free(ovals);
}
+static int get_nr_prios_with_samples(struct thread_stat *ts, enum fio_ddir ddir)
+{
+ int i, nr_prios_with_samples = 0;
+
+ for (i = 0; i < ts->nr_clat_prio[ddir]; i++) {
+ if (ts->clat_prio[ddir][i].clat_stat.samples)
+ nr_prios_with_samples++;
+ }
+
+ return nr_prios_with_samples;
+}
+
bool calc_lat(struct io_stat *is, unsigned long long *min,
unsigned long long *max, double *mean, double *dev)
{
unsigned long long min, max, bw, iops;
double mean, dev;
char *io_p, *bw_p, *bw_p_alt, *iops_p, *post_st = NULL;
- int i2p;
+ int i2p, i;
+ const char *clat_type = ts->lat_percentiles ? "lat" : "clat";
if (ddir_sync(ddir)) {
if (calc_lat(&ts->sync_stat, &min, &max, &mean, &dev)) {
display_lat("clat", min, max, mean, dev, out);
if (calc_lat(&ts->lat_stat[ddir], &min, &max, &mean, &dev))
display_lat(" lat", min, max, mean, dev, out);
- if (calc_lat(&ts->clat_high_prio_stat[ddir], &min, &max, &mean, &dev)) {
- display_lat(ts->lat_percentiles ? "high prio_lat" : "high prio_clat",
- min, max, mean, dev, out);
- if (calc_lat(&ts->clat_low_prio_stat[ddir], &min, &max, &mean, &dev))
- display_lat(ts->lat_percentiles ? "low prio_lat" : "low prio_clat",
- min, max, mean, dev, out);
+
+ /* Only print per prio stats if there are >= 2 prios with samples */
+ if (get_nr_prios_with_samples(ts, ddir) >= 2) {
+ for (i = 0; i < ts->nr_clat_prio[ddir]; i++) {
+ if (calc_lat(&ts->clat_prio[ddir][i].clat_stat, &min,
+ &max, &mean, &dev)) {
+ char buf[64];
+
+ snprintf(buf, sizeof(buf),
+ "%s prio %u/%u",
+ clat_type,
+ ts->clat_prio[ddir][i].ioprio >> 13,
+ ts->clat_prio[ddir][i].ioprio & 7);
+ display_lat(buf, min, max, mean, dev, out);
+ }
+ }
}
if (ts->slat_percentiles && ts->slat_stat[ddir].samples > 0)
ts->percentile_precision, "lat", out);
if (ts->clat_percentiles || ts->lat_percentiles) {
- const char *name = ts->lat_percentiles ? "lat" : "clat";
- char prio_name[32];
+ char prio_name[64];
uint64_t samples;
if (ts->lat_percentiles)
else
samples = ts->clat_stat[ddir].samples;
- /* Only print this if some high and low priority stats were collected */
- if (ts->clat_high_prio_stat[ddir].samples > 0 &&
- ts->clat_low_prio_stat[ddir].samples > 0)
- {
- sprintf(prio_name, "high prio (%.2f%%) %s",
- 100. * (double) ts->clat_high_prio_stat[ddir].samples / (double) samples,
- name);
- show_clat_percentiles(ts->io_u_plat_high_prio[ddir],
- ts->clat_high_prio_stat[ddir].samples,
- ts->percentile_list,
- ts->percentile_precision, prio_name, out);
-
- sprintf(prio_name, "low prio (%.2f%%) %s",
- 100. * (double) ts->clat_low_prio_stat[ddir].samples / (double) samples,
- name);
- show_clat_percentiles(ts->io_u_plat_low_prio[ddir],
- ts->clat_low_prio_stat[ddir].samples,
- ts->percentile_list,
- ts->percentile_precision, prio_name, out);
+ /* Only print per prio stats if there are >= 2 prios with samples */
+ if (get_nr_prios_with_samples(ts, ddir) >= 2) {
+ for (i = 0; i < ts->nr_clat_prio[ddir]; i++) {
+ uint64_t prio_samples = ts->clat_prio[ddir][i].clat_stat.samples;
+
+ if (prio_samples > 0) {
+ snprintf(prio_name, sizeof(prio_name),
+ "%s prio %u/%u (%.2f%% of IOs)",
+ clat_type,
+ ts->clat_prio[ddir][i].ioprio >> 13,
+ ts->clat_prio[ddir][i].ioprio & 7,
