From mboxrd@z Thu Jan  1 00:00:00 1970
Message-ID: <31d2b19469a4d6da457fe426ec14417c@hamnavoe.com>
To: 9fans@9fans.net
From: Richard Miller <9fans@hamnavoe.com>
Date: Wed,  7 Mar 2012 15:27:31 +0000
In-Reply-To: <2579b9.4d6b93e5.B75p.mx@tumtum.plumbweb.net>
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
Subject: Re: [9fans] usb slowness
Topicbox-Message-UUID: 67774fd8-ead7-11e9-9d60-3106f5b1d025

> does anybody get less than 10 sec for
>
> dd -if /dev/sdU0.0/data -of /dev/null -count 1024 -bs 65536 ?
>
> or even less than 20 sec?

10.4 sec on a sheevaplug (with 1 microframe interrupt threshold).

By the way, everyone has been very tactful not to point out my
silly mistake in saying:

> ... You can use time(1) while
> reading usb disk to see if cpu is really the bottleneck, or if
> in fact your machine is spending most of its time waiting for
> a usb interrupt.

Of course most of the user+sys cpu time involved in reading from usb
disk will be charged to the usb/disk process (normally a subprocess of
usbd), not to user command doing the reading.