* Unicast hash for IXGBEVF driver @ 2011-08-27 7:23 J.Hwan Kim 2011-08-27 7:34 ` Jeff Kirsher 0 siblings, 1 reply; 4+ messages in thread From: J.Hwan Kim @ 2011-08-27 7:23 UTC (permalink / raw) To: netdev Hi, everyone How can I distribute the packets according to destination MAC address into multi-virtual fucntion queue? Now, my setting is that all bit of PFUTA are '1' and ROPE bit is 1, so all mac packet is duplicated to all VF queue. I cannot understand the meaning of bits of PFUTA and the relation with mac address. I want to distribute the received packets to RX queues respectively, not duplicated. Thanks in advance. Best Regards, J.Hwan Kim ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Unicast hash for IXGBEVF driver 2011-08-27 7:23 Unicast hash for IXGBEVF driver J.Hwan Kim @ 2011-08-27 7:34 ` Jeff Kirsher 2011-08-29 18:24 ` Rose, Gregory V 0 siblings, 1 reply; 4+ messages in thread From: Jeff Kirsher @ 2011-08-27 7:34 UTC (permalink / raw) To: J.Hwan Kim, Greg Rose; +Cc: netdev, e1000-devel On Sat, Aug 27, 2011 at 00:23, J.Hwan Kim <frog1120@gmail.com> wrote: > Hi, everyone > > How can I distribute the packets according to destination MAC address > into multi-virtual fucntion queue? > Now, my setting is that all bit of PFUTA are '1' and ROPE bit is 1, > so all mac packet is duplicated to all VF queue. > I cannot understand the meaning of bits of PFUTA and the relation > with mac address. > I want to distribute the received packets to RX queues respectively, > not duplicated. > > > Thanks in advance. > > Best Regards, > J.Hwan Kim > Adding Greg Rose, since he is the ixgbevf driver maintainer. He should be able to answer your questions early next week, unless he is checking his email over the weekend. -- Cheers, Jeff ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Unicast hash for IXGBEVF driver 2011-08-27 7:34 ` Jeff Kirsher @ 2011-08-29 18:24 ` Rose, Gregory V 2011-08-30 1:05 ` J.Hwan Kim 0 siblings, 1 reply; 4+ messages in thread From: Rose, Gregory V @ 2011-08-29 18:24 UTC (permalink / raw) To: Kirsher, Jeffrey T, J.Hwan Kim; +Cc: e1000-devel@lists.sourceforge.net, netdev The ROPE bits should not be set for any of the VFs and only on the PF when it is in promiscuous mode. The PFUTA bits are imperfect MAC address hash filters. By setting them all to ones and then turning on the ROPE bit for each of the VFs you're essentially putting the VF into a sort of fake promiscuous mode. This is not recommended. Older drivers that did this had a bug in them. - Greg > -----Original Message----- > From: tarbal@gmail.com [mailto:tarbal@gmail.com] On Behalf Of Jeff Kirsher > Sent: Saturday, August 27, 2011 12:35 AM > To: J.Hwan Kim; Rose, Gregory V > Cc: netdev; e1000-devel@lists.sourceforge.net > Subject: Re: Unicast hash for IXGBEVF driver > > On Sat, Aug 27, 2011 at 00:23, J.Hwan Kim <frog1120@gmail.com> wrote: > > Hi, everyone > > > > How can I distribute the packets according to destination MAC address > > into multi-virtual fucntion queue? > > Now, my setting is that all bit of PFUTA are '1' and ROPE bit is 1, > > so all mac packet is duplicated to all VF queue. > > I cannot understand the meaning of bits of PFUTA and the relation > > with mac address. > > I want to distribute the received packets to RX queues respectively, > > not duplicated. > > > > > > Thanks in advance. > > > > Best Regards, > > J.Hwan Kim > > > > Adding Greg Rose, since he is the ixgbevf driver maintainer. He > should be able to answer your questions early next week, unless he is > checking his email over the weekend. > > -- > Cheers, > Jeff ------------------------------------------------------------------------------ Special Offer -- Download ArcSight Logger for FREE! Finally, a world-class log management solution at an even better price-free! And you'll get a free "Love Thy Logs" t-shirt when you download Logger. Secure your free ArcSight Logger TODAY! http://p.sf.net/sfu/arcsight-sdnews _______________________________________________ E1000-devel mailing list E1000-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/e1000-devel To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Unicast hash for IXGBEVF driver 2011-08-29 18:24 ` Rose, Gregory V @ 2011-08-30 1:05 ` J.Hwan Kim 0 siblings, 0 replies; 4+ messages in thread From: J.Hwan Kim @ 2011-08-30 1:05 UTC (permalink / raw) To: netdev On 2011년 08월 30일 03:24, Rose, Gregory V wrote: > The ROPE bits should not be set for any of the VFs and only on the PF when it is in promiscuous mode. > > The PFUTA bits are imperfect MAC address hash filters. By setting them all to ones and then turning on the ROPE bit for each of the VFs you're essentially putting the VF into a sort of fake promiscuous mode. > > This is not recommended. Older drivers that did this had a bug in them. > > - Greg Hi, Greg, Thank you for reply. When I have two streams of which destination mac address, for example 34:22:11:13:23:55 and 14:12:34:23:12:33, and I have 2VFs, how can I set the PFUTA register for distributting the streams into 2VFs according to the MAC address? I want to first MAC address stream to first VF and second MAC address stream to second VF. >> -----Original Message----- >> From: tarbal@gmail.com [mailto:tarbal@gmail.com] On Behalf Of Jeff Kirsher >> Sent: Saturday, August 27, 2011 12:35 AM >> To: J.Hwan Kim; Rose, Gregory V >> Cc: netdev; e1000-devel@lists.sourceforge.net >> Subject: Re: Unicast hash for IXGBEVF driver >> >> On Sat, Aug 27, 2011 at 00:23, J.Hwan Kim<frog1120@gmail.com> wrote: >>> Hi, everyone >>> >>> How can I distribute the packets according to destination MAC address >>> into multi-virtual fucntion queue? >>> Now, my setting is that all bit of PFUTA are '1' and ROPE bit is 1, >>> so all mac packet is duplicated to all VF queue. >>> I cannot understand the meaning of bits of PFUTA and the relation >>> with mac address. >>> I want to distribute the received packets to RX queues respectively, >>> not duplicated. >>> >>> >>> Thanks in advance. >>> >>> Best Regards, >>> J.Hwan Kim >>> >> Adding Greg Rose, since he is the ixgbevf driver maintainer. He >> should be able to answer your questions early next week, unless he is >> checking his email over the weekend. >> >> -- >> Cheers, >> Jeff ^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2011-08-30 1:05 UTC | newest] Thread overview: 4+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2011-08-27 7:23 Unicast hash for IXGBEVF driver J.Hwan Kim 2011-08-27 7:34 ` Jeff Kirsher 2011-08-29 18:24 ` Rose, Gregory V 2011-08-30 1:05 ` J.Hwan Kim
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).