+ 100. * (double) prio_samples / (double) samples);
+ show_clat_percentiles(ts->clat_prio[ddir][i].io_u_plat,
+ prio_samples, ts->percentile_list,
+ ts->percentile_precision,
+ prio_name, out);
+ }
+ }
}
}
if (ts_lcl)
show_ddir_status(rs, ts_lcl, DDIR_READ, out);
+ free_clat_prio_stats(ts_lcl);
free(ts_lcl);
}
if (ts_lcl)
show_ddir_status_terse(ts_lcl, rs, DDIR_READ, ver, out);
+ free_clat_prio_stats(ts_lcl);
free(ts_lcl);
}
if (ts_lcl)
add_ddir_status_json(ts_lcl, rs, DDIR_READ, parent);
+ free_clat_prio_stats(ts_lcl);
free(ts_lcl);
}
return 0;
}
+static int grow_clat_prio_stat(struct thread_stat *dst, enum fio_ddir ddir)
+{
+ int curr_len = dst->nr_clat_prio[ddir];
+ void *new_arr;
+
+ new_arr = scalloc(curr_len + 1, sizeof(*dst->clat_prio[ddir]));
+ if (!new_arr) {
+ log_err("fio: failed to grow clat prio array\n");
+ return 1;
+ }
+
+ memcpy(new_arr, dst->clat_prio[ddir],
+ curr_len * sizeof(*dst->clat_prio[ddir]));
+ sfree(dst->clat_prio[ddir]);
+
+ dst->clat_prio[ddir] = new_arr;
+ dst->clat_prio[ddir][curr_len].clat_stat.min_val = ULONG_MAX;
+ dst->nr_clat_prio[ddir]++;
+
+ return 0;
+}
+
+static int find_clat_prio_index(struct thread_stat *dst, enum fio_ddir ddir,
+ uint32_t ioprio)
+{
+ int i, nr_prios = dst->nr_clat_prio[ddir];
+
+ for (i = 0; i < nr_prios; i++) {
+ if (dst->clat_prio[ddir][i].ioprio == ioprio)
+ return i;
+ }
+
+ return -1;
+}
+
+static int alloc_or_get_clat_prio_index(struct thread_stat *dst,
+ enum fio_ddir ddir, uint32_t ioprio,
+ int *idx)
+{
+ int index = find_clat_prio_index(dst, ddir, ioprio);
+
+ if (index == -1) {
+ index = dst->nr_clat_prio[ddir];
+
+ if (grow_clat_prio_stat(dst, ddir))
+ return 1;
+
+ dst->clat_prio[ddir][index].ioprio = ioprio;
+ }
+
+ *idx = index;
+
+ return 0;
+}
+
+static int clat_prio_stats_copy(struct thread_stat *dst, struct thread_stat *src,
+ enum fio_ddir dst_ddir, enum fio_ddir src_ddir)
+{
+ size_t sz = sizeof(*src->clat_prio[src_ddir]) *
+ src->nr_clat_prio[src_ddir];
+
+ dst->clat_prio[dst_ddir] = smalloc(sz);
+ if (!dst->clat_prio[dst_ddir]) {
+ log_err("fio: failed to alloc clat prio array\n");
+ return 1;
+ }
+
+ memcpy(dst->clat_prio[dst_ddir], src->clat_prio[src_ddir], sz);
+ dst->nr_clat_prio[dst_ddir] = src->nr_clat_prio[src_ddir];
+
+ return 0;
+}
+
+static int clat_prio_stat_add_samples(struct thread_stat *dst,
+ enum fio_ddir dst_ddir, uint32_t ioprio,
+ struct io_stat *io_stat,
+ uint64_t *io_u_plat)
+{
+ int i, dst_index;
+
+ if (!io_stat->samples)
+ return 0;
+
+ if (alloc_or_get_clat_prio_index(dst, dst_ddir, ioprio, &dst_index))
+ return 1;
+
+ sum_stat(&dst->clat_prio[dst_ddir][dst_index].clat_stat, io_stat,
+ false);
+
+ for (i = 0; i < FIO_IO_U_PLAT_NR; i++)
+ dst->clat_prio[dst_ddir][dst_index].io_u_plat[i] += io_u_plat[i];
+
+ return 0;
+}
+
+static int sum_clat_prio_stats_src_single_prio(struct thread_stat *dst,
+ struct thread_stat *src,
+ enum fio_ddir dst_ddir,
+ enum fio_ddir src_ddir)
+{
+ struct io_stat *io_stat;
+ uint64_t *io_u_plat;
+
+ /*
+ * If src ts has no clat_prio_stat array, then all I/Os were submitted
+ * using src->ioprio. Thus, the global samples in src->clat_stat (or
+ * src->lat_stat) can be used as the 'per prio' samples for src->ioprio.
+ */
+ assert(!src->clat_prio[src_ddir]);
+ assert(src->nr_clat_prio[src_ddir] == 0);
+
+ if (src->lat_percentiles) {
+ io_u_plat = src->io_u_plat[FIO_LAT][src_ddir];
+ io_stat = &src->lat_stat[src_ddir];
+ } else {
+ io_u_plat = src->io_u_plat[FIO_CLAT][src_ddir];
+ io_stat = &src->clat_stat[src_ddir];
+ }
+
+ return clat_prio_stat_add_samples(dst, dst_ddir, src->ioprio, io_stat,
+ io_u_plat);
+}
+
+static int sum_clat_prio_stats_src_multi_prio(struct thread_stat *dst,
+ struct thread_stat *src,
+ enum fio_ddir dst_ddir,
+ enum fio_ddir src_ddir)
+{
+ int i;
+
+ /*
+ * If src ts has a clat_prio_stat array, then there are multiple prios
+ * in use (i.e. src ts had cmdprio_percentage or cmdprio_bssplit set).
+ * The samples for the default prio will exist in the src->clat_prio
+ * array, just like the samples for any other prio.
+ */
+ assert(src->clat_prio[src_ddir]);
+ assert(src->nr_clat_prio[src_ddir]);
+
+ /* If the dst ts doesn't yet have a clat_prio array, simply memcpy. */
+ if (!dst->clat_prio[dst_ddir])
+ return clat_prio_stats_copy(dst, src, dst_ddir, src_ddir);
+
+ /* The dst ts already has a clat_prio_array, add src stats into it. */
+ for (i = 0; i < src->nr_clat_prio[src_ddir]; i++) {
+ struct io_stat *io_stat = &src->clat_prio[src_ddir][i].clat_stat;
+ uint64_t *io_u_plat = src->clat_prio[src_ddir][i].io_u_plat;
+ uint32_t ioprio = src->clat_prio[src_ddir][i].ioprio;
+
+ if (clat_prio_stat_add_samples(dst, dst_ddir, ioprio, io_stat, io_u_plat))
+ return 1;
+ }
+
+ return 0;
+}
+
+static int sum_clat_prio_stats(struct thread_stat *dst, struct thread_stat *src,
+ enum fio_ddir dst_ddir, enum fio_ddir src_ddir)
+{
+ if (dst->disable_prio_stat)
+ return 0;
+
+ if (!src->clat_prio[src_ddir])
+ return sum_clat_prio_stats_src_single_prio(dst, src, dst_ddir,
+ src_ddir);
+
+ return sum_clat_prio_stats_src_multi_prio(dst, src, dst_ddir, src_ddir);
+}
+
void sum_thread_stats(struct thread_stat *dst, struct thread_stat *src)
{
int k, l, m;
for (l = 0; l < DDIR_RWDIR_CNT; l++) {
if (dst->unified_rw_rep != UNIFIED_MIXED) {
sum_stat(&dst->clat_stat[l], &src->clat_stat[l], false);
- sum_stat(&dst->clat_high_prio_stat[l], &src->clat_high_prio_stat[l], false);
- sum_stat(&dst->clat_low_prio_stat[l], &src->clat_low_prio_stat[l], false);
