MIME-Version: 1.0
From: Marc Millas <marc.millas@mokadb.com>
Date: Fri, 25 Apr 2025 15:42:59 +0200
Message-ID: <CADX_1abjKJhk10vWz6S=cwgXsppGXw2VjNnLVByE3EMJzLzD4w@mail.gmail.com>
Subject: shared buffers
To: "pgsql-general@lists.postgresql.org" <pgsql-general@lists.postgresql.org>
Content-Type: multipart/alternative; boundary="000000000000f4468c06339a8390"
Archived-At: <https://www.postgresql.org/message-id/CADX_1abjKJhk10vWz6S%3DcwgXsppGXw2VjNnLVByE3EMJzLzD4w%40mail.gmail.com>
Precedence: bulk

--000000000000f4468c06339a8390
Content-Type: text/plain; charset="UTF-8"

hello,

got something strange to me:
Same db ie. same data, around 1.2TB,one on pg13, one on pg16
same 16 GB of shared_buffers,
I am the single user.
both have track_io_timing on

on pg13, if I run a big request with explain (analyze,buffers),
I see around 6 GB read
if I do rerun the very same request, no more read(s), all data in the
shared buffers cache. fine
If I check with pg_buffercache what's in it, I see the biggest tables of my
request within the biggest users (in number of blocks used). All this is
fine.

next, if I do the very same on the pg16 machine, whatever the number of
times I rerun the explain (analyze, buffers) of the same request, each
time, the explain shows the same volume of reads. again and again.
If I check with pg_buffercache, the set of objects stay the same, WITHOUT
the objects of my request, just like if those objects where sticky.

any idea ?

thanks

Marc MILLAS
Senior Architect
+33607850334
www.mokadb.com

--000000000000f4468c06339a8390
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div>hello,</div><div><br></div><div>got something strange=
 to me:</div><div>Same db ie. same data, around 1.2TB,one on pg13, one on p=
g16</div><div>same 16 GB of shared_buffers,</div><div>I am the single user.=
</div><div>both have track_io_timing on</div><div><br></div><div>on pg13, i=
f I run a big request with explain (analyze,buffers),=C2=A0</div><div>I see=
 around 6 GB read</div><div>if I do rerun the very same request, no more re=
ad(s), all data in the shared buffers cache. fine</div><div>If I check with=
 pg_buffercache what&#39;s in it, I see the biggest tables of my request wi=
thin the biggest users (in number of blocks used). All this is fine.</div><=
div><br></div><div>next, if I do the very same on the pg16 machine, whateve=
r the number of times I rerun the explain=C2=A0(analyze, buffers) of the sa=
me request, each time, the explain shows the same volume of reads. again an=
d again.</div><div>If I check with pg_buffercache, the set of objects stay =
the same, WITHOUT the objects of my request, just like if those objects whe=
re sticky.</div><div><br></div><div>any idea ?</div><div><br></div><div>tha=
nks</div><div><br></div><div><div dir=3D"ltr" class=3D"gmail_signature" dat=
a-smartmail=3D"gmail_signature"><div dir=3D"ltr"><div><div dir=3D"ltr">Marc=
 MILLAS<div>Senior Architect</div><div>+33607850334</div><div><a href=3D"ht=
tp://www.mokadb.com" target=3D"_blank">www.mokadb.com</a></div><div><br></d=
iv></div></div></div></div></div></div>

--000000000000f4468c06339a8390--