Glaesemann. Also, tweak OLD/NEW
test to avoid expensive contain_vars_of_level() scan in the normal case
where we're not inside a rule.
Michael Meskes [Wed, 2 Aug 2006 13:53:45 +0000 (13:53 +0000)]
Some more regression test files
Michael Meskes [Wed, 2 Aug 2006 13:52:11 +0000 (13:52 +0000)]
One more file to remove
Michael Meskes [Wed, 2 Aug 2006 13:51:32 +0000 (13:51 +0000)]
Removed old test files
Michael Meskes [Wed, 2 Aug 2006 13:43:23 +0000 (13:43 +0000)]
ynced parser and keyword list.
Implemented EXEC SQL UNDEF.
Applied first version of the regression test patch by Joachim Wieland <joe@mcknight.de>.
Bruce Momjian [Wed, 2 Aug 2006 13:36:45 +0000 (13:36 +0000)]
Update:
< o Add COPY TO STDIN / STDOUT handling
> o Add COPY TO STDIN handling
Bruce Momjian [Wed, 2 Aug 2006 13:29:54 +0000 (13:29 +0000)]
Add:
> o In rules, allow VALUES() to contain a mixture of 'old' and 'new'
> references
Bruce Momjian [Wed, 2 Aug 2006 03:11:54 +0000 (03:11 +0000)]
Done:
o -Allow INSERT INTO tab (col1, ..) VALUES (val1, ..), (val2, ..)
Joe Conway [Wed, 2 Aug 2006 01:59:48 +0000 (01:59 +0000)]
Add support for multi-row VALUES clauses as part of INSERT statements
(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.
Bruce Momjian [Tue, 1 Aug 2006 21:05:00 +0000 (21:05 +0000)]
Fix bug I introduced while cleaning up pg_dump -t/-n patch.
Alvaro Herrera [Tue, 1 Aug 2006 19:17:18 +0000 (19:17 +0000)]
Editorialize a bit on the recent patch, reverting to the original versions
of the text where appropiate.
Bruce Momjian [Tue, 1 Aug 2006 19:03:11 +0000 (19:03 +0000)]
Add support for loadable modules to allocated shared memory and
lightweight locks.
Marc Munro
Bruce Momjian [Tue, 1 Aug 2006 18:21:44 +0000 (18:21 +0000)]
Add pg_dump -X no-data-for-failed-tables option to suppress loading data
if table creation failed (the table already exists).
Martin Pitt
Bruce Momjian [Tue, 1 Aug 2006 18:07:36 +0000 (18:07 +0000)]
Done:
< o %Allow pg_dump to use multiple -t and -n switches [pg_dump]
<
< http://archives.postgresql.org/pgsql-patches/2006-01/msg00190.php
<
> o -Allow pg_dump to use multiple -t and -n switches, exclusion
> ability, and regular expression object matching
Bruce Momjian [Tue, 1 Aug 2006 18:06:27 +0000 (18:06 +0000)]
Remove TODO.detail/pg_dump.
Bruce Momjian [Tue, 1 Aug 2006 18:05:04 +0000 (18:05 +0000)]
Allow multiple -n (schema) and -t (table) pg_dump options, and add -T
and -N options to exclude objects. Also support regular expressions for
option object names.
Greg Sabino Mullane
Bruce Momjian [Tue, 1 Aug 2006 18:01:36 +0000 (18:01 +0000)]
Remove extra argument to printf().
Andrew Dunstan [Tue, 1 Aug 2006 14:56:29 +0000 (14:56 +0000)]
have pg_regress fall back on testing with the canonical results file if an
alternative test is specified but none succeeds.
Bruce Momjian [Tue, 1 Aug 2006 00:09:06 +0000 (00:09 +0000)]
Improvements to Maintenance and External Projects documentation.
Joshua D. Drake
Robert Treat
Bruce Momjian [Mon, 31 Jul 2006 23:04:13 +0000 (23:04 +0000)]
Add:
> * Consider compressed annealing to search for query plans
>
> This might replace GEQO, http://sixdemonbag.org/Djinni.
Tom Lane [Mon, 31 Jul 2006 20:09:10 +0000 (20:09 +0000)]
Change the relation_open protocol so that we obtain lock on a relation
(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.
