[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 25/29] numa: add '-numa cpu, ...' option for property
From: |
Eduardo Habkost |
Subject: |
[Qemu-devel] [PULL 25/29] numa: add '-numa cpu, ...' option for property based node mapping |
Date: |
Thu, 11 May 2017 16:18:39 -0300 |
From: Igor Mammedov <address@hidden>
legacy cpu to node mapping is using cpu index values to map
VCPU to node with help of '-numa node,nodeid=node,cpus=x[-y]'
option. However cpu index is internal concept and QEMU users
have to guess /reimplement qemu's logic/ to map it to
a concrete cpu socket/core/thread to make sane CPUs
placement across numa nodes.
This patch allows to map cpu objects to numa nodes using
the same properties as used for cpus with -device/device_add
(socket-id/core-id/thread-id/node-id).
At present valid properties/values to address CPUs could be
fetched using hotpluggable-cpus monitor/qmp command, it will
require user to start qemu twice when creating domain to fetch
possible CPUs for a machine type/-smp layout first and
then the second time with numa explicit mapping for actual
usage. The first step results could be saved and reused to
set/change mapping later as far as machine type/-smp stays
the same.
Proposed impl. supports exact and wildcard matching to
simplify CLI and allow to set mapping for a specific cpu
or group of cpu objects specified by matched properties.
For example:
# exact mapping x86
-numa cpu,node-id=x,socket-id=y,core-id=z,thread-id=n
# exact mapping SPAPR
-numa cpu,node-id=x,core-id=y
# wildcard mapping, all cpu objects that match socket-id=y
# are mapped to node-id=x
-numa cpu,node-id=x,socket-id=y
Signed-off-by: Igor Mammedov <address@hidden>
Message-Id: <address@hidden>
Reviewed-by: David Gibson <address@hidden>
Signed-off-by: Eduardo Habkost <address@hidden>
---
qapi-schema.json | 21 +++++++++++++++++++--
numa.c | 15 +++++++++++++++
qemu-options.hx | 20 ++++++++++++++++++++
3 files changed, 54 insertions(+), 2 deletions(-)
diff --git a/qapi-schema.json b/qapi-schema.json
index c3051fb901..80603cfc51 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -5690,10 +5690,12 @@
#
# @dist: NUMA distance configuration (since 2.10)
#
+# @cpu: property based CPU(s) to node mapping (Since: 2.10)
+#
# Since: 2.1
##
{ 'enum': 'NumaOptionsType',
- 'data': [ 'node', 'dist' ] }
+ 'data': [ 'node', 'dist', 'cpu' ] }
##
# @NumaOptions:
@@ -5707,7 +5709,8 @@
'discriminator': 'type',
'data': {
'node': 'NumaNodeOptions',
- 'dist': 'NumaDistOptions' }}
+ 'dist': 'NumaDistOptions',
+ 'cpu': 'NumaCpuOptions' }}
##
# @NumaNodeOptions:
@@ -5757,6 +5760,20 @@
'val': 'uint8' }}
##
+# @NumaCpuOptions:
+#
+# Option "-numa cpu" overrides default cpu to node mapping.
+# It accepts the same set of cpu properties as returned by
+# query-hotpluggable-cpus[].props, where node-id could be used to
+# override default node mapping.
