Log Message:
-----------
Update TODO for short header versions:
< 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.
<
< 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
Modified Files:
--------------
pgsql/doc:
TODO (r1.1983 -> r1.1984)
(http://developer.postgresql.org/cvsweb.cgi/pgsql/doc/TODO.diff?r1=1.1983&r2=1.1984)
pgsql/doc/src/FAQ:
TODO.html (r1.485 -> r1.486)
(http://developer.postgresql.org/cvsweb.cgi/pgsql/doc/src/FAQ/TODO.html.diff?r1=1.485&r2=1.486)
---------------------------(end of broadcast)---------------------------
TIP 9: In versions below 8.0, the planner will ignore your desire to
choose an index scan if your joining column's datatypes do not
match
