b795854b1f
Ideally it would be possible to distinguish between NUMA hinting faults that are private to a task and those that are shared. If treated identically there is a risk that shared pages bounce between nodes depending on the order they are referenced by tasks. Ultimately what is desirable is that task private pages remain local to the task while shared pages are interleaved between sharing tasks running on different nodes to give good average performance. This is further complicated by THP as even applications that partition their data may not be partitioning on a huge page boundary. To start with, this patch assumes that multi-threaded or multi-process applications partition their data and that in general the private accesses are more important for cpu->memory locality in the general case. Also, no new infrastructure is required to treat private pages properly but interleaving for shared pages requires additional infrastructure. To detect private accesses the pid of the last accessing task is required but the storage requirements are a high. This patch borrows heavily from Ingo Molnar's patch "numa, mm, sched: Implement last-CPU+PID hash tracking" to encode some bits from the last accessing task in the page flags as well as the node information. Collisions will occur but it is better than just depending on the node information. Node information is then used to determine if a page needs to migrate. The PID information is used to detect private/shared accesses. The preferred NUMA node is selected based on where the maximum number of approximately private faults were measured. Shared faults are not taken into consideration for a few reasons. First, if there are many tasks sharing the page then they'll all move towards the same node. The node will be compute overloaded and then scheduled away later only to bounce back again. Alternatively the shared tasks would just bounce around nodes because the fault information is effectively noise. Either way accounting for shared faults the same as private faults can result in lower performance overall. The second reason is based on a hypothetical workload that has a small number of very important, heavily accessed private pages but a large shared array. The shared array would dominate the number of faults and be selected as a preferred node even though it's the wrong decision. The third reason is that multiple threads in a process will race each other to fault the shared page making the fault information unreliable. Signed-off-by: Mel Gorman <mgorman@suse.de> [ Fix complication error when !NUMA_BALANCING. ] Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1381141781-10992-30-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
95 lines
2.9 KiB
C
95 lines
2.9 KiB
C
#ifndef PAGE_FLAGS_LAYOUT_H
|
|
#define PAGE_FLAGS_LAYOUT_H
|
|
|
|
#include <linux/numa.h>
|
|
#include <generated/bounds.h>
|
|
|
|
/*
|
|
* When a memory allocation must conform to specific limitations (such
|
|
* as being suitable for DMA) the caller will pass in hints to the
|
|
* allocator in the gfp_mask, in the zone modifier bits. These bits
|
|
* are used to select a priority ordered list of memory zones which
|
|
* match the requested limits. See gfp_zone() in include/linux/gfp.h
|
|
*/
|
|
#if MAX_NR_ZONES < 2
|
|
#define ZONES_SHIFT 0
|
|
#elif MAX_NR_ZONES <= 2
|
|
#define ZONES_SHIFT 1
|
|
#elif MAX_NR_ZONES <= 4
|
|
#define ZONES_SHIFT 2
|
|
#else
|
|
#error ZONES_SHIFT -- too many zones configured adjust calculation
|
|
#endif
|
|
|
|
#ifdef CONFIG_SPARSEMEM
|
|
#include <asm/sparsemem.h>
|
|
|
|
/* SECTION_SHIFT #bits space required to store a section # */
|
|
#define SECTIONS_SHIFT (MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)
|
|
|
|
#endif /* CONFIG_SPARSEMEM */
|
|
|
|
/*
|
|
* page->flags layout:
|
|
*
|
|
* There are five possibilities for how page->flags get laid out. The first
|
|
* pair is for the normal case without sparsemem. The second pair is for
|
|
* sparsemem when there is plenty of space for node and section information.
|
|
* The last is when there is insufficient space in page->flags and a separate
|
|
* lookup is necessary.
|
|
*
|
|
* No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS |
|
|
* " plus space for last_nidpid: | NODE | ZONE | LAST_NIDPID ... | FLAGS |
|
|
* classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS |
|
|
* " plus space for last_nidpid: | SECTION | NODE | ZONE | LAST_NIDPID ... | FLAGS |
|
|
* classic sparse no space for node: | SECTION | ZONE | ... | FLAGS |
|
|
*/
|
|
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
|
|
#define SECTIONS_WIDTH SECTIONS_SHIFT
|
|
#else
|
|
#define SECTIONS_WIDTH 0
|
|
#endif
|
|
|
|
#define ZONES_WIDTH ZONES_SHIFT
|
|
|
|
#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
|
|
#define NODES_WIDTH NODES_SHIFT
|
|
#else
|
|
#ifdef CONFIG_SPARSEMEM_VMEMMAP
|
|
#error "Vmemmap: No space for nodes field in page flags"
|
|
#endif
|
|
#define NODES_WIDTH 0
|
|
#endif
|
|
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
#define LAST__PID_SHIFT 8
|
|
#define LAST__PID_MASK ((1 << LAST__PID_SHIFT)-1)
|
|
|
|
#define LAST__NID_SHIFT NODES_SHIFT
|
|
#define LAST__NID_MASK ((1 << LAST__NID_SHIFT)-1)
|
|
|
|
#define LAST_NIDPID_SHIFT (LAST__PID_SHIFT+LAST__NID_SHIFT)
|
|
#else
|
|
#define LAST_NIDPID_SHIFT 0
|
|
#endif
|
|
|
|
#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_NIDPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
|
|
#define LAST_NIDPID_WIDTH LAST_NIDPID_SHIFT
|
|
#else
|
|
#define LAST_NIDPID_WIDTH 0
|
|
#endif
|
|
|
|
/*
|
|
* We are going to use the flags for the page to node mapping if its in
|
|
* there. This includes the case where there is no node, so it is implicit.
|
|
*/
|
|
#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
|
|
#define NODE_NOT_IN_PAGE_FLAGS
|
|
#endif
|
|
|
|
#if defined(CONFIG_NUMA_BALANCING) && LAST_NIDPID_WIDTH == 0
|
|
#define LAST_NIDPID_NOT_IN_PAGE_FLAGS
|
|
#endif
|
|
|
|
#endif /* _LINUX_PAGE_FLAGS_LAYOUT */
|