As you know, QEMU can't direct it's memory allocation now, this may cause
guest cross node access performance regression.
And, the worse thing is that if PCI-passthrough is used,
direct-attached-device uses DMA transfer between device and qemu process.
All pages of the guest will be pinned by get_user_pages().
KVM_ASSIGN_PCI_DEVICE ioctl
kvm_vm_ioctl_assign_device()
=>kvm_assign_device()
=> kvm_iommu_map_memslots()
=> kvm_iommu_map_pages()
=> kvm_pin_pages()
So, with direct-attached-device, all guest page's page count will be +1 and
any page migration will not work. AutoNUMA won't too.
So, we should set the guest nodes memory allocation policy before
the pages are really mapped.
According to this patch set, we are able to set guest nodes memory policy
like following:
-numa node,nodeid=0,cpus=0, \
-numa mem,size=1024M,policy=membind,host-nodes=0-1 \
-numa node,nodeid=1,cpus=1 \
-numa mem,size=1024M,policy=interleave,host-nodes=1
This supports "policy={membind|interleave|preferred},host-nodes=[+|!]{all|N-N}"
like format.
And patch 9/12 adds a QMP command "set-mem-policy" to set the memory policy
for every guest nodes:
set-mem-policy nodeid=0 policy=membind host-nodes=0-1
And patch 10/12 adds a monitor command "set-mem-policy" whose format like:
set-mem-policy 0 policy=membind,host-nodes=0-1
And patch 11/12 adds a QMP command "query-numa" to show numa info through
this API.
And patch 12/12 converts the "info numa" monitor command to use this
QMP command "query-numa".
V1->V2:
change to use QemuOpts in numa options (Paolo)
handle Error in mpol parser (Paolo)
change qmp command format to mem-policy=membind,mem-hostnode=0-1 like
(Paolo)
V2->V3:
also handle Error in cpus parser (5/10)
split out common parser from cpus and hostnode parser (Bandan 6/10)
V3-V4:
rebase to request for comments
V4->V5:
use OptVisitor and split -numa option (Paolo)
- s/set-mpol/set-mem-policy (Andreas)
- s/mem-policy/policy
- s/mem-hostnode/host-nodes
fix hmp command process after error (Luiz)
add qmp command query-numa and convert info numa to it (Luiz)
Wanlong Gao (12):
NUMA: add NumaOptions, NumaNodeOptions and NumaMemOptions
NUMA: split -numa option
NUMA: move numa related code to numa.c
NUMA: Add numa_info structure to contain numa nodes info
NUMA: Add Linux libnuma detection
NUMA: parse guest numa nodes memory policy
NUMA: split out the common range parser
NUMA: set guest numa nodes memory policy
NUMA: add qmp command set-mem-policy to set memory policy for NUMA
node
NUMA: add hmp command set-mem-policy
NUMA: add qmp command query-numa
NUMA: convert hmp command info_numa to use qmp command query_numa
Makefile.target | 2 +-
configure | 32 +++
cpus.c | 14 --
hmp-commands.hx | 16 ++
hmp.c | 70 +++++++
hmp.h | 2 +
hw/i386/pc.c | 4 +-
hw/net/eepro100.c | 1 -
include/sysemu/cpus.h | 1 -
include/sysemu/sysemu.h | 20 +-
monitor.c | 21 +-
numa.c | 513 ++++++++++++++++++++++++++++++++++++++++++++++++
qapi-schema.json | 103 ++++++++++
qemu-options.hx | 6 +-
qmp-commands.hx | 84 ++++++++
vl.c | 157 ++-------------
16 files changed, 861 insertions(+), 185 deletions(-)
create mode 100644 numa.c
--
1.8.3.2.634.g7a3187e
