Postgres Pro
Downloads
Home   >   mailing lists

Re: huge SubtransSLRU and SubtransBuffer wait_event - Mailing list pgsql-performance

From Nikolay Samokhvalov
Subject Re: huge SubtransSLRU and SubtransBuffer wait_event
Date
Msg-id CANNMO++EdBcR7yHMp4hsYO3NcyKwj_VFy4jzuqA0AGeCfn2XjA@mail.gmail.com
Whole thread Raw
In response to Re: huge SubtransSLRU and SubtransBuffer wait_event  (Laurenz Albe <laurenz.albe@cybertec.at>)
Responses Re: huge SubtransSLRU and SubtransBuffer wait_event  (Laurenz Albe <laurenz.albe@cybertec.at>)
RE: huge SubtransSLRU and SubtransBuffer wait_event  ("James Pang (chaolpan)" <chaolpan@cisco.com>)
List pgsql-performance
Tree view


On Thu, Feb 1, 2024 at 04:42 Laurenz Albe <laurenz.albe@cybertec.at> wrote:
Today, the only feasible solution is not to create more than 64 subtransactions
(savepoints or PL/pgSQL EXCEPTION clauses) per transaction.

Sometimes, a single subtransaction is enough to experience a bad SubtransSLRU spike: 

I think 64+ nesting level is quite rare, but this kind of problem that hits you when you have high XID growth (lots of writes) + long-running transaction is quite easy to bump into. Or this case involving MultiXactIDs: 

Nik

pgsql-performance by date:

Previous
From: Lars Aksel Opsahl
Date:
Subject: Re: huge SubtransSLRU and SubtransBuffer wait_event
Next
From: Laurenz Albe
Date:
Subject: Re: huge SubtransSLRU and SubtransBuffer wait_event