@@ -668,31 +668,43 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
return 0;
}
-static int cmp_memslot(const void *slot1, const void *slot2)
+static void swap_memslot(struct kvm_memory_slot *s1, struct kvm_memory_slot *s2)
{
- struct kvm_memory_slot *s1, *s2;
+ struct kvm_memory_slot tmp;
- s1 = (struct kvm_memory_slot *)slot1;
- s2 = (struct kvm_memory_slot *)slot2;
-
- if (s1->npages < s2->npages)
- return 1;
- if (s1->npages > s2->npages)
- return -1;
-
- return 0;
+ tmp = *s2;
+ *s2 = *s1;
+ *s1 = tmp;
}
/*
- * Sort the memslots base on its size, so the larger slots
- * will get better fit.
+ * Insert memslot and re-sort memslots based on their size,
+ * so the larger slots will get better fit. Sorting algorithm
+ * takes advantage of having initially sorted array and
+ * known changed memslot position.
*/
-static void sort_memslots(struct kvm_memslots *slots)
+static void insert_memslot(struct kvm_memslots *slots,
+ struct kvm_memory_slot *new)
{
- int i;
+ int i = slots->id_to_index[new->id];
+ struct kvm_memory_slot *old = id_to_memslot(slots, new->id);
+ struct kvm_memory_slot *mslots = slots->memslots;
- sort(slots->memslots, KVM_MEM_SLOTS_NUM,
- sizeof(struct kvm_memory_slot), cmp_memslot, NULL);
+ if (new->npages == old->npages)
+ return;
+
+ *old = *new;
+ while (1) {
+ if (i < (KVM_MEM_SLOTS_NUM - 1) &&
+ mslots[i].npages < mslots[i + 1].npages) {
+ swap_memslot(&mslots[i], &mslots[i + 1]);
+ i++;
+ } else if (i > 0 && mslots[i].npages > mslots[i - 1].npages) {
+ swap_memslot(&mslots[i], &mslots[i - 1]);
+ i--;
+ } else
+ break;
+ }
for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
slots->id_to_index[slots->memslots[i].id] = i;
@@ -702,13 +714,7 @@ static void update_memslots(struct kvm_memslots *slots,
struct kvm_memory_slot *new)
{
if (new) {
- int id = new->id;
- struct kvm_memory_slot *old = id_to_memslot(slots, id);
- unsigned long npages = old->npages;
-
- *old = *new;
- if (new->npages != npages)
- sort_memslots(slots);
+ insert_memslot(slots, new);
}
}
memslots is a sorted array, when slot changes in it with current heapsort it would take O(n log n) time to update array, while using insertion sort like algorithm on array with 1 item out of order will take only O(n) time. Replace current heapsort with custom sort that takes advantage of memslots usage pattern and known position of changed slot. performance change of 128 memslots insersions with gradually increasing size (the worst case): heap sort custom sort max: 249747 15654 cycles min: 52536 5562 cycles with custom sort alg taking 90% less then original update time. Signed-off-by: Igor Mammedov <imammedo@redhat.com> --- virt/kvm/kvm_main.c | 54 +++++++++++++++++++++++++++++------------------------ 1 file changed, 30 insertions(+), 24 deletions(-)