Michael Meskes [Mon, 31 Jul 2006 13:26:46 +0000 (13:26 +0000)]
Added missing ECPGget_sqlca() call
Michael Meskes [Mon, 31 Jul 2006 10:15:31 +0000 (10:15 +0000)]
First small patches needed for regression tests
Tatsuo Ishii [Mon, 31 Jul 2006 05:15:14 +0000 (05:15 +0000)]
Fix memory allocation bug in pgbench.
patches submitted by ITAGAKI Takahiro.
Tom Lane [Mon, 31 Jul 2006 01:16:38 +0000 (01:16 +0000)]
Change the bootstrap sequence so that toast tables for system catalogs are
created in the bootstrap phase proper, rather than added after-the-fact
by initdb. This is cleaner than before because it allows us to retire the
undocumented ALTER TABLE ... CREATE TOAST TABLE command, but the real reason
I'm doing it is so that toast tables of shared catalogs will now have
predetermined OIDs. This will allow a reasonably clean solution to the
problem of locking tables before we load their relcache entries, to appear
in a forthcoming patch.
Alvaro Herrera [Mon, 31 Jul 2006 01:10:56 +0000 (01:10 +0000)]
Fix confusion between COPY FROM and COPY TO, per Gavin Sharry and Arul Shaji.
Tom Lane [Sun, 30 Jul 2006 20:17:11 +0000 (20:17 +0000)]
Fix a couple of comments.
Michael Meskes [Sun, 30 Jul 2006 16:28:58 +0000 (16:28 +0000)]
Replaced $Header$ by $§PosgreSQL$
Michael Meskes [Sun, 30 Jul 2006 10:24:10 +0000 (10:24 +0000)]
Added missing $Header$ entries.
Alvaro Herrera [Sun, 30 Jul 2006 02:07:18 +0000 (02:07 +0000)]
Modify snapshot definition so that lazy vacuums are ignored by other
vacuums. This allows a OLTP-like system with big tables to continue
regular vacuuming on small-but-frequently-updated tables while the
big tables are being vacuumed.
Original patch from Hannu Krossing, rewritten by Tom Lane and updated
by me.
Bruce Momjian [Sun, 30 Jul 2006 01:48:40 +0000 (01:48 +0000)]
Add:
> * Consider detoasting keys before sorting
Bruce Momjian [Sun, 30 Jul 2006 01:45:21 +0000 (01:45 +0000)]
Fix WIN32 wait() return value macros to be accurate, particularly
because they are used for testing the return value from system().
(WIN32 doesn't overlay the return code with other failure conditions
like Unix does, so they are just simple macros.)
Fix regression checks to properly handle diff failures on Win32 using
the new macros.
Andrew Dunstan [Sat, 29 Jul 2006 19:55:18 +0000 (19:55 +0000)]
prevent multiplexing Windows kernel event objects we listen for across various sockets - should fix the occasional stats test regression failures we see.
Bruce Momjian [Sat, 29 Jul 2006 18:08:36 +0000 (18:08 +0000)]
Add entry:
> * Add column to pg_stat_activity that shows the progress of long-running
> commands like CREATE INDEX and VACUUM
Bruce Momjian [Sat, 29 Jul 2006 17:35:07 +0000 (17:35 +0000)]
Don't use #include <crtdefs.h> for MSVC <= 1400.
Hiroshi Saito
Bruce Momjian [Sat, 29 Jul 2006 15:56:32 +0000 (15:56 +0000)]
Add:
> * Add support for SQL-standard GENERATED/IDENTITY columns
>
> http://archives.postgresql.org/pgsql-hackers/2006-07/msg00543.php
Bruce Momjian [Sat, 29 Jul 2006 15:22:27 +0000 (15:22 +0000)]
Add #include postgres_fe.h in two win32-specific files, because there is
pg-specific code in those files, or might be some day.
Tom Lane [Sat, 29 Jul 2006 03:02:56 +0000 (03:02 +0000)]
Adjust initialization sequence for timezone_abbreviations so that
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.
