From: Zhihong Wang Date: Thu, 29 Jan 2015 02:38:46 +0000 (+0800) Subject: app/test: extend memcpy test coverage X-Git-Tag: spdx-start~9546 X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=667d534aa7852c6e8221fa188b95026deee82186;p=dpdk.git app/test: extend memcpy test coverage Main code changes: 1. Added more typical data points for a thorough performance test 2. Added unaligned test cases since it's common in DPDK usage Signed-off-by: Zhihong Wang Acked-by: Cunming Liang Acked-by: Pablo de Lara --- diff --git a/app/test/test_memcpy_perf.c b/app/test/test_memcpy_perf.c index 7809610c90..754828e9d7 100644 --- a/app/test/test_memcpy_perf.c +++ b/app/test/test_memcpy_perf.c @@ -54,9 +54,10 @@ /* List of buffer sizes to test */ #if TEST_VALUE_RANGE == 0 static size_t buf_sizes[] = { - 0, 1, 7, 8, 9, 15, 16, 17, 31, 32, 33, 63, 64, 65, 127, 128, 129, 255, - 256, 257, 320, 384, 511, 512, 513, 1023, 1024, 1025, 1518, 1522, 1600, - 2048, 3072, 4096, 5120, 6144, 7168, 8192 + 1, 2, 3, 4, 5, 6, 7, 8, 9, 12, 15, 16, 17, 31, 32, 33, 63, 64, 65, 127, 128, + 129, 191, 192, 193, 255, 256, 257, 319, 320, 321, 383, 384, 385, 447, 448, + 449, 511, 512, 513, 767, 768, 769, 1023, 1024, 1025, 1518, 1522, 1536, 1600, + 2048, 2560, 3072, 3584, 4096, 4608, 5120, 5632, 6144, 6656, 7168, 7680, 8192 }; /* MUST be as large as largest packet size above */ #define SMALL_BUFFER_SIZE 8192 @@ -78,7 +79,7 @@ static size_t buf_sizes[TEST_VALUE_RANGE]; #define TEST_BATCH_SIZE 100 /* Data is aligned on this many bytes (power of 2) */ -#define ALIGNMENT_UNIT 16 +#define ALIGNMENT_UNIT 32 /* * Pointers used in performance tests. The two large buffers are for uncached @@ -94,19 +95,19 @@ init_buffers(void) { unsigned i; - large_buf_read = rte_malloc("memcpy", LARGE_BUFFER_SIZE, ALIGNMENT_UNIT); + large_buf_read = rte_malloc("memcpy", LARGE_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT); if (large_buf_read == NULL) goto error_large_buf_read; - large_buf_write = rte_malloc("memcpy", LARGE_BUFFER_SIZE, ALIGNMENT_UNIT); + large_buf_write = rte_malloc("memcpy", LARGE_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT); if (large_buf_write == NULL) goto error_large_buf_write; - small_buf_read = rte_malloc("memcpy", SMALL_BUFFER_SIZE, ALIGNMENT_UNIT); + small_buf_read = rte_malloc("memcpy", SMALL_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT); if (small_buf_read == NULL) goto error_small_buf_read; - small_buf_write = rte_malloc("memcpy", SMALL_BUFFER_SIZE, ALIGNMENT_UNIT); + small_buf_write = rte_malloc("memcpy", SMALL_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT); if (small_buf_write == NULL) goto error_small_buf_write; @@ -140,25 +141,25 @@ free_buffers(void) /* * Get a random offset into large array, with enough space needed to perform - * max copy size. Offset is aligned. + * max copy size. Offset is aligned, uoffset is used for unalignment setting. */ static inline size_t -get_rand_offset(void) +get_rand_offset(size_t uoffset) { - return ((rte_rand() % (LARGE_BUFFER_SIZE - SMALL_BUFFER_SIZE)) & - ~(ALIGNMENT_UNIT - 1)); + return (((rte_rand() % (LARGE_BUFFER_SIZE - SMALL_BUFFER_SIZE)) & + ~(ALIGNMENT_UNIT - 1)) + uoffset); } /* Fill in source and destination addresses. */ static inline void -fill_addr_arrays(size_t *dst_addr, int is_dst_cached, - size_t *src_addr, int is_src_cached) +fill_addr_arrays(size_t *dst_addr, int is_dst_cached, size_t dst_uoffset, + size_t *src_addr, int is_src_cached, size_t src_uoffset) { unsigned int i; for (i = 0; i < TEST_BATCH_SIZE; i++) { - dst_addr[i] = (is_dst_cached) ? 0 : get_rand_offset(); - src_addr[i] = (is_src_cached) ? 0 : get_rand_offset(); + dst_addr[i] = (is_dst_cached) ? dst_uoffset : get_rand_offset(dst_uoffset); + src_addr[i] = (is_src_cached) ? src_uoffset : get_rand_offset(src_uoffset); } } @@ -169,16 +170,17 @@ fill_addr_arrays(size_t *dst_addr, int is_dst_cached, */ static void do_uncached_write(uint8_t *dst, int is_dst_cached, - const uint8_t *src, int is_src_cached, size_t size) + const uint8_t *src, int is_src_cached, size_t size) { unsigned i, j; size_t dst_addrs[TEST_BATCH_SIZE], src_addrs[TEST_BATCH_SIZE]; for (i = 0; i < (TEST_ITERATIONS / TEST_BATCH_SIZE); i++) { - fill_addr_arrays(dst_addrs, is_dst_cached, - src_addrs, is_src_cached); - for (j = 0; j < TEST_BATCH_SIZE; j++) + fill_addr_arrays(dst_addrs, is_dst_cached, 0, + src_addrs, is_src_cached, 0); + for (j = 0; j < TEST_BATCH_SIZE; j++) { rte_memcpy(dst+dst_addrs[j], src+src_addrs[j], size); + } } } @@ -186,52 +188,111 @@ do_uncached_write(uint8_t *dst, int is_dst_cached, * Run a single memcpy performance test. This is a macro to ensure that if * the "size" parameter is a constant it won't be converted to a variable. */ -#define SINGLE_PERF_TEST(dst, is_dst_cached, src, is_src_cached, size) do { \ - unsigned int iter, t; \ - size_t dst_addrs[TEST_BATCH_SIZE], src_addrs[TEST_BATCH_SIZE]; \ - uint64_t start_time, total_time = 0; \ - uint64_t total_time2 = 0; \ - for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) { \ - fill_addr_arrays(dst_addrs, is_dst_cached, \ - src_addrs, is_src_cached); \ - start_time = rte_rdtsc(); \ - for (t = 0; t < TEST_BATCH_SIZE; t++) \ - rte_memcpy(dst+dst_addrs[t], src+src_addrs[t], size); \ - total_time += rte_rdtsc() - start_time; \ - } \ - for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) { \ - fill_addr_arrays(dst_addrs, is_dst_cached, \ - src_addrs, is_src_cached); \ - start_time = rte_rdtsc(); \ - for (t = 0; t < TEST_BATCH_SIZE; t++) \ - memcpy(dst+dst_addrs[t], src+src_addrs[t], size); \ - total_time2 += rte_rdtsc() - start_time; \ - } \ - printf("%8.0f -", (double)total_time /TEST_ITERATIONS); \ - printf("%5.0f", (double)total_time2 / TEST_ITERATIONS); \ +#define SINGLE_PERF_TEST(dst, is_dst_cached, dst_uoffset, \ + src, is_src_cached, src_uoffset, size) \ +do { \ + unsigned int iter, t; \ + size_t dst_addrs[TEST_BATCH_SIZE], src_addrs[TEST_BATCH_SIZE]; \ + uint64_t start_time, total_time = 0; \ + uint64_t total_time2 = 0; \ + for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) { \ + fill_addr_arrays(dst_addrs, is_dst_cached, dst_uoffset, \ + src_addrs, is_src_cached, src_uoffset); \ + start_time = rte_rdtsc(); \ + for (t = 0; t < TEST_BATCH_SIZE; t++) \ + rte_memcpy(dst+dst_addrs[t], src+src_addrs[t], size); \ + total_time += rte_rdtsc() - start_time; \ + } \ + for (iter = 0; iter < (TEST_ITERATIONS / TEST_BATCH_SIZE); iter++) { \ + fill_addr_arrays(dst_addrs, is_dst_cached, dst_uoffset, \ + src_addrs, is_src_cached, src_uoffset); \ + start_time = rte_rdtsc(); \ + for (t = 0; t < TEST_BATCH_SIZE; t++) \ + memcpy(dst+dst_addrs[t], src+src_addrs[t], size); \ + total_time2 += rte_rdtsc() - start_time; \ + } \ + printf("%8.0f -", (double)total_time /TEST_ITERATIONS); \ + printf("%5.0f", (double)total_time2 / TEST_ITERATIONS); \ } while (0) -/* Run memcpy() tests for each cached/uncached permutation. */ -#define ALL_PERF_TESTS_FOR_SIZE(n) do { \ - if (__builtin_constant_p(n)) \ - printf("\nC%6u", (unsigned)n); \ - else \ - printf("\n%7u", (unsigned)n); \ - SINGLE_PERF_TEST(small_buf_write, 1, small_buf_read, 1, n); \ - SINGLE_PERF_TEST(large_buf_write, 0, small_buf_read, 1, n); \ - SINGLE_PERF_TEST(small_buf_write, 1, large_buf_read, 0, n); \ - SINGLE_PERF_TEST(large_buf_write, 0, large_buf_read, 0, n); \ +/* Run aligned memcpy tests for each cached/uncached permutation */ +#define ALL_PERF_TESTS_FOR_SIZE(n) \ +do { \ + if (__builtin_constant_p(n)) \ + printf("\nC%6u", (unsigned)n); \ + else \ + printf("\n%7u", (unsigned)n); \ + SINGLE_PERF_TEST(small_buf_write, 1, 0, small_buf_read, 1, 0, n); \ + SINGLE_PERF_TEST(large_buf_write, 0, 0, small_buf_read, 1, 0, n); \ + SINGLE_PERF_TEST(small_buf_write, 1, 0, large_buf_read, 0, 0, n); \ + SINGLE_PERF_TEST(large_buf_write, 0, 0, large_buf_read, 0, 0, n); \ } while (0) -/* - * Run performance tests for a number of different sizes and cached/uncached - * permutations. - */ +/* Run unaligned memcpy tests for each cached/uncached permutation */ +#define ALL_PERF_TESTS_FOR_SIZE_UNALIGNED(n) \ +do { \ + if (__builtin_constant_p(n)) \ + printf("\nC%6u", (unsigned)n); \ + else \ + printf("\n%7u", (unsigned)n); \ + SINGLE_PERF_TEST(small_buf_write, 1, 1, small_buf_read, 1, 5, n); \ + SINGLE_PERF_TEST(large_buf_write, 0, 1, small_buf_read, 1, 5, n); \ + SINGLE_PERF_TEST(small_buf_write, 1, 1, large_buf_read, 0, 5, n); \ + SINGLE_PERF_TEST(large_buf_write, 0, 1, large_buf_read, 0, 5, n); \ +} while (0) + +/* Run memcpy tests for constant length */ +#define ALL_PERF_TEST_FOR_CONSTANT \ +do { \ + TEST_CONSTANT(6U); TEST_CONSTANT(64U); TEST_CONSTANT(128U); \ + TEST_CONSTANT(192U); TEST_CONSTANT(256U); TEST_CONSTANT(512U); \ + TEST_CONSTANT(768U); TEST_CONSTANT(1024U); TEST_CONSTANT(1536U); \ +} while (0) + +/* Run all memcpy tests for aligned constant cases */ +static inline void +perf_test_constant_aligned(void) +{ +#define TEST_CONSTANT ALL_PERF_TESTS_FOR_SIZE + ALL_PERF_TEST_FOR_CONSTANT; +#undef TEST_CONSTANT +} + +/* Run all memcpy tests for unaligned constant cases */ +static inline void +perf_test_constant_unaligned(void) +{ +#define TEST_CONSTANT ALL_PERF_TESTS_FOR_SIZE_UNALIGNED + ALL_PERF_TEST_FOR_CONSTANT; +#undef TEST_CONSTANT +} + +/* Run all memcpy tests for aligned variable cases */ +static inline void +perf_test_variable_aligned(void) +{ + unsigned n = sizeof(buf_sizes) / sizeof(buf_sizes[0]); + unsigned i; + for (i = 0; i < n; i++) { + ALL_PERF_TESTS_FOR_SIZE((size_t)buf_sizes[i]); + } +} + +/* Run all memcpy tests for unaligned variable cases */ +static inline void +perf_test_variable_unaligned(void) +{ + unsigned n = sizeof(buf_sizes) / sizeof(buf_sizes[0]); + unsigned i; + for (i = 0; i < n; i++) { + ALL_PERF_TESTS_FOR_SIZE_UNALIGNED((size_t)buf_sizes[i]); + } +} + +/* Run all memcpy tests */ static int perf_test(void) { - const unsigned num_buf_sizes = sizeof(buf_sizes) / sizeof(buf_sizes[0]); - unsigned i; int ret; ret = init_buffers(); @@ -239,7 +300,8 @@ perf_test(void) return ret; #if TEST_VALUE_RANGE != 0 - /* Setup buf_sizes array, if required */ + /* Set up buf_sizes array, if required */ + unsigned i; for (i = 0; i < TEST_VALUE_RANGE; i++) buf_sizes[i] = i; #endif @@ -248,28 +310,23 @@ perf_test(void) do_uncached_write(large_buf_write, 0, small_buf_read, 1, SMALL_BUFFER_SIZE); printf("\n** rte_memcpy() - memcpy perf. tests (C = compile-time constant) **\n" - "======= ============== ============== ============== ==============\n" - " Size Cache to cache Cache to mem Mem to cache Mem to mem\n" - "(bytes) (ticks) (ticks) (ticks) (ticks)\n" - "------- -------------- -------------- -------------- --------------"); - - /* Do tests where size is a variable */ - for (i = 0; i < num_buf_sizes; i++) { - ALL_PERF_TESTS_FOR_SIZE((size_t)buf_sizes[i]); - } + "======= ============== ============== ============== ==============\n" + " Size Cache to cache Cache to mem Mem to cache Mem to mem\n" + "(bytes) (ticks) (ticks) (ticks) (ticks)\n" + "------- -------------- -------------- -------------- --------------"); + + printf("\n========================== %2dB aligned ============================", ALIGNMENT_UNIT); + /* Do aligned tests where size is a variable */ + perf_test_variable_aligned(); printf("\n------- -------------- -------------- -------------- --------------"); - /* Do tests where size is a compile-time constant */ - ALL_PERF_TESTS_FOR_SIZE(63U); - ALL_PERF_TESTS_FOR_SIZE(64U); - ALL_PERF_TESTS_FOR_SIZE(65U); - ALL_PERF_TESTS_FOR_SIZE(255U); - ALL_PERF_TESTS_FOR_SIZE(256U); - ALL_PERF_TESTS_FOR_SIZE(257U); - ALL_PERF_TESTS_FOR_SIZE(1023U); - ALL_PERF_TESTS_FOR_SIZE(1024U); - ALL_PERF_TESTS_FOR_SIZE(1025U); - ALL_PERF_TESTS_FOR_SIZE(1518U); - + /* Do aligned tests where size is a compile-time constant */ + perf_test_constant_aligned(); + printf("\n=========================== Unaligned ============================="); + /* Do unaligned tests where size is a variable */ + perf_test_variable_unaligned(); + printf("\n------- -------------- -------------- -------------- --------------"); + /* Do unaligned tests where size is a compile-time constant */ + perf_test_constant_unaligned(); printf("\n======= ============== ============== ============== ==============\n\n"); free_buffers(); @@ -277,7 +334,6 @@ perf_test(void) return 0; } - static int test_memcpy_perf(void) {