summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2011-02-01 09:53:28 -0500
committerMarcelo Tosatti <mtosatti@redhat.com>2011-03-17 13:08:29 -0300
commit217ece6129f2d3b4fdd18d9e79be9e43d8d14a42 (patch)
treeb2bbd81042f48e862e0c0b8743edc932102640bb /include
parent34bb10b79de7df118de832f6832efb630e646577 (diff)
downloadlinux-3.10-217ece6129f2d3b4fdd18d9e79be9e43d8d14a42.tar.gz
linux-3.10-217ece6129f2d3b4fdd18d9e79be9e43d8d14a42.tar.bz2
linux-3.10-217ece6129f2d3b4fdd18d9e79be9e43d8d14a42.zip
KVM: use yield_to instead of sleep in kvm_vcpu_on_spin
Instead of sleeping in kvm_vcpu_on_spin, which can cause gigantic slowdowns of certain workloads, we instead use yield_to to get another VCPU in the same KVM guest to run sooner. This seems to give a 10-15% speedup in certain workloads. Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
Diffstat (limited to 'include')
-rw-r--r--include/linux/kvm_host.h1
1 files changed, 1 insertions, 0 deletions
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4721b11b922..3751ea0d1f9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -235,6 +235,7 @@ struct kvm {
#endif
struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
atomic_t online_vcpus;
+ int last_boosted_vcpu;
struct list_head vm_list;
struct mutex lock;
struct kvm_io_bus *buses[KVM_NR_BUSES];