| To: | "David S. Miller" <davem@xxxxxxxxxx> |
|---|---|
| Subject: | Re: [RFC][PATCH] net drivers and cache alignment |
| From: | Andrew Morton <akpm@xxxxxxxxx> |
| Date: | Sat, 07 Dec 2002 15:42:00 -0800 |
| Cc: | jgarzik@xxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| References: | <3DF2844C.F9216283@xxxxxxxxx> <20021207.153045.26640406.davem@xxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
"David S. Miller" wrote: > > From: Andrew Morton <akpm@xxxxxxxxx> > Date: Sat, 07 Dec 2002 15:29:16 -0800 > > Jeff Garzik wrote: > > Attached is cut #2. Thanks for all the near-instant feedback so far :) > > Andrew, does the attached still need padding on SMP? > > It needs padding _only_ on SMP. ____cacheline_aligned_in_smp. > > non-smp machines lack L2 caches? That's new to me :-) > > More seriously, there are real benefits on non-SMP systems. Then I am most confused. None of these fields will be put under busmastering or anything like that, so what advantage is there in spreading them out? |
| Previous by Date: | Re: [RFC][PATCH] net drivers and cache alignment, J.A. Magallon |
|---|---|
| Next by Date: | Re: [RFC][PATCH] net drivers and cache alignment, Jeff Garzik |
| Previous by Thread: | Re: [RFC][PATCH] net drivers and cache alignment, David S. Miller |
| Next by Thread: | Re: [RFC][PATCH] net drivers and cache alignment, Andrew Morton |
| Indexes: | [Date] [Thread] [Top] [All Lists] |