Re: [PATCH v4 4/8] lib/string_kunit: add performance benchmark for strlen()

[Andy Shevchenko <andriy.shevchenko@intel.com>]

On Fri, Jan 23, 2026 at 04:58:37PM +0800, Feng Jiang wrote:
> Introduce a benchmarking framework to the string_kunit test suite to
> measure the execution efficiency of string functions.
> 
> The implementation is inspired by crc_benchmark(), measuring throughput
> (MB/s) and latency (ns/call) across a range of string lengths. It
> includes a warm-up phase, disables preemption during measurement, and
> uses a fixed seed for reproducible results.
> 
> This framework allows for comparing different implementations (e.g.,
> generic C vs. architecture-optimized assembly) within the KUnit
> environment.
> 
> Initially, provide a benchmark for strlen().

...

> +static void *alloc_max_bench_buffer(struct kunit *test,
> +		const size_t *lens, size_t count, size_t *buf_len)
> +{
> +	size_t i, max_len = 0;
> +	void *buf;

> +	for (i = 0; i < count; i++) {
> +		if (max_len < lens[i])
> +			max_len = lens[i];
> +	}

	size_t max_len = 0;
	void *buf;

	for (size_t i = 0; i < count; i++)
		max_len = max(lens[i], max_len);

> +	/* Add space for NUL character */
> +	max_len += 1;
> +
> +	buf = kunit_kzalloc(test, max_len, GFP_KERNEL);
> +	if (!buf)
> +		return NULL;
> +
> +	if (buf_len)
> +		*buf_len = max_len;
> +
> +	return buf;
> +}

...

> +#define STRING_BENCH(iters, func, ...)					\
> +({									\
> +	/* Volatile function pointer prevents dead code elimination */	\
> +	typeof(func) (* volatile __func) = (func);			\
> +	size_t __bn_iters = (iters);					\
> +	size_t __bn_warm_iters;						\

> +	size_t __bn_i;							\

Define it inside for-loop:s.

> +	u64 __bn_t;							\
> +									\
> +	__bn_warm_iters = max(__bn_iters / 10, 50U);			\
> +									\
> +	for (__bn_i = 0; __bn_i < __bn_warm_iters; __bn_i++)		\
> +		(void)__func(__VA_ARGS__);				\
> +									\
> +	preempt_disable();						\
> +	__bn_t = ktime_get_ns();					\
> +	for (__bn_i = 0; __bn_i < __bn_iters; __bn_i++)			\
> +		(void)__func(__VA_ARGS__);				\
> +	__bn_t = ktime_get_ns() - __bn_t;				\
> +	preempt_enable();						\
> +	__bn_t;								\
> +})

...

> +#define STRING_BENCH_BUF(test, buf_name, buf_size, func, ...)		\
> +do {									\
> +	size_t buf_size, _bn_i, _bn_iters, _bn_size = 0;		\
> +	u64 _bn_t, _bn_mbps = 0, _bn_lat = 0;				\
> +	char *buf_name, *_bn_buf;					\

> +	if (!IS_ENABLED(CONFIG_STRING_KUNIT_BENCH))			\
> +		kunit_skip(test, "not enabled");			\

Hmm... Since it's a macro anyway, I think the old style is okay:


#if IS_ENABLED(CONFIG_STRING_KUNIT_BENCH)
#define STRING_BENCH_BUF(test, buf_name, buf_size, func, ...)		\
	...
#else
#define STRING_BENCH_BUF(test, buf_name, buf_size, func, ...)		\
	kunit_skip(test, "not enabled");				\
#endif

But check it that it doesn't produce warnings in `make W=1` case.

> +	_bn_buf = alloc_max_bench_buffer(test, bench_lens,		\
> +			ARRAY_SIZE(bench_lens), &_bn_size);		\
> +	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, _bn_buf);			\
> +									\
> +	fill_random_string(_bn_buf, _bn_size);				\
> +									\
> +	for (_bn_i = 0; _bn_i < ARRAY_SIZE(bench_lens); _bn_i++) {	\
> +		buf_size = bench_lens[_bn_i];				\
> +		buf_name = _bn_buf + _bn_size - buf_size - 1;		\
> +		_bn_iters = STRING_BENCH_WORKLOAD / max(buf_size, 1U);	\
> +									\
> +		_bn_t = STRING_BENCH(_bn_iters, func, ##__VA_ARGS__);	\
> +									\
> +		if (_bn_t > 0) {					\
> +			_bn_mbps = (u64)(buf_size) * _bn_iters * 1000;	\

"KILO"? Or "(MEGA/KILO)"? I'm puzzled with this 1000 multiplier.

> +			_bn_mbps = div64_u64(_bn_mbps, _bn_t);		\
> +			_bn_lat = div64_u64(_bn_t, _bn_iters);		\
> +		}							\
> +		kunit_info(test, "len=%zu: %llu MB/s (%llu ns/call)\n",	\
> +				buf_size, _bn_mbps, _bn_lat);		\
> +	}								\
> +} while (0)

-- 
With Best Regards,
Andy Shevchenko



_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv