machine: Prefer cores over sockets in smp parsing since 6.2

In the real SMP hardware topology world, it's much more likely that
we have high cores-per-socket counts and few sockets totally. While
the current preference of sockets over cores in smp parsing results
in a virtual cpu topology with low cores-per-sockets counts and a
large number of sockets, which is just contrary to the real world.

Given that it is better to make the virtual cpu topology be more
reflective of the real world and also for the sake of compatibility,
we start to prefer cores over sockets over threads in smp parsing
since machine type 6.2 for different arches.

In this patch, a boolean "smp_prefer_sockets" is added, and we only
enable the old preference on older machines and enable the new one
since type 6.2 for all arches by using the machine compat mechanism.

Suggested-by: Daniel P. Berrange <berrange@redhat.com>
Signed-off-by: Yanan Wang <wangyanan55@huawei.com>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20210929025816.21076-10-wangyanan55@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/hw/arm/virt.c b/hw/arm/virt.c
index 1d59f0e59f7218afd97439a136e8b14667c93138..8c13deb5dbcdd49da3b43e5021f7f9f4d4755ba2 100644 (file)
--- a/hw/arm/virt.c
+++ b/hw/arm/virt.c
@@ -2815,6 +2815,7 @@ static void virt_machine_6_1_options(MachineClass *mc)
 
     virt_machine_6_2_options(mc);
     compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len);
+    mc->smp_prefer_sockets = true;
 
     /* qemu ITS was introduced with 6.2 */
     vmc->no_tcg_its = true;

diff --git a/hw/core/machine.c b/hw/core/machine.c
index e38ab760e62232cbfc83c05590f2a50ae820e57b..f2a34d98c06d18516b859a360a7efa7ba19cc002 100644 (file)
--- a/hw/core/machine.c
+++ b/hw/core/machine.c
@@ -748,6 +748,7 @@ void machine_set_cpu_numa_node(MachineState *machine,
 
 static void smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp)
 {
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
     unsigned cpus    = config->has_cpus ? config->cpus : 0;
     unsigned sockets = config->has_sockets ? config->sockets : 0;
     unsigned cores   = config->has_cores ? config->cores : 0;
@@ -759,7 +760,7 @@ static void smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp)
         return;
     }
 
-    /* compute missing values, prefer sockets over cores over threads */
+    /* compute missing values based on the provided ones */
     if (cpus == 0 && maxcpus == 0) {
         sockets = sockets > 0 ? sockets : 1;
         cores = cores > 0 ? cores : 1;
@@ -767,14 +768,30 @@ static void smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp)
     } else {
         maxcpus = maxcpus > 0 ? maxcpus : cpus;
 
-        if (sockets == 0) {
-            cores = cores > 0 ? cores : 1;
-            threads = threads > 0 ? threads : 1;
-            sockets = maxcpus / (cores * threads);
-        } else if (cores == 0) {
-            threads = threads > 0 ? threads : 1;
-            cores = maxcpus / (sockets * threads);
-        } else if (threads == 0) {
+        if (mc->smp_prefer_sockets) {
+            /* prefer sockets over cores before 6.2 */
+            if (sockets == 0) {
+                cores = cores > 0 ? cores : 1;
+                threads = threads > 0 ? threads : 1;
+                sockets = maxcpus / (cores * threads);
+            } else if (cores == 0) {
+                threads = threads > 0 ? threads : 1;
+                cores = maxcpus / (sockets * threads);
+            }
+        } else {
+            /* prefer cores over sockets since 6.2 */
+            if (cores == 0) {
+                sockets = sockets > 0 ? sockets : 1;
+                threads = threads > 0 ? threads : 1;
+                cores = maxcpus / (sockets * threads);
+            } else if (sockets == 0) {
+                threads = threads > 0 ? threads : 1;
+                sockets = maxcpus / (cores * threads);
+            }
+        }
+
+        /* try to calculate omitted threads at last */
+        if (threads == 0) {
             threads = maxcpus / (sockets * cores);
         }
     }

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 9216ad163d5dd2ff62cc0891aab01581281caf22..6cc32f4048f0a8b87ca0d12237ec9417d57048ab 100644 (file)
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -716,6 +716,7 @@ void pc_acpi_smi_interrupt(void *opaque, int irq, int level)
  */
 static void pc_smp_parse(MachineState *ms, SMPConfiguration *config, Error **errp)
 {
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
     unsigned cpus    = config->has_cpus ? config->cpus : 0;
     unsigned sockets = config->has_sockets ? config->sockets : 0;
     unsigned dies    = config->has_dies ? config->dies : 0;
@@ -726,7 +727,7 @@ static void pc_smp_parse(MachineState *ms, SMPConfiguration *config, Error **err
     /* directly default dies to 1 if it's omitted */
     dies = dies > 0 ? dies : 1;
 
