Skip site navigation (1) Skip section navigation (2)

Re: Inserting 8MB bytea: just 25% of disk perf used?

From: "Kevin Grittner" <Kevin(dot)Grittner(at)wicourts(dot)gov>
To: "fkater(at)googlemail(dot)com" <fkater(at)googlemail(dot)com>
Cc: <pgsql-performance(at)postgresql(dot)org>, "Scott Carey" <scott(at)richrelevance(dot)com>
Subject: Re: Inserting 8MB bytea: just 25% of disk perf used?
Date: 2010-01-19 15:13:51
Message-ID: 4B5577CF020000250002E746@gw.wicourts.gov (view raw or flat)
Thread:
Lists: pgsql-performance
"fkater(at)googlemail(dot)com" <fkater(at)googlemail(dot)com> wrote: 
> Scott Carey:
> 
>> You are CPU bound.
>> 
>> 30% of 4 cores is greater than 25%.  25% is one core fully
>> used.
> 
> I have measured the cores separately. Some of them reached
> 30%. I am not CPU bound here.
 
If you have numbers like that when running one big query, or a
stream of queries one-at-a-time, you are CPU bound.  A single
request only uses one CPU at a time although it could switch among a
number of them, if the OS doesn't make an effort to keep each
process with the same CPU.
 
-Kevin

In response to

pgsql-performance by date

Next:From: Tom LaneDate: 2010-01-19 15:25:46
Subject: Re: [HACKERS] Re: Faster CREATE DATABASE by delaying fsync (was 8.4.1 ubuntu karmic slow createdb)
Previous:From: Andres FreundDate: 2010-01-19 15:03:16
Subject: Re: [HACKERS] Re: Faster CREATE DATABASE by delaying fsync (was 8.4.1 ubuntu karmic slow createdb)

Privacy Policy | About PostgreSQL
Copyright © 1996-2014 The PostgreSQL Global Development Group