On Thu, Oct 22, 2020 at 5:37 PM Bjorn Helgaas <helgaas@xxxxxxxxxx> wrote: > > On Sun, Oct 18, 2020 at 01:35:27PM +0200, Ian Kumlien wrote: > > On Sat, Oct 17, 2020 at 12:41 AM Ian Kumlien <ian.kumlien@xxxxxxxxx> wrote: > > > On Fri, Oct 16, 2020 at 11:28 PM Bjorn Helgaas <helgaas@xxxxxxxxxx> wrote: > > > > > Can you please, please, collect these on your system, Ian? I assume > > > > that you can easily collect it once without your patch, when you see > > > > poor I211 NIC performance but the system is otherwise working. And > > > > you can collect it again *with* your patch. Same Kconfig, same > > > > *everything* except adding your patch. > > > > > > Yeah I can do that, but I would like the changes output from the > > > latest patch suggestion > > > running on Kai-Heng's system so we can actually see what it does... > > > > Is: > > https://bugzilla.kernel.org/show_bug.cgi?id=209725 > > That's a great start. Can you attach the patch to the bugzilla too, > please, so it is self-contained? > > And also the analysis of the path from Root Port to Endpoint, with the > exit latencies of each link, the acceptable latency of the endpoint > and > > (1) the computation done by the existing code that results in > "latency < acceptable" that means we can enable ASPM, and > > (2) the correct computation per spec that results in > "latency > acceptable" so we cannot enable ASPM? > > This analysis will be the core of the commit log, and the bugzilla > with lspci info is the supporting evidence. Ok, will do, there will be some bio-latency though Were you ok with the pr_cont output per endpoint? > Bjorn
