- 13 12月, 2014 4 次提交
-
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
- 12 12月, 2014 5 次提交
-
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
- 11 12月, 2014 2 次提交
-
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
Using "row_number" or "rownum" in views or derived tables had unexpected results if the outer query contained constraints for the given view.
-
- 10 12月, 2014 5 次提交
-
-
由 Thomas Mueller 提交于
MVStore: the Recover tool can now deal with more types of corruption in the file. MVStore: the TransactionStore now first needs to be initialized before it can be used.
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
Views and derived tables with equality and range conditions on the same columns did not work properly. example: select x from (select x from (select 1 as x) where x > 0 and x < 2) where x = 1
-
- 09 12月, 2014 9 次提交
-
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
The database URL setting PAGE_SIZE setting is now also used for the MVStore. MVStore: the default page split size for persistent stores is now 4096 (it was 16 KB so far). This should reduce the database file size for most situations (in some cases, less than half the size of the previous version).
-
由 Thomas Mueller 提交于
The database URL setting PAGE_SIZE setting is now also used for the MVStore. MVStore: the default page split size for persistent stores is now 4096 (it was 16 KB so far). This should reduce the database file size for most situations (in some cases, less than half the size of the previous version).
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
- 05 12月, 2014 1 次提交
-
-
由 noelgrandin@gmail.com 提交于
-
- 03 12月, 2014 1 次提交
-
-
由 noelgrandin@gmail.com 提交于
-
- 29 11月, 2014 2 次提交
-
-
由 Thomas Mueller 提交于
MVStore: use a mark & sweep GC algorithm instead of reference counting, to ensure used chunks are never overwrite, even if the reference counting algorithm does not work properly.
-
由 Thomas Mueller 提交于
MVStore: use a mark & sweep GC algorithm instead of reference counting, to ensure used chunks are never overwrite, even if the reference counting algorithm does not work properly.
-
- 26 11月, 2014 11 次提交
-
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
In the multi-threaded mode, database metadata operations did sometimes not work if the schema was changed at the same time (for example, if tables were dropped).
-
由 Thomas Mueller 提交于
Some CLOB and BLOB values could no longer be read when the original row was removed (even when using the MVCC mode).
-
由 noelgrandin@gmail.com 提交于
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
Some CLOB and BLOB values could no longer be read when the original row was removed (even when using the MVCC mode).
-
由 Thomas Mueller 提交于
Some CLOB and BLOB values could no longer be read when the original row was removed (even when using the MVCC mode).
-
由 Thomas Mueller 提交于
-
由 Thomas Mueller 提交于
Some CLOB and BLOB values could no longer be read when the original row was removed (even when using the MVCC mode).
-