MIME-Version: 1.0
References: <cb014f00-66b2-4328-a65e-d11c681c9f45@gmail.com>
 <CAEvyyTj0rEsgcQOQgkARbRPbupHR_mc=TUzHBBLNzd8JByUUTw@mail.gmail.com>
 <4c1d0b97-a5f8-472c-afdd-bdeb09b93f33@gmail.com> <OS9PR01MB12149A6CEE200E1A5A88D9F14F563A@OS9PR01MB12149.jpnprd01.prod.outlook.com>
 <CAEvyyTiQqd=rv3XUxc0YEaW-feopksBveZKKjVZNeSVG=GrY+A@mail.gmail.com> <TYRPR01MB121560B291DA3CD262CC7A09AF568A@TYRPR01MB12156.jpnprd01.prod.outlook.com>
In-Reply-To: <TYRPR01MB121560B291DA3CD262CC7A09AF568A@TYRPR01MB12156.jpnprd01.prod.outlook.com>
From: lakshmi <lakshmigcdac@gmail.com>
Date: Mon, 23 Feb 2026 17:42:49 +0530
Message-ID: <CAEvyyTjPWfvJLn3c_G_zLRffZ3=YqzMYj6c5znaNxpHyZAg3XQ@mail.gmail.com>
Subject: Re: parallel data loading for pgbench -i
To: "Hayato Kuroda (Fujitsu)" <kuroda.hayato@fujitsu.com>
Cc: Mircea Cadariu <cadariu.mircea@gmail.com>, 
	PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>, "tomas@vondra.me" <tomas@vondra.me>
Content-Type: multipart/alternative; boundary="000000000000231167064b7ca606"
Archived-At: <https://www.postgresql.org/message-id/CAEvyyTjPWfvJLn3c_G_zLRffZ3%3DYqzMYj6c5znaNxpHyZAg3XQ%40mail.gmail.com>
Precedence: bulk

--000000000000231167064b7ca606
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Fri, Feb 20, 2026 at 3:29=E2=80=AFPM Hayato Kuroda (Fujitsu) <
kuroda.hayato@fujitsu.com> wrote:

> Dear Iakshmi,
>
> Thanks for the measurement!
>
> > For scale 500, the serial initialization on my system takes around 34.3
> seconds.
> > Using parallel initialization without partitions (-j 10) makes the
> client-side
> > data generation noticeably faster,But the overall runtime ends up
> slightly
> > higher because the vacuum phase becomes much longer.
>
> To confirm, do you know the reason why the VACUUMing needs more time than
> serial case?
>
> Dear Hayato,

Thank you for the question.

From what I observed,in the non-partitioned parallel case the data
generation phase becomes much faster,but the VACUUM phase takes longer
compared to the serial run.

My current understanding is that this may be related to multiple workers
inserting into the same heap relation.That could potentially affect page
locality or increases the amount of freezing work required afterward.In
contrast,the partitioned case seems to benefit more clearly,likely because
each worker operates on a separate partition and COPY FREEZE reduces the
vacuum effort.

I have not yet done deeper internal analysis,so this is based on the
behavior I measured rather than detailed inspection.If needed,I can try to
collect additional statistics to better understand and difference.

please let me know if this reasoning aligns with your understanding.

Best regards
Lakshmi


>
>
>

--000000000000231167064b7ca606
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div dir=3D"ltr"><div><br></div></div><div class=3D"gmail_=
quote gmail_quote_container"><div dir=3D"ltr" class=3D"gmail_attr">On Fri, =
Feb 20, 2026 at 3:29=E2=80=AFPM Hayato Kuroda (Fujitsu) &lt;<a href=3D"mail=
to:kuroda.hayato@fujitsu.com">kuroda.hayato@fujitsu.com</a>&gt; wrote:<br><=
/div><blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;bo=
rder-left:1px solid rgb(204,204,204);padding-left:1ex">Dear Iakshmi,<br>
<br>
Thanks for the measurement!<br>
<br>
&gt; For scale 500, the serial initialization on my system takes around 34.=
3 seconds.<br>
&gt; Using parallel initialization without partitions (-j 10) makes the cli=
ent-side<br>
&gt; data generation noticeably faster,But the overall runtime ends up slig=
htly<br>
&gt; higher because the vacuum phase becomes much longer.<br>
<br>
To confirm, do you know the reason why the VACUUMing needs more time than s=
erial case?<br>
<br></blockquote><div>Dear Hayato,<br><br>Thank you for the question.<br><b=
r>From what I observed,in the non-partitioned parallel case the data genera=
tion phase becomes much faster,but the VACUUM phase takes longer compared t=
o the serial run.<br><br>My current understanding is that this may be relat=
ed to multiple workers inserting into the same heap relation.That could pot=
entially affect page locality or increases the amount of freezing work requ=
ired afterward.In contrast,the partitioned case seems to benefit more clear=
ly,likely because each worker operates on a separate partition and COPY FRE=
EZE reduces the vacuum effort.<br><br>I have not yet done deeper internal a=
nalysis,so this is based on the behavior I measured rather than detailed in=
spection.If needed,I can try to collect additional statistics to better und=
erstand and difference.<br><br>please let me know if this reasoning aligns =
with your understanding.<br><br>Best regards<br>Lakshmi=C2=A0</div><div>=C2=
=A0</div><blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8e=
x;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
<br>
</blockquote></div></div>

--000000000000231167064b7ca606--