In-Reply-To: <462F1734.3080705@enterprisedb.com>
References: <462EFA63.1030306@inea.com.pl> <462F1734.3080705@enterprisedb.com>
Mime-Version: 1.0 (Apple Message framework v752.3)
Content-Type: text/plain; charset=UTF-8; delsp=yes; format=flowed
Message-Id: <9AC3F7AB-0A59-4559-88A2-141BDD76D8AF@fastcrypt.com>
Cc: =?UTF-8?Q?Pawe=C5=82_Gruszczy=C5=84ski?= <pawel.gruszczynski@inea.com.pl>,
	pgsql-performance@postgresql.org
Content-Transfer-Encoding: quoted-printable
From: Dave Cramer <pg@fastcrypt.com>
Subject: Re: What`s wrong with JFS configuration?
Date: Wed, 25 Apr 2007 07:21:30 -0400
To: Heikki Linnakangas <heikki@enterprisedb.com>


On 25-Apr-07, at 4:54 AM, Heikki Linnakangas wrote:

> Pawe=C5=82 Gruszczy=C5=84ski wrote:
>> To test I use pgBench with default database schema, run for 25, =20
>> 50, 75 users at one time. Every test I run 5 time to take average.
>> Unfortunetly my result shows that ext is fastest, ext3 and jfs are =20=

>> very simillar. I can understand that ext2 without jurnaling is =20
>> faster than ext3, it is said that jfs is 40 - 60% faster. I cant =20
>> see the difference. Part of My results: (transaction type | =20
>> scaling factor | num of clients | tpl | num on transactions | tps =20
>> including connection time | tps excliding connection time)
>> EXT2:
>> TPC-B (sort of),50,75,13,975|975,338.286682,358.855582
>> ...
>> Can anyone tell me what`s wrong with my test? Or maybe it is normal?
>
> With a scaling factor of 50, your database size is ~ 1 GB, which =20
> fits comfortably in your RAM. You're not exercising your drives or =20
> filesystem much. Assuming you haven't disabled fsync, the =20
> performance of that test is bound by the speed your drives can =20
> flush WAL commit records to disk.
>
> I wouldn't expect the filesystem to make a big difference anyway, =20
> but you'll see..

If you really believe that jfs is 40 -60% faster ( which I highly =20
doubt ) you should see this by simply reading/writing a very large =20
file (2x your memory size) with dd .

Just curious but what data do you have that suggests this 40-60% =20
number ?

Dave
>
> --=20
>   Heikki Linnakangas
>   EnterpriseDB   http://www.enterprisedb.com
>
> ---------------------------(end of =20
> broadcast)---------------------------
> TIP 7: You can help support the PostgreSQL project by donating at
>
>                http://www.postgresql.org/about/donate