<br><br><div><span class="gmail_quote">On 3/1/06, <b class="gmail_sendername">Brian Wood</b> <<a href="mailto:beww@beww.org">beww@beww.org</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br><br>On Mar 1, 2006, at 1:42 PM, Dylan R. Semler wrote:<br><br>> <<a href="http://www.mythtv.org/wiki/index.php/PCI_Latency">http://www.mythtv.org/wiki/index.php/PCI_Latency</a>><br>><br>>>> I found my IDE controller latency was set to zero, so I reset it to
<br>>>> 32 (20hex). I'm not at home to try playback right now, but I was<br>>>> wondering what others who are having this problem find for their<br>>>> IDE/SATA controller latency. Maybe this could fix us up?!?! I'll
<br>>>> report back later tonight what I find out.<br>>>><br>>><br>>> So far, with a very limited number of samples, the people who have<br>>> found their disk controllers set to zero have either been unable to
<br>>> reset the latency value, or have not seen any positive results from<br>>> doing so.<br>>><br>>> Only the machines which have drive controller latency set to 32 or 64<br>>> initially have had much luck in adjusting them.
<br>>><br>>> Again, this is from a *very* limited number of samples (6 to be<br>>> exact)<br>>> so please report your results, positive or negative, as well as the<br>>> chipset your mobo is using (perhaps on the WiKi page ??)
<br>><br>> I just tried changing the latency on my three machines. I have two<br>> Dell<br>> 8200 desktops from about 2002 and a Sager laptop from December<br>> 2005. In<br>> all three machines, the initial IDE latency was 0 and changing it with
<br>><br>> setpci -v -s 00:1f.1 latency_timer=b0 (or any other value)<br>><br>> did not seem to do anything. At least lspci -v continued to display<br>> their latency as 0 (I have not been able to test this with Myth yet).
<br>> Furthermore, I found that if tried this command on ANY controller<br>> whose<br>> intial latency was 0, the command did nothing. If the initial latency<br>> was not zero, the command would change the latency to the desired
<br>> value. I Also tested that if a controller ititially had a non-zero<br>> latency, and I changed it to zero, I was still able to change it<br>> back to<br>> other values. I have no idea why this is or what can be done, but I
<br>> thought I'd add some more datapoints to the set. If anyone wants the<br>> maker of these mobos, I can probably find that out somehow.<br>><br><br>That matches out what I have recorded. The one incident of somebody
<br>setting a zero latency to something else could not be repeated and I<br>take it as bad data.<br><br>I think by spec latency does not have to be settable unless the<br>device is capable of bus mastering and bursting two or more shots
<br>over the bus, but I can't imagine a drive controller that wouldn't<br>want to be able to do that. The latency might just be fixed at some<br>unknown value and not readable by lspci for some reason.<br></blockquote></div>
<br><br>Maybe I'm an exception to the rule, but setpci lets me adjust the latency of the IDE controller, and checking again afterwards with lspci -v seems to indicate the change has held:<br><br>00:14.1 IDE interface: ATI Technologies Inc: Unknown device 4349 (prog-if 8a [Master SecP PriP])
<br> Subsystem: ATI Technologies Inc: Unknown device 4349<br> Flags: bus master, medium devsel, latency 32<br> I/O ports at <ignored><br> I/O ports at <ignored><br> I/O ports at <ignored>
<br> I/O ports at <ignored><br> I/O ports at ff00 [size=16]<br><br><br><br>however, the ISA bridge also has a latency of 0 and that doesn't change after setting with setpci:<br><br>00:14.3 ISA bridge: ATI Technologies Inc: Unknown device 434c
<br> Subsystem: ATI Technologies Inc: Unknown device 434c<br> Flags: bus master, 66Mhz, medium devsel, latency 0<br><br><br><br>