On Mon, Jan 21, 2008 at 10:59:41AM -0800, Joel Jaeggli wrote: |Malcolm Herbert wrote: |> I'm wondering about the usual speed of the net5501 USB port, as I seem |> to get no better than about 700KB/s to an attached external disk. | |That sounds really close to what you'd expect from usb1, about 5.6Mb/s...
that was my thinking, yes ... |I'll connect one up to my soekris and see what I get. thanks for that ... it may also be that the driver I have for USB doesn't recognise the chipset as being USB2-capable ... NetBSD-4.0 dmesg says: |ohci0 at pci0 dev 21 function 0: Advanced Micro Devices CS5536 OHCI USB Controller (rev. 0x02) |ohci0: interrupting at irq 15 |ohci0: OHCI version 1.0, legacy support |usb0 at ohci0: USB revision 1.0 |uhub0 at usb0 |uhub0: Advanced Micro OHCI root hub, class 9/0, rev 1.00/1.00, addr 1 |uhub0: 4 ports with 4 removable, self powered |ehci0 at pci0 dev 21 function 1: Advanced Micro Devices CS5536 EHCI USB Controller (rev. 0x02) |ehci0: interrupting at irq 15 |ehci0: EHCI version 1.0 |ehci0: companion controller, 4 ports each: ohci0 |usb1 at ehci0: USB revision 2.0 |uhub1 at usb1 |uhub1: Advanced Micro Devices EHCI root hub, class 9/0, rev 2.00/1.00, addr 1 |uhub1: 4 ports with 4 removable, self powered These two lines seem to be the culprit: |ohci0: OHCI version 1.0, legacy support |usb0 at ohci0: USB revision 1.0 ... so, I wonder if I'd get a better response from using the internal USB port or somehow the driver binding is ohci first then ehci ... |> I haven't yet worked out where the bottleneck is, but a 250GB RAID |> mirror is expected to take 4 days to sync, which seems to be a little |> too long to me ... it also seems to pound the CPU pretty hard when |> I do any sustained USB traffic ... | |So there's two disks in an external enclosure and one is being copied to |the other? no, one internal 2.5in 250GB PATA disk and one external USB disk in an enclosure which has gotten good reports from the vendor, hence my surprise at the performance I'll ask around on the netbsd-users list to see if I can either suppress ohci or reorder their binding and see if that makes a difference ... Regards, Malcolm -- Malcolm Herbert This brain intentionally [EMAIL PROTECTED] left blank _______________________________________________ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
