* Re: e1000 softirq load balancing [not found] <48F4ED7E.4070308@cs.utexas.edu> @ 2008-10-14 19:51 ` David Miller 2008-10-14 23:46 ` Don Porter 0 siblings, 1 reply; 4+ messages in thread From: David Miller @ 2008-10-14 19:51 UTC (permalink / raw) To: porterde; +Cc: linux-net, netdev From: Don Porter <porterde@cs.utexas.edu> Date: Tue, 14 Oct 2008 14:05:34 -0500 > It seems to me that with 4 independent NICs and plenty of CPUs to > spare, I ought to be able to assign one softirq daemon to each NIC > rather than funnelling all of the traffic through 1 or 2. Traffic doesn't get distributed unless the NIC has support for RX flow seperation and PCI MSI-X interrupts. Your NICs do not. So no matter how hard you try, each NIC is going to have it's packets processed essentially on one cpu. ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: e1000 softirq load balancing 2008-10-14 19:51 ` e1000 softirq load balancing David Miller @ 2008-10-14 23:46 ` Don Porter 2008-10-14 23:51 ` David Miller 0 siblings, 1 reply; 4+ messages in thread From: Don Porter @ 2008-10-14 23:46 UTC (permalink / raw) To: David Miller; +Cc: linux-net, netdev Thanks David. Would you mind giving me a bit of intuition why I can't have a 1:1 mapping of CPUs to NICs? I am a bit out of my depth here, but I'd like to learn. Best, Don David Miller wrote: > From: Don Porter <porterde@cs.utexas.edu> > Date: Tue, 14 Oct 2008 14:05:34 -0500 > > >> It seems to me that with 4 independent NICs and plenty of CPUs to >> spare, I ought to be able to assign one softirq daemon to each NIC >> rather than funnelling all of the traffic through 1 or 2. >> > > Traffic doesn't get distributed unless the NIC has support > for RX flow seperation and PCI MSI-X interrupts. Your NICs > do not. > > So no matter how hard you try, each NIC is going to have it's > packets processed essentially on one cpu. > ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: e1000 softirq load balancing 2008-10-14 23:46 ` Don Porter @ 2008-10-14 23:51 ` David Miller 2008-10-14 23:55 ` Donald Porter 0 siblings, 1 reply; 4+ messages in thread From: David Miller @ 2008-10-14 23:51 UTC (permalink / raw) To: porterde; +Cc: linux-net, netdev From: Don Porter <porterde@cs.utexas.edu> Date: Tue, 14 Oct 2008 18:46:11 -0500 > Would you mind giving me a bit of intuition why I can't have a 1:1 > mapping of CPUs to NICs? I didn't say that. I said that without HW flow seperation support, you can only expect N cpus to be busy where N is the number of NICs you have. ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: e1000 softirq load balancing 2008-10-14 23:51 ` David Miller @ 2008-10-14 23:55 ` Donald Porter 0 siblings, 0 replies; 4+ messages in thread From: Donald Porter @ 2008-10-14 23:55 UTC (permalink / raw) To: David Miller; +Cc: linux-net, netdev Ok. That seems very reasonable. So the behavior I am seeing is that I have 4 NICs, but all of the traffic is being funneled to 1-2 softirq handlers, despite the fact that the hardware interrupts are being delivered to 4 different CPUs. Any tips on how to debug this? Or perhaps there is some configuration step I am missing? Thanks, Don On Oct 14, 2008, at 6:51 PM, David Miller wrote: > From: Don Porter <porterde@cs.utexas.edu> > Date: Tue, 14 Oct 2008 18:46:11 -0500 > >> Would you mind giving me a bit of intuition why I can't have a 1:1 >> mapping of CPUs to NICs? > > I didn't say that. > > I said that without HW flow seperation support, you can only > expect N cpus to be busy where N is the number of NICs you > have. ^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2008-10-14 23:55 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <48F4ED7E.4070308@cs.utexas.edu>
2008-10-14 19:51 ` e1000 softirq load balancing David Miller
2008-10-14 23:46 ` Don Porter
2008-10-14 23:51 ` David Miller
2008-10-14 23:55 ` Donald Porter
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).