Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 19 Oct 2004 14:58:38 -0400
From:      Kenneth Culver <culverk@sweetdreamsracing.biz>
To:        Emanuel Strobl <Emanuel.Strobl@gmx.net>
Cc:        freebsd-current@freebsd.org
Subject:   Re: FreeBSD 5.3b7and poor ata performance
Message-ID:  <20041019145838.g0c0kwk0wcss04ks@www.sweetdreamsracing.biz>
In-Reply-To: <200410192031.12504.Emanuel.Strobl@gmx.net>
References:  <20041015190638.C5A0E5D04@ptavv.es.net> <200410192031.12504.Emanuel.Strobl@gmx.net>

next in thread | previous in thread | raw e-mail | index | archive | help
Quoting Emanuel Strobl <Emanuel.Strobl@gmx.net>:

> Am Samstag, 16. Oktober 2004 19:44 schrieb fandino:
> [...]
>> > Also, make sure that disk write-cache is enabled on both or disabled on
>> > both.
>>
>> write-cache was enable on all tests and disks were in UDMA5 mode.
>>
>> In this new round of tests I add FreeBSD witch async and OpenBSD (always
>> using the same hardware). FreeBSD is by far, the worst throughput of all
>> (about 50% slower than others) :-?
>>
>> GNU/Linux 2.4.18 with ext2:               56848 K/sec
>> FreeBSD 5.3b7 with default fs:            26347 K/sec
>> FreeBSD 5.3b7 with default fs(async):     26566 K/sec
>> FreeBSD 5.3b7 ata raid0* (two disks):     26131 K/sec
>> FreeBSD 5.3b7 geom stripe* (two disks):   30063 K/sec
>> FreeBSD 5.3b7 geom stripe** (four disks): 31891 K/sec
>> OpenBSD 3.5 UFS fs:                       55277 K/sec
>>
>> * Each disk of the raid had a throughput of approx. 15000 K/sec
>> ** Each disk of the raid had a throughput of approx. 7500 K/sec
>> Each disk of the read split the throughput by half.
>>
>> How is possible that FreeBSD performs as bad?
>
> I have to confirm that I also have even worse transfer rates.
> It's a ICH2 (i815e) with a not so brand new 80GB WD, but I'd expext about
> 50MB/s and I get 16MB/s.
>
> One interesting thing is that the transferrate is constant with blocksizes
> from 256 Byte on. Only with a blocksize of 128 Bytes I can see reduced
> throughput (10MB/s).
> I can remember, when I last did such "esoteric" tests throughput reached
> maximum at about 16k blocksize and rapidly degraded with blocksizes smaller
> than 10k. But now only very very small blocksizes limit the throughput!
>
> Some excerpts: (i815 ich2, 5.3-RC1, custom kernel)
>
> cale:/usr#22: atacontrol mode 0
> Master = UDMA100
> Slave  = BIOSPIO
>
> ATA channel 0:
>     Master:  ad0 <WDC WD800AB-00CBA0/03.06A03> ATA/ATAPI revision 5
>
> atapci0: <Intel ICH2 UDMA100 controller> port
> 0xffa0-0xffaf,0x376,0x170-0x177,0x3f6,0x1f0-0x1f7 at device 31.1 on pci0
> ata0: channel #0 on atapci0
> ata1: channel #1 on atapci0
>
> cale:/usr#25: uname -a
> FreeBSD cale.flintsbach.schmalzbauer.de 5.3-STABLE FreeBSD 5.3-STABLE #4: Sun
> Oct 17 02:33:58 CEST 2004
> root@cale.flintsbach.schmalzbauer.de:/usr/obj/usr/src/sys/CALE  i386


your poor performance could be because you have a UDMA100 device on the same
channel as a BIOSPIO device. I'd try taking the BIOSPIO device off that 
channel
and see what happens.

Ken



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20041019145838.g0c0kwk0wcss04ks>