RE: v7.1b4 bad performance

Поиск
Список
Период
Сортировка
От Schmidt, Peter
Тема RE: v7.1b4 bad performance
Дата
Msg-id F1DC8388AD52D411B83B00D0B774D6EB1928DF@winmail.prismedia.com
обсуждение исходный текст
Ответ на v7.1b4 bad performance  ("Schmidt, Peter" <peter.schmidt@prismedia.com>)
Ответы Re: v7.1b4 bad performance  (Bruce Momjian <pgman@candle.pha.pa.us>)
Re: v7.1b4 bad performance  (Tom Lane <tgl@sss.pgh.pa.us>)
Список pgsql-admin


> -----Original Message-----
> From: Bruce Momjian [mailto:pgman@candle.pha.pa.us]
> Sent: Friday, February 16, 2001 10:59 AM
> To: Schmidt, Peter
> Cc: 'Tom Lane'; 'Michael Ansley'; 'pgsql-admin@postgresql.org'
> Subject: Re: [ADMIN] v7.1b4 bad performance
>
>
> > > "Schmidt, Peter" <peter.schmidt@prismedia.com> writes:
> > > > However, what I'm interested in is the comparison between
> > > 7.0x and 7.1x.
> > > > Shouldn't the 7.1b4 database be faster? Have you (or anyone
> > > else) done this
> > > > comparison?
> > >
> > > 7.1 is considerably faster if you compare performance without -F.
> > > If you are comparing performance with -F, I'm not sure
> exactly how it
> > > stacks up.
> > >
> > >                   regards, tom lane
> > >
> >
> > Here are some of the results of my tests which are very
> consistent.  I
> > dropped and recreated postgres db before each test so the
> only user tables
> > were the pgbench tables.
> >
> > 7.1b4(no -F)        49 tps
> > 7.03 (no -F)        64 tps
> > 7.03 (with -F)      121 tps
> >
> > The test machine is a Dell Dimension 800mz w/128 RAM and it
> is dedicated to
> > this testing. Pgbench is run on the same machine. Any ideas
> why my results
> > differ? I will continue testing and appreciate all comments.
> > Peter
>
> This is very strange.  Is there any specific query that is causing the
> problem?  Does EXPLAIN show the same output on both versions?
>

"pgbench" doesn't execute any complex sql...

Explain shows exactly the same output for both versions(7.03 & 7.1b4):

update accounts set abalance = abalance + 1 where aid = 1
Index Scan using accounts_pkey on accounts  (cost=0.00..3.81 rows=1 width=30)

select abalance from accounts where aid = 1
Index Scan using accounts_pkey on accounts  (cost=0.00..3.81 rows=1 width=4)

update tellers set tbalance = tbalance + 1 where tid = 1
Seq Scan on tellers  (cost=0.00..1.12 rows=1 width=30)

update branches set bbalance = bbalance + 1 where bid = 1
Seq Scan on branches  (cost=0.00..1.01 rows=1 width=26)

insert into history(tid,bid,aid,delta,time) values(1,1,1,1,'now')
Result  (cost=0.00..0.00 rows=0 width=0)

Peter
 

В списке pgsql-admin по дате отправления:

Предыдущее
От: Jie Liang
Дата:
Сообщение: Re: Re: [GENERAL] what means "INSERT xxx yyy" ?
Следующее
От: Bruce Momjian
Дата:
Сообщение: Re: v7.1b4 bad performance