Some small NUMA placement improvements

@@ -105,6 +105,9 @@ out:
  *  - the number of vcpus runnable on the candidates is considered, and
  *    candidates with fewer of them are preferred. If two candidate have
  *    the same number of runnable vcpus,
+ *  - the sum of the node distances in the candidates is considered, and
+ *    candidates with smaller total distance are preferred. If total
+ *    distance is the same for the two candidatess,
  *  - the amount of free memory in the candidates is considered, and the
  *    candidate with greater amount of it is preferred.
  *

@@ -114,6 +117,10 @@ out:
  * overloading large (from a memory POV) nodes. That's right the effect
  * that counting the vcpus able to run on the nodes tries to prevent.
  *
+ * The relative distance within the nodes in the candidates is considered
+ * as the closer the nodes, the better for the domain ending up on the
+ * candidate.
+ *
  * Note that this completely ignore the number of nodes each candidate span,
  * as the fact that fewer nodes is better is already accounted for in the
  * algorithm.

@@ -124,6 +131,9 @@ static int numa_cmpf(const libxl__numa_c
     if (c1->nr_vcpus != c2->nr_vcpus)
         return c1->nr_vcpus - c2->nr_vcpus;
 
+    if (c1->dists_sum != c2->dists_sum)
+        return c1->dists_sum - c2->dists_sum;
+
     return c2->free_memkb - c1->free_memkb;
 }
 

@@ -2735,6 +2735,7 @@ static inline void libxl__ctx_unlock(lib
 typedef struct {
     int nr_cpus, nr_nodes;
     int nr_vcpus;
+    int dists_sum;
     uint32_t free_memkb;
     libxl_bitmap nodemap;
 } libxl__numa_candidate;

63 lines not on this page · raw message

@@ -219,6 +219,11 @@ int libxl__domain_build_info_setdefault(
 
     libxl_defbool_setdefault(&b_info->numa_placement, true);
 
+    if (!b_info->min_nodes)
+        b_info->min_nodes = 0;
+    if (!b_info->max_nodes)
+        b_info->max_nodes = 0;
+
     if (b_info->max_memkb == LIBXL_MEMKB_DEFAULT)
         b_info->max_memkb = 32 * 1024;
     if (b_info->target_memkb == LIBXL_MEMKB_DEFAULT)

@@ -174,7 +174,8 @@ static int numa_place_domain(libxl__gc *
     /* Find the best candidate with enough free memory and at least
      * as much pcpus as the domain has vcpus.  */
     rc = libxl__get_numa_candidate(gc, memkb, info->max_vcpus,
-                                   0, 0, &cpupool_info.cpumap,
+                                   info->min_nodes, info->max_nodes,
+                                   &cpupool_info.cpumap,
                                    numa_cmpf, &candidate, &found);
     if (rc)
         goto out;

@@ -731,6 +731,11 @@ static void parse_config_data(const char
         libxl_defbool_set(&b_info->numa_placement, false);
     }
 
+    if (!xlu_cfg_get_long (config, "minnodes", &l, 0))
+        b_info->min_nodes = l;
+    if (!xlu_cfg_get_long (config, "maxnodes", &l, 0))
+        b_info->max_nodes = l;
+
     if (!xlu_cfg_get_long (config, "memory", &l, 0)) {
         b_info->max_memkb = l * 1024;
         b_info->target_memkb = b_info->max_memkb;

129 lines not on this page · raw message