mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git
synced 2024-12-28 00:32:00 +00:00
crypto: xor - fix template benchmarking
Commitc055e3eae0
("crypto: xor - use ktime for template benchmarking") switched from using jiffies to ktime-based performance benchmarking. This works nicely on machines which have a fine-grained ktime() clocksource as e.g. x86 machines with TSC. But other machines, e.g. my 4-way HP PARISC server, don't have such fine-grained clocksources, which is why it seems that 800 xor loops take zero seconds, which then shows up in the logs as: xor: measuring software checksum speed 8regs : -1018167296 MB/sec 8regs_prefetch : -1018167296 MB/sec 32regs : -1018167296 MB/sec 32regs_prefetch : -1018167296 MB/sec Fix this with some small modifications to the existing code to improve the algorithm to always produce correct results without introducing major delays for architectures with a fine-grained ktime() clocksource: a) Delay start of the timing until ktime() just advanced. On machines with a fast ktime() this should be just one additional ktime() call. b) Count the number of loops. Run at minimum 800 loops and finish earliest when the ktime() counter has progressed. With that the throughput can now be calculated more accurately under all conditions. Fixes:c055e3eae0
("crypto: xor - use ktime for template benchmarking") Signed-off-by: Helge Deller <deller@gmx.de> Tested-by: John David Anglin <dave.anglin@bell.net> v2: - clean up coding style (noticed & suggested by Herbert Xu) - rephrased & fixed typo in commit message Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
parent
8400291e28
commit
ab9a244c39
31
crypto/xor.c
31
crypto/xor.c
@ -83,33 +83,30 @@ static void __init
|
||||
do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
|
||||
{
|
||||
int speed;
|
||||
int i, j;
|
||||
ktime_t min, start, diff;
|
||||
unsigned long reps;
|
||||
ktime_t min, start, t0;
|
||||
|
||||
tmpl->next = template_list;
|
||||
template_list = tmpl;
|
||||
|
||||
preempt_disable();
|
||||
|
||||
min = (ktime_t)S64_MAX;
|
||||
for (i = 0; i < 3; i++) {
|
||||
start = ktime_get();
|
||||
for (j = 0; j < REPS; j++) {
|
||||
mb(); /* prevent loop optimization */
|
||||
tmpl->do_2(BENCH_SIZE, b1, b2);
|
||||
mb();
|
||||
}
|
||||
diff = ktime_sub(ktime_get(), start);
|
||||
if (diff < min)
|
||||
min = diff;
|
||||
}
|
||||
reps = 0;
|
||||
t0 = ktime_get();
|
||||
/* delay start until time has advanced */
|
||||
while ((start = ktime_get()) == t0)
|
||||
cpu_relax();
|
||||
do {
|
||||
mb(); /* prevent loop optimization */
|
||||
tmpl->do_2(BENCH_SIZE, b1, b2);
|
||||
mb();
|
||||
} while (reps++ < REPS || (t0 = ktime_get()) == start);
|
||||
min = ktime_sub(t0, start);
|
||||
|
||||
preempt_enable();
|
||||
|
||||
// bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s]
|
||||
if (!min)
|
||||
min = 1;
|
||||
speed = (1000 * REPS * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
|
||||
speed = (1000 * reps * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
|
||||
tmpl->speed = speed;
|
||||
|
||||
pr_info(" %-16s: %5d MB/sec\n", tmpl->name, speed);
|
||||
|
Loading…
Reference in New Issue
Block a user