Received: from malur.postgresql.org ([2a02:16a8:dc51::56]) by arkaria.postgresql.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA384:256) (Exim 4.89) (envelope-from ) id 1fH69b-0005B1-6Y for pgsql-performance@arkaria.postgresql.org; Fri, 11 May 2018 11:24:03 +0000 Received: from localhost ([127.0.0.1] helo=malur.postgresql.org) by malur.postgresql.org with esmtp (Exim 4.89) (envelope-from ) id 1fH69V-0006ps-Md for pgsql-performance@arkaria.postgresql.org; Fri, 11 May 2018 11:23:57 +0000 Received: from magus.postgresql.org ([2a02:c0:301:0:ffff::29]) by malur.postgresql.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA384:256) (Exim 4.89) (envelope-from ) id 1fH69V-0006pj-9E for pgsql-performance@lists.postgresql.org; Fri, 11 May 2018 11:23:57 +0000 Received: from post.visena.com ([46.226.10.50]) by magus.postgresql.org with esmtps (TLS1.2:DHE_RSA_AES_256_CBC_SHA1:256) (Exim 4.89) (envelope-from ) id 1fH69Q-0007J7-KN for pgsql-performance@lists.postgresql.org; Fri, 11 May 2018 11:23:56 +0000 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=visena.com; s=20141101.wh; h=Content-Type:MIME-Version:Subject:In-Reply-To:Message-ID:To:From:Date; bh=2j44+6kjLiEO3SEErpk3U0b6nOiJVFK2SxuGONZZs80=; b=pYLEFIXbyY6gQdmcko81iQmvP8PbSGMopBmuF9e9mhWuwNQK0WVvvzhPtAVcNXRb0UoRbKOxcqEKpeI9u7NSbTtZJ4zDNHfZIe0LHD2OdWxgPjZmZbg2SrJj78dz35paKITF2BhCmmAVwg+sSymHO00Wn0kfL5j6lsjX5KYQlco=; Received: from [10.0.1.10] (helo=tc7-visena.wh.internal.visena.com) by post.visena.com with esmtp (Exim 4.82) (envelope-from ) id 1fH69M-0002jg-Q7 for pgsql-performance@lists.postgresql.org; Fri, 11 May 2018 13:23:50 +0200 Received: from localhost ([127.0.0.1] helo=tc7-visena.wh.internal.visena.com) by tc7-visena.wh.internal.visena.com with esmtp (Exim 4.86_2) (envelope-from ) id 1fH69S-0006yZ-NH for pgsql-performance@lists.postgresql.org; Fri, 11 May 2018 13:23:54 +0200 Date: Fri, 11 May 2018 13:23:54 +0200 (CEST) From: Andreas Joseph Krogh To: pgsql-performance@lists.postgresql.org Message-ID: In-Reply-To: Subject: Sv: Sv: Re: Latest advice on SSD? MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="----=_Part_240_901208163.1526037834553" X-Mailer: Visena Mail 2.1.52 X-Spam-Score: -1.0 X-Spam-Report: SpamAssasin (score=-1.0, required 5.0 ALL_TRUSTED=-1,HTML_MESSAGE=0.001) List-Id: List-Help: List-Subscribe: List-Post: List-Owner: List-Archive: Precedence: bulk ------=_Part_240_901208163.1526037834553 Content-Type: multipart/related; boundary="----=_Part_241_496187313.1526037834553" ------=_Part_241_496187313.1526037834553 Content-Type: multipart/alternative; boundary="----=_Part_242_517556938.1526037834574" ------=_Part_242_517556938.1526037834574 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable P=C3=A5 onsdag 09. mai 2018 kl. 22:00:16, skrev Andreas Joseph Krogh < andreas@visena.com >: P=C3=A5 tirsdag 10. april 2018 kl. 19:41:59, skrev Craig James < cjames@emolecules.com >: =C2=A0 =C2=A0 On Tue, Apr 10, 2018 at 12:21 AM, Andreas Joseph Krogh > wrote: P=C3=A5 tirsdag 10. april 2018 kl. 04:3= 6:27,=20 skrev Craig James >: One of our four "big iron" (spinning disks) servers went belly up today.=20 (Thanks, Postgres and pgbackrest! Easy recovery.) We're planning to move to= a=20 cloud service at the end of the year, so bad timing on this. We didn't want= to=20 buy any more hardware, but now it looks like we have to.