PostgreSQL TODO List
====================
-Last updated: Thu Sep 14 17:43:58 EDT 2006
+Last updated: Sat Sep 16 18:06:27 EDT 2006
The most recent version of this document can be viewed at
http://www.postgresql.org/docs/faqs.TODO.html.
* Consider ways of storing rows more compactly on disk
- o Reorder physical storage order to reduce 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.
-
o Support a smaller header for short variable-length fields?
- One idea is to store the header in network byte order (high bits
- first), and read the high bits to determine the header length.
- http://archives.postgresql.org/pgsql-hackers/2006-09/msg00848.php
+ One idea is to create zero-or-one-byte-header versions
+ of varlena data types. In involves setting the high-bit and
+ 0-127 length in the single-byte header, or clear the high bit
+ and store the 7-bit ASCII value in the rest of the byte.
+ The small-header versions have no alignment requirements.
+ http://archives.postgresql.org/pgsql-hackers/2006-09/msg01372.php
o Reduce the row header size?
-Last updated: Thu Sep 14 17:43:58 EDT 2006
+Last updated: Sat Sep 16 18:06:27 EDT 2006
The most recent version of this document can be viewed at
Consider ways of storing rows more compactly on disk
-
Reorder physical storage order to reduce 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.
-
-
Store disk pages with no alignment/padding?
-
This necessitates adding CPU-required padding when moving
- rows from disk to memory.
-
-
Support a smaller header for short variable-length fields?
-
One idea is to store the header in network byte order (high bits
- first), and read the high bits to determine the header length.
+
Support a smaller header for short variable-length fields?
+
One idea is to create zero-or-one-byte-header versions
+ of varlena data types. In involves setting the high-bit and
+ 0-127 length in the single-byte header, or clear the high bit
+ and store the 7-bit ASCII value in the rest of the byte.
+ The small-header versions have no alignment requirements.
Reduce the row header size?