Hello,
We noticed a sustained increased in IO Wait of read queries after
upgrading from 13.13 to 13.21. Eventually, we narrowed it down to a
spike in index_blocks_read of a certain table where Bitmap Heap Scans do
happen.
Do you think that this change (i.e. removing the optimization) could be
what caused this regression?
Thanks
On 3/5/25 1:12 PM, Matthias van de Meent wrote:
On Sun, 2 Mar 2025 at 01:35, Tom Lane <[email protected]> wrote:
Peter Geoghegan <[email protected]> writes:
Is everybody in agreement about committing and back patching this fix,
which simply disables the optimization altogether?
I myself don't see a better way, but thought I'd ask before proceeding
with review and commit.
If you don't see a clear path forward, then "disable" is the only
reasonable choice for the back branches. Maybe we'll find a fix
in future, but it seems unlikely that it'd be back-patchable.
Agreed.
Here's patch v5 for the master branch (now up to f4694e0f), with no
interesting changes other than fixing apply conflicts caused by
bfe56cdf.
Kind regards,
Matthias van de Meent
Neon (https://neon.tech)
