#include <math.h>
#include "fio.h"
+#include "diskutil.h"
+#include "ieee754.h"
+
+void update_rusage_stat(struct thread_data *td)
+{
+ struct thread_stat *ts = &td->ts;
+
+ 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));
+}
/*
- * Cheesy number->string conversion, complete with carry rounding error.
+ * 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 char *num2str(unsigned long num, int maxlen, int base, int pow2)
+static unsigned int plat_val_to_idx(unsigned int val)
{
- char postfix[] = { ' ', 'K', 'M', 'G', 'P', 'E' };
- unsigned int thousand;
- char *buf;
- int i;
+ unsigned int msb, error_bits, base, offset, idx;
- if (pow2)
- thousand = 1024;
+ /* Find MSB starting from bit 0 */
+ if (val == 0)
+ msb = 0;
else
- thousand = 1000;
+ msb = (sizeof(val)*8) - __builtin_clz(val) - 1;
- buf = malloc(128);
+ /*
+ * 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;
- for (i = 0; base > 1; i++)
- base /= thousand;
+ /* Compute the number of error bits to discard*/
+ error_bits = msb - FIO_IO_U_PLAT_BITS;
- do {
- int len, carry = 0;
+ /* Compute the number of buckets before the group */
+ base = (error_bits + 1) << FIO_IO_U_PLAT_BITS;
- len = sprintf(buf, "%'lu", num);
- if (len <= maxlen) {
- if (i >= 1) {
- buf[len] = postfix[i];
- buf[len + 1] = '\0';
- }
- return buf;
- }
+ /*
+ * 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);
- if ((num % thousand) >= (thousand / 2))
- carry = 1;
+ /* 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);
- num /= thousand;
- num += carry;
- i++;
- } while (i <= 5);
+ 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;
- return buf;
+ /* 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));
}
-void update_rusage_stat(struct thread_data *td)
+static int double_cmp(const void *a, const void *b)
{
- struct thread_stat *ts = &td->ts;
+ 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.u.f > fb.u.f)
+ cmp = 1;
+ else if (fa.u.f < fb.u.f)
+ cmp = -1;
+
+ return cmp;
+}
- getrusage(RUSAGE_SELF, &ts->ru_end);
+/*
+ * 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 long sum = 0;
+ unsigned int len, i, j = 0;
+ int is_last = 0;
+
+ len = 0;
+ while (len < FIO_IO_U_LIST_MAX_LEN && plist[len].u.f != 0.0)
+ len++;
+
+ /*
+ * Sort the percentile list. Note that it may already be sorted if
+ * we are using the default values, but since it's a short list this
+ * isn't a worry. Also note that this does not work for NaN values.
+ */
+ if (len > 1)
+ qsort((void*)plist, len, sizeof(plist[0]), double_cmp);
+
+ log_info(" clat percentiles (usec) :");
- 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;
+ for (i = 0; i < FIO_IO_U_PLAT_NR && !is_last; i++) {
+ sum += io_u_plat[i];
+ while (sum >= (plist[j].u.f / 100.0 * nr)) {
+ assert(plist[j].u.f <= 100.0);
- memcpy(&ts->ru_start, &ts->ru_end, sizeof(ts->ru_end));
+ /* 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,
*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("\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);
+
if (!rs->max_run[i])
continue;
- p1 = num2str(rs->io_kb[i], 6, 1000, 1);
- p2 = num2str(rs->agg[i], 6, 1000, 1);
- p3 = num2str(rs->min_bw[i], 6, 1000, 1);
- p4 = num2str(rs->max_bw[i], 6, 1000, 1);
+ p1 = num2str(rs->io_kb[i], 6, rs->kb_base, i2p);
+ p2 = num2str(rs->agg[i], 6, rs->kb_base, i2p);
+ p3 = num2str(rs->min_bw[i], 6, rs->kb_base, i2p);
+ p4 = num2str(rs->max_bw[i], 6, rs->kb_base, i2p);
- log_info("%s: io=%siB, aggrb=%siB/s, minb=%siB/s, maxb=%siB/s,"
+ log_info("%s: io=%sB, aggrb=%sB/s, minb=%sB/s, maxb=%sB/s,"
