#include "fio.h"
#include "steadystate.h"
-#include "helper_thread.h"
bool steadystate_enabled = false;
-static void steadystate_alloc(struct thread_data *td)
+void steadystate_free(struct thread_data *td)
{
- int i;
+ free(td->ss.iops_data);
+ free(td->ss.bw_data);
+ td->ss.iops_data = NULL;
+ td->ss.bw_data = NULL;
+}
- td->ss.bw_data = malloc(td->ss.dur * sizeof(uint64_t));
- td->ss.iops_data = malloc(td->ss.dur * sizeof(uint64_t));
- /* initialize so that it is obvious if the cache is not full in the output */
- for (i = 0; i < td->ss.dur; i++)
- td->ss.iops_data[i] = td->ss.bw_data[i] = 0;
+static void steadystate_alloc(struct thread_data *td)
+{
+ td->ss.bw_data = calloc(td->ss.dur, sizeof(uint64_t));
+ td->ss.iops_data = calloc(td->ss.dur, sizeof(uint64_t));
- td->ss.state |= __FIO_SS_DATA;
+ td->ss.state |= FIO_SS_DATA;
}
void steadystate_setup(void)
{
- int i, prev_groupid;
struct thread_data *td, *prev_td;
+ int i, prev_groupid;
if (!steadystate_enabled)
return;
}
if (prev_groupid != td->groupid) {
- if (prev_td != NULL) {
+ if (prev_td)
steadystate_alloc(prev_td);
- }
prev_groupid = td->groupid;
}
prev_td = td;
}
- if (prev_td != NULL && prev_td->o.group_reporting) {
+ if (prev_td && prev_td->o.group_reporting)
steadystate_alloc(prev_td);
- }
}
static bool steadystate_slope(uint64_t iops, uint64_t bw,
ss->bw_data[ss->tail] = bw;
ss->iops_data[ss->tail] = iops;
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
new_val = iops;
else
new_val = bw;
- if (ss->state & __FIO_SS_BUFFER_FULL || ss->tail - ss->head == ss->dur - 1) {
- if (!(ss->state & __FIO_SS_BUFFER_FULL)) {
+ if (ss->state & FIO_SS_BUFFER_FULL || ss->tail - ss->head == ss->dur - 1) {
+ if (!(ss->state & FIO_SS_BUFFER_FULL)) {
/* first time through */
for(i = 0, ss->sum_y = 0; i < ss->dur; i++) {
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
ss->sum_y += ss->iops_data[i];
else
ss->sum_y += ss->bw_data[i];
j = (ss->head + i) % ss->dur;
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
ss->sum_xy += i * ss->iops_data[j];
else
ss->sum_xy += i * ss->bw_data[j];
}
- ss->state |= __FIO_SS_BUFFER_FULL;
+ ss->state |= FIO_SS_BUFFER_FULL;
} else { /* easy to update the sums */
ss->sum_y -= ss->oldest_y;
ss->sum_y += new_val;
ss->sum_xy = ss->sum_xy - ss->sum_y + ss->dur * new_val;
}
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
ss->oldest_y = ss->iops_data[ss->head];
else
ss->oldest_y = ss->bw_data[ss->head];
*/
ss->slope = (ss->sum_xy - (double) ss->sum_x * ss->sum_y / ss->dur) /
(ss->sum_x_sq - (double) ss->sum_x * ss->sum_x / ss->dur);
- if (ss->state & __FIO_SS_PCT)
+ if (ss->state & FIO_SS_PCT)
ss->criterion = 100.0 * ss->slope / (ss->sum_y / ss->dur);
else
ss->criterion = ss->slope;
ss->bw_data[ss->tail] = bw;
ss->iops_data[ss->tail] = iops;
- if (ss->state & __FIO_SS_BUFFER_FULL || ss->tail - ss->head == ss->dur - 1) {
- if (!(ss->state & __FIO_SS_BUFFER_FULL)) {
+ if (ss->state & FIO_SS_BUFFER_FULL || ss->tail - ss->head == ss->dur - 1) {
+ if (!(ss->state & FIO_SS_BUFFER_FULL)) {
/* first time through */
for(i = 0, ss->sum_y = 0; i < ss->dur; i++)
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
ss->sum_y += ss->iops_data[i];
else
ss->sum_y += ss->bw_data[i];
- ss->state |= __FIO_SS_BUFFER_FULL;
+ ss->state |= FIO_SS_BUFFER_FULL;
} else { /* easy to update the sum */
ss->sum_y -= ss->oldest_y;
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
ss->sum_y += ss->iops_data[ss->tail];
else
ss->sum_y += ss->bw_data[ss->tail];
