pgsql: Update TODO for short header versions: < o Reorder physical

Поиск
Список
Период
Сортировка
От momjian@postgresql.org (Bruce Momjian)
Тема pgsql: Update TODO for short header versions: < o Reorder physical
Дата
Msg-id 20060916220655.14FE79FB24D@postgresql.org
обсуждение исходный текст
Список pgsql-committers
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)

В списке pgsql-committers по дате отправления:

Предыдущее
От: tgl@postgresql.org (Tom Lane)
Дата:
Сообщение: pgsql: Rename the recently-added pg_timezonenames view to
Следующее
От: gsmet@pgfoundry.org (User Gsmet)
Дата:
Сообщение: pgfouine - pgfouine: resynced prepared statements support with current