- 15 9月, 2006 10 次提交
-
-
由 Bruce Momjian 提交于
< o -Allow commenting of variables in postgresql.conf to restore them > o Allow commenting of variables in postgresql.conf to restore them
-
由 Tom Lane 提交于
-
由 Bruce Momjian 提交于
< * Research storing only active XIDs in subtransaction cache
-
由 Bruce Momjian 提交于
> * Research storing only active XIDs in subtransaction cache
-
由 Bruce Momjian 提交于
> > * Improve XML support > > http://developer.postgresql.org/index.php/XML_Support
-
由 Bruce Momjian 提交于
> One idea is to store the header in network byte order (high bits > first), and read the high bits to determine the header length.
-
由 Bruce Momjian 提交于
< 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 >
-
由 Bruce Momjian 提交于
-
由 Bruce Momjian 提交于
UTF8 escapes.
-
- 14 9月, 2006 3 次提交
-
-
由 Teodor Sigaev 提交于
-
由 Teodor Sigaev 提交于
Thanks to Christopher Kings-Lynne <chris.kingslynne@gmail.com> for initial version and Jeff Davis <pgsql@j-davis.com> for inspection
-
由 Tom Lane 提交于
CONCURRENTLY. Greg Stark, some further tweaks by me.
-
- 13 9月, 2006 1 次提交
-
-
由 Bruce Momjian 提交于
> * David is David Fetter <david@fetter.org>
-
- 11 9月, 2006 4 次提交
-
-
由 Bruce Momjian 提交于
< * 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?
-
由 Tom Lane 提交于
Per gripe from Jack Orenstein.
-
由 Tom Lane 提交于
-
由 Tom Lane 提交于
-
- 10 9月, 2006 2 次提交
-
-
由 Tom Lane 提交于
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.
-
由 Tom Lane 提交于
-
- 08 9月, 2006 2 次提交
-
-
由 Tom Lane 提交于
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.
-
由 Tom Lane 提交于
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.
-
- 07 9月, 2006 6 次提交
-
-
由 Bruce Momjian 提交于
-
由 Bruce Momjian 提交于
-
由 Bruce Momjian 提交于
Andrew Dunstan
-
由 Bruce Momjian 提交于
-
由 Bruce Momjian 提交于
-
由 Tom Lane 提交于
that has parameters is always planned afresh for each Bind command, treating the parameter values as constants in the planner. This removes the performance penalty formerly often paid for using out-of-line parameters --- with this definition, the planner can do constant folding, LIKE optimization, etc. After a suggestion by Andrew@supernews.
-
- 06 9月, 2006 1 次提交
-
-
由 Tom Lane 提交于
can create or modify rules for the table. Do setRuleCheckAsUser() while loading rules into the relcache, rather than when defining a rule. This ensures that permission checks for tables referenced in a rule are done with respect to the current owner of the rule's table, whereas formerly ALTER TABLE OWNER would fail to update the permission checking for associated rules. Removal of separate RULE privilege is needed to prevent various scenarios in which a grantee of RULE privilege could effectively have any privilege of the table owner. For backwards compatibility, GRANT/REVOKE RULE is still accepted, but it doesn't do anything. Per discussion here: http://archives.postgresql.org/pgsql-hackers/2006-04/msg01138.php
-
- 05 9月, 2006 6 次提交
-
-
由 Bruce Momjian 提交于
Christopher Kings-Lynne
-
由 Bruce Momjian 提交于
Jun Kuwamura
-
由 Bruce Momjian 提交于
-
由 Bruce Momjian 提交于
Albe Laurenz
-
由 Bruce Momjian 提交于
Christopher Kings-Lynne
-
由 Bruce Momjian 提交于
Simon Riggs
-
- 04 9月, 2006 4 次提交
-
-
由 Tom Lane 提交于
of the syntax as this fundamentally dead-end approach can, in particular combinations of single and multi column assignments. Improve rather inadequate documentation and provide some regression tests.
-
由 Tom Lane 提交于
-
由 Tom Lane 提交于
-
由 Tom Lane 提交于
is only invoked on completed WAL segments, period --- there's no 'by default' about it.
-
- 03 9月, 2006 1 次提交
-
-
由 Bruce Momjian 提交于
< * Change LIMIT/OFFSET and FETCH/MOVE to use int8
-