From: MichaelDBA <MichaelDBA@sqlexec.com>
To: Dirk Krautschick <Dirk.Krautschick@trivadis.com>
Cc: pgsql-performance@lists.postgresql.org <pgsql-performance@lists.postgresql.org>
Subject: Re: sizing / capacity planning tipps related to expected request or transactions per second
Date: Mon, 24 Aug 2020 12:49:21 -0400
Message-ID: <bee06a6c-f409-c5d2-daa1-5340ed3ee2f9@sqlexec.com> (raw)
In-Reply-To: <AM0PR05MB6082A57CCA80CBFFC16F08A1E9560@AM0PR05MB6082.eurprd05.prod.outlook.com>
References: <AM0PR05MB6082A57CCA80CBFFC16F08A1E9560@AM0PR05MB6082.eurprd05.prod.outlook.com>
Hi Dirk,
There are a bunch of other things to consider besides just TPS and size
of database. Since PG is process-bound, I would consider connection
activity: How many active connections at any one time? This greatly
affects your CPUs. SQL workload is another big factor: a lot of complex
queries may use up or want to use up large amounts of work_mem, which
greatly affects your memory capacity.
Bunch of other stuff, but these are my top 2.
Regards,
Michael Vitale
Dirk Krautschick wrote on 8/24/2020 12:39 PM:
> Hi,
>
> are there any nice rules of thumb about capacity planning in relation the expected
> amount of transactions or request per second?
>
> For example, if I have around 100 000 transactions per second on a 5 TB database.
> With what amount of Memory and CPUs/Cores and which settings would you basically
> Start to evaluate the performance.
>
> Or are there any other recommendations or experiences here?
>
> Thanks and best regards
>
> Dirk
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: MichaelDBA@sqlexec.com, Dirk.Krautschick@trivadis.com, pgsql-performance@lists.postgresql.org
Subject: Re: sizing / capacity planning tipps related to expected request or transactions per second
In-Reply-To: <bee06a6c-f409-c5d2-daa1-5340ed3ee2f9@sqlexec.com>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox