|To:||Robert Olsson <Robert.Olsson@xxxxxxxxxxx>, Andrew Morton <akpm@xxxxxxxx>|
|Subject:||Re: Fw: [BUG/PATCH] CONFIG_NET_HW_FLOWCONTROL and SMP|
|From:||Jeff Garzik <jgarzik@xxxxxxxxx>|
|Date:||Thu, 02 Oct 2003 13:47:40 -0400|
|References:||<20030929123734.5bd97a47.akpm@xxxxxxxx> <16248.41796.797321.700866@xxxxxxxxxxxx> <3F78A691.1040406@xxxxxxxxx> <16252.17618.866515.952549@xxxxxxxxxxxx>|
|User-agent:||Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.4) Gecko/20030703|
Robert Olsson wrote:
Jeff Garzik writes:> > If someone had a NAPI patch for tulip, we could remove HW_FLOWCONTROL > option altogether :)Hello! Here is something for 2.6.0-test6: * ifdef's to keep current non-NAPI tulip intact * Port based on Alexey's orig NAPI tulip design (Only RX handled by dev->poll) * tulip HW_FLOW removed * NAPI and HW-mitigation options in Kconfig
Looks great to me. I'll give it some testing here, and 99% likely will apply it.
Andrew, would you be willing to merge this into -mm for some simultaneous netwide testing?
FWIW, I seem to recall that the older NAPI patch you sent didn't apply for some reason. But forget about that, this one looks good.
|<Prev in Thread]||Current Thread||[Next in Thread>|
|Previous by Date:||Re: [RFC] add rtnl semaphore to linux-atm, Mitchell Blank Jr|
|Next by Date:||Re: [PATCH] skbuff more likely/unlikely, Mitchell Blank Jr|
|Previous by Thread:||Re: Fw: [BUG/PATCH] CONFIG_NET_HW_FLOWCONTROL and SMP, Robert Olsson|
|Next by Thread:||Re: Fw: [BUG/PATCH] CONFIG_NET_HW_FLOWCONTROL and SMP, Andrew Morton|
|Indexes:||[Date] [Thread] [Top] [All Lists]|