Igor Mammedov 57924bcd87 numa: introduce machine callback for VCPU to node mapping
Current default round-robin way of distributing VCPUs among
NUMA nodes might be wrong in case on multi-core/threads
CPUs. Making guests confused wrt topology where cores from
the same socket are on different nodes.

Allow a machine to override default mapping by providing
 MachineClass::cpu_index_to_socket_id()
callback which would allow it group VCPUs from a socket
on the same NUMA node.

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
2015-03-19 16:12:09 -03:00
2015-03-19 17:47:08 +00:00
2015-03-19 11:30:37 +03:00
2015-03-19 11:39:18 +03:00
2015-03-19 11:11:55 +03:00
2015-03-09 09:14:28 +00:00
2015-03-19 11:30:37 +03:00
2015-03-19 17:47:08 +00:00
2015-03-16 12:10:30 -04:00
2015-03-08 06:43:32 +00:00
2015-03-19 11:17:27 +03:00
2015-03-18 12:07:34 +01:00
2015-03-19 11:35:52 +03:00
2015-03-17 17:11:33 +00:00
2015-03-17 14:31:15 +01:00
2015-03-12 09:13:07 +00:00
2015-03-19 14:10:20 +00:00
2015-03-19 17:47:08 +00:00
2015-03-19 17:47:08 +00:00
2015-03-10 11:33:35 +01:00
2015-03-10 09:26:22 +01:00
2015-03-17 18:58:33 +00:00

Read the documentation in qemu-doc.html or on http://wiki.qemu-project.org

- QEMU team
Description
No description provided
Readme 404 MiB
Languages
C 82.6%
C++ 6.5%
Python 3.4%
Dylan 2.9%
Shell 1.6%
Other 2.8%