MIME-Version: 1.0
From: Kaixi Luo <kaixiluo@gmail.com>
Date: Tue, 05 Jul 2016 14:50:46 +0000
Message-ID: 
 <CAHo5iyjcQuVnmigtfv6RsQQ-Cw3CCWBjw65KADGeHhkNzT87fg@mail.gmail.com>
Subject: Tuning guidelines for server with 256GB of RAM and SSDs?
To: pgsql-performance@postgresql.org
Content-Type: multipart/alternative; boundary=001a114dccea8e0b110536e494e4
Precedence: bulk
Sender: pgsql-performance-owner@postgresql.org

--001a114dccea8e0b110536e494e4
Content-Type: text/plain; charset=UTF-8

Hello,

I've been reading Mr. Greg Smith's "Postgres 9.0 - High Performance" book
and I have some questions regarding the guidelines I found in the book,
because I suspect some of them can't be followed blindly to the letter on a
server with lots of RAM and SSDs.

Here are my server specs:

Intel Xeon E5-1650 v3 Hexa-Core Haswell
256GB DDR4 ECC RAM
Battery backed hardware RAID with 512MB of WriteBack cache (LSI MegaRAID
SAS 9260-4i)
RAID1 - 2x480GB Samsung SSD with power loss protection (will be used to
store the PostgreSQL database)
RAID1 - 2x240GB Crucial SSD with power loss protection. (will be used to
store PostgreSQL transactions logs)

First of all, the book suggests that I should enable the WriteBack cache of
the HWRAID and disable the disk cache to increase performance and ensure
data safety. Is it still advisable to do this on SSDs, specifically the
step of disabling the disk cache? Wouldn't that increase the wear rate of
the SSD?

Secondly, the book suggests that we increase the device readahead from 256
to 4096. As far as I understand, this was done in order to reduce the
number of seeks on a rotating hard drive, so again, is this still
applicable to SSDs?

The other tunable I've been looking into is vm.dirty_ratio and
vm.dirty_background_ratio. I reckon that the book's recommendation to lower
vm.dirty_background_ratio to 5 and vm.dirty_ratio to 10 is not enough for a
server with such big amount of RAM. How much lower should I set these
values, given that my RAID's WriteBack cache size is 512MB?

Thank you very much.

Kaixi Luo

--001a114dccea8e0b110536e494e4
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">Hello,<div><br></div><div>I&#39;ve been reading Mr. Greg S=
mith&#39;s &quot;Postgres 9.0 - High Performance&quot; book and I have some=
 questions regarding the guidelines I found in the book, because I suspect =
some of them can&#39;t be followed blindly to the letter on a server with l=
ots of RAM and SSDs.</div><div><br></div><div>Here are my server specs:</di=
v><div><br></div><div><div>Intel Xeon E5-1650 v3=C2=A0<span style=3D"line-h=
eight:1.5">Hexa-Core Haswell=C2=A0</span></div></div><div>256GB DDR4 ECC RA=
M</div><div>Battery backed hardware RAID with 512MB of WriteBack cache (LSI=
 MegaRAID SAS 9260-4i)</div><div>RAID1 - 2x480GB Samsung SSD with power los=
s protection (will be used to store the PostgreSQL database)</div><div>RAID=
1 - 2x240GB Crucial SSD with power loss protection. (will be used to store =
PostgreSQL transactions logs)</div><div><br></div><div>First of all, the bo=
ok suggests that I should enable the WriteBack cache of the HWRAID and disa=
ble the disk cache to increase performance and ensure data safety. Is it st=
ill advisable to do this on SSDs, specifically the step of disabling the di=
sk cache? Wouldn&#39;t that increase the wear rate of the SSD?</div><div><b=
r></div><div>Secondly, the book suggests that we increase the device readah=
ead from 256 to 4096. As far as I understand, this was done in order to red=
uce the number of seeks on a rotating hard drive, so again, is this still a=
pplicable to SSDs?</div><div><br></div><div>The other tunable I&#39;ve been=
 looking into is vm.dirty_ratio and vm.dirty_background_ratio. I reckon tha=
t the book&#39;s recommendation to lower vm.dirty_background_ratio to 5 and=
 vm.dirty_ratio to 10 is not enough for a server with such big amount of RA=
M. How much lower should I set these values, given that my RAID&#39;s Write=
Back cache size is 512MB?</div><div><br></div><div>Thank you very much.</di=
v><div><br></div><div>Kaixi Luo</div></div>

--001a114dccea8e0b110536e494e4--