=C2=A0 I followed the discussions about SSD drives when they were first becoming= =20 mainstream; at that time, the Intel devices were king. Can anyone recommend= =20 what's a good SSD configuration these days? I don't think we want to buy a = new=20 server with spinning disks. =C2=A0 We're replacing: =C2=A0 8 core (Intel) =C2=A0 48GB memory =C2=A0 12-drive 7200 RPM 500GB =C2=A0 =C2=A0 =C2=A0RAID1 (2 disks, OS and WAL log) =C2=A0 =C2=A0 =C2=A0RAID10 (8 disks, postgres data dir) =C2=A0 =C2=A0 =C2=A02 spares =C2=A0 Ubuntu 16.04 =C2=A0 Postgres 9.6 =C2=A0 The current system peaks at about 7000 TPS from pgbench. =C2=A0 With what arguments (also initialization)? =C2=A0 =C2=A0 pgbench -i -s 100 -U test pgbench -U test -c ... -t ... =C2=A0 -c=C2=A0 -t=C2=A0 =C2=A0 =C2=A0TPS 5=C2=A0 =C2=A020000=C2=A0 5202 10=C2=A0 10000=C2=A0 7916 20=C2=A0 5000=C2=A0 =C2=A07924 30=C2=A0 3333=C2=A0 =C2=A07270 40=C2=A0 2500=C2=A0 =C2=A05020 50=C2=A0 2000=C2=A0 =C2=A06417 =C2=A0 FWIW; We're testing=20 this:=C2=A0https://www.supermicro.nl/products/system/1U/1029/SYS-1029U-TN10= RT.cfm with=C2=A04 x Micron NVMe 9200 PRO NVMe 3.84TB U.2 in RAID-10: =C2=A0 $ pgbench -s 100 -c 64 -t 10000 pgbench scale option ignored, using count from pgbench_branches table (100) starting vacuum...end. transaction type: scaling factor: 100 query mode: simple number of clients: 64 number of threads: 1 number of transactions per client: 10000 number of transactions actually processed: 640000/640000 latency average =3D 2.867 ms tps =3D 22320.942063 (including connections establishing) tps =3D 22326.370955 (excluding connections establishing) =C2=A0 Sorry, wrong disks; this is correct: =C2=A0 48 clients: pgbench -s 100 -c 48 -t 10000 pgbench=C2=A0 scale option ignored, using count from pgbench_branches table (100) starting vacuum...end. transaction type: scaling factor: 100 query mode: simple number of clients: 48 number of threads: 1 number of transactions per client: 10000 number of transactions actually processed: 480000/480000 latency average =3D 1.608 ms tps =3D 29846.511054 (including connections establishing) tps =3D 29859.483666 (excluding connections establishing) =C2=A0 =C2=A0 64=C2=A0clients: pgbench -s 100 -c 64 -t 10000 pgbench=C2=A0 scale option ignored, using count from pgbench_branches table (100) starting vacuum...end. transaction type: scaling factor: 100 query mode: simple number of clients: 64 number of threads: 1 number of transactions per client: 10000 number of transactions actually processed: 640000/640000 latency average =3D 2.279 ms tps =3D 28077.261708 (including connections establishing) tps =3D 28085.730160 (excluding connections establishing) =C2=A0 -- Andreas Joseph Krogh CTO / Partner - Visena AS Mobile: +47 909 56 963 andreas@visena.com www.visena.com =C2=A0 ------=_Part_242_517556938.1526037834574 Content-Type: text/html;charset=UTF-8 Content-Transfer-Encoding: quoted-printable
P=C3=A5 onsdag 09. mai 2018 kl. 22:00:16, skrev Andreas Joseph Krogh &= lt;andreas@visena.com>:
P=C3=A5 tirsdag 10. april 2018 kl. 19:41:59, skrev Craig James <cjames@emolecules.com>:
=C2=A0
=C2=A0
On Tue, Apr 10, 2018 at 12:21 AM, Andreas Joseph= Krogh <andreas@visena.com> wrote:
P=C3=A5 tirsdag 10. april 2018 kl. 04:36:27, skrev Craig James <cjames@emolecules.c= om>:
One of our four "big iron" (spinning disks) serv= ers 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 ti= ming on this. We didn't want to buy any more hardware, but now it looks lik= e we have to.
=C2=A0
I followed the discussions about SSD drives when they were first becom= ing mainstream; at that time, the Intel devices were king. Can anyone recom= mend what's a good SSD configuration these days? I don't think we want to b= uy a new server with spinning disks.
=C2=A0
We're replacing:
=C2=A0 8 core (Intel)
=C2=A0 48GB memory
=C2=A0 12-drive 7200 RPM 500GB
=C2=A0 =C2=A0 =C2=A0RAID1 (2 disks, OS and WAL log)
=C2=A0 =C2=A0 =C2=A0RAID10 (8 disks, postgres data dir)
=C2=A0 =C2=A0 =C2=A02 spares
=C2=A0 Ubuntu 16.04
=C2=A0 Postgres 9.6
=C2=A0
The current system peaks at about 7000 TPS from pgbench.
