X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=stat.c;h=cfb297886b7288e7ead21258a32c28af4055866e;hp=b5ff0101b7b0feca625721bc10b351a48825a271;hb=5ba13ea6968cf2773f10d34376afe28ef81aeee5;hpb=562c2d2f25ae829c812a58c10bc1a03ab6f6f52b diff --git a/stat.c b/stat.c index b5ff0101..cfb29788 100644 --- a/stat.c +++ b/stat.c @@ -14,18 +14,159 @@ void update_rusage_stat(struct thread_data *td) { struct thread_stat *ts = &td->ts; - getrusage(RUSAGE_SELF, &ts->ru_end); - - ts->usr_time += mtime_since(&ts->ru_start.ru_utime, - &ts->ru_end.ru_utime); - ts->sys_time += mtime_since(&ts->ru_start.ru_stime, - &ts->ru_end.ru_stime); - ts->ctx += ts->ru_end.ru_nvcsw + ts->ru_end.ru_nivcsw - - (ts->ru_start.ru_nvcsw + ts->ru_start.ru_nivcsw); - ts->minf += ts->ru_end.ru_minflt - ts->ru_start.ru_minflt; - ts->majf += ts->ru_end.ru_majflt - ts->ru_start.ru_majflt; - - memcpy(&ts->ru_start, &ts->ru_end, sizeof(ts->ru_end)); + getrusage(RUSAGE_SELF, &td->ru_end); + + ts->usr_time += mtime_since(&td->ru_start.ru_utime, + &td->ru_end.ru_utime); + ts->sys_time += mtime_since(&td->ru_start.ru_stime, + &td->ru_end.ru_stime); + ts->ctx += td->ru_end.ru_nvcsw + td->ru_end.ru_nivcsw + - (td->ru_start.ru_nvcsw + td->ru_start.ru_nivcsw); + ts->minf += td->ru_end.ru_minflt - td->ru_start.ru_minflt; + ts->majf += td->ru_end.ru_majflt - td->ru_start.ru_majflt; + + memcpy(&td->ru_start, &td->ru_end, sizeof(td->ru_end)); +} + +/* + * Given a latency, return the index of the corresponding bucket in + * the structure tracking percentiles. + * + * (1) find the group (and error bits) that the value (latency) + * belongs to by looking at its MSB. (2) find the bucket number in the + * group by looking at the index bits. + * + */ +static unsigned int plat_val_to_idx(unsigned int val) +{ + unsigned int msb, error_bits, base, offset, idx; + + /* Find MSB starting from bit 0 */ + if (val == 0) + msb = 0; + else + msb = (sizeof(val)*8) - __builtin_clz(val) - 1; + + /* + * MSB <= (FIO_IO_U_PLAT_BITS-1), cannot be rounded off. Use + * all bits of the sample as index + */ + if (msb <= FIO_IO_U_PLAT_BITS) + return val; + + /* Compute the number of error bits to discard*/ + error_bits = msb - FIO_IO_U_PLAT_BITS; + + /* Compute the number of buckets before the group */ + base = (error_bits + 1) << FIO_IO_U_PLAT_BITS; + + /* + * Discard the error bits and apply the mask to find the + * index for the buckets in the group + */ + offset = (FIO_IO_U_PLAT_VAL - 1) & (val >> error_bits); + + /* Make sure the index does not exceed (array size - 1) */ + idx = (base + offset) < (FIO_IO_U_PLAT_NR - 1)? + (base + offset) : (FIO_IO_U_PLAT_NR - 1); + + return idx; +} + +/* + * Convert the given index of the bucket array to the value + * represented by the bucket + */ +static unsigned int plat_idx_to_val(unsigned int idx) +{ + unsigned int error_bits, k, base; + + assert(idx < FIO_IO_U_PLAT_NR); + + /* MSB <= (FIO_IO_U_PLAT_BITS-1), cannot be rounded off. Use + * all bits of the sample as index */ + if (idx < (FIO_IO_U_PLAT_VAL << 1) ) + return idx; + + /* Find the group and compute the minimum value of that group */ + error_bits = (idx >> FIO_IO_U_PLAT_BITS) -1; + base = 1 << (error_bits + FIO_IO_U_PLAT_BITS); + + /* Find its bucket number of the group */ + k = idx % FIO_IO_U_PLAT_VAL; + + /* Return the mean of the range of the bucket */ + return base + ((k + 0.5) * (1 << error_bits)); +} + +static int double_cmp(const void *a, const void *b) +{ + const double fa = *(const double *)a; + const double fb = *(const double *)b; + int cmp = 0; + + if (fa > fb) + cmp = 1; + else if (fa < fb) + 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) +{ + 