On Thursday 23 March 2006 8:36 pm, Bill Rees wrote: > Hi Folks, > > I have an ASUS 8N SLI - Deluxe > (http://usa.asus.com/products4.aspx?l1=3&l2=15&l3=0&model=375&modelmenu=1) > motherboard with an nvidia nforce4-sli chipset. USB 1.1 seems to run > about 1/3 what I get on other systems and the only diff I can see is > that the other systems loaded the uhci_hcd and the ASUS loaded the > ohci_hcd. Should there be this disparity? Does anyone else experience > this problem?
Last time I measured OHCI vs UHCI was probably three years ago, and what I saw was the opposite: round trips through the Linux-USB stack (for the same device) took under 1 msec for OHCI, and almost 3 msec for UHCI. Throughput was maybe a bit lower with UHCI. That was with classic northbridge/southbridge architecture, no hypertransport. You didn't say what you were measuring (latency vs throughput) or how, so it's hard to say what's up. It's also possible that something's chewing up the PCI or memory bandwidth on that system. SLI could be a big factor, for example, as could the PCI arbiter. (I've seen some systems with absurd penalties for DMA from PCI devices.) - Dave ------------------------------------------------------- This SF.Net email is sponsored by xPML, a groundbreaking scripting language that extends applications into web and mobile media. Attend the live webcast and join the prime developer group breaking into this new coding territory! http://sel.as-us.falkag.net/sel?cmd=lnk&kid=110944&bid=241720&dat=121642 _______________________________________________ linux-usb-devel@lists.sourceforge.net To unsubscribe, use the last form field at: https://lists.sourceforge.net/lists/listinfo/linux-usb-devel
