| From: | Jeff Davis <pgsql(at)j-davis(dot)com> |
|---|---|
| To: | Andres Freund <andres(at)anarazel(dot)de> |
| Cc: | pgsql-hackers(at)postgresql(dot)org |
| Subject: | Re: Should io_method=worker remain the default? |
| Date: | 2025-09-05 23:07:09 |
| Message-ID: | 1b50102876dc9564049c985cff0ec1903cc8d502.camel@j-davis.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Fri, 2025-09-05 at 13:25 -0700, Jeff Davis wrote:
> As an aside, I'm building with meson using -Dc_args="-msse4.2 -Wtype-
> limits -Werror=missing-braces". But I notice that the meson build
> doesn't seem to use -funroll-loops or -ftree-vectorize when building
> checksums.c. Is that intentional? If not, perhaps slower checksum
> calculations explain my results.
Attached a patch. I'm not sure if it's the right way to do things, but
the resulting compiler command seems right to me.
It doesn't affect my tests in this thread much, but it seems best to be
consistent with autoconf.
Regards,
Jeff Davis
| Attachment | Content-Type | Size |
|---|---|---|
| v1-0001-meson-build-checksums-with-extra-optimization-fla.patch | text/x-patch | 1.1 KB |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Masahiko Sawada | 2025-09-05 23:21:02 | Re: POC: enable logical decoding when wal_level = 'replica' without a server restart |
| Previous Message | Tatsuo Ishii | 2025-09-05 22:58:52 | Re: Raw parse tree is not dumped to log |