|From:||Andrey Borodin <x4mmm(at)yandex-team(dot)ru>|
|To:||Michail Nikolaev <michail(dot)nikolaev(at)gmail(dot)com>|
|Cc:||Alexander Korotkov <aekorotkov(at)gmail(dot)com>, Andres Freund <andres(at)anarazel(dot)de>, Kirill Reshke <reshkekirill(at)gmail(dot)com>, PostgreSQL Hackers <pgsql-hackers(at)postgresql(dot)org>|
|Subject:||Re: Slow standby snapshot|
|Views:||Raw Message | Whole Thread | Download mbox | Resend email|
> On 22 Nov 2021, at 14:05, Michail Nikolaev <michail(dot)nikolaev(at)gmail(dot)com> wrote:
>> Write barrier must be issued after write, not before.
>> Don't we need to issue read barrier too?
> The write barrier is issued after the changes to KnownAssignedXidsNext
> and KnownAssignedXidsValid arrays and before the update of
> So, it seems to be correct. We make sure once the CPU sees changes of
> headKnownAssignedXids - underlying arrays contain all the required
Patch on barrier seems too complicated to me right now. I’d propose to focus on KnowAssignedXidsNext patch: it’s clean, simple and effective.
I’ve rebased the patch so that it does not depend on previous step. Please check out it’s current state, if you are OK with it - let’s mark the patch Ready for Committer. Just maybe slightly better commit message would make the patch easier to understand.
Thanks! Best regards, Andrey Borodin.
|Next Message||Justin Pryzby||2022-02-20 19:36:55||Re: Adding CI to our tree (ccache)|
|Previous Message||Robert Haas||2022-02-20 15:30:21||Re: Removing more vacuumlazy.c special cases, relfrozenxid optimizations|