Messages in this thread | | | Date | Mon, 12 Jan 2009 23:40:37 +0100 | From | Ingo Molnar <> | Subject | Re: [patch] tlb flush_data: replace per_cpu with an array |
| |
* Andi Kleen <andi@firstfloor.org> wrote:
> On Mon, Jan 12, 2009 at 10:35:42PM +0100, Frederik Deweerdt wrote: > > Hi, > > > > On x86_64 flush tlb data is stored in per_cpu variables. This is > > unnecessary because only the first NUM_INVALIDATE_TLB_VECTORS entries > > are accessed. > > > > This patch aims at making the code less confusing (there's nothing > > really "per_cpu") by using a plain array. It also would save some > > memory on most distros out there (Ubuntu x86_64 has NR_CPUS=64 by > > default). > > Nope it doesn't save memory on most systems because per cpu is only > allocated based on the CPUs that are actually there. And if you have > more than 8 cores you can likely afford a few bytes per CPU.
No distro kernel will build with less than 8 CPUs anyway so this point is moot.
> You would need to cache line pad each entry then, otherwise you risk > false sharing. [...]
They are already cache line padded.
> [...] That would make the array 1K on 128 bytes cache line system.
512 bytes.
> [...] This means on small systems this would actually waste much more > memory.
Really small systems will be UP and wont do cross-CPU TLB flushes, so if they are a worry the flush code can be UP optimized. (Nobody bothered so far.)
Ingo
| |