Received: from malur.postgresql.org ([217.196.149.56]) by arkaria.postgresql.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA384:256) (Exim 4.89) (envelope-from ) id 1f64jV-0008Ic-3G for pgsql-performance@arkaria.postgresql.org; Wed, 11 Apr 2018 01:39:33 +0000 Received: from localhost ([127.0.0.1] helo=malur.postgresql.org) by malur.postgresql.org with esmtp (Exim 4.89) (envelope-from ) id 1f64jT-0005Ti-BX for pgsql-performance@arkaria.postgresql.org; Wed, 11 Apr 2018 01:39:31 +0000 Received: from makus.postgresql.org ([2001:4800:1501:1::229]) by malur.postgresql.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA384:256) (Exim 4.89) (envelope-from ) id 1f64jS-0005TZ-SR for pgsql-performance@lists.postgresql.org; Wed, 11 Apr 2018 01:39:31 +0000 Received: from master.mhcomputing.net ([74.208.228.170] helo=mail.mhcomputing.net) by makus.postgresql.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA384:256) (Exim 4.89) (envelope-from ) id 1f64jP-0000O9-KG for pgsql-performance@lists.postgresql.org; Wed, 11 Apr 2018 01:39:29 +0000 Received: from [30.218.160.37] (66-87-118-37.pools.spcsdns.net [66.87.118.37]) by mail.mhcomputing.net (Postfix) with ESMTPSA id EEA39153 for ; Tue, 10 Apr 2018 18:39:23 -0700 (PDT) From: Matthew Hall Content-Type: multipart/alternative; boundary=Apple-Mail-B418783F-4E3D-4FB3-AE54-C2317EF6F229 Content-Transfer-Encoding: 7bit Mime-Version: 1.0 (1.0) Date: Tue, 10 Apr 2018 18:39:21 -0700 Subject: Re: Latest advice on SSD? Message-Id: <45F04B78-1877-4628-A758-2ABE0C57BA7C@mhcomputing.net> References: In-Reply-To: To: pgsql-performance@lists.postgresql.org X-Mailer: iPhone Mail (15E216) List-Id: List-Help: List-Subscribe: List-Post: List-Owner: List-Archive: Precedence: bulk --Apple-Mail-B418783F-4E3D-4FB3-AE54-C2317EF6F229 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable The most critical bit of advice I've found is setting this preference: https://amplitude.engineering/how-a-single-postgresql-config-change-improved= -slow-query-performance-by-50x-85593b8991b0 I'm using 4 512GB Samsung 850 EVOs in a hardware RAID 10 on a 1U server with= about 144 GB RAM and 8 Xeon cores. I usually burn up CPU more than I burn u= p disks or RAM as compared to using magnetic where I had horrible IO wait pe= rcentages, so it seems to be performing quite well so far.=20 Matthew Hall > On Apr 9, 2018, at 7:36 PM, Craig James wrote: >=20 > One of our four "big iron" (spinning disks) servers went belly up today. (= Thanks, Postgres and pgbackrest! Easy recovery.) We're planning to move to a= cloud service at the end of the year, so bad timing on this. We didn't want= to buy any more hardware, but now it looks like we have to. >=20 > I followed the discussions about SSD drives when they were first becoming m= ainstream; at that time, the Intel devices were king. Can anyone recommend w= hat's a good SSD configuration these days? I don't think we want to buy a ne= w server with spinning disks. >=20 > We're replacing: > 8 core (Intel) > 48GB memory > 12-drive 7200 RPM 500GB > RAID1 (2 disks, OS and WAL log) > RAID10 (8 disks, postgres data dir) > 2 spares > Ubuntu 16.04 > Postgres 9.6 >=20 > The current system peaks at about 7000 TPS from pgbench. >=20 > Our system is a mix of non-transactional searching (customers) and transac= tional data loading (us). >=20 > Thanks! > Craig >=20 > --=20 > --------------------------------- > Craig A. James > Chief Technology Officer > eMolecules, Inc. > --------------------------------- --Apple-Mail-B418783F-4E3D-4FB3-AE54-C2317EF6F229 Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable The most critical bit of advice I've found i= s setting this preference:

https://amplitude.engineering/how-a-single-postgre= sql-config-change-improved-slow-query-performance-by-50x-85593b8991b0

I'm using 4 512GB Samsung 850 EVOs in a hardware RAID= 10 on a 1U server with about 144 GB RAM and 8 Xeon cores. I usually burn up= CPU more than I burn up disks or RAM as compared to using magnetic where I h= ad horrible IO wait percentages, so it seems to be performing quite well so f= ar. 

Matthew Hall
=
On Apr 9, 2018, at 7:36 PM, Craig James <cjames@emolecules.com> wrote:

One of our four "big iron" (spinning disk= s) servers went belly up today. (Thanks, Postgres and pgbackrest! Easy recov= ery.) We're planning to move to a cloud service at the end of the year, so b= ad timing on this. We didn't want to buy any more hardware, but now it looks= like we have to.

I followed the discussions about SSD dr= ives when they were first becoming mainstream; at that time, the Intel devic= es were king. Can anyone recommend what's a good SSD configuration these day= s? I don't think we want to buy a new server with spinning disks.
=
We're replacing:
  8 core (Intel)
  48GB memory
  12-drive 72= 00 RPM 500GB
     RAID1 (2 disks, OS and WAL log)
     RAID10 (8 disks, postgres data dir)
&= nbsp;    2 spares
  Ubuntu 16.04
&nbs= p; Postgres 9.6

The current system peaks at about 7= 000 TPS from pgbench.

Our system is a mix of non-tr= ansactional searching (customers) and transactional data loading (us).
=

Thanks!
Craig

= --
---------------------------------
Craig A. J= ames
Chief Technology Officer
eMolecules, Inc.
--= -------------------------------
= --Apple-Mail-B418783F-4E3D-4FB3-AE54-C2317EF6F229--