}
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
ss->oldest_y = ss->iops_data[ss->head];
else
ss->oldest_y = ss->bw_data[ss->head];
ss->deviation = 0.0;
for (i = 0; i < ss->dur; i++) {
- if (ss->state & __FIO_SS_IOPS)
+ if (ss->state & FIO_SS_IOPS)
diff = ss->iops_data[i] - mean;
else
diff = ss->bw_data[i] - mean;
ss->deviation = max(ss->deviation, diff * (diff < 0.0 ? -1.0 : 1.0));
}
- if (ss->state & __FIO_SS_PCT)
+ if (ss->state & FIO_SS_PCT)
ss->criterion = 100.0 * ss->deviation / mean;
else
ss->criterion = ss->deviation;
int i, j, ddir, prev_groupid, group_ramp_time_over = 0;
unsigned long rate_time;
struct thread_data *td, *td2;
- struct timeval now;
+ struct timespec now;
uint64_t group_bw = 0, group_iops = 0;
uint64_t td_iops, td_bytes;
bool ret;
prev_groupid = -1;
for_each_td(td, i) {
+ const bool needs_lock = td_async_processing(td);
struct steadystate_data *ss = &td->ss;
if (!ss->dur || td->runstate <= TD_SETTING_UP ||
- td->runstate >= TD_EXITED || (ss->state & __FIO_SS_ATTAINED))
+ td->runstate >= TD_EXITED || !ss->state ||
+ ss->state & FIO_SS_ATTAINED)
continue;
td_iops = 0;
prev_groupid = td->groupid;
fio_gettime(&now, NULL);
- if (ss->ramp_time && !(ss->state & __FIO_SS_RAMP_OVER)) {
+ if (ss->ramp_time && !(ss->state & FIO_SS_RAMP_OVER)) {
/*
* Begin recording data one second after ss->ramp_time
* has elapsed
*/
if (utime_since(&td->epoch, &now) >= (ss->ramp_time + 1000000L))
- ss->state |= __FIO_SS_RAMP_OVER;
+ ss->state |= FIO_SS_RAMP_OVER;
}
- td_io_u_lock(td);
- for (ddir = DDIR_READ; ddir < DDIR_RWDIR_CNT; ddir++) {
+ if (needs_lock)
+ __td_io_u_lock(td);
+
+ for (ddir = 0; ddir < DDIR_RWDIR_CNT; ddir++) {
td_iops += td->io_blocks[ddir];
td_bytes += td->io_bytes[ddir];
}
- td_io_u_unlock(td);
+
+ if (needs_lock)
+ __td_io_u_unlock(td);
rate_time = mtime_since(&ss->prev_time, &now);
memcpy(&ss->prev_time, &now, sizeof(now));
* prev_iops/bw the first time through after ss->ramp_time
* is done.
*/
- if (ss->state & __FIO_SS_RAMP_OVER) {
+ if (ss->state & FIO_SS_RAMP_OVER) {
group_bw += 1000 * (td_bytes - ss->prev_bytes) / rate_time;
group_iops += 1000 * (td_iops - ss->prev_iops) / rate_time;
++group_ramp_time_over;
ss->prev_iops = td_iops;
ss->prev_bytes = td_bytes;
- if (td->o.group_reporting && !(ss->state & __FIO_SS_DATA))
+ if (td->o.group_reporting && !(ss->state & FIO_SS_DATA))
continue;
/*
(unsigned long long) group_bw,
ss->head, ss->tail);
- if (td->o.ss & __FIO_SS_SLOPE)
+ if (ss->state & FIO_SS_SLOPE)
ret = steadystate_slope(group_iops, group_bw, td);
else
ret = steadystate_deviation(group_iops, group_bw, td);
if (td->o.group_reporting) {
for_each_td(td2, j) {
if (td2->groupid == td->groupid) {
- td2->ss.state |= __FIO_SS_ATTAINED;
+ td2->ss.state |= FIO_SS_ATTAINED;
fio_mark_td_terminate(td2);
}
}
} else {
- ss->state |= __FIO_SS_ATTAINED;
+ ss->state |= FIO_SS_ATTAINED;
fio_mark_td_terminate(td);
}
}
ss->limit = o->ss_limit.u.f;
ss->ramp_time = o->ss_ramp_time;
- ss->state = o->ss;
+ ss->state = o->ss_state;
if (!td->ss.ramp_time)
- ss->state |= __FIO_SS_RAMP_OVER;
+ ss->state |= FIO_SS_RAMP_OVER;
ss->sum_x = o->ss_dur * (o->ss_dur - 1) / 2;
ss->sum_x_sq = (o->ss_dur - 1) * (o->ss_dur) * (2*o->ss_dur - 1) / 6;
int i;
uint64_t sum;
+ if (!ts->ss_dur)
+ return 0;
+
for (i = 0, sum = 0; i < ts->ss_dur; i++)
sum += ts->ss_bw_data[i];
int i;
uint64_t sum;
+ if (!ts->ss_dur)
+ return 0;
+
for (i = 0, sum = 0; i < ts->ss_dur; i++)
sum += ts->ss_iops_data[i];