diff options
author | Robert Haas <rhaas@postgresql.org> | 2024-03-21 12:54:58 -0400 |
---|---|---|
committer | Robert Haas <rhaas@postgresql.org> | 2024-03-21 12:54:58 -0400 |
commit | 57184c3b5d89763c882a15adfcdb00990a09d382 (patch) | |
tree | 190b9defc80bd6e0ee772d2cfc1648457b4c89e6 /src/backend/executor/nodeModifyTable.c | |
parent | 84d80663199b98db32625b80b039a07487a11b47 (diff) | |
download | postgresql-57184c3b5d89763c882a15adfcdb00990a09d382.tar.gz postgresql-57184c3b5d89763c882a15adfcdb00990a09d382.zip |
docs: Make claims about the benefits of HOT updates more precise.
The old text claims that HOT completely removes old row versions.
It was unclear whether it just meant the tuples themselves, or the
tuples together with their line pointers. If it meant the former,
it was wrong because we can remove dead row versions even when no
HOT updates have occurred, so it's not describing a benefit of HOT.
If it meant the latter, it was wrong because HOT doesn't allow
reclaiming the root tuple's line pointer.
This section does seems like it's intended to be more of an
informal introduction to HOT than a precise technical description
of every detail of how it works, but we still don't want it to
say things that are just not true, so update the text enough
to avoid that.
Patch by me, reviewed by James Coleman (although he would have
preferred more extensive changes) and Shubham Khanna.
Discussion: http://postgr.es/m/CA+TgmobH6DPmR-u--Xgeg8cYUwhDhypNsv38nDrAJyf_xno=TQ@mail.gmail.com
Diffstat (limited to 'src/backend/executor/nodeModifyTable.c')
0 files changed, 0 insertions, 0 deletions