Re: Issue with the PRNG used by Postgres

From: Andres Freund <andres(at)anarazel(dot)de>
To: Parag Paul <parag(dot)paul(at)gmail(dot)com>
Cc: pgsql-hackers(at)lists(dot)postgresql(dot)org
Subject: Re: Issue with the PRNG used by Postgres
Date: 2024-04-10 16:09:31
Message-ID: 20240410160931.bddurkdqmnizfyh7@awork3.anarazel.de
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

Hi,

On 2024-04-10 07:55:16 -0700, Parag Paul wrote:
> This is a little bit more complex than that. The spinlocks are taken in the
> LWLock(Mutex) code, when the lock is not available right away.
> The spinlock is taken to attach the current backend to the wait list of the
> LWLock. This means, that this cannot be controlled.
> The repro when it happens, it affects any mutex or LWLock code path, since
> the low hamming index can cause problems by removing fairness from the
> system.

Please provide a profile of a problematic workload. I'm fairly suspicious
of the claim that RNG unfairness is a real part of the problem here.

Greetings,

Andres Freund

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Tom Lane 2024-04-10 16:28:10 Re: Issue with the PRNG used by Postgres
Previous Message Tom Lane 2024-04-10 16:02:25 Re: Issue with the PRNG used by Postgres