> On 10 Apr 2024, at 21:48, Parag Paul <parag.p...@gmail.com> wrote:
>
> Yes, the probability of this happening is astronomical, but in production
> with 128 core servers with 7000 max_connections, with petabyte scale data,
> this did repro 2 times in the last month. We had to move to a local approach
> to manager our ratelimiting counters.
FWIW we observed such failure on this [0] LWLock two times too. Both cases were
recent (February).
We have ~15k clusters with 8MTPS, so it’s kind of infrequent, but not
astronomic. We decided to remove that lock.
Best regards, Andrey Borodin.
[0]
https://github.com/munakoiso/logerrors/pull/25/files#diff-f8903c463a191f399b3e84c815ed6dc60adbbfc0fb0b2db490be1e58dc692146L85