From: root <root@xxxxxxxxxxx>
Changes since v1:
----------------
- Use bitmap functions that are already in qemu (instead
of cpu_set_t macro's)
- Added a check for endvalue >= max_cpus.
- Fix to address the round-robbing assignment (for the case
when cpu's are not explicitly specified)
Note: Continuing to use a new constant for
allocation of the cpumask (max_cpus was
not getting set early enough).
-----------------------------------------------
v1:
--
The -numa option to qemu is used to create [fake] numa nodes
and expose them to the guest OS instance.
There are a couple of issues with the -numa option:
a) Max VCPU's that can be specified for a guest while using
the qemu's -numa option is 64. Due to a typecasting issue
when the number of VCPUs is > 32 the VCPUs don't show up
under the specified [fake] numa nodes.
b) KVM currently has support for 160VCPUs per guest. The
qemu's -numa option has only support for upto 64VCPUs
per guest.
This patch addresses these two issues.
Below are examples of (a) and (b)
a) >32 VCPUs are specified with the -numa option:
/usr/local/bin/qemu-system-x86_64 \
-enable-kvm \
71:01:01 \
-net tap,ifname=tap0,script=no,downscript=no \
-vnc :4
...
Upstream qemu :
--------------
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
6 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9 32 33 34 35 36 37 38 39 40 41
node 0 size: 131072 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19 42 43 44 45 46 47 48 49 50 51
node 1 size: 131072 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29 52 53 54 55 56 57 58 59
node 2 size: 131072 MB
node 3 cpus: 30
node 3 size: 131072 MB
node 4 cpus:
node 4 size: 131072 MB
node 5 cpus: 31
node 5 size: 131072 MB
With the patch applied :
-----------------------
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
6 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9
node 0 size: 131072 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19
node 1 size: 131072 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29
node 2 size: 131072 MB
node 3 cpus: 30 31 32 33 34 35 36 37 38 39
node 3 size: 131072 MB
node 4 cpus: 40 41 42 43 44 45 46 47 48 49
node 4 size: 131072 MB
node 5 cpus: 50 51 52 53 54 55 56 57 58 59
node 5 size: 131072 MB
b) >64 VCPUs specified with -numa option:
/usr/local/bin/qemu-system-x86_64 \
-enable-kvm \
-cpu Westmere,+rdtscp,+pdpe1gb,+dca,+pdcm,+xtpr,+tm2,+est,+smx,+vmx,+ds_cpl,+monitor,+dtes64,+pclmuldq,+pbe,+tm,+ht,+ss,+acpi,+ds,+vme \
-smp sockets=8,cores=10,threads=1 \
-numa node,nodeid=0,cpus=0-9,mem=64g \
-numa node,nodeid=1,cpus=10-19,mem=64g \
-numa node,nodeid=2,cpus=20-29,mem=64g \
-numa node,nodeid=3,cpus=30-39,mem=64g \
-numa node,nodeid=4,cpus=40-49,mem=64g \
-numa node,nodeid=5,cpus=50-59,mem=64g \
-numa node,nodeid=6,cpus=60-69,mem=64g \
-numa node,nodeid=7,cpus=70-79,mem=64g \
-m 524288 \
-name vm1 \
-chardev socket,id=charmonitor,path=/var/lib/libvirt/qemu/vm1.monitor,server,nowait \
-drive file=/dev/libvirt_lvm/vm.img,if=none,id=drive-virtio-disk0,format=raw,cache=none,aio=native \
-device virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,id=virtio-disk0,bootindex=1 \
-monitor stdio \
-net nic,macaddr=52:54:00:71:01:01 \
-net tap,ifname=tap0,script=no,downscript=no \
-vnc :4
...
Upstream qemu :
--------------
only 63 CPUs in NUMA mode supported.
only 64 CPUs in NUMA mode supported.
