Re: pgBufferUsage.blk_{read|write}_time are zero although there are pgBufferUsage.local_blks_{read|written}

From: Robert Haas <robertmhaas(at)gmail(dot)com>
To: Nazir Bilal Yavuz <byavuz81(at)gmail(dot)com>
Cc: Melanie Plageman <melanieplageman(at)gmail(dot)com>, pgsql-hackers <pgsql-hackers(at)postgresql(dot)org>
Subject: Re: pgBufferUsage.blk_{read|write}_time are zero although there are pgBufferUsage.local_blks_{read|written}
Date: 2023-10-05 12:51:40
Message-ID: CA+Tgmob5rveOZ608eYNQgja8J=aJvYQC4KH85fFJJOBmr6kn+g@mail.gmail.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

On Thu, Oct 5, 2023 at 6:25 AM Nazir Bilal Yavuz <byavuz81(at)gmail(dot)com> wrote:
> What do you think about the second patch, counting extend calls'
> timings in blk_write_time? In my opinion if something increments
> {shared|local}_blks_written, then it needs to be counted in
> blk_write_time too. I am not sure why it is decided like that.

I agree that an extend should be counted the same way as a write. But
I'm suspicious that here too we have confusion about whether
blk_write_time is supposed to be covering shared buffers and local
buffers or just shared buffers.

--
Robert Haas
EDB: http://www.enterprisedb.com

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Isaac Morland 2023-10-05 13:10:23 Re: Pre-proposal: unicode normalized text
Previous Message Matthias van de Meent 2023-10-05 12:31:00 Re: Change of behaviour for creating same type name in multiple schemas