Horton

Re: Non-reproducible AIO failure

Tom Lane <tgl@sss.pgh.pa.us>

View thread
From: Tom Lane <tgl@sss.pgh.pa.us>
To: Andres Freund <andres@anarazel.de>
Cc: Konstantin Knizhnik <knizhnik@garret.ru>, PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>
Date: 2025-06-17T14:15:37Z
Lists: pgsql-hackers

Commits

Same data as JSON: GET /api/v1/messages/:b64id/commits the thread's linked commits as JSON, with link sources. API reference →

  1. aio: Stop using enum bitfields due to bad code generation

  2. amcheck: Fix posting tree checks in gin_index_check()

  3. aio: Add missing memory barrier when waiting for IO handle

Andres Freund <andres@anarazel.de> writes:
> Both of you are running Ventura, right?

FTR, the machines I'm trying this on are all running current Sequoia:

[tgl@minim4 ~]$ uname -a
Darwin minim4.sss.pgh.pa.us 24.5.0 Darwin Kernel Version 24.5.0: Tue Apr 22 19:53:27 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6041 arm64

Interestingly, the M1 seems to be using a different kernel build than
my two M4 machines:

[tgl@minim1 ~]$ uname -a
Darwin minim1.sss.pgh.pa.us 24.5.0 Darwin Kernel Version 24.5.0: Tue Apr 22 19:48:46 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8103 arm64

although Apple has a history of using kernels customized to specific
core counts, so maybe that's all there is there.

These are all personally-owned bare metal:

[tgl@minim4 ~]$ profiles status -type enrollment
Enrolled via DEP: No
MDM enrollment: No
[tgl@minim4 ~]$ kextstat -l | grep -v com.apple
Executing: /usr/bin/kmutil showloaded --list-only
No variant specified, falling back to release

As for your previous question, I tried both c=16 and c=32 on
the M4.

			regards, tom lane