Tatsuo Ishii [Fri, 28 Jul 2006 22:58:26 +0000 (22:58 +0000)]
Change the delta val from 0 and 10000 to -5000 and 5000 per recent
discussion in hackers list. Also enhance predefined benchmark
scenarios to reflect the scaling factor parameter flexibly.
Bruce Momjian [Fri, 28 Jul 2006 19:28:08 +0000 (19:28 +0000)]
Remove update TODO.detail item.
Bruce Momjian [Fri, 28 Jul 2006 19:00:45 +0000 (19:00 +0000)]
Updates per Tom:
> * Allow DISTINCT to work in multiple-argument aggregate calls
< o Allow UPDATE to handle complex aggregates [update]?
Tom Lane [Fri, 28 Jul 2006 18:33:04 +0000 (18:33 +0000)]
SQL2003-standard statistical aggregates, by Sergey Koposov. I've added only
the float8 versions of the aggregates, which is all that the standard requires.
Sergey's original patch also provided versions using numeric arithmetic,
but given the size and slowness of the code, I doubt we ought to include
those in core.
Tom Lane [Fri, 28 Jul 2006 16:21:57 +0000 (16:21 +0000)]
Fix table title.
Tom Lane [Fri, 28 Jul 2006 15:33:17 +0000 (15:33 +0000)]
Make it clearer that not every Postgres character set can be used as a
server-side character set.
Bruce Momjian [Fri, 28 Jul 2006 12:24:07 +0000 (12:24 +0000)]
Update Tatsuo:
< * Tatsuo is Tatsuo Ishii <t-ishii@sra.co.jp> of Software Research Assoc.
> * Tatsuo is Tatsuo Ishii <ishii@sraoss.co.jp> of SRA OSS, Inc. Japan
Michael Meskes [Fri, 28 Jul 2006 11:49:36 +0000 (11:49 +0000)]
Variables should be free'ed only once.
Michael Meskes [Fri, 28 Jul 2006 10:12:56 +0000 (10:12 +0000)]
Removed superfluous comment
Michael Meskes [Fri, 28 Jul 2006 10:10:42 +0000 (10:10 +0000)]
And one more:
Connection identifier has to be unique
Michael Meskes [Fri, 28 Jul 2006 09:08:01 +0000 (09:08 +0000)]
Added more SoC changes by Joachim Wieland <joe@mcknight.de>:
- SHOW statement puts result into a variable
- COPY TO STDOUT works
Bruce Momjian [Thu, 27 Jul 2006 22:05:49 +0000 (22:05 +0000)]
Add URL for UPDATE/SET for multiple values.
Bruce Momjian [Thu, 27 Jul 2006 22:01:34 +0000 (22:01 +0000)]
Add for UPDATE SET for multiple values:
>
> A subselect can also be used as the value source.
Tom Lane [Thu, 27 Jul 2006 21:55:09 +0000 (21:55 +0000)]
Fix incorrect function return code in cube_cmp and cube_dim;
update regression expected files to what I think is correct.
Andrew Dunstan [Thu, 27 Jul 2006 19:58:39 +0000 (19:58 +0000)]
revert last change - broke non-AIX platforms.
Tom Lane [Thu, 27 Jul 2006 19:52:07 +0000 (19:52 +0000)]
Aggregate functions now support multiple input arguments. I also took
the opportunity to treat COUNT(*) as a zero-argument aggregate instead
of the old hack that equated it to COUNT(1); this is materially cleaner
(no more weird ANYOID cases) and ought to be at least a tiny bit faster.
Original patch by Sergey Koposov; review, documentation, simple regression
tests, pg_dump and psql support by moi.
Andrew Dunstan [Thu, 27 Jul 2006 18:38:54 +0000 (18:38 +0000)]
another try at keeping AIX/ppc happy on cube test.
Andrew Dunstan [Thu, 27 Jul 2006 16:12:36 +0000 (16:12 +0000)]
fix most regression tests for new cube code.
Tom Lane [Thu, 27 Jul 2006 15:37:19 +0000 (15:37 +0000)]
Original coding of pg_regress.c made the results and log directories
with restrictive permissions, which was not the behavior of the shell
script and doesn't seem very desirable. Use the umask setting instead.
