Jonathan Thorpe wrote:
However, the BIOS on this board (an AMI BIOS, latest release from the motherboard vendor) has an option called "PCI Latency (PCI Clocks)" with a default setting of 32. I changed this to the maximum, which is 248 and the stability was far greater than before, on both NEC and VIA controllers.
Interesting ... and the fact that you got better thoughput with the VIA (VT8235 in that case?) is further evidence that a PCI issue is part of what makes the VIA EHCI be problematic. (Hmm, PCI issues on VIA ... I think I've heard that story before.) You should get the same effect with something like
# setpci -s 00:10.3 latency_timer=f8 Now, why should that affect stability? Near as I can tell, it shouldn't. Here's where a PCI analyser would help identify the problem. Did you try any other values?
Interesting on two counts. One, that you had any issues with NEC at all.The NEC controller would not get a reading before hanging the machine, but with a PCI Latency Value of 248, I could get the following (at one stage, I got just over 9Mb/sec on the VIA controller): -- /dev/sda: Timing buffered disk reads: 64 MB in 7.32 seconds = 8.74 MB/sec
Two, that this almost erased the performance lead I saw on 2.4 with the
NEC and Philips controllers, over the VT8235. But I couldn't reproduce
it on my hardware; it still seemed to give only a bit over 4 MByte/sec.
- Dave
-------------------------------------------------------
This SF.NET email is sponsored by: Thawte.com - A 128-bit supercerts will
allow you to extend the highest allowed 128 bit encryption to all your clients even if they use browsers that are limited to 40 bit encryption. Get a guide here:http://ads.sourceforge.net/cgi-bin/redirect.pl?thaw0030en
_______________________________________________
[EMAIL PROTECTED]
To unsubscribe, use the last form field at:
https://lists.sourceforge.net/lists/listinfo/linux-usb-devel