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}; + + plist = user_list; + if (!plist) + plist = def_list; + + for (len = 0; len 1) + qsort((void*)user_list, len, sizeof(user_list[0]), double_cmp); + + log_info(" clat percentiles (usec) :"); + + 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); + + /* for formatting */ + if (j != 0 && (j % 4) == 0) + log_info(" "); + + /* end of the list */ + is_last = (j == len - 1); + + log_info(" %2.2fth=%u%c", plist[j], plat_idx_to_val(i), + (is_last? '\n' : ',')); + + if (is_last) + break; + + if (j % 4 == 3) /* for formatting */ + log_info("\n"); + j++; + } + } } static int calc_lat(struct io_stat *is, unsigned long *min, unsigned long *max, @@ -50,13 +191,13 @@ static int calc_lat(struct io_stat *is, unsigned long *min, unsigned long *max, 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("\nRun 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); @@ -169,10 +310,10 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts, io_p = num2str(ts->io_bytes[ddir], 6, 1, i2p); bw_p = num2str(bw, 6, 1, i2p); - iops = (1000 * ts->total_io_u[ddir]) / runt; + iops = (1000 * (uint64_t)ts->total_io_u[ddir]) / runt; iops_p = num2str(iops, 6, 1, 0); - log_info(" %s: io=%sB, bw=%sB/s, iops=%s, runt=%6lumsec\n", + log_info(" %s: io=%sB, bw=%sB/s, iops=%s, runt=%6llumsec\n", ddir_str[ddir], io_p, bw_p, iops_p, ts->runtime[ddir]); @@ -228,6 +369,11 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts, free(minp); free(maxp); } + if (ts->clat_percentiles) { + show_clat_percentiles(ts->io_u_plat[ddir], + ts->clat_stat[ddir].samples, + ts->percentile_list); + } if (calc_lat(&ts->bw_stat[ddir], &min, &max, &mean, &dev)) { double p_of_agg; @@ -287,8 +433,7 @@ 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; @@ -380,7 +525,7 @@ static void show_ddir_status_terse(struct thread_stat *ts, if (ts->runtime[ddir]) bw = ts->io_bytes[ddir] / ts->runtime[ddir]; - log_info(";%llu;%llu;%lu", ts->io_bytes[ddir] >> 10, bw, + log_info(";%llu;%llu;%llu", ts->io_bytes[ddir] >> 10, bw, ts->runtime[ddir]); if (calc_lat(&ts->slat_stat[ddir], &min, &max, &mean, &dev)) @@ -472,23 +617,33 @@ static void sum_stat(struct io_stat *dst, struct io_stat *src, int nr) { double mean, S; + if (src->samples == 0) + return; + dst->min_val = min(dst->min_val, src->min_val); dst->max_val = max(dst->max_val, src->max_val); - dst->samples += src->samples; /* - * Needs a new method for calculating stddev, we cannot just - * average them we do below for nr > 1 + * Compute new mean and S after the merge + * */ if (nr == 1) { mean = src->mean; S = src->S; } else { - mean = ((src->mean * (double) (nr - 1)) - + dst->mean) / ((double) nr); - S = ((src->S * (double) (nr - 1)) + dst->S) / ((double) nr); + double delta = src->mean - dst->mean; + + mean = ((src->mean * src->samples) + + (dst->mean * dst->samples)) / + (dst->samples + src->samples); + + S = src->S + dst->S + pow(delta, 2.0) * + (dst->samples * src->samples) / + (dst->samples + src->samples); } + dst->samples += src->samples; dst->mean = mean; dst->S = S; } @@ -558,6 +713,12 @@ void show_run_stats(void) ts = &threadstats[j]; + ts->clat_percentiles = td->o.clat_percentiles; + if (td->o.overwrite_plist) + ts->percentile_list = td->o.percentile_list; + else + ts->percentile_list = NULL; + idx++; ts->members++; @@ -565,8 +726,13 @@ void show_run_stats(void) /* * These are per-group shared already */ - ts->name = td->o.name; - ts->description = td->o.description; + strncpy(ts->name, td->o.name, 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; /* @@ -588,10 +754,10 @@ void show_run_stats(void) if (!td->error && td->o.continue_on_error && td->first_error) { ts->error = td->first_error; - ts->verror = td->verror; + strcpy(ts->verror, td->verror); } else if (td->error) { ts->error = td->error; - ts->verror = td->verror; + strcpy(ts->verror, td->verror); } } @@ -601,7 +767,6 @@ void show_run_stats(void) 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->stat_io_bytes[l] += td->ts.stat_io_bytes[l]; ts->io_bytes[l] += td->ts.io_bytes[l]; if (ts->runtime[l] < td->ts.runtime[l]) @@ -631,6 +796,12 @@ void show_run_stats(void) 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; @@ -690,15 +861,24 @@ 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); + } show_disk_util(); } @@ -728,7 +908,7 @@ static inline void add_stat_sample(struct io_stat *is, unsigned long data) static void __add_log_sample(struct io_log *iolog, unsigned long val, enum fio_ddir ddir, unsigned int bs, - unsigned long time) + unsigned long t) { const int nr_samples = iolog->nr_samples; @@ -740,7 +920,7 @@ static void __add_log_sample(struct io_log *iolog, unsigned long val, } iolog->log[nr_samples].val = val; - iolog->log[nr_samples].time = time; + iolog->log[nr_samples].time = t; iolog->log[nr_samples].ddir = ddir; iolog->log[nr_samples].bs = bs; iolog->nr_samples++; @@ -767,6 +947,15 @@ void add_agg_sample(unsigned long val, enum fio_ddir ddir, unsigned int bs) __add_log_sample(iolog, val, ddir, bs, mtime_since_genesis()); } +static void add_clat_percentile_sample(struct thread_stat *ts, + unsigned long usec, enum fio_ddir ddir) +{ + unsigned int idx = plat_val_to_idx(usec); + assert(idx < FIO_IO_U_PLAT_NR); + + ts->io_u_plat[ddir][idx]++; +} + void add_clat_sample(struct thread_data *td, enum fio_ddir ddir, unsigned long usec, unsigned int bs) { @@ -777,8 +966,11 @@ void add_clat_sample(struct thread_data *td, enum fio_ddir ddir, add_stat_sample(&ts->clat_stat[ddir], usec); - if (ts->clat_log) - add_log_sample(td, ts->clat_log, usec, ddir, bs); + if (td->clat_log) + add_log_sample(td, td->clat_log, usec, ddir, bs); + + if (ts->clat_percentiles) + add_clat_percentile_sample(ts, usec, ddir); } void add_slat_sample(struct thread_data *td, enum fio_ddir ddir, @@ -791,8 +983,8 @@ void add_slat_sample(struct thread_data *td, enum fio_ddir ddir, add_stat_sample(&ts->slat_stat[ddir], usec); - if (ts->slat_log) - add_log_sample(td, ts->slat_log, usec, ddir, bs); + if (td->slat_log) + add_log_sample(td, td->slat_log, usec, ddir, bs); } void add_lat_sample(struct thread_data *td, enum fio_ddir ddir, @@ -805,8 +997,8 @@ void add_lat_sample(struct thread_data *td, enum fio_ddir ddir, add_stat_sample(&ts->lat_stat[ddir], usec); - if (ts->lat_log) - add_log_sample(td, ts->lat_log, usec, ddir, bs); + if (td->lat_log) + add_log_sample(td, td->lat_log, usec, ddir, bs); } void add_bw_sample(struct thread_data *td, enum fio_ddir ddir, unsigned int bs, @@ -818,17 +1010,17 @@ void add_bw_sample(struct thread_data *td, enum fio_ddir ddir, unsigned int bs, if (!ddir_rw(ddir)) return; - spent = mtime_since(&ts->stat_sample_time[ddir], t); + spent = mtime_since(&td->stat_sample_time[ddir], t); if (spent < td->o.bw_avg_time) return; - rate = (td->this_io_bytes[ddir] - ts->stat_io_bytes[ddir]) * + rate = (td->this_io_bytes[ddir] - td->stat_io_bytes[ddir]) * 1000 / spent / 1024; add_stat_sample(&ts->bw_stat[ddir], rate); - if (ts->bw_log) - add_log_sample(td, ts->bw_log, rate, ddir, bs); + if (td->bw_log) + add_log_sample(td, td->bw_log, rate, ddir, bs); - fio_gettime(&ts->stat_sample_time[ddir], NULL); - ts->stat_io_bytes[ddir] = td->this_io_bytes[ddir]; + fio_gettime(&td->stat_sample_time[ddir], NULL); + td->stat_io_bytes[ddir] = td->this_io_bytes[ddir]; }