Bruce Momjian [Thu, 27 Jul 2006 13:20:24 +0000 (13:20 +0000)]
Allow LDAP lookups from pg_service.conf.
Albe Laurenz
Peter Eisentraut [Thu, 27 Jul 2006 08:30:41 +0000 (08:30 +0000)]
Allow units to be specified with configuration settings.
Tom Lane [Wed, 26 Jul 2006 19:31:51 +0000 (19:31 +0000)]
Code review for bigint-LIMIT patch. Fix missed planner dependency,
eliminate unnecessary code, force initdb because stored rules change
(limit nodes are now supposed to be int8 not int4 expressions).
Update comments and error messages, which still all said 'integer'.
Bruce Momjian [Wed, 26 Jul 2006 17:23:02 +0000 (17:23 +0000)]
Reorder items:
< o Allow point-in-time recovery to archive partially filled
< write-ahead logs? [pitr]
> o Add command to archive partially filled write-ahead logs? [pitr]
< of a disk failure. This could be triggered by a user command or
< a timer.
> of a disk failure.
< recovery. A function call to do this would also be useful.
> recovery.
> o Add reporting of the current WAL file and offset, perhaps as
> part of partial log file archiving
>
> The offset allows parts of a WAL file to be archived using
> an external program.
>
< o Add reporting of the current WAL file and offset, perhaps as
< part of partial log file archiving
<
< The offset allows parts of a WAL file to be archived using
< an external program.
Bruce Momjian [Wed, 26 Jul 2006 17:17:28 +0000 (17:17 +0000)]
Work around bug in strxfmt() but in MS VS2005.
William ZHANG
Peter Eisentraut [Wed, 26 Jul 2006 11:39:47 +0000 (11:39 +0000)]
When a GUC string variable is not set, print the empty string (in SHOW etc.),
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.
Peter Eisentraut [Wed, 26 Jul 2006 11:35:56 +0000 (11:35 +0000)]
Convert effective_cache_size to an integer, for better integration with
upcoming units feature.
Tatsuo Ishii [Wed, 26 Jul 2006 07:24:50 +0000 (07:24 +0000)]
New features contributed by Tomoaki Sato.
- predefined variable "tps"
The value of variable tps is taken from the scaling factor
specified by -s option.
- -D option
Variable values can be defined by -D option.
- \set command now allows arithmetic calculations.
Bruce Momjian [Wed, 26 Jul 2006 00:35:01 +0000 (00:35 +0000)]
Done:
> * -Change LIMIT/OFFSET and FETCH/MOVE to use int8
Bruce Momjian [Wed, 26 Jul 2006 00:34:48 +0000 (00:34 +0000)]
Change LIMIT/OFFSET to use int8
Dhanaraj M
Bruce Momjian [Tue, 25 Jul 2006 23:23:45 +0000 (23:23 +0000)]
/contrib/cube improvements:
Update the calling convention for all external facing functions. By
external facing, I mean all functions that are directly referenced in
cube.sql. Prior to my update, all functions used the older V0 calling
convention. They now use V1.
New Functions:
cube(float[]), which makes a zero volume cube from a float array
cube(float[], float[]), which allows the user to create a cube from
two float arrays; one for the upper right and one for the lower left
coordinate.
cube_subset(cube, int4[]), to allow you to reorder or choose a subset of
dimensions from a cube, using index values specified in the array.
Joshua Reich
Tom Lane [Tue, 25 Jul 2006 19:13:00 +0000 (19:13 +0000)]
Modify btree to delete known-dead index entries without an actual VACUUM.
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
Bruce Momjian [Tue, 25 Jul 2006 16:23:42 +0000 (16:23 +0000)]
Add reason for WAL offset reporting:
>
> The offset allows parts of a WAL file to be archived using
> an external program.
Bruce Momjian [Tue, 25 Jul 2006 15:27:24 +0000 (15:27 +0000)]
Add offset mention:
< o Add reporting of the current WAL file, perhaps as part of
< partial log file archiving
> o Add reporting of the current WAL file and offset, perhaps as
> part of partial log file archiving
Bruce Momjian [Tue, 25 Jul 2006 15:21:48 +0000 (15:21 +0000)]
Update PITR:
< write-ahead logs [pitr]
> write-ahead logs? [pitr]
< recovery.
> recovery. A function call to do this would also be useful.
Tom Lane [Tue, 25 Jul 2006 13:49:21 +0000 (13:49 +0000)]
Add missing @OVERRIDE to 'India' config file, per Michael Fuhr.
Add $PostgreSQL$ lines for CVS identity, too.
Bruce Momjian [Tue, 25 Jul 2006 04:11:24 +0000 (04:11 +0000)]
Done:
> o -Allow customization of the known set of TZ names (generalize the
Tom Lane [Tue, 25 Jul 2006 03:51:23 +0000 (03:51 +0000)]
Remove hard-wired lists of timezone abbreviations in favor of providing
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.
Andrew Dunstan [Tue, 25 Jul 2006 01:37:42 +0000 (01:37 +0000)]
Use correct ifdef test for cygwin, namely __CYGWIN__ (note underscores).
Tom Lane [Tue, 25 Jul 2006 01:23:34 +0000 (01:23 +0000)]
Make the order of operations in PostmasterMain a bit saner ... some
recent patches had added stuff in rather random spots.
Peter Eisentraut [Mon, 24 Jul 2006 16:55:59 +0000 (16:55 +0000)]
Fix spectacular misspellings of procedural language names
Peter Eisentraut [Mon, 24 Jul 2006 16:32:45 +0000 (16:32 +0000)]
DTrace support, with a small initial set of probes
by Robert Lor
Peter Eisentraut [Mon, 24 Jul 2006 10:44:40 +0000 (10:44 +0000)]
Mark postgresql.conf entries that require server restart; some minor
editing and reformatting.
Andrew Dunstan [Mon, 24 Jul 2006 01:50:22 +0000 (01:50 +0000)]
Remove dubious and redundant (we think) setting of libdir in PATH for non temp-install case.
Tom Lane [Mon, 24 Jul 2006 01:19:48 +0000 (01:19 +0000)]
Add a fudge factor to genericcostestimate() to prevent the planner from
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.)
Tom Lane [Sun, 23 Jul 2006 23:08:46 +0000 (23:08 +0000)]
Convert the lock manager to use the new dynahash.c support for partitioned
hash tables, instead of the previous kluge involving multiple hash tables.
This partially undoes my patch of last December.
Tom Lane [Sun, 23 Jul 2006 18:34:45 +0000 (18:34 +0000)]
Fix oversight in sizing of shared buffer lookup hashtable. Because
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.
Tom Lane [Sun, 23 Jul 2006 03:07:58 +0000 (03:07 +0000)]
Split the buffer mapping table into multiple separately lockable
partitions, as per discussion. Passes functionality checks, but
I don't have any performance data yet.
Tom Lane [Sat, 22 Jul 2006 23:04:39 +0000 (23:04 +0000)]
Add support to dynahash.c for partitioning shared hashtables according
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.
Tom Lane [Sat, 22 Jul 2006 21:04:40 +0000 (21:04 +0000)]
Hmm, seems --disable-spinlocks has been broken for awhile and nobody
noticed. Fix SpinlockSemas() to report the correct count considering
that PG 8.1 adds a spinlock to each shared-buffer header.
Tom Lane [Sat, 22 Jul 2006 15:41:56 +0000 (15:41 +0000)]
In the recent changes to make the planner account better for cache
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.
Andrew Dunstan [Sat, 22 Jul 2006 14:05:20 +0000 (14:05 +0000)]
Add libdir to PATH for Cygwin as well as WIN32 - should fix buildfarm eel.
Peter Eisentraut [Fri, 21 Jul 2006 22:37:37 +0000 (22:37 +0000)]
For automatic dependency tracking, replace our sed hackery with the GCC-
-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.
Tom Lane [Fri, 21 Jul 2006 20:51:33 +0000 (20:51 +0000)]
Add the full set of comparison functions for type TID, including a btree
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
Tom Lane [Fri, 21 Jul 2006 00:24:04 +0000 (00:24 +0000)]
Ah, I finally realize why Magnus wanted to add a --bindir option to
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.