Content-Type: text/plain;
	charset=utf-8
Mime-Version: 1.0 (1.0)
Subject: Re: Server upgrade advice [xpost]
From: Ian Harding <harding.ian@gmail.com>
In-Reply-To: <20190305220326.4qtowuv2s4zdpgc5@campbell-lange.net>
Date: Tue, 5 Mar 2019 21:04:01 -0800
Cc: pgsql-performance@postgresql.org
Content-Transfer-Encoding: quoted-printable
Message-Id: <37E61451-B744-4C7D-834C-BAA917ADE243@gmail.com>
References: <20190305220326.4qtowuv2s4zdpgc5@campbell-lange.net>
To: Rory Campbell-Lange <rory@campbell-lange.net>
Precedence: bulk

The two major version upgrade will bring many happy returns.  That=E2=80=99s=
 all I can contribute.=20

> On Mar 5, 2019, at 2:03 PM, Rory Campbell-Lange <rory@campbell-lange.net> w=
rote:
>=20
> Apologies for the cross-post to the general list. I realised I should
> have (possibly?) posted here instead. Advice gratefully received.
>=20
> We've been happy running a database server and replica for some years
> with the following details and specs:
>=20
>    postgres 9.5 (currently)
>    supermicro X9DRD-7LN4F
>    LSI Megaraid MR9261-8i with BBU
>        250gb raid 1 /
>        224gb raid 10 /db
>    126GB RAM (1066Mhz DDR3)
>    2 x Xeon E5-2609 v2 @ 2.5GHz
>=20
> Services on the server are scaling up quite quickly, so we are running
> out of disk space for the several hundred databases in the cluster.
> While the disk space is fairly easy to solve, our main issue is CPU
> hitting daily 5 minute peaks of 65% plus under load for complex plpgsql
> queries, causing query backups. While we don't often spill queries to
> disk, running out of RAM is an incipient problem too.=20
>=20
> While we could split the cluster there are some management issues to do
> with that, together with our having a policy of local and remote
> replicas.=20
>=20
> Consequently we're thinking of the following replacement servers:
>=20
>    postgres 11 (planned)
>    supermicro 113TQ-R700W=20
>    LSI MegaRAID 9271-8i SAS/SATA RAID Controller, 1Gb DDR3 Cache (PCIE- Ge=
n 3)
>        500gb raid 1 /
>        2tb raid 10 /db
>        with "zero maintenance flash cache protection"
>    256GB RAM (2666MHz DDR4)
>    2x E5-2680 v4 Intel Xeon, 14 Cores, 2.40GHz, 35M Cache,
>=20
> This configuration gives us lots more storage, double the RAM (with 8
> slots free) and just under 4x CPU (according to passmark) with lots more
> cores.
>=20
> We're hoping to get two to three years of service out of this upgrade,
> but then will split the cluster between servers if demand grows more
> than we anticipate.
>=20
> Any comments on this upgrade, strategy or the "zero maintenance" thingy
> (instead of a BBU) would be much appreciated.
>=20
> Rory
>=20