[PATCH 3/6] xen: modify memory ops to be NUMA-aware

[Ryan Harper <ryanh@us.ibm.com>]

>From [1]previous post:
> This patch modifies three memory operations to be NUMA-aware:
> 
> increase_reservation
> populate_physmap
> memory_exchange
> 
> These three operations request memory from the domain heap and have been
> modified to distribute the request across the physical cpus of the
> target domain evenly.  This make memory local to the physical cpus
> within the domain available for the guest.

Measuring the overhead has shown the distribution to be costly with at
the current time, no specific benefit since the best case would be
providing local memory in a multi-node guest environment.  As we
currently don't export this virtual domain topology to Linux, it can't
take advantage of the local allocations.  At this time, most domains
created on NUMA machines will modify their config file parameters to
ensure they fit within a single NUMA node and render the distribution
code useless.  This patch removes the extra logic and uses domain's vcpu
0 processor as the parameter into the heap allocation function.

Now domains will use VCPU0 to pick which node to allocate memory from
(using cpu_to_node mapping) and we don't pay for logic that won't be
leveraged.


[1] http://lists.xensource.com/archives/html/xen-devel/2006-07/msg00544.html

-- 
Ryan Harper
Software Engineer; Linux Technology Center
IBM Corp., Austin, Tx
(512) 838-9253   T/L: 678-9253
ryanh@us.ibm.com


diffstat output:
 memory.c |   21 ++++++++++++++-------
 1 files changed, 14 insertions(+), 7 deletions(-)

Signed-off-by: Ryan Harper <ryanh@us.ibm.com>
---
diff -r f362859d88c4 xen/common/memory.c
--- a/xen/common/memory.c	Mon Jul 31 10:30:02 2006 -0500
+++ b/xen/common/memory.c	Mon Jul 31 10:34:14 2006 -0500
@@ -40,6 +40,8 @@ increase_reservation(
     struct page_info *page;
     unsigned long i;
     xen_pfn_t mfn;
+    /* use domain's first processor for locality parameter */
+    unsigned int cpu = d->vcpu[0]->processor;
 
     if ( !guest_handle_is_null(extent_list) &&
          !guest_handle_okay(extent_list, nr_extents) )
@@ -57,8 +59,8 @@ increase_reservation(
             return i;
         }
 
-        if ( unlikely((page = alloc_domheap_pages(
-            d, extent_order, memflags)) == NULL) )
+        if ( unlikely((page = __alloc_domheap_pages( d, cpu, 
+            extent_order, memflags )) == NULL) ) 
         {
             DPRINTK("Could not allocate order=%d extent: "
                     "id=%d memflags=%x (%ld of %d)\n",
@@ -91,6 +93,8 @@ populate_physmap(
     unsigned long i, j;
     xen_pfn_t gpfn;
     xen_pfn_t mfn;
+    /* use domain's first processor for locality parameter */
+    unsigned int cpu = d->vcpu[0]->processor;
 
     if ( !guest_handle_okay(extent_list, nr_extents) )
         return 0;
@@ -110,8 +114,8 @@ populate_physmap(
         if ( unlikely(__copy_from_guest_offset(&gpfn, extent_list, i, 1)) )
             goto out;
 
-        if ( unlikely((page = alloc_domheap_pages(
-            d, extent_order, memflags)) == NULL) )
+        if ( unlikely((page = __alloc_domheap_pages( d, cpu, 
+            extent_order, memflags )) == NULL) ) 
         {
             DPRINTK("Could not allocate order=%d extent: "
                     "id=%d memflags=%x (%ld of %d)\n",
@@ -293,7 +297,7 @@ memory_exchange(XEN_GUEST_HANDLE(xen_mem
     unsigned long in_chunk_order, out_chunk_order;
     xen_pfn_t     gpfn, gmfn, mfn;
     unsigned long i, j, k;
-    unsigned int  memflags = 0;
+    unsigned int  memflags = 0, cpu;
     long          rc = 0;
     struct domain *d;
     struct page_info *page;
@@ -367,6 +371,9 @@ memory_exchange(XEN_GUEST_HANDLE(xen_mem
     }
     d = current->domain;
 
+    /* use domain's first processor for locality parameter */
+    cpu = d->vcpu[0]->processor;
+
     for ( i = 0; i < (exch.in.nr_extents >> in_chunk_order); i++ )
     {
         if ( hypercall_preempt_check() )
@@ -412,8 +419,8 @@ memory_exchange(XEN_GUEST_HANDLE(xen_mem
         /* Allocate a chunk's worth of anonymous output pages. */
         for ( j = 0; j < (1UL << out_chunk_order); j++ )
         {
-            page = alloc_domheap_pages(
-                NULL, exch.out.extent_order, memflags);
+            page = __alloc_domheap_pages( NULL, cpu, 
+                  exch.out.extent_order, memflags);
             if ( unlikely(page == NULL) )
             {
                 rc = -ENOMEM;