Re: Reducing WaitEventSet syscall churn

From: Thomas Munro <thomas(dot)munro(at)gmail(dot)com>
To: pgsql-hackers <pgsql-hackers(at)postgresql(dot)org>
Subject: Re: Reducing WaitEventSet syscall churn
Date: 2020-02-07 21:15:18
Message-ID: CA+hUKGJ6Ogrrq0CJmD8qp96xm2zdyutj4KWSYsjdtcRGX3a_mA@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Sat, Feb 8, 2020 at 10:00 AM Thomas Munro <thomas(dot)munro(at)gmail(dot)com> wrote:
> On Tue, Jan 21, 2020 at 1:45 PM Thomas Munro <thomas(dot)munro(at)gmail(dot)com> wrote:
> > Here are some patches to get rid of frequent system calls.
>
> Here is one more case that I was sitting on because I wasn't sure how
> to do it: walreceiver.c. To make that work, libpq needs to be able to
> tell you when the socket has changed, which I did with a counter that
> is exposed to client code in patch 0004. The walreceiver change in
> 0005 works (trace the system calls on walreceiver to see the
> difference), but perhaps we can come up with a better way to code it
> so that eg logical/worker.c doesn't finish up duplicating the logic.
> Thoughts?

(To be clear: I know the 0005 patch doesn't clean up after itself in
various cases, it's for discussion only to see if others have ideas
about how to structure things to suit various potential users of
libpqwalreceiver.so.)

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Tomas Vondra 2020-02-07 21:35:19 Re: improve transparency of bitmap-only heap scans
Previous Message Stephen Frost 2020-02-07 21:13:39 Re: pg_basebackup and snapshots