From: | David Rowley <dgrowleyml(at)gmail(dot)com> |
---|---|
To: | Andres Freund <andres(at)anarazel(dot)de> |
Cc: | PostgreSQL Developers <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
Subject: | Re: Add palloc_aligned() to allow arbitrary power of 2 memory alignment |
Date: | 2022-11-08 03:53:49 |
Message-ID: | CAApHDvpfm7SnRLgvRZj4QEHYEQGeZ=oUeBbcJ9RNHaErPR6eWg@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
On Tue, 8 Nov 2022 at 14:57, David Rowley <dgrowleyml(at)gmail(dot)com> wrote:
> On Tue, 8 Nov 2022 at 05:24, Andres Freund <andres(at)anarazel(dot)de> wrote:
> > Should we handle the case where we get a suitably aligned pointer from
> > MemoryContextAllocExtended() differently?
>
> Maybe it would be worth the extra check. I'm trying to imagine future
> use cases. Maybe if someone wanted to ensure that we're aligned to
> CPU cache line boundaries then the chances of the pointer already
> being aligned to 64 bytes is decent enough. The problem is it that
> it's too late to save any memory, it just saves a bit of boxing and
> unboxing of the redirect headers.
Thinking about that a bit more, if we keep the repalloc support then
we can't do this as if we happen to get the right alignment by chance
during the palloc_aligned, then if we don't have the redirection
MemoryChunk, then we've no way to ensure we keep the alignment after a
repalloc.
David
From | Date | Subject | |
---|---|---|---|
Next Message | David Rowley | 2022-11-08 03:54:25 | Re: Add palloc_aligned() to allow arbitrary power of 2 memory alignment |
Previous Message | Hayato Kuroda (Fujitsu) | 2022-11-08 03:51:23 | RE: Perform streaming logical transactions by background workers and parallel apply |