=C2=A0
With what arguments (also initialization)?
=C2=A0
=C2=A0
pgbench -i -s 100 -U test
pgbench -U test -c ... -t ...
=C2=A0
-c=C2=A0 -t=C2=A0 =C2=A0 =C2=A0TPS=
5=C2=A0 =C2=A020000=C2=A0 5202
10=C2=A0 10000=C2=A0 7916
20=C2=A0 5000=C2=A0 =C2=A07924
30=C2=A0 3333=C2=A0 =C2=A07270
40=C2=A0 2500=C2=A0 =C2=A05020
50=C2=A0 2000=C2=A0 =C2=A06417
=C2=A0
FWIW; We're testing this:=C2=A0https://www.supermicro.nl/products/syst= em/1U/1029/SYS-1029U-TN10RT.cfm
with=C2=A04 x Micron NVMe 9200 PRO NVMe 3.84TB U.2 in RAID-10:
=C2=A0
$ pgbench -s 100 -c 64 -t 10000 pgbench
scale option ignored, using count from pgbench_branches table (100)
starting vacuum...end.
transaction type: <builtin: TPC-B (sort of)>
scaling factor: 100
query mode: simple
number of clients: 64
number of threads: 1
number of transactions per client: 10000
number of transactions actually processed: 640000/640000
latency average =3D 2.867 ms
tps =3D 22320.942063 (including connections establishing)
tps =3D 22326.370955 (excluding connections establishing)
=C2=A0
Sorry, wrong disks; this is correct:
=C2=A0
48 clients:
pgbench -s 100 -c 48 -t 10000 pgbench=C2=A0
scale option ignored, using count from pgbench_branches table (100)
starting vacuum...end.
transaction type: <builtin: TPC-B (sort of)>
scaling factor: 100
query mode: simple
number of clients: 48
number of threads: 1
number of transactions per client: 10000
number of transactions actually processed: 480000/480000
latency average =3D 1.608 ms
tps =3D 29846.511054 (including connections establishing)
tps =3D 29859.483666 (excluding connections establishing)

=C2=A0
=C2=A0
64=C2=A0clients:
pgbench -s 100 -c 64 -t 10000 pgbench=C2=A0
scale option ignored, using count from pgbench_branches table (100)
starting vacuum...end.
transaction type: <builtin: TPC-B (sort of)>
scaling factor: 100
query mode: simple
number of clients: 64
number of threads: 1
number of transactions per client: 10000
number of transactions actually processed: 640000/640000
latency average =3D 2.279 ms
tps =3D 28077.261708 (including connections establishing)
tps =3D 28085.730160 (excluding connections establishing)
=C2=A0
">
--
Andrea= s Joseph Krogh
CTO / Partner<= /span> - Visena AS
Mobile: +47 90= 9 56 963
=3D""
=C2=A0
