| From: | David Rowley <dgrowleyml(at)gmail(dot)com> |
|---|---|
| To: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
| Cc: | Tomas Vondra <tomas(dot)vondra(at)enterprisedb(dot)com>, Amit Kapila <amit(dot)kapila16(at)gmail(dot)com>, Andres Freund <andres(at)anarazel(dot)de>, Robert Haas <robertmhaas(at)gmail(dot)com>, Yura Sokolov <y(dot)sokolov(at)postgrespro(dot)ru>, PostgreSQL Developers <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
| Subject: | Re: Reducing the chunk header sizes on all memory context types |
| Date: | 2022-09-02 08:11:12 |
| Message-ID: | CAApHDvqOJ8Uo8=pQwq0nF6EH4ugCdEOMd6sZRgFHL35j5WZv6w@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Thu, 1 Sept 2022 at 12:46, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> wrote:
>
> David Rowley <dgrowleyml(at)gmail(dot)com> writes:
> > Maybe we should just consider always making room for a sentinel for
> > chunks that are on dedicated blocks. At most that's an extra 8 bytes
> > in some allocation that's either over 1024 or 8192 (depending on
> > maxBlockSize).
>
> Agreed, if we're not doing that already then we should.
Here's a patch to that effect.
I've made it so that there's always space for the sentinel for all
generation.c and slab.c allocations. There is no power of 2 rounding
with those, so no concern about doubling the memory for power-of-2
sized allocations.
With aset.c, I'm only adding sentinel space when size >
allocChunkLimit, aka external chunks.
David
| Attachment | Content-Type | Size |
|---|---|---|
| v1-0001-Make-more-effort-to-have-a-sentinel-byte-in-memor.patch | text/plain | 10.5 KB |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Michael Paquier | 2022-09-02 08:14:29 | Re: [Commitfest 2022-09] Begins This Thursday |
| Previous Message | Michael Paquier | 2022-09-02 08:09:14 | Re: Avoid erroring out when unable to remove or parse logical rewrite files to save checkpoint work |