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
8 nodes
node 0 cpus: 6 7 8 9 38 39 40 41 70 71 72 73
node 0 size: 65536 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19 42 43 44 45 46 47 48 49 50 51 74 75 76 77 78 79
node 1 size: 65536 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29 52 53 54 55 56 57 58 59 60 61
node 2 size: 65536 MB
node 3 cpus: 30 62
node 3 size: 65536 MB
node 4 cpus:
node 4 size: 65536 MB
node 5 cpus:
node 5 size: 65536 MB
node 6 cpus: 31 63
node 6 size: 65536 MB
node 7 cpus: 0 1 2 3 4 5 32 33 34 35 36 37 64 65 66 67 68 69
node 7 size: 65536 MB
With the patch applied :
-----------------------
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
8 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9
node 0 size: 65536 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19
node 1 size: 65536 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29
node 2 size: 65536 MB
node 3 cpus: 30 31 32 33 34 35 36 37 38 39
node 3 size: 65536 MB
node 4 cpus: 40 41 42 43 44 45 46 47 48 49
node 4 size: 65536 MB
node 5 cpus: 50 51 52 53 54 55 56 57 58 59
node 5 size: 65536 MB
node 6 cpus: 60 61 62 63 64 65 66 67 68 69
node 6 size: 65536 MB
node 7 cpus: 70 71 72 73 74 75 76 77 78 79
Signed-off-by: Chegu Vinod <chegu_vinod@xxxxxx>, Jim Hull <jim.hull@xxxxxx>, Craig Hada <craig.hada@xxxxxx>
---
cpus.c | 3 ++-
hw/pc.c | 4 +++-
sysemu.h | 3 ++-
vl.c | 48 ++++++++++++++++++++++++++----------------------
4 files changed, 33 insertions(+), 25 deletions(-)
diff --git a/cpus.c b/cpus.c
index b182b3d..89ce04d 100644
--- a/cpus.c
+++ b/cpus.c
@@ -36,6 +36,7 @@
#include "cpus.h"
#include "qtest.h"
#include "main-loop.h"
+#include "bitmap.h"
#ifndef _WIN32
#include "compatfd.h"
@@ -1145,7 +1146,7 @@ void set_numa_modes(void)
for (env = first_cpu; env != NULL; env = env->next_cpu) {
for (i = 0; i < nb_numa_nodes; i++) {
- if (node_cpumask[i] & (1 << env->cpu_index)) {
+ if (test_bit(env->cpu_index, node_cpumask[i])) {
env->numa_node = i;
}
}
diff --git a/hw/pc.c b/hw/pc.c
index c7e9ab3..8800fc0 100644
--- a/hw/pc.c
+++ b/hw/pc.c
@@ -48,6 +48,7 @@
#include "memory.h"
#include "exec-memory.h"
#include "arch_init.h"
+#include "bitmap.h"
/* output Bochs bios info messages */
//#define DEBUG_BIOS
@@ -637,9 +638,10 @@ static void *bochs_bios_init(void)
*/
numa_fw_cfg = g_malloc0((1 + max_cpus + nb_numa_nodes) * 8);
numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
+
for (i = 0; i < max_cpus; i++) {
for (j = 0; j < nb_numa_nodes; j++) {
- if (node_cpumask[j] & (1 << i)) {
+ if (test_bit(i, node_cpumask[j])) {
numa_fw_cfg[i + 1] = cpu_to_le64(j);
break;
}
diff --git a/sysemu.h b/sysemu.h
index bc2c788..6813115 100644
--- a/sysemu.h
+++ b/sysemu.h
@@ -133,9 +133,10 @@ extern uint8_t qemu_extra_params_fw[2];
extern QEMUClock *rtc_clock;
#define MAX_NODES 64
+#define MAX_CPUMASK_BITS 254