------=_Part_242_517556938.1526037834574-- ------=_Part_241_496187313.1526037834553 Content-Type: image/png Content-Transfer-Encoding: base64 Content-Disposition: inline Content-ID: iVBORw0KGgoAAAANSUhEUgAAAIUAAAAYCAYAAADUIj6hAAAABHNCSVQICAgIfAhkiAAABzBJREFU aEPtmNFxHDcMhmVP3i1VECpvnjzkVIHWFfhcgVcVRKrAUgWRK/C6Al8H3lTgy0PGbzFdQc4VJP/H ADs43q6kROeJNbOYgQACIAgCWJKng4MZ5gxUGXh0U0b+SIuF9G+EWXj2Q15vbrE/NPtk9uub7Gfd t5mBx1NhqSEo8HshjbEUtlO2yIM9tsx5dZP9rPt2MzDZFAqZE4LGcFjdsg3saQaHt7fY70X949On aS+OZidDBkavD33157L4xaw2os+Mp/DAC10l2XhOCeStj0W5ajrJL8WfCi80Xgf9vVlrhg9yRONe /f7xI2vNsIcM7JwU9o6oGyJrLT8JOA1aX9sKP4wl94bAniukEbo/n7YPmuTETzIab4Y9ZWCrKexd 8M58lxPCvvD6aihfvexbEQoPYO8NQRO0JnddGO6FJYaVsBde7cXj7KRk4LsqDxQzCYeGsJNgaXZe +JXkyGgWINq3Gp+bHNILz+wEYs5qH1eJrouNrpDXtk4O6x1IvtD40GWyJYYdkF0jIbYZlN16xygI gl9smbMDsmFdfAKb23xGB8H/mv3tOJfArs1kukk79DEPdQ5u0g1vCvvqKXIW8mZYW+F3Tg4r8HvZ kQCCLydK8EFMQCe5N8RgL9mRG0SqQFuNvdE6beSs0qPDBuCdg0+gvClso8SbTO4ki7mQzQqBrcMH QPwReg2wW8umEe/+L8T/LEzBGF9nXjzZ46s+ITHvhegW8LL39xm6App7KYL/GE+vcYnFbJiP/0aY hdiCnRC7jaj7eiK2ETInC5PRF6LYkSN0+HabF75WuT6syCyI0YkVGGMvUC33AmfZTDUEj8u6IVhu EhRUJ2U2g6UlugyNb03Hl9obHwlxJbcRzcYjO4QPjVfGFTQav4vrmp7cpMp2qbHnBxWJbisbho2Q XI6C1sIHDUFhH4Hij4UbIev66eANeiwbkA+LBsO36zAHzoXU7AhbqLAXEiOYTXcSdO8VS9L4wN8U BIYhBd6oSUgYMijOkecRuTdQa/YiBXhbXFcnCnI2SrfeBG9NydrLYMhGHa5qB9pQIxlzAE6Okjzx JO5afGe6kmhBicWKQNKuTZ5EW+MjQY8v/9rQ0bhJSJyNGUe/JH1t8h1iMbdSPAvxHYin6YmN9YBX QmTYZZNh14vHhhhal5vtcIrJjmvszPRJdExH3MWHvykoBEc9CoCGWJisOLOGoCORs1FvIMbYA8z3 kwM59oemy6LlWrLxFLmWgiQAfEGd8S+NssbK+EhyGLxUkhhiy717waBqHOJYSEacwBejkFNhjJNj v/gANOdQxPfciP/JVBCK2cOIcg3RRJ+CPrLPNVhhN6F38VKMF3XLlIJrjU5C8gMFxvKDvOcPc4rV NjCn7KM0BV+161V8viSCuJZ8SITGJGEh7IUUlxOFMYUH1kJOCN4Wh+I5pqCuK01k40kSNtnKiKIl UfxAgW5sU5JlS05rtt5YFJF1SWoqHv6BRgQcA4/bdb9WRjmMk3jyUMAbIoyJq9e4cVmgzKt9j5gN J/aYDhk+hhjExwaPcz5PObA5Zd9bvz5UzCTZuZDidu5AchpiKSwPR+TV1bCWqBQ9nCjJ5neivC82 Nr4LeS2j1gw5LUqwBuhGQQU5UwHeSslXkwIynz2U2A2yKDgG7OffwLA3TpGRpk0Tzpj3ZEJXi/GR a6GN0e0NtppChePdcAz1FTS+FN8Kpxoiykk+J8fC5tenjbu9kSqpHLu9jBrhUuhNwVGbpyZrzrl0 HPVD8SXj5EOOD/eDC64VjvYBZLuUbIVAfBN1t/C/SU+cAGtdGo+fVnzycUX5wmn6eCKPmWYJG2E/ ppTsuRCbvUD9fwquksG5GqLVKhzDQ3GrEyLKSXhsiK3T5j9EyxffCFOYi2wUlPyFFDQAhehESDjQ GoX0ho0oj8RPou6TxHJdcT0NTcWkO0AnG7+uXsnHqcas/72wvWF+mSf7N/Watp9kTXoluzeS0fB9 9CcZ/hvhSZTfh99pispZOXL9KrGrARkNUMu9ITbScZWs7xOYNt9pwxSZtYDsX/GE3xTkrXgwAsXm fud08FiTeC+m2/o7ppo+PTS/NBK5ARpDG5YHr++DpmVfreYdiX8mnp+DzPEG9WbqJON0JBenZofs sxBA1gj5NXGvfJu/Qh7HwQh/VDUEyUxCit5hH94QfKkEdu+GwK8BX0hvCF+D67xhjmXQCXMwJCZ+ olK0A1EKRCE4snsh42w8Mv/Zhxw9iD7Cjo7CyQC/KyF6oBfShL4PYgG+CHsYKyZxvxZSZBAgjhIz YDz+AbfD37GtbaoSKzgGt+lKfI/GZtay6vG4VXTpPsh+IcQhOk9I7WYeP5AM3HZ9+DaSGIp9HIuu huC4pCGGx+YD2fcc5tfIAA0h/Et4/jX8zz4fWAasIf4UbR9Y6HO4d8jAnd4U0Y8ageuCB+c+H5R3 CHU2mTMwZ+B/y8DfSMBLLOYXVuEAAAAASUVORK5CYII= ------=_Part_241_496187313.1526037834553-- ------=_Part_240_901208163.1526037834553--