Re: Performance of packet writing: Blocksize matters

Gustavo Guillermo PĂ©rez <[email protected]> Tue, 12 Dec 2006 17:59:49 -0600
Newsgroups gmane.linux.suse.packet-writing
Organization www.compunauta.com
Message-ID <[email protected]>
El Martes, 12 de Diciembre de 2006 17:26, Johannes Niess escribi=F3:
> mbuffer does two things in this example. First it makes sure that pktcdvd
> always has data to write. Second is that it feeds this data in 4k chunks
> (reblocking).
>
> These results from the dd approach are consistant with my earlier testing:
>
> stingray ~ # dd if=3D/dev/zero of=3D/dev/hdc bs=3D32768 count=3D25000
> 25000+0 records in
> 25000+0 records out
> 819200000 bytes (819 MB) copied, 92.2253 seconds, 8.9 MB/s
>
> stingray ~ # dd if=3D/dev/zero of=3D/dev/hdc bs=3D32769 count=3D25000
> 2643+0 records in
> 2643+0 records out
> 86608467 bytes (87 MB) copied, 223.764 seconds, 387 kB/s
>
> stingray ~ # pktsetup dvdrw /dev/hdc
> stingray ~ # dd if=3D/dev/zero of=3D/dev/pktcdvd/dvdrw bs=3D32768 count=
=3D25000
> 25000+0 records in
> 25000+0 records out
> 819200000 bytes (819 MB) copied, 86.3305 seconds, 9.5 MB/s
>
> stingray ~ # dd if=3D/dev/zero of=3D/dev/pktcdvd/dvdrw bs=3D32769 count=
=3D25000
> 25000+0 records in
> 25000+0 records out
> 819225000 bytes (819 MB) copied, 1312.45 seconds, 624 kB/s
>
> Basically this tells me that pktcdvd does no or inefficient merging of
> incoming data (at least in my case). Or pktcdvd is slowed down for a
> different (internal) reason.
>
> For the slow performance cases I see a initial peak of good write speed
This is ovious buffer
> followed by "noisy" and slow write speeds.
When buffer starts to being written onto disc and you need to still readig=
=20
folders or compare files, or even write too small files you'll got low=20
performance as well.
> What other data do you need to=20
> diagnose this strange problem?
>
> Thank you very much fot your help!
>
> Johannes Nie=DF

=2D-=20
Gustavo Guillermo P=E9rez
Compunauta uLinux
www.compunauta.com