numa: equally distribute memory on nodes

When there are more nodes than available memory to put the minimum
allowed memory by node, all the memory is put on the last node.

This is because we put (ram_size / nb_numa_nodes) &
~((1 << mc->numa_mem_align_shift) - 1); on each node, and in this
case the value is 0. This is particularly true with pseries,
as the memory must be aligned to 256MB.

To avoid this problem, this patch uses an error diffusion algorithm [1]
to distribute equally the memory on nodes.

We introduce numa_auto_assign_ram() function in MachineClass
to keep compatibility between machine type versions.
The legacy function is used with pseries-2.9, pc-q35-2.9 and
pc-i440fx-2.9 (and previous), the new one with all others.

Example:

qemu-system-ppc64 -S -nographic  -nodefaults -monitor stdio -m 1G -smp 8 \
                  -numa node -numa node -numa node \
                  -numa node -numa node -numa node

Before:

(qemu) info numa
6 nodes
node 0 cpus: 0 6
node 0 size: 0 MB
node 1 cpus: 1 7
node 1 size: 0 MB
node 2 cpus: 2
node 2 size: 0 MB
node 3 cpus: 3
node 3 size: 0 MB
node 4 cpus: 4
node 4 size: 0 MB
node 5 cpus: 5
node 5 size: 1024 MB

After:
(qemu) info numa
6 nodes
node 0 cpus: 0 6
node 0 size: 0 MB
node 1 cpus: 1 7
node 1 size: 256 MB
node 2 cpus: 2
node 2 size: 0 MB
node 3 cpus: 3
node 3 size: 256 MB
node 4 cpus: 4
node 4 size: 256 MB
node 5 cpus: 5
node 5 size: 256 MB

[1] https://en.wikipedia.org/wiki/Error_diffusion

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20170502162955.1610-2-lvivier@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
[ehabkost: s/ram_size/size/ at numa_default_auto_assign_ram()]
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>

diff --git a/hw/core/machine.c b/hw/core/machine.c
index ada9eea483b555cada33b04f709ccfb1c0011a1e..2482c630c1ec248f3e61a9ce28975da73d84b545 100644 (file)
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -17,6 +17,7 @@
 #include "qapi/visitor.h"
 #include "hw/sysbus.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/numa.h"
 #include "qemu/error-report.h"
 #include "qemu/cutils.h"
 
@@ -400,6 +401,7 @@ static void machine_class_init(ObjectClass *oc, void *data)
      * On Linux, each node's border has to be 8MB aligned
      */
     mc->numa_mem_align_shift = 23;
+    mc->numa_auto_assign_ram = numa_default_auto_assign_ram;
 
     object_class_property_add_str(oc, "accel",
         machine_get_accel, machine_set_accel, &error_abort);

diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 9f102aa388752f7427a51b8006761907c50114e6..d468b963fbc3726f3969ee27069f0a1618d5c18f 100644 (file)
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -54,6 +54,7 @@
 #endif
 #include "migration/migration.h"
 #include "kvm_i386.h"
+#include "sysemu/numa.h"
 
 #define MAX_IDE_BUS 2
 
@@ -442,6 +443,7 @@ static void pc_i440fx_2_9_machine_options(MachineClass *m)
     pc_i440fx_machine_options(m);
     m->alias = "pc";
     m->is_default = 1;
+    m->numa_auto_assign_ram = numa_legacy_auto_assign_ram;
 }
 
 DEFINE_I440FX_MACHINE(v2_9, "pc-i440fx-2.9", NULL,

diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index dd792a8547b3845aa2f7076d3d892a51352cd22b..66303a78cff85245084eeae1a55ac2be81d6b915 100644 (file)
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -47,6 +47,7 @@
 #include "hw/usb.h"
 #include "qemu/error-report.h"
 #include "migration/migration.h"
+#include "sysemu/numa.h"
 
 /* ICH9 AHCI has 6 ports */
 #define MAX_SATA_PORTS     6
@@ -305,6 +306,7 @@ static void pc_q35_2_9_machine_options(MachineClass *m)
 {
     pc_q35_machine_options(m);
     m->alias = "q35";
+    m->numa_auto_assign_ram = numa_legacy_auto_assign_ram;
 }
 
 DEFINE_Q35_MACHINE(v2_9, "pc-q35-2.9", NULL,

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 80d12d005c6a7335c1171218c1df12dad507e000..bdc31ce56c69aea979d6747d83d3a36e55d51b9a 100644 (file)
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -3242,6 +3242,7 @@ static void spapr_machine_2_9_class_options(MachineClass *mc)
 {
     spapr_machine_2_10_class_options(mc);
     SET_MACHINE_COMPAT(mc, SPAPR_COMPAT_2_9);
+    mc->numa_auto_assign_ram = numa_legacy_auto_assign_ram;
 }
 
