summaryrefslogtreecommitdiffstats
path: root/virt
diff options
context:
space:
mode:
authorRaghavendra K T <raghavendra.kt@linux.vnet.ibm.com>2013-01-22 13:09:24 +0530
committerGleb Natapov <gleb@redhat.com>2013-01-29 15:38:45 +0200
commitc45c528e899094b9049b3c900e2cf1f00aa0490c (patch)
treeee8562c37a74f74f9fbc30772a3bc4e7c69db8d6 /virt
parent7b270f609982f68f2433442bf167f735e7364b06 (diff)
downloadlinux-c45c528e899094b9049b3c900e2cf1f00aa0490c.tar.gz
linux-c45c528e899094b9049b3c900e2cf1f00aa0490c.tar.bz2
linux-c45c528e899094b9049b3c900e2cf1f00aa0490c.zip
kvm: Handle yield_to failure return code for potential undercommit case
yield_to returns -ESRCH, When source and target of yield_to run queue length is one. When we see three successive failures of yield_to we assume we are in potential undercommit case and abort from PLE handler. The assumption is backed by low probability of wrong decision for even worst case scenarios such as average runqueue length between 1 and 2. More detail on rationale behind using three tries: if p is the probability of finding rq length one on a particular cpu, and if we do n tries, then probability of exiting ple handler is: p^(n+1) [ because we would have come across one source with rq length 1 and n target cpu rqs with length 1 ] so num tries: probability of aborting ple handler (1.5x overcommit) 1 1/4 2 1/8 3 1/16 We can increase this probability with more tries, but the problem is the overhead. Also, If we have tried three times that means we would have iterated over 3 good eligible vcpus along with many non-eligible candidates. In worst case if we iterate all the vcpus, we reduce 1x performance and overcommit performance get hit. note that we do not update last boosted vcpu in failure cases. Thank Avi for raising question on aborting after first fail from yield_to. Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Tested-by: Chegu Vinod <chegu_vinod@hp.com> Signed-off-by: Gleb Natapov <gleb@redhat.com>
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/kvm_main.c26
1 files changed, 16 insertions, 10 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index abc23e27173d..a83ca63d26fc 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1694,6 +1694,7 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
{
struct pid *pid;
struct task_struct *task = NULL;
+ bool ret = false;
rcu_read_lock();
pid = rcu_dereference(target->pid);
@@ -1701,17 +1702,15 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
task = get_pid_task(target->pid, PIDTYPE_PID);
rcu_read_unlock();
if (!task)
- return false;
+ return ret;
if (task->flags & PF_VCPU) {
put_task_struct(task);
- return false;
- }
- if (yield_to(task, 1)) {
- put_task_struct(task);
- return true;
+ return ret;
}
+ ret = yield_to(task, 1);
put_task_struct(task);
- return false;
+
+ return ret;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
@@ -1752,12 +1751,14 @@ bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
return eligible;
}
#endif
+
void kvm_vcpu_on_spin(struct kvm_vcpu *me)
{
struct kvm *kvm = me->kvm;
struct kvm_vcpu *vcpu;
int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
int yielded = 0;
+ int try = 3;
int pass;
int i;
@@ -1769,7 +1770,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
* VCPU is holding the lock that we need and will release it.
* We approximate round-robin by starting at the last boosted VCPU.
*/
- for (pass = 0; pass < 2 && !yielded; pass++) {
+ for (pass = 0; pass < 2 && !yielded && try; pass++) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!pass && i <= last_boosted_vcpu) {
i = last_boosted_vcpu;
@@ -1782,10 +1783,15 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;
- if (kvm_vcpu_yield_to(vcpu)) {
+
+ yielded = kvm_vcpu_yield_to(vcpu);
+ if (yielded > 0) {
kvm->last_boosted_vcpu = i;
- yielded = 1;
break;
+ } else if (yielded < 0) {
+ try--;
+ if (!try)
+ break;
}
}
}