" mint=%llumsec, maxt=%llumsec\n", ddir_str[i], p1, p2,
p3, p4, rs->min_run[i],
rs->max_run[i]);
int ddir)
{
const char *ddir_str[] = { "read ", "write" };
- unsigned long min, max;
+ unsigned long min, max, runt;
unsigned long long bw, iops;
double mean, dev;
char *io_p, *bw_p, *iops_p;
+ int i2p;
+
+ assert(ddir_rw(ddir));
if (!ts->runtime[ddir])
return;
- bw = ts->io_bytes[ddir] / ts->runtime[ddir];
- iops = (1000 * ts->total_io_u[ddir]) / ts->runtime[ddir];
- io_p = num2str(ts->io_bytes[ddir] >> 10, 6, 1000, 1);
- bw_p = num2str(bw, 6, 1000, 1);
+ i2p = is_power_of_2(rs->kb_base);
+ runt = ts->runtime[ddir];
+
+ bw = (1000 * ts->io_bytes[ddir]) / runt;
+ io_p = num2str(ts->io_bytes[ddir], 6, 1, i2p);
+ bw_p = num2str(bw, 6, 1, i2p);
+
+ iops = (1000 * (uint64_t)ts->total_io_u[ddir]) / runt;
iops_p = num2str(iops, 6, 1, 0);
- log_info(" %s: io=%siB, bw=%siB/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]);
free(minp);
free(maxp);
}
+ if (calc_lat(&ts->lat_stat[ddir], &min, &max, &mean, &dev)) {
+ const char *base = "(usec)";
+ char *minp, *maxp;
+
+ if (!usec_to_msec(&min, &max, &mean, &dev))
+ base = "(msec)";
+
+ minp = num2str(min, 6, 1, 0);
+ maxp = num2str(max, 6, 1, 0);
+
+ log_info(" lat %s: min=%s, max=%s, avg=%5.02f,"
+ " stdev=%5.02f\n", base, minp, maxp, mean, dev);
+
+ 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;
p_of_agg = mean * 100 / (double) rs->agg[ddir];
- log_info(" bw (KiB/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);
}
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;
io_u_dist[1], io_u_dist[2],
io_u_dist[3], io_u_dist[4],
io_u_dist[5], io_u_dist[6]);
- log_info(" issued r/w: total=%lu/%lu, short=%lu/%lu\n",
+ log_info(" issued r/w/d: total=%lu/%lu/%lu, short=%lu/%lu/%lu\n",
ts->total_io_u[0], ts->total_io_u[1],
- ts->short_io_u[0], ts->short_io_u[1]);
+ ts->total_io_u[2],
+ ts->short_io_u[0], ts->short_io_u[1],
+ ts->short_io_u[2]);
stat_calc_lat_u(ts, io_u_lat_u);
stat_calc_lat_m(ts, io_u_lat_m);
show_latencies(io_u_lat_u, io_u_lat_m);
+ if (ts->continue_on_error) {
+ log_info(" errors : total=%lu, first_error=%d/<%s>\n",
+ ts->total_err_count,
+ ts->first_error,
+ strerror(ts->first_error));
+ }
}
static void show_ddir_status_terse(struct thread_stat *ts,
unsigned long long bw;
double mean, dev;
+ assert(ddir_rw(ddir));
+
bw = 0;
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))
else
log_info(";%lu;%lu;%f;%f", 0UL, 0UL, 0.0, 0.0);
+ if (calc_lat(&ts->lat_stat[ddir], &min, &max, &mean, &dev))
+ log_info(";%lu;%lu;%f;%f", min, max, mean, dev);
+ else
+ log_info(";%lu;%lu;%f;%f", 0UL, 0UL, 0.0, 0.0);
+
if (calc_lat(&ts->bw_stat[ddir], &min, &max, &mean, &dev)) {
double p_of_agg;
log_info(";%lu;%lu;%f%%;%f;%f", 0UL, 0UL, 0.0, 0.0, 0.0);
}
+#define FIO_TERSE_VERSION "2"
static void show_thread_status_terse(struct thread_stat *ts,
struct group_run_stats *rs)
double usr_cpu, sys_cpu;
int i;
- log_info("%s;%d;%d", ts->name, ts->groupid, ts->error);
-
+ /* General Info */
+ log_info("%s;%s;%d;%d", FIO_TERSE_VERSION, ts->name, ts->groupid,
+ ts->error);
+ /* Log Read Status */
show_ddir_status_terse(ts, rs, 0);
+ /* Log Write Status */
show_ddir_status_terse(ts, rs, 1);
+ /* CPU Usage */
if (ts->total_run_time) {
double runt = (double) ts->total_run_time;
log_info(";%f%%;%f%%;%lu;%lu;%lu", usr_cpu, sys_cpu, ts->ctx, ts->majf,
ts->minf);
+ /* Calc % distribution of IO depths, usecond, msecond latency */
stat_calc_dist(ts->io_u_map, ts_total_io_u(ts), io_u_dist);
stat_calc_lat_u(ts, io_u_lat_u);
stat_calc_lat_m(ts, io_u_lat_m);
