Date: Wed, 4 Mar 2009 19:10:57 +0100 From: Hans Petter Selasky <hselasky@c2i.net> To: Andrew Thompson <thompsa@freebsd.org> Cc: freebsd-usb@freebsd.org Subject: Re: Low perfomance when read from usb flash drive Message-ID: <200903041910.58446.hselasky@c2i.net> In-Reply-To: <20090304163343.GD17847@citylink.fud.org.nz> References: <200903032243.31914.hselasky@c2i.net> <200903041001.37376.hselasky@c2i.net> <20090304163343.GD17847@citylink.fud.org.nz>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wednesday 04 March 2009, Andrew Thompson wrote: > On Wed, Mar 04, 2009 at 10:01:36AM +0100, Hans Petter Selasky wrote: > > On Wednesday 04 March 2009, M. Warner Losh wrote: > > > In message: <200903040922.48163.hselasky@c2i.net> > > > > > > : > I am looking at using FreeBSD in an embedded product. I have not > > > : > examined your ehci software, but I am aware of how Linux and other > > > : > OSes run the controller. > > > : > > > > : > Why are you taking an interrupt every uFrame SOF? > > > : > > > : If the transaction completes before 125us we take the interrupt > > > : before 125us. The problem is that the interrupt delay becomes > > > : critical to performance when the interrupt rate is close to the > > > : interrupt limitation. > > > : > > > : For example: > > > : > > > : Transferring 13Mbyte/sec at blocksize equal to 65536 bytes generates > > > : 600 interrupts. Hence the Mass Storage state machine has three steps > > > : the throughput is computed like (600/3)*65536 bytes. If we on the > > > : average have to wait 0.5ms for an interrupt we loose throughput. > > > > > > Shouldn't you be using filters and such to make this less relevant? A > > > filter runs on the order of 5us after the interrupt on fast machines, > > > and 20us on slower (400MHz) ones. You can feed the pipeline better, > > > and handle higher interrupt rates... > > > > Yes, that's one possibility. It looks like there is some timing slightly > > out of sync. I have an AMD box with the same symptoms. I will try to > > figure out what is causing it. > > If you do change to filters then this is much easier with taskqueues as > it has a fast variant, otherwise you would need an intermediate step in > order to signal the existing usb threading scheme. The taskqueue > changeover will be happening soonish anyway. I am not going to do anything with filters. I'm going to try some other things. --HPS
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200903041910.58446.hselasky>