Re: musb throughput issues

2013-05-13 Thread Ming Lei
On Mon, May 13, 2013 at 9:00 PM, Frederik Schmid wrote: > On Monday 13 May 2013 20.46.40 Ming Lei wrote: >> On Mon, May 13, 2013 at 12:58 PM, Frederik Schmid >> >> wrote: >> > Ming, >> > >> > The ehci controller is bogged down because the frames from the camera and >> > other stuff are being rela

Re: musb throughput issues

2013-05-13 Thread Frederik Schmid
On Monday 13 May 2013 20.46.40 Ming Lei wrote: > On Mon, May 13, 2013 at 12:58 PM, Frederik Schmid > > wrote: > > Ming, > > > > The ehci controller is bogged down because the frames from the camera and > > other stuff are being relayed over ethernet. > > If you mean usb camera and usb ethernet

Re: musb throughput issues

2013-05-13 Thread Ruslan Bilovol
Hi Frederik, On Fri, May 10, 2013 at 2:22 PM, Frederik Schmid wrote: > Hi Ruslan, > > Thanks for the tips! A few comments below: > > On Friday 10 May 2013 13.54.53 Ruslan Bilovol wrote: >> Hello Frederic, >> >> On Fri, May 10, 2013 at 12:54 PM, Frederik Schmid >> >> wrote: >> > Well, my conclusi

Re: musb throughput issues

2013-05-13 Thread Frederik Schmid
On Monday 13 May 2013 05.44.22 Greg KH wrote: > On Mon, May 13, 2013 at 02:23:55PM +0200, Frederik Schmid wrote: > > On Monday 13 May 2013 05.01.01 Greg KH wrote: > > > Why do the two have any relation to each other, with the exception of > > > possible CPU usage? Are they sharing an interrupt and

Re: musb throughput issues

2013-05-13 Thread Ming Lei
On Mon, May 13, 2013 at 12:58 PM, Frederik Schmid wrote: > Ming, > > The ehci controller is bogged down because the frames from the camera and > other stuff are being relayed over ethernet. If you mean usb camera and usb ethernet need to be used at the same time, it might be a problem, suppose yo

Re: musb throughput issues

2013-05-13 Thread Greg KH
On Mon, May 13, 2013 at 02:23:55PM +0200, Frederik Schmid wrote: > On Monday 13 May 2013 05.01.01 Greg KH wrote: > > Why do the two have any relation to each other, with the exception of > > possible CPU usage? Are they sharing an interrupt and that is somehow a > > problem? > > They don't have a

Re: musb throughput issues

2013-05-13 Thread Frederik Schmid
On Monday 13 May 2013 05.01.01 Greg KH wrote: > Why do the two have any relation to each other, with the exception of > possible CPU usage? Are they sharing an interrupt and that is somehow a > problem? They don't have any relation. The reason why we're trying to use the musb controller is so th

Re: musb throughput issues

2013-05-13 Thread Greg KH
On Mon, May 13, 2013 at 06:58:37AM +0200, Frederik Schmid wrote: > Ming, > > The ehci controller is bogged down because the frames from the camera and > other stuff are being relayed over ethernet. Why do the two have any relation to each other, with the exception of possible CPU usage? Are the

Re: musb throughput issues

2013-05-12 Thread Frederik Schmid
Ming, The ehci controller is bogged down because the frames from the camera and other stuff are being relayed over ethernet. /Frederik On Friday 10 May 2013 23.24.32 Ming Lei wrote: > > Why do you think it's bogged down with ethernet? The ethernet throughput > can go beyond 90Mbps on Pandaboa

Re: musb throughput issues

2013-05-10 Thread Ming Lei
On Fri, May 10, 2013 at 1:26 PM, Frederik Schmid wrote: > Hi Greg, > > The kernel is based on 3.4.11 from omapzoom.org (ti-ubuntu-3.4-1487) with > Variscite BSP patches from: > > http://www.variwiki.com/index.php?title=VAR-SOM-OM44_-_Ubuntu_Precise > > I was expecting 200-250Mbps which is entirly

Re: musb throughput issues

2013-05-10 Thread Greg KH
On Fri, May 10, 2013 at 07:26:35AM +0200, Frederik Schmid wrote: > Hi Greg, > > The kernel is based on 3.4.11 from omapzoom.org (ti-ubuntu-3.4-1487) with > Variscite BSP patches from: > > http://www.variwiki.com/index.php?title=VAR-SOM-OM44_-_Ubuntu_Precise Then I would ask for support from the

Re: musb throughput issues

2013-05-10 Thread Frederik Schmid
Hi Ruslan, Thanks for the tips! A few comments below: On Friday 10 May 2013 13.54.53 Ruslan Bilovol wrote: > Hello Frederic, > > On Fri, May 10, 2013 at 12:54 PM, Frederik Schmid > > wrote: > > Well, my conclusion is that this setup, IDS-camera + musb, is horribly > > sensitive to interrupt la

Re: musb throughput issues

2013-05-10 Thread Ruslan Bilovol
Hello Frederic, On Fri, May 10, 2013 at 12:54 PM, Frederik Schmid wrote: > Well, my conclusion is that this setup, IDS-camera + musb, is horribly > sensitive to interrupt latency. > > If the musb-interrupt is blocked for ~100us the pipe is stalled. Most of the > interrupts on my target were route

Re: musb throughput issues

2013-05-10 Thread Frederik Schmid
Well, my conclusion is that this setup, IDS-camera + musb, is horribly sensitive to interrupt latency. If the musb-interrupt is blocked for ~100us the pipe is stalled. Most of the interrupts on my target were routed to CPU0 while CPU1 had few. When I re-route the musb interrupts to CPU1 through

Re: musb throughput issues

2013-05-09 Thread Frederik Schmid
Hi Greg, The kernel is based on 3.4.11 from omapzoom.org (ti-ubuntu-3.4-1487) with Variscite BSP patches from: http://www.variwiki.com/index.php?title=VAR-SOM-OM44_-_Ubuntu_Precise I was expecting 200-250Mbps which is entirly possible on the same chip using its ehci-controller. musb seems to s

Re: musb throughput issues

2013-05-09 Thread Greg KH
On Thu, May 09, 2013 at 10:44:05AM +0200, Frederik Schmid wrote: > Hi, > > I'm developing a camera application on a TI OMAP4460. I have a cmos > usb-camera > from IDS (UI-1551-LE-C-HQ) connected to the OTG-port (musb as host) on the > OMAP. > > I get very poor frame rates with this setup relia

musb throughput issues

2013-05-09 Thread Frederik Schmid
Hi, I'm developing a camera application on a TI OMAP4460. I have a cmos usb-camera from IDS (UI-1551-LE-C-HQ) connected to the OTG-port (musb as host) on the OMAP. I get very poor frame rates with this setup reliably. The throughput rate is ~50-70Mbps. (1600x1200,8bpp,3-5fps) I uploaded a scr