[PATCH 2/2] mm: numa: Do not clear PTEs or PMDs for NUMA hinting faults

2015-03-05 Thread Mel Gorman
Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the -o

Re: [PATCH 2/2] mm: numa: Do not clear PTEs or PMDs for NUMA hinting faults

2015-03-05 Thread Linus Torvalds
On Thu, Mar 5, 2015 at 3:54 PM, Mel Gorman mgor...@suse.de wrote: if (!prot_numa || !pmd_protnone(*pmd)) { - entry = pmdp_get_and_clear_notify(mm, addr, pmd); - entry = pmd_modify(entry, newprot); + /* +

Re: [PATCH 2/2] mm: numa: Do not clear PTEs or PMDs for NUMA hinting faults

2015-03-05 Thread Dave Chinner
On Thu, Mar 05, 2015 at 11:54:52PM +, Mel Gorman wrote: Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points