On Thu, Jun 5, 2025 at 8:02 AM Andres Freund <andres@anarazel.de> wrote:
> On 2025-06-03 08:00:01 +0300, Alexander Lakhin wrote:
> > 2025-06-03 00:19:09.282 EDT [25175:1] LOG: !!!pgaio_io_before_start| ioh:
> > 0x104c3e1a0, ioh->op: 1, ioh->state: 1, ioh->result: 0, ioh->num_callbacks:
> > 2, ioh->generation: 21694
>
> But here it somehow turned to 1 (PGAIO_OP_READV), despite there not being any
> "normal" reason for that. We know that the IO wasn't actually started as
> otherwise pgaio_io_start_readv() would have logged that fact.
A cheap/easy thing to try, maybe: give that enumeration more
distinctive values like 0xaaaa, 0xbbbb, or whatever, to see if we get
a wild 1 here?