+ /* Only show fixed 7 I/O depth levels*/
log_info(";%3.1f%%;%3.1f%%;%3.1f%%;%3.1f%%;%3.1f%%;%3.1f%%;%3.1f%%",
io_u_dist[0], io_u_dist[1], io_u_dist[2], io_u_dist[3],
io_u_dist[4], io_u_dist[5], io_u_dist[6]);
+ /* Microsecond latency */
for (i = 0; i < FIO_IO_U_LAT_U_NR; i++)
log_info(";%3.2f%%", io_u_lat_u[i]);
+ /* Millisecond latency */
for (i = 0; i < FIO_IO_U_LAT_M_NR; i++)
log_info(";%3.2f%%", io_u_lat_m[i]);
+ /* 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);
log_info("\n");
+ /* Additional output if description is set */
if (ts->description)
log_info(";%s", ts->description);
{
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
+ * <http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
+ * #Parallel_algorithm>
*/
if (nr == 1) {
- mean = src->mean;
- S = src->S;
+ mean = src->mean.u.f;
+ S = src->S.u.f;
} 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.u.f - dst->mean.u.f;
+
+ mean = ((src->mean.u.f * src->samples) +
+ (dst->mean.u.f * dst->samples)) /
+ (dst->samples + src->samples);
+
+ S = src->S.u.f + dst->S.u.f + pow(delta, 2.0) *
+ (dst->samples * src->samples) /
+ (dst->samples + src->samples);
}
- dst->mean = mean;
- dst->S = S;
+ dst->samples += src->samples;
+ dst->mean.u.f = mean;
+ dst->S.u.f = S;
}
void show_run_stats(void)
struct thread_data *td;
struct thread_stat *threadstats, *ts;
int i, j, k, l, nr_ts, last_ts, idx;
+ int kb_base_warned = 0;
runstats = malloc(sizeof(struct group_run_stats) * (groupid + 1));
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 = &threadstats[j];
+ ts->clat_percentiles = td->o.clat_percentiles;
+ if (td->o.overwrite_plist)
+ memcpy(ts->percentile_list, td->o.percentile_list, sizeof(td->o.percentile_list));
+ else
+ memcpy(ts->percentile_list, def_percentile_list, sizeof(def_percentile_list));
+
idx++;
ts->members++;
/*
* 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;
/*
* first pid in group, not very useful...
*/
ts->pid = td->pid;
+
+ ts->kb_base = td->o.kb_base;
+ } else if (ts->kb_base != td->o.kb_base && !kb_base_warned) {
+ log_info("fio: kb_base differs for jobs in group, using"
+ " %u as the base\n", ts->kb_base);
+ kb_base_warned = 1;
}
- if (td->error && !ts->error) {
- ts->error = td->error;
- ts->verror = td->verror;
+ ts->continue_on_error = td->o.continue_on_error;
+ ts->total_err_count += td->total_err_count;
+ ts->first_error = td->first_error;
+ if (!ts->error) {
+ if (!td->error && td->o.continue_on_error &&
+ td->first_error) {
+ ts->error = td->first_error;
+ strcpy(ts->verror, td->verror);
+ } else if (td->error) {
+ ts->error = td->error;
+ strcpy(ts->verror, td->verror);
+ }
}
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->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])
ts->io_u_lat_m[k] += td->ts.io_u_lat_m[k];
- for (k = 0; k <= DDIR_WRITE; 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;
ts = &threadstats[i];
rs = &runstats[ts->groupid];
+ rs->kb_base = ts->kb_base;
for (j = 0; j <= DDIR_WRITE; j++) {
if (!ts->runtime[j])
rs->max_run[j] = ts->runtime[j];
bw = 0;
- if (ts->runtime[j])
- bw = ts->io_bytes[j]
- / (unsigned long long) ts->runtime[j];
+ if (ts->runtime[j]) {
+ unsigned long runt;
+
+ runt = ts->runtime[j];
+ bw = ts->io_bytes[j] / runt;
+ }
if (bw < rs->min_bw[j])
rs->min_bw[j] = bw;
if (bw > rs->max_bw[j])
rs->max_bw[j] = bw;
- rs->io_kb[j] += ts->io_bytes[j] >> 10;
+ rs->io_kb[j] += ts->io_bytes[j] / rs->kb_base;
}
}
for (i = 0; i < groupid + 1; i++) {
+ unsigned long max_run[2];
+
rs = &runstats[i];
