@@ -279,7 +279,7 @@ static void run_iteration(struct kvm_vm *vm, int nr_vcpus, const char *descripti
static void access_memory(struct kvm_vm *vm, int nr_vcpus,
enum access_type access, const char *description)
{
- perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
+ perf_test_set_write_percent(vm, (access == ACCESS_READ) ? 0 : 100);
iteration_work = ITERATION_ACCESS_MEMORY;
run_iteration(vm, nr_vcpus, description);
}
@@ -128,10 +128,10 @@ static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
struct test_params {
unsigned long iterations;
uint64_t phys_offset;
- int wr_fract;
bool partition_vcpu_memory_access;
enum vm_mem_backing_src_type backing_src;
int slots;
+ uint32_t write_percent;
uint32_t random_seed;
};
@@ -229,7 +229,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
/* If no argument provided, random seed will be 1. */
pr_info("Random seed: %u\n", p->random_seed);
perf_test_set_random_seed(vm, p->random_seed ? p->random_seed : 1);
- perf_test_set_wr_fract(vm, p->wr_fract);
+ perf_test_set_write_percent(vm, p->write_percent);
guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm->page_shift;
guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -252,6 +252,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
for (i = 0; i < nr_vcpus; i++)
vcpu_last_completed_iteration[i] = -1;
+ /*
+ * Use 100% writes during the population phase to ensure all
+ * memory is actually populated and not just mapped to the zero
+ * page. The prevents expensive copy-on-write faults from
+ * occurring during the dirty memory iterations below, which
+ * would pollute the performance results.
+ */
+ perf_test_set_write_percent(vm, 100);
perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
/* Allow the vCPUs to populate memory */
@@ -273,6 +281,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
+ perf_test_set_write_percent(vm, p->write_percent);
+
while (iteration < p->iterations) {
/*
* Incrementing the iteration number will start the vCPUs
@@ -357,7 +367,7 @@ static void help(char *name)
puts("");
printf("usage: %s [-h] [-i iterations] [-p offset] [-g] "
"[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-r random seed ] [-s mem type]"
- "[-x memslots]\n", name);
+ "[-x memslots] [-w percentage]\n", name);
puts("");
printf(" -i: specify iteration counts (default: %"PRIu64")\n",
TEST_HOST_LOOP_N);
@@ -377,10 +387,6 @@ static void help(char *name)
printf(" -b: specify the size of the memory region which should be\n"
" dirtied by each vCPU. e.g. 10M or 3G.\n"
" (default: 1G)\n");
- printf(" -f: specify the fraction of pages which should be written to\n"
- " as opposed to simply read, in the form\n"
- " 1/<fraction of pages to write>.\n"
- " (default: 1 i.e. all pages are written to.)\n");
printf(" -v: specify the number of vCPUs to run.\n");
printf(" -o: Overlap guest memory accesses instead of partitioning\n"
" them into a separate region of memory for each vCPU.\n");
@@ -388,6 +394,11 @@ static void help(char *name)
backing_src_help("-s");
printf(" -x: Split the memory region into this number of memslots.\n"
" (default: 1)\n");
+ printf(" -w: specify the percentage of pages which should be written to\n"
+ " as an integer from 0-100 inclusive. This is probabalistic,\n"
+ " so -w X means each page has an X%% chance of writing\n"
+ " and a (100-X)%% chance of reading.\n"
+ " (default: 100 i.e. all pages are written to.)\n");
puts("");
exit(0);
}
@@ -397,10 +408,10 @@ int main(int argc, char *argv[])
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
struct test_params p = {
.iterations = TEST_HOST_LOOP_N,
- .wr_fract = 1,
.partition_vcpu_memory_access = true,
.backing_src = DEFAULT_VM_MEM_SRC,
.slots = 1,
+ .write_percent = 100,
};
int opt;
@@ -411,7 +422,7 @@ int main(int argc, char *argv[])
guest_modes_append_default();
- while ((opt = getopt(argc, argv, "eghi:p:m:nb:f:v:or:s:x:")) != -1) {
+ while ((opt = getopt(argc, argv, "eghi:p:m:nb:v:or:s:x:w:")) != -1) {
switch (opt) {
case 'e':
/* 'e' is for evil. */
@@ -434,10 +445,11 @@ int main(int argc, char *argv[])
case 'b':
guest_percpu_mem_size = parse_size(optarg);
break;
- case 'f':
- p.wr_fract = atoi(optarg);
- TEST_ASSERT(p.wr_fract >= 1,
- "Write fraction cannot be less than one");
+ case 'w':
+ p.write_percent = atoi(optarg);
+ TEST_ASSERT(p.write_percent >= 0
+ && p.write_percent <= 100,
+ "Write percentage must be between 0 and 100");
break;
case 'v':
nr_vcpus = atoi(optarg);
@@ -36,7 +36,7 @@ struct perf_test_args {
uint64_t size;
uint64_t guest_page_size;
uint32_t random_seed;
- int wr_fract;
+ uint32_t write_percent;
/* Run vCPUs in L2 instead of L1, if the architecture supports it. */
bool nested;
@@ -52,7 +52,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
bool partition_vcpu_memory_access);
void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
+void perf_test_set_write_percent(struct kvm_vm *vm, uint32_t write_percent);
void perf_test_set_random_seed(struct kvm_vm *vm, uint32_t random_seed);
void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
@@ -61,7 +61,7 @@ void perf_test_guest_code(uint32_t vcpu_idx)
for (i = 0; i < pages; i++) {
uint64_t addr = gva + (i * pta->guest_page_size);
- if (i % pta->wr_fract == 0)
+ if (guest_random_u32(&rand_state) % 100 < pta->write_percent)
*(uint64_t *)addr = 0x0123456789ABCDEF;
else
READ_ONCE(*(uint64_t *)addr);
@@ -122,7 +122,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
/* By default vCPUs will write to memory. */
- pta->wr_fract = 1;
+ pta->write_percent = 100;
/*
* Snapshot the non-huge page size. This is used by the guest code to
@@ -224,10 +224,10 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
kvm_vm_free(vm);
}
-void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
+void perf_test_set_write_percent(struct kvm_vm *vm, uint32_t write_percent)
{
- perf_test_args.wr_fract = wr_fract;
- sync_global_to_guest(vm, perf_test_args);
+ perf_test_args.write_percent = write_percent;
+ sync_global_to_guest(vm, perf_test_args.write_percent);
}
void perf_test_set_random_seed(struct kvm_vm *vm, uint32_t random_seed)