sum_stat(&dst->slat_stat[l], &src->slat_stat[l], false);
sum_stat(&dst->lat_stat[l], &src->lat_stat[l], false);
sum_stat(&dst->bw_stat[l], &src->bw_stat[l], true);
sum_stat(&dst->iops_stat[l], &src->iops_stat[l], true);
+ sum_clat_prio_stats(dst, src, l, l);
dst->io_bytes[l] += src->io_bytes[l];
dst->runtime[l] = src->runtime[l];
} else {
sum_stat(&dst->clat_stat[0], &src->clat_stat[l], false);
- sum_stat(&dst->clat_high_prio_stat[0], &src->clat_high_prio_stat[l], false);
- sum_stat(&dst->clat_low_prio_stat[0], &src->clat_low_prio_stat[l], false);
sum_stat(&dst->slat_stat[0], &src->slat_stat[l], false);
sum_stat(&dst->lat_stat[0], &src->lat_stat[l], false);
sum_stat(&dst->bw_stat[0], &src->bw_stat[l], true);
sum_stat(&dst->iops_stat[0], &src->iops_stat[l], true);
+ sum_clat_prio_stats(dst, src, 0, l);
dst->io_bytes[0] += src->io_bytes[l];
for (k = 0; k < FIO_IO_U_PLAT_NR; k++)
dst->io_u_sync_plat[k] += src->io_u_sync_plat[k];
- for (k = 0; k < DDIR_RWDIR_CNT; k++) {
- for (m = 0; m < FIO_IO_U_PLAT_NR; m++) {
- if (dst->unified_rw_rep != UNIFIED_MIXED) {
- dst->io_u_plat_high_prio[k][m] += src->io_u_plat_high_prio[k][m];
- dst->io_u_plat_low_prio[k][m] += src->io_u_plat_low_prio[k][m];
- } else {
- dst->io_u_plat_high_prio[0][m] += src->io_u_plat_high_prio[k][m];
- dst->io_u_plat_low_prio[0][m] += src->io_u_plat_low_prio[k][m];
- }
-
- }
- }
-
dst->total_run_time += src->total_run_time;
dst->total_submit += src->total_submit;
dst->total_complete += src->total_complete;
ts->lat_stat[i].min_val = ULONG_MAX;
ts->bw_stat[i].min_val = ULONG_MAX;
ts->iops_stat[i].min_val = ULONG_MAX;
- ts->clat_high_prio_stat[i].min_val = ULONG_MAX;
- ts->clat_low_prio_stat[i].min_val = ULONG_MAX;
}
ts->sync_stat.min_val = ULONG_MAX;
}
log_info_flush();
free(runstats);
+
+ /* free arrays allocated by sum_thread_stats(), if any */
+ for (i = 0; i < nr_ts; i++) {
+ ts = &threadstats[i];
+ free_clat_prio_stats(ts);
+ }
free(threadstats);
free(opt_lists);
}
is->samples++;
}
+static inline void add_stat_prio_sample(struct clat_prio_stat *clat_prio,
+ unsigned short clat_prio_index,
+ unsigned long long nsec)
+{
+ if (clat_prio)
+ add_stat_sample(&clat_prio[clat_prio_index].clat_stat, nsec);
+}
+
/*
* Return a struct io_logs, which is added to the tail of the log
* list for 'iolog'.