 DEFINE_SPAPR_MACHINE(2_9, "2.9", false);

diff --git a/include/hw/boards.h b/include/hw/boards.h
index 31d9c72fb04a68ccad5f89a8664dbaab11909f47..99458eb859daee5366d79738ffe58af897da3423 100644 (file)
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -136,6 +136,8 @@ struct MachineClass {
     int minimum_page_bits;
     bool has_hotpluggable_cpus;
     int numa_mem_align_shift;
+    void (*numa_auto_assign_ram)(MachineClass *mc, NodeInfo *nodes,
+                                 int nb_nodes, ram_addr_t size);
 
     HotplugHandler *(*get_hotplug_handler)(MachineState *machine,
                                            DeviceState *dev);

diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h
index f08d327aeca5ec14b9f139736fc101bc1b784795..7d8505730c168e1bb41089506d2c1feadfaa7580 100644 (file)
--- a/include/qemu/typedefs.h
+++ b/include/qemu/typedefs.h
@@ -97,5 +97,6 @@ typedef struct SSIBus SSIBus;
 typedef struct uWireSlave uWireSlave;
 typedef struct VirtIODevice VirtIODevice;
 typedef struct Visitor Visitor;
+typedef struct node_info NodeInfo;
 
 #endif /* QEMU_TYPEDEFS_H */

diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
index 0ea1bc086e30690b76925f6d71d8d073e85d12a6..70e56214e5a7f068c5773f8bce7e7f860849706c 100644 (file)
--- a/include/sysemu/numa.h
+++ b/include/sysemu/numa.h
@@ -16,14 +16,14 @@ struct numa_addr_range {
     QLIST_ENTRY(numa_addr_range) entry;
 };
 
-typedef struct node_info {
+struct node_info {
     uint64_t node_mem;
     unsigned long *node_cpu;
     struct HostMemoryBackend *node_memdev;
     bool present;
     QLIST_HEAD(, numa_addr_range) addr; /* List to store address ranges */
     uint8_t distance[MAX_NODES];
-} NodeInfo;
+};
 
 extern NodeInfo numa_info[MAX_NODES];
 void parse_numa_opts(MachineClass *mc);
@@ -33,6 +33,11 @@ extern QemuOptsList qemu_numa_opts;
 void numa_set_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node);
 void numa_unset_mem_node_id(ram_addr_t addr, uint64_t size, uint32_t node);
 uint32_t numa_get_node(ram_addr_t addr, Error **errp);
+void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
+                                 int nb_nodes, ram_addr_t size);
+void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
+                                  int nb_nodes, ram_addr_t size);
+
 
 /* on success returns node index in numa_info,
  * on failure returns nb_numa_nodes */

diff --git a/numa.c b/numa.c
index 2b3fc69915c638b57110aa189a99e7aedd76a5d8..d753687dec195487f3424cfc8b13b920c41c6273 100644 (file)
--- a/numa.c
+++ b/numa.c
@@ -407,6 +407,42 @@ static void complete_init_numa_distance(void)
     }
 }
 
+void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
+                                 int nb_nodes, ram_addr_t size)
+{
+    int i;
+    uint64_t usedmem = 0;
+
+    /* Align each node according to the alignment
+     * requirements of the machine class
+     */
+
+    for (i = 0; i < nb_nodes - 1; i++) {
+        nodes[i].node_mem = (size / nb_nodes) &
+                            ~((1 << mc->numa_mem_align_shift) - 1);
+        usedmem += nodes[i].node_mem;
+    }
+    nodes[i].node_mem = size - usedmem;
+}
+
+void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes,
+                                  int nb_nodes, ram_addr_t size)
+{
+    int i;
+    uint64_t usedmem = 0, node_mem;
+    uint64_t granularity = size / nb_nodes;
+    uint64_t propagate = 0;
+
+    for (i = 0; i < nb_nodes - 1; i++) {
+        node_mem = (granularity + propagate) &
+                   ~((1 << mc->numa_mem_align_shift) - 1);
+        propagate = granularity + propagate - node_mem;
+        nodes[i].node_mem = node_mem;
+        usedmem += node_mem;
+    }
+    nodes[i].node_mem = size - usedmem;
+}
+
 void parse_numa_opts(MachineClass *mc)
 {
     int i;
@@ -449,17 +485,8 @@ void parse_numa_opts(MachineClass *mc)
             }
         }
         if (i == nb_numa_nodes) {
-            uint64_t usedmem = 0;
-
-            /* Align each node according to the alignment
-             * requirements of the machine class
-             */
-            for (i = 0; i < nb_numa_nodes - 1; i++) {
-                numa_info[i].node_mem = (ram_size / nb_numa_nodes) &
-                                        ~((1 << mc->numa_mem_align_shift) - 1);
-                usedmem += numa_info[i].node_mem;
-            }
-            numa_info[i].node_mem = ram_size - usedmem;
+            assert(mc->numa_auto_assign_ram);
+            mc->numa_auto_assign_ram(mc, numa_info, nb_numa_nodes, ram_size);
         }
 
         numa_total = 0;