| Message ID | 20230418114506.46788-7-ilpo.jarvinen@linux.intel.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | selftests/resctrl: Fixes, cleanups, and rewritten CAT test | expand |
Hi Ilpo, On 4/18/2023 4:44 AM, Ilpo Järvinen wrote: > Make MBA and MBM tests to use megabytes to represent span. CMT test > uses bytes. > > Convert MBA and MBM tests to use bytes like CMT test to remove the > inconsistency between the tests. This also allows removing test > dependent buffer sizing from run_benchmark(). It is not clear to me how this patch achieves this goal since after it show_mba_info() still displays results in MB. Reinette
On Fri, 21 Apr 2023, Reinette Chatre wrote: > On 4/18/2023 4:44 AM, Ilpo Järvinen wrote: > > Make MBA and MBM tests to use megabytes to represent span. CMT test > > uses bytes. > > > > Convert MBA and MBM tests to use bytes like CMT test to remove the > > inconsistency between the tests. This also allows removing test > > dependent buffer sizing from run_benchmark(). > > It is not clear to me how this patch achieves this goal since after > it show_mba_info() still displays results in MB. This was more for internal consistency as there was the test type dependent span calculation in run_benchmark(). I can fix the changelog to reflect that, however, what you think would be the best approach in show_bw_info(), should I leave the print to use MB (converting the internal representation back from bytes to MB there)?
diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 3c389ccfea41..ea2ea5721e76 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -40,7 +40,7 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, unsigned long span) ksft_print_msg("%s Check MBM diff within %d%%\n", ret ? "Fail:" : "Pass:", MAX_DIFF_PERCENT); ksft_print_msg("avg_diff_per: %d%%\n", avg_diff_per); - ksft_print_msg("Span (MB): %lu\n", span); + ksft_print_msg("Span in bytes: %lu\n", span); ksft_print_msg("avg_bw_imc: %lu\n", avg_bw_imc); ksft_print_msg("avg_bw_resc: %lu\n", avg_bw_resc); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 6bc0eda25e5d..f1ed2c89f228 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -185,7 +185,7 @@ int main(int argc, char **argv) char *benchmark_cmd[BENCHMARK_ARGS], bw_report[64], bm_type[64]; char benchmark_cmd_area[BENCHMARK_ARGS][BENCHMARK_ARG_SIZE]; int c, cpu_no = 1, argc_new = argc, i, no_of_bits = 0; - unsigned long span = 250; + unsigned long span = 250 * MB; int ben_ind, ben_count, tests = 0; bool cat_test = true; diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 45f785213143..09e0a69c81c4 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -296,7 +296,7 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no) void run_benchmark(int signum, siginfo_t *info, void *ucontext) { int operation, ret, malloc_and_init_memory, memflush; - unsigned long span, buffer_span; + unsigned long span; char **benchmark_cmd; char resctrl_val[64]; FILE *fp; @@ -319,12 +319,7 @@ void run_benchmark(int signum, siginfo_t *info, void *ucontext) operation = atoi(benchmark_cmd[4]); sprintf(resctrl_val, "%s", benchmark_cmd[5]); - if (strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - buffer_span = span * MB; - else - buffer_span = span; - - if (run_fill_buf(buffer_span, malloc_and_init_memory, memflush, + if (run_fill_buf(span, malloc_and_init_memory, memflush, operation, resctrl_val)) fprintf(stderr, "Error in running fill buffer\n"); } else {