After talking about this a bit this morning we truly believe that this is still an ASPM issue and are looking to get you (Nils) as good way to test our theory. We'll be getting you something soon.
Cheers, John > -----Original Message----- > From: Tantilov, Emil S > Sent: Monday, August 09, 2010 11:02 AM > To: Nils Faerber; Ronciak, John > Cc: [email protected] > Subject: RE: [E1000-devel] e1000e latency issues > > Nils Faerber wrote: > > Ronciak, John wrote: > >> This may be kernel problem. Do you have to use one of the new > >> kernels for now? Since changing the driver doesn't change things > >> this most likely is not a driver problem. > > > > Well, I do not *have* to. The latest working one for me was 2.6.32. > > > >> Are you sure nothing else on the network has changed? Like a switch > >> or router? Or even a switch configuration change? > > > > Pretty sure, yes, since I tried this in different setups up to direct > > connection with my embedded board. > > > >> Is spanning tree enabled on your switch? > > > > Nope - I only have quite dumb pocket switches. > > > >> Does it go back to working if you go back to an older kernel? > > > > Yes, 2.6.32 is working nicely. > > What speed/duplex are you connected to? Could you provide the output > of: > ethtool eth0 > ethtool -d eth0 > > Also if you don't mind filing a bug at e1000.sf.net with all the > information you provided thus far? > > Thanks, > Emil ------------------------------------------------------------------------------ This SF.net email is sponsored by Make an app they can't live without Enter the BlackBerry Developer Challenge http://p.sf.net/sfu/RIM-dev2dev _______________________________________________ E1000-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/e1000-devel To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired
