@@ -8,7 +8,8 @@
#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark)
struct gup_benchmark {
- __u64 delta_usec;
+ __u64 get_delta_usec;
+ __u64 put_delta_usec;
__u64 addr;
__u64 size;
__u32 nr_pages_per_call;
@@ -47,14 +48,17 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
}
end_time = ktime_get();
- gup->delta_usec = ktime_us_delta(end_time, start_time);
+ gup->get_delta_usec = ktime_us_delta(end_time, start_time);
gup->size = addr - gup->addr;
+ start_time = ktime_get();
for (i = 0; i < nr_pages; i++) {
if (!pages[i])
break;
put_page(pages[i]);
}
+ end_time = ktime_get();
+ gup->put_delta_usec = ktime_us_delta(end_time, start_time);
kvfree(pages);
return 0;
@@ -17,7 +17,8 @@
#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark)
struct gup_benchmark {
- __u64 delta_usec;
+ __u64 get_delta_usec;
+ __u64 put_delta_usec;
__u64 addr;
__u64 size;
__u32 nr_pages_per_call;
@@ -81,7 +82,8 @@ int main(int argc, char **argv)
if (ioctl(fd, GUP_FAST_BENCHMARK, &gup))
perror("ioctl"), exit(1);
- printf("Time: %lld us", gup.delta_usec);
+ printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
+ gup.put_delta_usec);
if (gup.size != size)
printf(", truncated (size: %lld)", gup.size);
printf("\n");
We'd like to measure time to unpin user pages, so this adds a second benchmark timer on put_page, separate from get_page. This will break ABI on this ioctl, but being an in-kernel benchmark may be acceptable. Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Keith Busch <keith.busch@intel.com> --- mm/gup_benchmark.c | 8 ++++++-- tools/testing/selftests/vm/gup_benchmark.c | 6 ++++-- 2 files changed, 10 insertions(+), 4 deletions(-)