io_u_plat[i] = 0;
}
+static inline void reset_clat_prio_stats(struct thread_stat *ts)
+{
+ enum fio_ddir ddir;
+ int i;
+
+ for (ddir = 0; ddir < DDIR_RWDIR_CNT; ddir++) {
+ if (!ts->clat_prio[ddir])
+ continue;
+
+ for (i = 0; i < ts->nr_clat_prio[ddir]; i++) {
+ reset_io_stat(&ts->clat_prio[ddir][i].clat_stat);
+ reset_io_u_plat(ts->clat_prio[ddir][i].io_u_plat);
+ }
+ }
+}
+
void reset_io_stats(struct thread_data *td)
{
struct thread_stat *ts = &td->ts;
int i, j;
for (i = 0; i < DDIR_RWDIR_CNT; i++) {
- reset_io_stat(&ts->clat_high_prio_stat[i]);
- reset_io_stat(&ts->clat_low_prio_stat[i]);
reset_io_stat(&ts->clat_stat[i]);
reset_io_stat(&ts->slat_stat[i]);
reset_io_stat(&ts->lat_stat[i]);
ts->total_io_u[i] = 0;
ts->short_io_u[i] = 0;
ts->drop_io_u[i] = 0;
-
- reset_io_u_plat(ts->io_u_plat_high_prio[i]);
- reset_io_u_plat(ts->io_u_plat_low_prio[i]);
}
for (i = 0; i < FIO_LAT_CNT; i++)
for (j = 0; j < DDIR_RWDIR_CNT; j++)
reset_io_u_plat(ts->io_u_plat[i][j]);
+ reset_clat_prio_stats(ts);
+
ts->total_io_u[DDIR_SYNC] = 0;
reset_io_u_plat(ts->io_u_sync_plat);
ts->io_u_plat[lat][ddir][idx]++;
}
-static inline void add_lat_percentile_prio_sample(struct thread_stat *ts,
- unsigned long long nsec,
- enum fio_ddir ddir,
- bool high_prio)
+static inline void
+add_lat_percentile_prio_sample(struct thread_stat *ts, unsigned long long nsec,
+ enum fio_ddir ddir,
+ unsigned short clat_prio_index)
{
unsigned int idx = plat_val_to_idx(nsec);
- if (!high_prio)
- ts->io_u_plat_low_prio[ddir][idx]++;
- else
- ts->io_u_plat_high_prio[ddir][idx]++;
+ if (ts->clat_prio[ddir])
+ ts->clat_prio[ddir][clat_prio_index].io_u_plat[idx]++;
}
void add_clat_sample(struct thread_data *td, enum fio_ddir ddir,
unsigned long long nsec, unsigned long long bs,
- uint64_t offset, unsigned int ioprio, bool high_prio)
+ uint64_t offset, unsigned int ioprio,
+ unsigned short clat_prio_index)
{
const bool needs_lock = td_async_processing(td);
unsigned long elapsed, this_window;
add_stat_sample(&ts->clat_stat[ddir], nsec);
/*
- * When lat_percentiles=1 (default 0), the reported high/low priority
+ * When lat_percentiles=1 (default 0), the reported per priority
* percentiles and stats are used for describing total latency values,
* even though the variable names themselves start with clat_.
*
* lat_percentiles=0. add_lat_sample() will add the prio stat sample
* when lat_percentiles=1.
*/
- if (!ts->lat_percentiles) {
- if (high_prio)
- add_stat_sample(&ts->clat_high_prio_stat[ddir], nsec);
- else
- add_stat_sample(&ts->clat_low_prio_stat[ddir], nsec);
- }
+ if (!ts->lat_percentiles)
+ add_stat_prio_sample(ts->clat_prio[ddir], clat_prio_index,
+ nsec);
if (td->clat_log)
add_log_sample(td, td->clat_log, sample_val(nsec), ddir, bs,
add_lat_percentile_sample(ts, nsec, ddir, FIO_CLAT);
if (!ts->lat_percentiles)
add_lat_percentile_prio_sample(ts, nsec, ddir,
- high_prio);
+ clat_prio_index);
}
if (iolog && iolog->hist_msec) {
void add_lat_sample(struct thread_data *td, enum fio_ddir ddir,
unsigned long long nsec, unsigned long long bs,
- uint64_t offset, unsigned int ioprio, bool high_prio)
+ uint64_t offset, unsigned int ioprio,
+ unsigned short clat_prio_index)
{
const bool needs_lock = td_async_processing(td);
struct thread_stat *ts = &td->ts;
offset, ioprio);
/*
- * When lat_percentiles=1 (default 0), the reported high/low priority
+ * When lat_percentiles=1 (default 0), the reported per priority
* percentiles and stats are used for describing total latency values,
* even though the variable names themselves start with clat_.
*
*/
if (ts->lat_percentiles) {
add_lat_percentile_sample(ts, nsec, ddir, FIO_LAT);
- add_lat_percentile_prio_sample(ts, nsec, ddir, high_prio);
- if (high_prio)
- add_stat_sample(&ts->clat_high_prio_stat[ddir], nsec);
- else
- add_stat_sample(&ts->clat_low_prio_stat[ddir], nsec);
-
+ add_lat_percentile_prio_sample(ts, nsec, ddir, clat_prio_index);
+ add_stat_prio_sample(ts->clat_prio[ddir], clat_prio_index,
+ nsec);
}
if (needs_lock)
__td_io_u_unlock(td);
projects / fio.git / blobdiff