| From: | Alexandre Felipe <o(dot)alexandre(dot)felipe(at)gmail(dot)com> |
|---|---|
| To: | shihao zhong <zhong950419(at)gmail(dot)com> |
| Cc: | Andres Freund <andres(at)anarazel(dot)de>, PostgreSQL Hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
| Subject: | Re: Throwing away unnecessary spin-locks |
| Date: | 2026-10-02 12:16:37 |
| Message-ID: | CAE8JnxOQjWEkOyW8ZaZNUDtQ5ixa823U6h_C47UazX03aUVHkQ@mail.gmail.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Hi Shihao,
On Fri, Oct 2, 2026 at 6:30 AM shihao zhong <zhong950419(at)gmail(dot)com> wrote:
>
> I think the safer route is what recent commits like df3978c2340 did,
> convert the field to pg_atomic and use pg_atomic_read_membarrier_u32()
> and pg_atomic_write_membarrier_u32().
>
Actually, v1 conflicted with that commit, rebasing.
The reason I didn't want to do that is that I wanted a uniform way to handle
all types.
v1.1 pg_atomic_{write,read}_membarrier_uint{32,64} and keeps the
lock for 8- and 16-bits.
Can we use pg_atomic_flag for bool, or will that have different
representations?
Regards,
Alexandre felipe
| Attachment | Content-Type | Size |
|---|---|---|
| v1.1-0002-replace-slock_-read-write-_.patch | application/octet-stream | 24.6 KB |
| v1.1-0001-Spare-locks-for-uint32-and-uint64.patch | application/octet-stream | 4.5 KB |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Andres Freund | 2026-10-02 13:19:54 | Re: Throwing away unnecessary spin-locks |
| Previous Message | Ayush Tiwari | 2026-10-02 11:08:17 | Re: PANIC serves too many masters |