extern int nb_numa_nodes;
extern uint64_t node_mem[MAX_NODES];
-extern uint64_t node_cpumask[MAX_NODES];
+extern uint64_t *node_cpumask[MAX_NODES];
#define MAX_OPTION_ROMS 16
typedef struct QEMUOptionRom {
diff --git a/vl.c b/vl.c
index 1329c30..dd4ba75 100644
--- a/vl.c
+++ b/vl.c
@@ -28,6 +28,7 @@
#include <errno.h>
#include <sys/time.h>
#include <zlib.h>
+#include "bitmap.h"
/* Needed early for CONFIG_BSD etc. */
#include "config-host.h"
@@ -240,7 +241,7 @@ QTAILQ_HEAD(, FWBootEntry) fw_boot_order = QTAILQ_HEAD_INITIALIZER(fw_boot_order
int nb_numa_nodes;
uint64_t node_mem[MAX_NODES];
-uint64_t node_cpumask[MAX_NODES];
+uint64_t *node_cpumask[MAX_NODES];
uint8_t qemu_uuid[16];
@@ -950,6 +951,9 @@ static void numa_add(const char *optarg)
char *endptr;
unsigned long long value, endvalue;
int nodenr;
+ int i;
+
+ value = endvalue = 0;
optarg = get_opt_name(option, 128, optarg, ',') + 1;
if (!strcmp(option, "node")) {
@@ -970,27 +974,24 @@ static void numa_add(const char *optarg)
}
node_mem[nodenr] = sval;
}
- if (get_param_value(option, 128, "cpus", optarg) == 0) {
- node_cpumask[nodenr] = 0;
- } else {
+ if (get_param_value(option, 128, "cpus", optarg) != 0) {
value = strtoull(option, &endptr, 10);
- if (value >= 64) {
- value = 63;
- fprintf(stderr, "only 64 CPUs in NUMA mode supported.\n");
+ if (*endptr == '-') {
+ endvalue = strtoull(endptr+1, &endptr, 10);
} else {
- if (*endptr == '-') {
- endvalue = strtoull(endptr+1, &endptr, 10);
- if (endvalue >= 63) {
- endvalue = 62;
- fprintf(stderr,
- "only 63 CPUs in NUMA mode supported.\n");
- }
- value = (2ULL << endvalue) - (1ULL << value);
- } else {
- value = 1ULL << value;
- }
+ endvalue = value;
+ }
+
+ if (endvalue >= max_cpus) {
+ endvalue = max_cpus - 1;
+ fprintf(stderr,
+ "A max of %d CPUs are supported in a guest on this host\n",
+ max_cpus);
+ }
+
+ for (i = value; i <= endvalue; ++i) {
+ set_bit(i, node_cpumask[nodenr]);
}
- node_cpumask[nodenr] = value;
}
nb_numa_nodes++;
}
@@ -2331,7 +2332,8 @@ int main(int argc, char **argv, char **envp)
for (i = 0; i < MAX_NODES; i++) {
node_mem[i] = 0;
- node_cpumask[i] = 0;
+ node_cpumask[i] = (unsigned long *) g_malloc0(MAX_CPUMASK_BITS);
+ bitmap_zero(node_cpumask[i], MAX_CPUMASK_BITS);
}
nb_numa_nodes = 0;
@@ -3469,16 +3471,18 @@ int main(int argc, char **argv, char **envp)
}
for (i = 0; i < nb_numa_nodes; i++) {
- if (node_cpumask[i] != 0)
+ if (!bitmap_empty(node_cpumask[i], MAX_CPUMASK_BITS)) {
break;
+ }
}
+
/* assigning the VCPUs round-robin is easier to implement, guest OSes
* must cope with this anyway, because there are BIOSes out there in
* real machines which also use this scheme.
*/
if (i == nb_numa_nodes) {
for (i = 0; i < max_cpus; i++) {
- node_cpumask[i % nb_numa_nodes] |= 1 << i;
+ set_bit(i, node_cpumask[i % nb_numa_nodes]);
}
}
}
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
