There is a downside of halt_poll_ns since poll is still happen for idle
VCPU which can waste cpu usage. This patchset add the ability to adjust
halt_poll_ns dynamically, grows halt_poll_ns if an interrupt arrives and
shrinks halt_poll_ns when idle VCPU is detected.
There are two new kernel parameters for changing the halt_poll_ns:
halt_poll_ns_grow and halt_poll_ns_shrink.
Test w/ high cpu overcommit ratio, pin vCPUs, and the halt_poll_ns of
halt-poll is the default 500000ns, the max halt_poll_ns of dynamic
halt-poll is 2ms. Then watch the %C0 in the dump of Powertop tool.
The test method is almost from David.
+-----------------+----------------+-------------------+
| | | |
| w/o halt-poll | w/ halt-poll | dynamic halt-poll |
+-----------------+----------------+-------------------+
| | | |
| ~0.9% | ~1.8% | ~1.2% |
+-----------------+----------------+-------------------+
The always halt-poll will increase ~0.9% cpu usage for idle vCPUs and the
dynamic halt-poll drop it to ~0.3% which means that reduce the 67% overhead
introduced by always halt-poll.
Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
---
virt/kvm/kvm_main.c | 41 ++++++++++++++++++++++++++++++++++++++++-
1 file changed, 40 insertions(+), 1 deletion(-)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c06e57c..d63790d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -66,9 +66,18 @@
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
-static unsigned int halt_poll_ns;
+/* halt polling only reduces halt latency by 5-7 us, 2ms is enough */
+static unsigned int halt_poll_ns = 2000000;
module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR);
+/* Default doubles per-vcpu halt_poll_ns. */
+static unsigned int halt_poll_ns_grow = 2;
+module_param(halt_poll_ns_grow, int, S_IRUGO);
+
+/* Default resets per-vcpu halt_poll_ns . */
+static unsigned int halt_poll_ns_shrink;
+module_param(halt_poll_ns_shrink, int, S_IRUGO);
+
/*
* Ordering of locks:
*
@@ -1907,6 +1916,31 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
+static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
+{
+ int val = vcpu->halt_poll_ns;
+
+ /* 500us step */
+ if (val == 0 && halt_poll_ns_grow)
+ val = 500000;
+ else
+ val *= halt_poll_ns_grow;
+
+ vcpu->halt_poll_ns = val;
+}
+
+static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
+{
+ int val = vcpu->halt_poll_ns;
+
+ if (halt_poll_ns_shrink == 0)
+ val = 0;
+ else
+ val /= halt_poll_ns_shrink;
+
+ vcpu->halt_poll_ns = val;
+}
+
static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu)
{
if (kvm_arch_vcpu_runnable(vcpu)) {
@@ -1961,6 +1995,11 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
cur = ktime_get();
out:
+ if (waited && vcpu->halt_poll_ns > 0)
+ shrink_halt_poll_ns(vcpu);
+ else if (vcpu->halt_poll_ns < halt_poll_ns)
+ grow_halt_poll_ns(vcpu);
+
trace_kvm_vcpu_wakeup(ktime_to_ns(cur) - ktime_to_ns(start), waited);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_block);
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