+ max_run[0] = rs->max_run[0];
+ max_run[1] = rs->max_run[1];
if (rs->max_run[0])
- rs->agg[0] = (rs->io_kb[0]*1024) / rs->max_run[0];
+ rs->agg[0] = (rs->io_kb[0] * 1000) / max_run[0];
if (rs->max_run[1])
- rs->agg[1] = (rs->io_kb[1]*1024) / rs->max_run[1];
+ rs->agg[1] = (rs->io_kb[1] * 1000) / max_run[1];
}
/*
* don't overwrite last signal output
*/
if (!terse_output)
- printf("\n");
+ log_info("\n");
for (i = 0; i < nr_ts; i++) {
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();
}
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++;
}
static void __add_log_sample(struct io_log *iolog, unsigned long val,
- enum fio_ddir ddir, unsigned long time)
+ enum fio_ddir ddir, unsigned int bs,
+ unsigned long t)
{
+ const int nr_samples = iolog->nr_samples;
+
if (iolog->nr_samples == iolog->max_samples) {
int new_size = sizeof(struct io_sample) * iolog->max_samples*2;
iolog->max_samples <<= 1;
}
- iolog->log[iolog->nr_samples].val = val;
- iolog->log[iolog->nr_samples].time = time;
- iolog->log[iolog->nr_samples].ddir = ddir;
+ iolog->log[nr_samples].val = val;
+ iolog->log[nr_samples].time = t;
+ iolog->log[nr_samples].ddir = ddir;
+ iolog->log[nr_samples].bs = bs;
iolog->nr_samples++;
}
static void add_log_sample(struct thread_data *td, struct io_log *iolog,
- unsigned long val, enum fio_ddir ddir)
+ unsigned long val, enum fio_ddir ddir,
+ unsigned int bs)
+{
+ if (!ddir_rw(ddir))
+ return;
+
+ __add_log_sample(iolog, val, ddir, bs, mtime_since_now(&td->epoch));
+}
+
+void add_agg_sample(unsigned long val, enum fio_ddir ddir, unsigned int bs)
{
- __add_log_sample(iolog, val, ddir, mtime_since_now(&td->epoch));
+ struct io_log *iolog;
+
+ if (!ddir_rw(ddir))
+ return;
+
+ iolog = agg_io_log[ddir];
+ __add_log_sample(iolog, val, ddir, bs, mtime_since_genesis());
}
-void add_agg_sample(unsigned long val, enum fio_ddir ddir)
+static void add_clat_percentile_sample(struct thread_stat *ts,
+ unsigned long usec, enum fio_ddir ddir)
{
- struct io_log *iolog = agg_io_log[ddir];
+ unsigned int idx = plat_val_to_idx(usec);
+ assert(idx < FIO_IO_U_PLAT_NR);
- __add_log_sample(iolog, val, ddir, mtime_since_genesis());
+ ts->io_u_plat[ddir][idx]++;
}
void add_clat_sample(struct thread_data *td, enum fio_ddir ddir,
- unsigned long usec)
+ unsigned long usec, unsigned int bs)
{
struct thread_stat *ts = &td->ts;
+ if (!ddir_rw(ddir))
+ return;
+
add_stat_sample(&ts->clat_stat[ddir], usec);
- if (ts->clat_log)
- add_log_sample(td, ts->clat_log, usec, ddir);
+ 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,
- unsigned long usec)
+ unsigned long usec, unsigned int bs)
{
struct thread_stat *ts = &td->ts;
+ if (!ddir_rw(ddir))
+ return;
+
add_stat_sample(&ts->slat_stat[ddir], usec);
- if (ts->slat_log)
- add_log_sample(td, ts->slat_log, usec, ddir);
+ 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,
+ unsigned long usec, unsigned int bs)
+{
+ struct thread_stat *ts = &td->ts;
+
+ if (!ddir_rw(ddir))
+ return;
+
+ add_stat_sample(&ts->lat_stat[ddir], usec);
+
+ 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,
+void add_bw_sample(struct thread_data *td, enum fio_ddir ddir, unsigned int bs,
struct timeval *t)
{
struct thread_stat *ts = &td->ts;
- unsigned long spent = mtime_since(&ts->stat_sample_time[ddir], t);
- unsigned long rate;
+ unsigned long spent, rate;
+
+ if (!ddir_rw(ddir))
+ return;
+ 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]) / spent;
+ 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);
+ 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];
}