X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=stat.c;h=a053c8be67051bf9014b2136f927eb9ff92303c5;hp=564edf342014bd07d4f61f99c09aa57c63f6f731;hb=c7c6cb4cb3114ec4ce3107e15c184e161b50122e;hpb=f6bb5b88614073878cbbd2666a1553481720faee diff --git a/stat.c b/stat.c index 564edf34..a053c8be 100644 --- a/stat.c +++ b/stat.c @@ -9,6 +9,7 @@ #include "fio.h" #include "diskutil.h" +#include "lib/ieee754.h" void update_rusage_stat(struct thread_data *td) { @@ -101,72 +102,136 @@ static unsigned int plat_idx_to_val(unsigned int idx) static int double_cmp(const void *a, const void *b) { - const double fa = *(const double *)a; - const double fb = *(const double *)b; + const fio_fp64_t fa = *(const fio_fp64_t *) a; + const fio_fp64_t fb = *(const fio_fp64_t *) b; int cmp = 0; - if (fa > fb) + if (fa.u.f > fb.u.f) cmp = 1; - else if (fa < fb) + else if (fa.u.f < fb.u.f) cmp = -1; return cmp; } -/* - * Find and display the p-th percentile of clat - */ -static void show_clat_percentiles(unsigned int* io_u_plat, unsigned long nr, - double* user_list) +static unsigned int calc_clat_percentiles(unsigned int *io_u_plat, + unsigned long nr, fio_fp64_t *plist, + unsigned int **output, + unsigned int *maxv, + unsigned int *minv) { unsigned long sum = 0; unsigned int len, i, j = 0; - const double *plist; - int is_last = 0; - static const double def_list[FIO_IO_U_LIST_MAX_LEN] = { - 1.0, 5.0, 10.0, 20.0, 30.0, - 40.0, 50.0, 60.0, 70.0, 80.0, - 90.0, 95.0, 99.0, 99.5, 99.9}; + unsigned int oval_len = 0; + unsigned int *ovals = NULL; + int is_last; + + *minv = -1U; + *maxv = 0; - plist = user_list; - if (!plist) - plist = def_list; + len = 0; + while (len < FIO_IO_U_LIST_MAX_LEN && plist[len].u.f != 0.0) + len++; - for (len = 0; len 1) - qsort((void*)user_list, len, sizeof(user_list[0]), double_cmp); - - log_info(" clat percentiles (usec) :"); + if (len > 1) + qsort((void*)plist, len, sizeof(plist[0]), double_cmp); + /* + * Calculate bucket values, note down max and min values + */ + is_last = 0; for (i = 0; i < FIO_IO_U_PLAT_NR && !is_last; i++) { sum += io_u_plat[i]; - while (sum >= (plist[j] / 100 * nr)) { - assert(plist[j] <= 100.0); + while (sum >= (plist[j].u.f / 100.0 * nr)) { + assert(plist[j].u.f <= 100.0); - /* for formatting */ - if (j != 0 && (j % 4) == 0) - log_info(" "); - - /* end of the list */ - is_last = (j == len - 1); + if (j == oval_len) { + oval_len += 100; + ovals = realloc(ovals, oval_len * sizeof(unsigned int)); + } - log_info(" %2.2fth=%u%c", plist[j], plat_idx_to_val(i), - (is_last? '\n' : ',')); + ovals[j] = plat_idx_to_val(i); + if (ovals[j] < *minv) + *minv = ovals[j]; + if (ovals[j] > *maxv) + *maxv = ovals[j]; + is_last = (j == len - 1); if (is_last) break; - if (j % 4 == 3) /* for formatting */ - log_info("\n"); j++; } } + + *output = ovals; + return len; +} + +/* + * Find and display the p-th percentile of clat + */ +static void show_clat_percentiles(unsigned int *io_u_plat, unsigned long nr, + fio_fp64_t *plist) +{ + unsigned int len, j = 0, minv, maxv; + unsigned int *ovals; + int is_last, scale_down; + + len = calc_clat_percentiles(io_u_plat, nr, plist, &ovals, &maxv, &minv); + if (!len) + goto out; + + /* + * We default to usecs, but if the value range is such that we + * should scale down to msecs, do