Messages in this thread | | | Date | Mon, 17 Jan 2000 16:53:56 +0100 (CET) | From | Ingo Molnar <> | Subject | Re: [patch] smp-2.3.40-A3, SMP fixes |
| |
On Mon, 17 Jan 2000, Manfred Spraul wrote:
> From: "Ingo Molnar" <mingo@chiara.csoma.elte.hu> > > __flush_tlb() is noticeably faster than __flush_tlb_global(). > > The two affected places, zap_low_mappings() and flush_all_zero_pkmaps() > > are now using the new flush_tlb_all_kernel() call. > > I guess flush_all_zero_pkmaps() will happen quite often, it might be the > most common caller of flush_tlb_all() [other reasons are module load/unload, > or creating a process that uses more than 1024 file handles - extremely rare > events] . I would remove the PAGE_GLOBAL bit from the kmap pages, then we do > not need another flush_tlb function that's referenced from the > cross-platform part of the kernel.
no, it does not happen often at all, even under heavy load the ratio between cached kmaps and full flushes is 1:10000. So the advantage of using _PG_GLOBAL in kmaps is pretty significant i believe, especially since the pagecache is in high memory.
i believe mapping/unmapping memory in threaded apps generates the most TLB flushes.
-- mingo
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |