pg.ddx.io pgsql-admin@postgresql.org mailing list archive help / color / mirror / Atom feed From: Scott Marlowe <scott.marlowe@gmail.com>
To: c k <shreeseva.learning@gmail.com>
Cc: pgsql-admin@postgresql.org
Subject: Re: Multi-processors
Date: Fri, 19 Sep 2008 08:29:32 -0600
Message-ID: <dcc563d10809190729g1cd2679bo79a0d40980cdb293@mail.gmail.com> (raw )
In-Reply-To: <d8e7a1e30809190455p15b9b83fw4ed297ca2d4d102c@mail.gmail.com >
References: <d8e7a1e30809190455p15b9b83fw4ed297ca2d4d102c@mail.gmail.com >
On Fri, Sep 19, 2008 at 5:55 AM, c k <shreeseva.learning@gmail.com> wrote:
> Hello PG Community,
> Does PG uses multiple processors/cores if available by default on various
> OSes?
Yes, see attached top extract from my primary db server at work
> What are the limitations on using multiple processors/cores and main
> memory?
Do you mean how many CPUs and how much memory? no real limits on a 64
bit machine. Note that it's often better to let the os do the majority
of caching, depending on your work load. This is especially true in
OLTP where the cost of pgsql maintaining a large buffer is higher than
the benefit it provides, but the kernel can cache much larger datasets
faster, in my experience.
Attachments:
db-top.txt (text/plain, 3.2K) download
top - 08:27:03 up 38 days, 19:10, 1 user, load average: 3.67, 4.26, 4.39
Tasks: 316 total, 8 running, 308 sleeping, 0 stopped, 0 zombie
Cpu0 : 10.4%us, 0.9%sy, 0.0%ni, 88.7%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu1 : 21.6%us, 5.2%sy, 0.0%ni, 73.3%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu2 : 4.3%us, 1.7%sy, 0.0%ni, 93.1%id, 0.0%wa, 0.0%hi, 0.9%si, 0.0%st
Cpu3 : 14.8%us, 0.9%sy, 0.0%ni, 83.5%id, 0.0%wa, 0.0%hi, 0.9%si, 0.0%st
Cpu4 : 51.3%us, 2.6%sy, 0.0%ni, 46.1%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu5 : 47.8%us, 2.6%sy, 0.0%ni, 48.7%id, 0.0%wa, 0.0%hi, 0.9%si, 0.0%st
Cpu6 : 57.4%us, 2.6%sy, 0.0%ni, 40.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu7 : 62.6%us, 4.3%sy, 0.0%ni, 26.1%id, 0.0%wa, 0.9%hi, 6.1%si, 0.0%st
Mem: 33031252k total, 30858572k used, 2172680k free, 521644k buffers
Swap: 9767480k total, 8032k used, 9759448k free, 27457352k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
13827 postgres 16 0 8353m 112m 103m R 37 0.3 0:01.37 postgres: webguy www 10.0.0.59(43081) SELECT
11115 postgres 15 0 8363m 2.0g 2.0g R 32 6.3 7:44.41 postgres: webguy www 10.0.0.58(42066) SELECT
13651 postgres 15 0 8358m 426m 416m S 25 1.3 0:04.70 postgres: webguy www 10.0.0.52(59220) idle
13746 postgres 15 0 8360m 396m 384m S 20 1.2 0:03.44 postgres: webguy www 10.0.0.58(53244) idle
13775 postgres 15 0 8357m 403m 394m S 20 1.3 0:03.25 postgres: webguy www 10.0.0.59(38550) idle
13840 postgres 15 0 8355m 138m 130m S 16 0.4 0:01.81 postgres: webguy www 10.0.0.58(60554) idle
13813 postgres 16 0 8357m 372m 362m R 13 1.2 0:02.44 postgres: webguy www 10.0.0.59(41723) SELECT
13893 postgres 15 0 8349m 28m 25m S 10 0.1 0:00.14 postgres: webguy www 10.0.0.52(47776) idle
13598 postgres 15 0 8360m 566m 553m S 9 1.8 0:12.42 postgres: webguy www 10.0.0.59(55696) idle
13854 postgres 15 0 8355m 92m 84m S 9 0.3 0:00.90 postgres: webguy www 10.0.0.59(44909) idle
13718 postgres 15 0 8358m 437m 426m S 8 1.4 0:08.55 postgres: webguy www 10.0.0.59(34177) idle
13794 postgres 15 0 8354m 32m 27m S 8 0.1 0:00.26 postgres: webguy www 10.0.0.153(36273) idle
13820 postgres 15 0 8358m 194m 184m S 8 0.6 0:02.03 postgres: webguy www 10.0.0.58(58962) idle
13791 postgres 15 0 8359m 258m 246m S 7 0.8 0:04.30 postgres: webguy www 10.0.0.59(40007) idle
13439 postgres 15 0 8358m 604m 594m S 6 1.9 0:10.06 postgres: webguy www 10.0.0.58(33212) idle
13570 postgres 16 0 8359m 322m 311m S 6 1.0 0:09.51 postgres: webguy www 10.0.0.58(41747) idle
13736 postgres 15 0 8359m 300m 289m S 6 0.9 0:04.50 postgres: webguy www 10.0.0.59(36212) idle
13809 postgres 15 0 8351m 229m 219m R 5 0.7 0:02.05 postgres: webguy www 10.0.0.58(57974) SELECT
view thread (3+ messages)
Message-ID: <dcc563d10809190729g1cd2679bo79a0d40980cdb293@mail.gmail.com>
Permalink: ../dcc563d10809190729g1cd2679bo79a0d40980cdb293@mail.gmail.com/
Also on: postgresql.org/message-id/dcc563d10809190729g1cd2679bo79a0d40980cdb293@mail.gmail.com
copy link · copy postgr.es
reply 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-admin@postgresql.org
Cc: scott.marlowe@gmail.com, shreeseva.learning@gmail.com
Subject: Re: Multi-processors
In-Reply-To: <dcc563d10809190729g1cd2679bo79a0d40980cdb293@mail.gmail.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