On Mon, Mar 03, 2008 at 10:53:52AM +0100, Eric Dumazet wrote:Because I thought that in most of the cases, we also want some cacheline alignment on UP systems as well because we care about the layout of the structure WRT the cachelines for the mandatory/capacity miss cases, as well as wanting to avoid false sharing misses on SMP. Actually I didn't think _too_ hard about them, possibly some could be removed. But the problem is that these things do require careful thought so I should not change them unless I have done that ;) I guess there are some basic guidelines -- if size is a problem (ie if there can be lots of these structures), then that is going to be a factor; if the total pool of objects is likely to be fairly densely resident in cache, then it will start to favour dense packing rather than good alignment. --
| Vladislav Bolkhovitin | Re: Integration of SCST in the mainstream Linux kernel |
| Peter Zijlstra | [PATCH 6/6] sched: disabled rt-bandwidth by default |
| Tejun Heo | [PATCHSET] CUSE: implement CUSE |
| Richard Jonsson | forcedeth: MAC-address reversed on resume from suspend |
git: | |
| Junio C Hamano | [0/4] What's not in 1.5.2 (overview) |
| Jan Hudec | Smart fetch via HTTP? |
| Johannes Schindelin | Re: git log filtering |
| Junio C Hamano | [PATCH] combine-diff: reuse diff from the same blob. |
| Julien TOUCHE | setting up ssh tunnel/vpn |
| Jordi Prats | OpenBSD with pf on a mini-ITX? |
| GVG GVG | ssh_exchange_identification: Connection closed by remote host |
| Reyk Floeter | Re: hoststated(8): DNS Relay uses unexpected source IP address |
| David Miller | Re: [ANNOUNCE] Btrfs v0.12 released |
| Christophe Saout | Re: silent semantic changes with reiser4 |
| Anton Altaparmakov | Re: [RFC] add FIEMAP ioctl to efficiently map file allocation |
| Rik van Riel | Re: [RFD] Incremental fsck |
