Re: Two fsync related performance issues?

From: Thomas Munro <thomas(dot)munro(at)gmail(dot)com>
To: Paul Guo <pguo(at)pivotal(dot)io>
Cc: PostgreSQL mailing lists <pgsql-hackers(at)postgresql(dot)org>
Subject: Re: Two fsync related performance issues?
Date: 2020-09-10 11:40:22
Message-ID: CA+hUKG+oPhL4KCWqavPpdXZ-r0dmxZJSBLhfkGcfJOk6iN1cwQ@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Thu, Sep 3, 2020 at 12:09 PM Thomas Munro <thomas(dot)munro(at)gmail(dot)com> wrote:
> On Tue, May 12, 2020 at 12:43 PM Paul Guo <pguo(at)pivotal(dot)io> wrote:
> > RecreateTwoPhaseFile(gxact->xid, buf, len);

> I hadn't previously focused on this second part of your email. I
> think the fsync() call in RecreateTwoPhaseFile() might be a candidate
> for processing by the checkpoint code through the new facilities in
> sync.c, which effectively does something like what you describe. Take

I looked at this more closely and realised that I misunderstood; I was
thinking of a problem like the one that was already solved years ago
with commit 728bd991c3c4389fb39c45dcb0fe57e4a1dccd71. Sorry for the
noise.

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message torikoshia 2020-09-10 11:53:53 Re: Get memory contexts of an arbitrary backend process
Previous Message vignesh C 2020-09-10 11:21:22 Re: Improvements in Copy From