d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
9e3e3fe5b3
freebsd-nq/sys/vm/vm_phys.h
Adrian Chadd 6520495abc Add an initial NUMA affinity/policy configuration for threads and processes. 
This is based on work done by jeff@ and jhb@, as well as the numa.diff
patch that has been circulating when someone asks for first-touch NUMA
on -10 or -11.

* Introduce a simple set of VM policy and iterator types.
* tie the policy types into the vm_phys path for now, mirroring how
  the initial first-touch allocation work was enabled.
* add syscalls to control changing thread and process defaults.
* add a global NUMA VM domain policy.
* implement a simple cascade policy order - if a thread policy exists, use it;
  if a process policy exists, use it; use the default policy.
* processes inherit policies from their parent processes, threads inherit
  policies from their parent threads.
* add a simple tool (numactl) to query and modify default thread/process
  policities.
* add documentation for the new syscalls, for numa and for numactl.
* re-enable first touch NUMA again by default, as now policies can be
  set in a variety of methods.

This is only relevant for very specific workloads.

This doesn't pretend to be a final NUMA solution.

The previous defaults in -HEAD (with MAXMEMDOM set) can be achieved by
'sysctl vm.default_policy=rr'.

This is only relevant if MAXMEMDOM is set to something other than 1.
Ie, if you're using GENERIC or a modified kernel with non-NUMA, then
this is a glorified no-op for you.

Thank you to Norse Corp for giving me access to rather large
(for FreeBSD!) NUMA machines in order to develop and verify this.

Thank you to Dell for providing me with dual socket sandybridge
and westmere v3 hardware to do NUMA development with.

Thank you to Scott Long at Netflix for providing me with access
to the two-socket, four-domain haswell v3 hardware.

Thank you to Peter Holm for running the stress testing suite
against the NUMA branch during various stages of development!

Tested:

* MIPS (regression testing; non-NUMA)
* i386 (regression testing; non-NUMA GENERIC)
* amd64 (regression testing; non-NUMA GENERIC)
* westmere, 2 socket (thankyou norse!)
* sandy bridge, 2 socket (thankyou dell!)
* ivy bridge, 2 socket (thankyou norse!)
* westmere-EX, 4 socket / 1TB RAM (thankyou norse!)
* haswell, 2 socket (thankyou norse!)
* haswell v3, 2 socket (thankyou dell)
* haswell v3, 2x18 core (thankyou scott long / netflix!)

* Peter Holm ran a stress test suite on this work and found one
  issue, but has not been able to verify it (it doesn't look NUMA
  related, and he only saw it once over many testing runs.)

* I've tested bhyve instances running in fixed NUMA domains and cpusets;
  all seems to work correctly.

Verified:

* intel-pcm - pcm-numa.x and pcm-memory.x, whilst selecting different
  NUMA policies for processes under test.

Review:

This was reviewed through phabricator (https://reviews.freebsd.org/D2559)
as well as privately and via emails to freebsd-arch@.  The git history
with specific attributes is available at https://github.com/erikarn/freebsd/
in the NUMA branch (https://github.com/erikarn/freebsd/compare/local/adrian_numa_policy).

This has been reviewed by a number of people (stas, rpaulo, kib, ngie,
wblock) but not achieved a clear consensus.  My hope is that with further
exposure and testing more functionality can be implemented and evaluated.

Notes:

* The VM doesn't handle unbalanced domains very well, and if you have an overly
  unbalanced memory setup whilst under high memory pressure, VM page allocation
  may fail leading to a kernel panic.  This was a problem in the past, but it's
  much more easily triggered now with these tools.

* This work only controls the path through vm_phys; it doesn't yet strongly/predictably
  affect contigmalloc, KVA placement, UMA, etc.  So, driver placement of memory
  isn't really guaranteed in any way.  That's next on my plate.

Sponsored by:	Norse Corp, Inc.; Dell
2015-07-11 15:21:37 +00:00

125 lines
3.9 KiB
C
Raw Blame History

/*-
* Copyright (c) 2002-2006 Rice University
* Copyright (c) 2007 Alan L. Cox <alc@cs.rice.edu>
* All rights reserved.
*
* This software was developed for the FreeBSD Project by Alan L. Cox,
* Olivier Crameri, Peter Druschel, Sitaram Iyer, and Juan Navarro.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* HOLDERS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
* OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
* AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY
* WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*
* $FreeBSD$
*/
/*
* Physical memory system definitions
*/
#ifndef _VM_PHYS_H_
#define _VM_PHYS_H_
#ifdef _KERNEL
/* Domains must be dense (non-sparse) and zero-based. */
struct mem_affinity {
vm_paddr_t start;
vm_paddr_t end;
int domain;
};
struct vm_freelist {
struct pglist pl;
int lcnt;
};
struct vm_phys_seg {
vm_paddr_t start;
vm_paddr_t end;
vm_page_t first_page;
int domain;
struct vm_freelist (*free_queues)[VM_NFREEPOOL][VM_NFREEORDER];
};
extern struct mem_affinity *mem_affinity;
extern int *mem_locality;
extern int vm_ndomains;
extern struct vm_phys_seg vm_phys_segs[];
extern int vm_phys_nsegs;
/*
* The following functions are only to be used by the virtual memory system.
*/
void vm_phys_add_page(vm_paddr_t pa);
void vm_phys_add_seg(vm_paddr_t start, vm_paddr_t end);
vm_page_t vm_phys_alloc_contig(u_long npages, vm_paddr_t low, vm_paddr_t high,
u_long alignment, vm_paddr_t boundary);
vm_page_t vm_phys_alloc_freelist_pages(int freelist, int pool, int order);
vm_page_t vm_phys_alloc_pages(int pool, int order);
boolean_t vm_phys_domain_intersects(long mask, vm_paddr_t low, vm_paddr_t high);
int vm_phys_fictitious_reg_range(vm_paddr_t start, vm_paddr_t end,
vm_memattr_t memattr);
void vm_phys_fictitious_unreg_range(vm_paddr_t start, vm_paddr_t end);
vm_page_t vm_phys_fictitious_to_vm_page(vm_paddr_t pa);
void vm_phys_free_contig(vm_page_t m, u_long npages);
void vm_phys_free_pages(vm_page_t m, int order);
void vm_phys_init(void);
vm_page_t vm_phys_paddr_to_vm_page(vm_paddr_t pa);
void vm_phys_set_pool(int pool, vm_page_t m, int order);
boolean_t vm_phys_unfree_page(vm_page_t m);
boolean_t vm_phys_zero_pages_idle(void);
int vm_phys_mem_affinity(int f, int t);
/*
* vm_phys_domain:
*
* Return the memory domain the page belongs to.
*/
static inline struct vm_domain *
vm_phys_domain(vm_page_t m)
{
#if MAXMEMDOM > 1
int domn, segind;
/* XXXKIB try to assert that the page is managed */
segind = m->segind;
KASSERT(segind < vm_phys_nsegs, ("segind %d m %p", segind, m));
domn = vm_phys_segs[segind].domain;
KASSERT(domn < vm_ndomains, ("domain %d m %p", domn, m));
return (&vm_dom[domn]);
#else
return (&vm_dom[0]);
#endif
}
static inline void
vm_phys_freecnt_adj(vm_page_t m, int adj)
{
mtx_assert(&vm_page_queue_free_mtx, MA_OWNED);
vm_cnt.v_free_count += adj;
vm_phys_domain(m)->vmd_free_count += adj;
}
#endif /* _KERNEL */
#endif /* !_VM_PHYS_H_ */
Reference in New Issue View Git Blame Copy Permalink