-    /* compute missing values, prefer sockets over cores over threads */
+    /* compute missing values based on the provided ones */
     if (cpus == 0 && maxcpus == 0) {
         sockets = sockets > 0 ? sockets : 1;
         cores = cores > 0 ? cores : 1;
@@ -734,14 +735,30 @@ static void pc_smp_parse(MachineState *ms, SMPConfiguration *config, Error **err
     } else {
         maxcpus = maxcpus > 0 ? maxcpus : cpus;
 
-        if (sockets == 0) {
-            cores = cores > 0 ? cores : 1;
-            threads = threads > 0 ? threads : 1;
-            sockets = maxcpus / (dies * cores * threads);
-        } else if (cores == 0) {
-            threads = threads > 0 ? threads : 1;
-            cores = maxcpus / (sockets * dies * threads);
-        } else if (threads == 0) {
+        if (mc->smp_prefer_sockets) {
+            /* prefer sockets over cores before 6.2 */
+            if (sockets == 0) {
+                cores = cores > 0 ? cores : 1;
+                threads = threads > 0 ? threads : 1;
+                sockets = maxcpus / (dies * cores * threads);
+            } else if (cores == 0) {
+                threads = threads > 0 ? threads : 1;
+                cores = maxcpus / (sockets * dies * threads);
+            }
+        } else {
+            /* prefer cores over sockets since 6.2 */
+            if (cores == 0) {
+                sockets = sockets > 0 ? sockets : 1;
+                threads = threads > 0 ? threads : 1;
+                cores = maxcpus / (sockets * dies * threads);
+            } else if (sockets == 0) {
+                threads = threads > 0 ? threads : 1;
+                sockets = maxcpus / (dies * cores * threads);
+            }
+        }
+
+        /* try to calculate omitted threads at last */
+        if (threads == 0) {
             threads = maxcpus / (sockets * dies * cores);
         }
     }

diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 6cc834aff61a2e9ef76e6ef8f963cc6431d00575..932e6e2cfe41a597163ddfece97b48080691f35f 100644 (file)
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -432,6 +432,7 @@ static void pc_i440fx_6_1_machine_options(MachineClass *m)
     m->is_default = false;
     compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len);
     compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len);
+    m->smp_prefer_sockets = true;
 }
 
 DEFINE_I440FX_MACHINE(v6_1, "pc-i440fx-6.1", NULL,

diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index 5481d5c9651ce00d1d9202991860a7a3332c304b..57ab07e5b7223d3c6a6f26ee425a1a62b8763948 100644 (file)
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -372,6 +372,7 @@ static void pc_q35_6_1_machine_options(MachineClass *m)
     m->alias = NULL;
     compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len);
     compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len);
+    m->smp_prefer_sockets = true;
 }
 
 DEFINE_Q35_MACHINE(v6_1, "pc-q35-6.1", NULL,

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index b7bee5f4ffb02ce4a118972673a9af92876593e6..2986108b5a22bcc89db5756a2c5e0294ff9121ae 100644 (file)
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -4685,6 +4685,7 @@ static void spapr_machine_6_1_class_options(MachineClass *mc)
     spapr_machine_6_2_class_options(mc);
     compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len);
     smc->pre_6_2_numa_affinity = true;
+    mc->smp_prefer_sockets = true;
 }
 
 DEFINE_SPAPR_MACHINE(6_1, "6.1", false);

diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c
index 61aeccb163f79befa3f75d6847dbf27918b9cf3a..5401c985cf8a500006ea69e01359bd7a8abf5b60 100644 (file)
--- a/hw/s390x/s390-virtio-ccw.c
+++ b/hw/s390x/s390-virtio-ccw.c
@@ -814,6 +814,7 @@ static void ccw_machine_6_1_class_options(MachineClass *mc)
 {
     ccw_machine_6_2_class_options(mc);
     compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len);
+    mc->smp_prefer_sockets = true;
 }
 DEFINE_CCW_MACHINE(6_1, "6.1", false);
 

diff --git a/include/hw/boards.h b/include/hw/boards.h
index 463a5514f97d8fd53eecbbb10b500039e080978a..2ae039b74fca4f6721fc27fe2967fcaa4e98c233 100644 (file)
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -247,6 +247,7 @@ struct MachineClass {
     bool nvdimm_supported;
     bool numa_mem_supported;
     bool auto_enable_numa;
+    bool smp_prefer_sockets;
     const char *default_ram_id;
 
     HotplugHandler *(*get_hotplug_handler)(MachineState *machine,

diff --git a/qemu-options.hx b/qemu-options.hx
index 2eac830fdb6867ceb17465f3a87a1c0de103c73d..8ef178180db6f2d7f5ec405ffd0735e7ec7eea3b 100644 (file)
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -244,7 +244,8 @@ SRST
     Historically preference was given to the coarsest topology parameters
     when computing missing values (ie sockets preferred over cores, which
     were preferred over threads), however, this behaviour is considered
-    liable to change.
+    liable to change. Prior to 6.2 the preference was sockets over cores
+    over threads. Since 6.2 the preference is cores over sockets over threads.
 ERST
 
 DEF("numa", HAS_ARG, QEMU_OPTION_numa,