On Tue, Jun 09, 2015 at 11:32:03PM +0100, Mel Gorman wrote: > On Tue, Jun 09, 2015 at 02:54:01PM -0700, Linus Torvalds wrote: > > On Tue, Jun 9, 2015 at 2:14 PM, Dave Hansen <dave.hansen@xxxxxxxxx> wrote: > > > > > > The 0 cycle TLB miss was also interesting. It goes back up to something > > > reasonable if I put the mb()/mfence's back. > > > > So I've said it before, and I'll say it again: Intel does really well > > on TLB fills. > > > > The reason is partly historical, with Win95 doing a ton of TLB > > invalidation (I think every single GDI call ended up invalidating the > > TLB, so under some important Windows benchmarks of the time, you > > literally had a TLB flush every 10k instructions!). > > > > But partly it is because people are wrong in thinking that TLB fills > > have to be slow. There's a lot of complete garbage RISC machines where > > the TLB fill took forever, because in the name of simplicity it would > > stop the pipeline and often be done in SW. > > > > The zero-cycle TLB fill is obviously a bit optimistic, but at the same > > time it's not completely insane. TLB fills can be prefetched, and the > > table walker can hit the cache, if you do them right. And Intel mostly > > does. > > > > So the normal full (non-global) TLB fill really is fairly cheap. It's > > been optimized for, and the TLB gets re-filled fairly efficiently. I > > suspect that it's really the case that doing more than just a couple > > of single-tlb flushes is a complete waste of time: the flushing takes > > longer than re-filling the TLB well. > > > > I expect I'll do another revision of the series after 4.2-rc1 as it's way > too close to 4.1's release. When that happens, I'll drop patch 4 and leave > just the full non-global flush patch. In the event there is an architecture > that really cares about the refill cost or we find that there is a corner > case where the TLB refill hurts then patch 4 will be in the mail archives > to consider for rebase and testing. > To be clear I meant patch 4 from v6 of the series will be dropped. In that series, patch 2 does a full non-global flush and patch 4 does the per-pfn tracking with multiple single page frame flushes. -- Mel Gorman SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>