that. + */ + if (minv > 2000 && maxv > 99999) { + scale_down = 1; + log_info(" clat percentiles (msec):\n |"); + } else { + scale_down = 0; + log_info(" clat percentiles (usec):\n |"); + } + + for (j = 0; j < len; j++) { + char fbuf[8]; + + /* for formatting */ + if (j != 0 && (j % 4) == 0) + log_info(" |"); + + /* end of the list */ + is_last = (j == len - 1); + + if (plist[j].u.f < 10.0) + sprintf(fbuf, " %2.2f", plist[j].u.f); + else + sprintf(fbuf, "%2.2f", plist[j].u.f); + + if (scale_down) + ovals[j] = (ovals[j] + 999) / 1000; + + log_info(" %sth=[%5u]%c", fbuf, ovals[j], is_last ? '\n' : ','); + + if (is_last) + break; + + if (j % 4 == 3) /* for formatting */ + log_info("\n"); + } + +out: + if (ovals) + free(ovals); } static int calc_lat(struct io_stat *is, unsigned long *min, unsigned long *max, @@ -181,23 +246,23 @@ static int calc_lat(struct io_stat *is, unsigned long *min, unsigned long *max, *max = is->max_val; n = (double) is->samples; - *mean = is->mean; + *mean = is->mean.u.f; if (n > 1.0) - *dev = sqrt(is->S / (n - 1.0)); + *dev = sqrt(is->S.u.f / (n - 1.0)); else *dev = 0; return 1; } -static void show_group_stats(struct group_run_stats *rs, int id) +void show_group_stats(struct group_run_stats *rs) { char *p1, *p2, *p3, *p4; const char *ddir_str[] = { " READ", " WRITE" }; int i; - log_info("\nRun status group %d (all jobs):\n", id); + log_info("Run status group %d (all jobs):\n", rs->groupid); for (i = 0; i <= DDIR_WRITE; i++) { const int i2p = is_power_of_2(rs->kb_base); @@ -378,7 +443,7 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts, double p_of_agg; p_of_agg = mean * 100 / (double) rs->agg[ddir]; - log_info(" bw (KB/s) : min=%5lu, max=%5lu, per=%3.2f%%," + log_info(" bw (KB/s) : min=%5lu, max=%5lu, per=%3.2f%%," " avg=%5.02f, stdev=%5.02f\n", min, max, p_of_agg, mean, dev); } @@ -433,8 +498,7 @@ static void show_latencies(double *io_u_lat_u, double *io_u_lat_m) log_info("\n"); } -static void show_thread_status(struct thread_stat *ts, - struct group_run_stats *rs) +void show_thread_status(struct thread_stat *ts, struct group_run_stats *rs) { double usr_cpu, sys_cpu; unsigned long runtime; @@ -517,16 +581,23 @@ static void show_ddir_status_terse(struct thread_stat *ts, struct group_run_stats *rs, int ddir) { unsigned long min, max; - unsigned long long bw; + unsigned long long bw, iops; + unsigned int *ovals = NULL; double mean, dev; + unsigned int len, minv, maxv; + int i; assert(ddir_rw(ddir)); - bw = 0; - if (ts->runtime[ddir]) - bw = ts->io_bytes[ddir] / ts->runtime[ddir]; + iops = bw = 0; + if (ts->runtime[ddir]) { + uint64_t runt = ts->runtime[ddir]; + + bw = ts->io_bytes[ddir] / runt; + iops = (1000 * (uint64_t) ts->total_io_u[ddir]) / runt; + } - log_info(";%llu;%llu;%llu", ts->io_bytes[ddir] >> 10, bw, + log_info(";%llu;%llu;%llu;%llu", ts->io_bytes[ddir] >> 10, bw, iops, ts->runtime[ddir]); if (calc_lat(&ts->slat_stat[ddir], &min, &max, &mean, &dev)) @@ -544,6 +615,24 @@ static void show_ddir_status_terse(struct thread_stat *ts, else log_info(";%lu;%lu;%f;%f", 0UL, 0UL, 0.0, 0.0); + if (ts->clat_percentiles) { + len = calc_clat_percentiles(ts->io_u_plat[ddir], + ts->clat_stat[ddir].samples, + ts->percentile_list, &ovals, &maxv, + &minv); + } else + len = 0; + + for (i = 0; i < FIO_IO_U_LIST_MAX_LEN; i++) { + if (i >= len) { + log_info(";0%%=0"); + continue; + } + log_info(";%2.2f%%=%u", ts->percentile_list[i].u.f, ovals[i]); + } + if (ovals) + free(ovals); + if (calc_lat(&ts->bw_stat[ddir], &min, &max, &mean, &dev)) { double p_of_agg; @@ -553,7 +642,7 @@ static void show_ddir_status_terse(struct thread_stat *ts, log_info(";%lu;%lu;%f%%;%f;%f", 0UL, 0UL, 0.0, 0.0, 0.0); } -#define FIO_TERSE_VERSION "2" +#define FIO_TERSE_VERSION "3" static void show_thread_status_terse(struct thread_stat *ts, struct group_run_stats *rs) @@ -602,6 +691,10 @@ static void show_thread_status_terse(struct thread_stat *ts, /* Millisecond latency */ for (i = 0; i < FIO_IO_U_LAT_M_NR; i++) log_info(";%3.2f%%", io_u_lat_m[i]); + + /* disk util stats, if any */ + show_disk_util(1); + /* Additional output if continue_on_error set - default off*/ if (ts->continue_on_error) log_info(";%lu;%d", ts->total_err_count, ts->first_error); @@ -630,23 +723,114 @@ static void sum_stat(struct io_stat *dst, struct io_stat *src, int nr) * #Parallel_algorithm> */ if (nr == 1) { - mean = src->mean; - S = src->S; + mean = src->mean.u.f; + S = src->S.u.f; } else { - double delta = src->mean - dst->mean; + double delta = src->mean.u.f - dst->mean.u.f; - mean = ((src->mean * src->samples) + - (dst->mean * dst->samples)) / + mean = ((src->mean.u.f * src->samples) + + (dst->mean.u.f * dst->samples)) / (dst->samples + src->samples); - S = src->S + dst->S + pow(delta, 2.0) * + S = src->S.u.f + dst->S.u.f + pow(delta, 2.0) * (dst->samples * src->samples) / (dst->samples + src->samples); } dst->samples += src->samples; - dst->mean = mean; - dst->S = S; + dst->mean.u.f = mean; + dst->S.u.f = S; +} + +void sum_group_stats(struct group_run_stats *dst, struct group_run_stats *src) +{ + int i; + + for (i = 0; i < 2; i++) { + if (dst->max_run[i] < src->max_run[i]) + dst->max_run[i] = src->max_run[i]; + if (dst->min_run[i] && dst->min_run[i] > src->min_run[i]) + dst->min_run[i] = src->min_run[i]; + if (dst->max_bw[i] < src->max_bw[i]) + dst->max_bw[i] = src->max_bw[i]; + if (dst->min_bw[i] && dst->min_bw[i] > src->min_bw[i]) + dst->min_bw[i] = src->min_bw[i]; + + dst->io_kb[i] += src->io_kb[i]; + dst->agg[i] += src->agg[i]; + } + +} + +void sum_thread_stats(struct thread_stat *dst, struct thread_stat *src, int nr) +{ + int l, k; + + for (l = 0; l <= DDIR_WRITE; l++) { + sum_stat(&dst->clat_stat[l], &src->clat_stat[l], nr); + sum_stat(&dst->slat_stat[l], &src->slat_stat[l], nr); + sum_stat(&dst->lat_stat[l], &src->lat_stat[l], nr); + sum_stat(&dst->bw_stat[l], &src->bw_stat[l], nr); + + dst->io_bytes[l] += src->io_bytes[l]; + + if (dst->runtime[l] < src->runtime[l]) + dst->runtime[l] = src->runtime[l]; + } + + dst->usr_time += src->usr_time; + dst->sys_time += src->sys_time; + dst->ctx += src->ctx; + dst->majf += src->majf; + dst->minf += src->minf; + + for (k = 0; k < FIO_IO_U_MAP_NR; k++) + dst->io_u_map[k] += src->io_u_map[k]; + for (k = 0; k < FIO_IO_U_MAP_NR; k++) + dst->io_u_submit[k] += src->io_u_submit[k]; + for (k = 0; k < FIO_IO_U_MAP_NR; k++) + dst->io_u_complete[k] += src->io_u_complete[k]; + for (k = 0; k < FIO_IO_U_LAT_U_NR; k++) + dst->io_u_lat_u[k] += src->io_u_lat_u[k]; + for (k = 0; k < FIO_IO_U_LAT_M_NR; k++) + dst->io_u_lat_m[k] += src->io_u_lat_m[k]; + + for (k = 0; k <= 2; k++) { + dst->total_io_u[k] += src->total_io_u[k]; + dst->short_io_u[k] += src->short_io_u[k]; + } + + for (k = 0; k <= DDIR_WRITE; k++) { + int m; + for (m = 0; m < FIO_IO_U_PLAT_NR; m++) + dst->io_u_plat[k][m] += src->io_u_plat[k][m]; + } + + dst->total_run_time += src->total_run_time; + dst->total_submit += src->total_submit; + dst->total_complete += src->total_complete; +} + +void init_group_run_stat(struct group_run_stats *gs) +{ + memset(gs, 0, sizeof(*gs)); + gs->min_bw[0] = gs->min_run[0] = ~0UL; + gs->min_bw[1] = gs->min_run[1] = ~0UL; +} + +void init_thread_stat(struct thread_stat *ts) +{ + int j; + + memset(ts, 0, sizeof(*ts)); + + for (j = 0; j <= DDIR_WRITE; j++) { + ts->lat_stat[j].min_val = -1UL; + ts->clat_stat[j].min_val = -1UL; + ts->slat_stat[j].min_val = -1UL; + ts->bw_stat[j].min_val = -1UL; + } + ts->groupid = -1; } void show_run_stats(void) @@ -654,18 +838,13 @@ void show_run_stats(void) struct group_run_stats *runstats, *rs; struct thread_data *td; struct thread_stat *threadstats, *ts; - int i, j, k, l, nr_ts, last_ts, idx; + int i, j, nr_ts, last_ts, idx; int kb_base_warned = 0; runstats = malloc(sizeof(struct group_run_stats) * (groupid + 1)); - for (i = 0; i < groupid + 1; i++) { - rs = &runstats[i]; - - memset(rs, 0, sizeof(*rs)); - rs->min_bw[0] = rs->min_run[0] = ~0UL; - rs->min_bw[1] = rs->min_run[1] = ~0UL; - } + for (i = 0; i < groupid + 1; i++) + init_group_run_stat(&runstats[i]); /* * find out how many threads stats we need. if group reporting isn't @@ -687,18 +866,8 @@ void show_run_stats(void) threadstats = malloc(nr_ts * sizeof(struct thread_stat)); - for (i = 0; i < nr_ts; i++) { - ts = &threadstats[i]; - - memset(ts, 0, sizeof(*ts)); - for (j = 0; j <= DDIR_WRITE; j++) { - ts->lat_stat[j].min_val = -1UL; - ts->clat_stat[j].min_val = -1UL; - ts->slat_stat[j].min_val = -1UL; - ts->bw_stat[j].min_val = -1UL; - } - ts->groupid = -1; - } + for (i = 0; i < nr_ts; i++) + init_thread_stat(&threadstats[i]); j = 0; last_ts = -1; @@ -716,9 +885,9 @@ void show_run_stats(void) ts->clat_percentiles = td->o.clat_percentiles; if (td->o.overwrite_plist) - ts->percentile_list = td->o.percentile_list; + memcpy(ts->percentile_list, td->o.percentile_list, sizeof(td->o.percentile_list)); else - ts->percentile_list = NULL; + memcpy(ts->percentile_list, def_percentile_list, sizeof(def_percentile_list)); idx++; ts->members++; @@ -728,8 +897,12 @@ void show_run_stats(void) * These are per-group shared already */ strncpy(ts->name, td->o.name, FIO_JOBNAME_SIZE); - strncpy(ts->description, td->o.description, - FIO_JOBNAME_SIZE); + if (td->o.description) + strncpy(ts->description, td->o.description, + FIO_JOBNAME_SIZE); + else + memset(ts->description, 0, FIO_JOBNAME_SIZE); + ts->groupid = td->groupid; /* @@ -758,50 +931,7 @@ void show_run_stats(void) } } - for (l = 0; l <= DDIR_WRITE; l++) { - sum_stat(&ts->clat_stat[l], &td->ts.clat_stat[l], idx); - sum_stat(&ts->slat_stat[l], &td->ts.slat_stat[l], idx); - sum_stat(&ts->lat_stat[l], &td->ts.lat_stat[l], idx); - sum_stat(&ts->bw_stat[l], &td->ts.bw_stat[l], idx); - - ts->io_bytes[l] += td->ts.io_bytes[l]; - - if (ts->runtime[l] < td->ts.runtime[l]) - ts->runtime[l] = td->ts.runtime[l]; - } - - ts->usr_time += td->ts.usr_time; - ts->sys_time += td->ts.sys_time; - ts->ctx += td->ts.ctx; - ts->majf += td->ts.majf; - ts->minf += td->ts.minf; - - for (k = 0; k < FIO_IO_U_MAP_NR; k++) - ts->io_u_map[k] += td->ts.io_u_map[k]; - for (k = 0; k < FIO_IO_U_MAP_NR; k++) - ts->io_u_submit[k] += td->ts.io_u_submit[k]; - for (k = 0; k < FIO_IO_U_MAP_NR; k++) - ts->io_u_complete[k] += td->ts.io_u_complete[k]; - for (k = 0; k < FIO_IO_U_LAT_U_NR; k++) - ts->io_u_lat_u[k] += td->ts.io_u_lat_u[k]; - for (k = 0; k < FIO_IO_U_LAT_M_NR; k++) - ts->io_u_lat_m[k] += td->ts.io_u_lat_m[k]; - - - for (k = 0; k <= 2; k++) { - ts->total_io_u[k] += td->ts.total_io_u[k]; - ts->short_io_u[k] += td->ts.short_io_u[k]; - } - - for (k = 0; k <= DDIR_WRITE; k++) { - int m; - for (m = 0; m < FIO_IO_U_PLAT_NR; m++) - ts->io_u_plat[k][m] += td->ts.io_u_plat[k][m]; - } - - ts->total_run_time += td->ts.total_run_time; - ts->total_submit += td->ts.total_submit; - ts->total_complete += td->ts.total_complete; + sum_thread_stats(ts, &td->ts, idx); } for (i = 0; i < nr_ts; i++) { @@ -858,17 +988,31 @@ void show_run_stats(void) ts = &threadstats[i]; rs = &runstats[ts->groupid]; - if (terse_output) + if (is_backend) + fio_server_send_ts(ts, rs); + else if (terse_output) show_thread_status_terse(ts, rs); else show_thread_status(ts, rs); } if (!terse_output) { - for (i = 0; i < groupid + 1; i++) - show_group_stats(&runstats[i], i); + for (i = 0; i < groupid + 1; i++) { + rs = &runstats[i]; + + rs->groupid = i; + if (is_backend) + fio_server_send_gs(rs); + else + show_group_stats(rs); + } + + if (is_backend) + fio_server_send_du(); + else + show_disk_util(0); - show_disk_util(); + free_disk_util(); } free(runstats); @@ -885,10 +1029,10 @@ static inline void add_stat_sample(struct io_stat *is, unsigned long data) if (data < is->min_val) is->min_val = data; - delta = val - is->mean; + delta = val - is->mean.u.f; if (delta) { - is->mean += delta / (is->samples + 1.0); - is->S += delta * (val - is->mean); + is->mean.u.f += delta / (is->samples + 1.0); + is->S.u.f += delta * (val - is->mean.u.f); } is->samples++; @@ -998,7 +1142,7 @@ void add_bw_sample(struct thread_data *td, enum fio_ddir ddir, unsigned int bs, if (!ddir_rw(ddir)) return; - spent = mtime_since(&td->stat_sample_time[ddir], t); + spent = mtime_since(&td->bw_sample_time, t); if (spent < td->o.bw_avg_time) return; @@ -1009,6 +1153,32 @@ void add_bw_sample(struct thread_data *td, enum fio_ddir ddir, unsigned int bs, if (td->bw_log) add_log_sample(td, td->bw_log, rate, ddir, bs); - fio_gettime(&td->stat_sample_time[ddir], NULL); + fio_gettime(&td->bw_sample_time, NULL); td->stat_io_bytes[ddir] = td->this_io_bytes[ddir]; } + +void add_iops_sample(struct thread_data *td, enum fio_ddir ddir, + struct timeval *t) +{ + struct thread_stat *ts = &td->ts; + unsigned long spent, iops; + + if (!ddir_rw(ddir)) + return; + + spent = mtime_since(&td->iops_sample_time, t); + if (spent < td->o.iops_avg_time) + return; + + iops = ((td->this_io_blocks[ddir] - td->stat_io_blocks[ddir]) * 1000) / spent; + + add_stat_sample(&ts->iops_stat[ddir], iops); + + if (td->iops_log) { + assert(iops); + add_log_sample(td, td->iops_log, iops, ddir, 0); + } + + fio_gettime(&td->iops_sample_time, NULL); + td->stat_io_blocks[ddir] = td->this_io_blocks[ddir]; +}