+#
+# Since: 2.10
+##
+{ 'struct': 'NumaCpuOptions',
+ 'base': 'CpuInstanceProperties',
+ 'data' : {} }
+
+##
# @HostMemPolicy:
#
# Host memory policy types
diff --git a/numa.c b/numa.c
index ca122ccb13..84ce2af9b4 100644
--- a/numa.c
+++ b/numa.c
@@ -290,6 +290,21 @@ static int parse_numa(void *opaque, QemuOpts *opts, Error
**errp)
goto end;
}
break;
+ case NUMA_OPTIONS_TYPE_CPU:
+ if (!object->u.cpu.has_node_id) {
+ error_setg(&err, "Missing mandatory node-id property");
+ goto end;
+ }
+ if (!numa_info[object->u.cpu.node_id].present) {
+ error_setg(&err, "Invalid node-id=%" PRId64 ", NUMA node must be "
+ "defined with -numa node,nodeid=ID before it's used with "
+ "-numa cpu,node-id=ID", object->u.cpu.node_id);
+ goto end;
+ }
+
+ machine_set_cpu_numa_node(ms, qapi_NumaCpuOptions_base(&object->u.cpu),
+ &err);
+ break;
default:
abort();
}
diff --git a/qemu-options.hx b/qemu-options.hx
index e10c1454d1..6ffa98097d 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -145,10 +145,12 @@ STEXI
@item -numa node[,address@hidden,address@hidden@var{lastcpu}]][,address@hidden
@itemx -numa node[,address@hidden,address@hidden@var{lastcpu}]][,address@hidden
@itemx -numa dist,address@hidden,address@hidden,address@hidden
address@hidden -numa
cpu,address@hidden,address@hidden,address@hidden,address@hidden
@findex -numa
Define a NUMA node and assign RAM and VCPUs to it.
Set the NUMA distance from a source node to a destination node.
+Legacy VCPU assignment uses @samp{cpus} option where
@var{firstcpu} and @var{lastcpu} are CPU indexes. Each
@samp{cpus} option represent a contiguous range of CPU indexes
(or a single VCPU if @var{lastcpu} is omitted). A non-contiguous
@@ -162,6 +164,24 @@ a NUMA node:
-numa node,cpus=0-2,cpus=5
@end example
address@hidden option is a new alternative to @samp{cpus} option
+which uses @samp{socket-id|core-id|thread-id} properties to assign
+CPU objects to a @var{node} using topology layout properties of CPU.
+The set of properties is machine specific, and depends on used
+machine type/@samp{smp} options. It could be queried with
address@hidden monitor command.
address@hidden property specifies @var{node} to which CPU object
+will be assigned, it's required for @var{node} to be declared
+with @samp{node} option before it's used with @samp{cpu} option.
+
+For example:
address@hidden
+-M pc \
+-smp 1,sockets=2,maxcpus=2 \
+-numa node,nodeid=0 -numa node,nodeid=1 \
+-numa cpu,node-id=0,socket-id=0 -numa cpu,node-id=1,socket-id=1
address@hidden example
+
@samp{mem} assigns a given RAM amount to a node. @samp{memdev}
assigns RAM from a given memory backend device to a node. If
@samp{mem} and @samp{memdev} are omitted in all nodes, RAM is
--
2.11.0.259.g40922b1
- [Qemu-devel] [PULL 15/29] numa: do default mapping based on possible_cpus instead of node_cpu bitmaps, (continued)
- [Qemu-devel] [PULL 15/29] numa: do default mapping based on possible_cpus instead of node_cpu bitmaps, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 16/29] pc: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu(), Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 17/29] spapr: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu(), Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 18/29] virt-arm: get numa node mapping from possible_cpus instead of numa_get_node_for_cpu(), Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 19/29] QMP: include CpuInstanceProperties into query_cpus output output, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 20/29] tests: numa: add case for QMP command query-cpus, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 21/29] numa: remove no longer need numa_post_machine_init(), Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 22/29] machine: call machine init from wrapper, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 23/29] numa: use possible_cpus for not mapped CPUs check, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 24/29] numa: remove node_cpu bitmaps as they are no longer used, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 25/29] numa: add '-numa cpu, ...' option for property based node mapping,
Eduardo Habkost <=
- [Qemu-devel] [PULL 26/29] tests: check -numa node, cpu=props_list usecase, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 27/29] migration/i386: Remove old non-softfloat 64bit FP support, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 28/29] vmstatification: i386 FPReg, Eduardo Habkost, 2017/05/11
- [Qemu-devel] [PULL 29/29] migration/i386: Remove support for pre-0.12 formats, Eduardo Habkost, 2017/05/11
- Re: [Qemu-devel] [PULL 00/29] x86 and machine queue, 2017-05-11, Stefan Hajnoczi, 2017/05/15