There are a couple of issues in eta.c: - The comparison for time- vs. rate-based ETA calculation is done the wrong way round. - The elapsed ramp time should only be subtracted when the thread has indeed entered the ramp phase. - Currently jobs that are stonewalled are not taken into account for ETA calculation. This patch at least fixes this for the case that there is only a single job per stonewall group. ---
This patch tries to fix some issues I have found, this may also be related to the ones mentioned earlier in http://www.spinics.net/lists/fio/msg04187.html The part regarding stonewalled jobs may require some further work, but at least it gives proper values now for my standard fio runs containing just a sequence of singular jobs. Also, I'm still wondering about the intention behind the way done_secs is meant to work. It cumulates time spent in finished jobs globally, but is being used in per-job ETA calculations. This seems to break at least for the case of stonewalled jobs, too. eta.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/eta.c b/eta.c index 7eb1c27..e73cc2c 100644 --- a/eta.c +++ b/eta.c @@ -214,7 +214,7 @@ static unsigned long thread_eta(struct thread_data *td) if (td->o.time_based) { if (timeout) { perc_t = (double) elapsed / (double) timeout; - if (perc_t < perc) + if (perc_t > perc) perc = perc_t; } else { /* @@ -226,6 +226,7 @@ static unsigned long thread_eta(struct thread_data *td) } eta_sec = (unsigned long) (elapsed * (1.0 / perc)) - elapsed; + // printf("eta_sec: %lu, elapsed: %lu, perc: %02.6f, done: %llu, total: %llu\n", eta_sec, elapsed, perc, bytes_done, bytes_total); if (td->o.timeout && eta_sec > (timeout + done_secs - elapsed)) @@ -250,7 +251,7 @@ static unsigned long thread_eta(struct thread_data *td) t_eta = __timeout + start_delay + ramp_time; t_eta /= 1000000ULL; - if (in_ramp_time(td)) { + if ((td->runstate == TD_RAMP) && in_ramp_time(td)) { unsigned long ramp_left; ramp_left = mtime_since_now(&td->epoch); @@ -438,19 +439,25 @@ int calc_thread_status(struct jobs_eta *je, int force) } } - if (exitall_on_terminate) + if (exitall_on_terminate) { je->eta_sec = INT_MAX; - else - je->eta_sec = 0; - - for_each_td(td, i) { - if (exitall_on_terminate) { + for_each_td(td, i) { if (eta_secs[i] < je->eta_sec) je->eta_sec = eta_secs[i]; - } else { - if (eta_secs[i] > je->eta_sec) - je->eta_sec = eta_secs[i]; } + } else { + unsigned long eta_stone = 0; + je->eta_sec = 0; + for_each_td(td, i) { + if ((td->runstate == TD_NOT_CREATED) && (td->o.stonewall)) { + eta_stone += eta_secs[i]; + } else { + if (eta_secs[i] > je->eta_sec) + je->eta_sec = eta_secs[i]; + } + } + je->eta_sec += eta_stone; + // printf("stoned: %lu\n", eta_stone); } free(eta_secs); -- 2.4.10 -- To unsubscribe from this list: send the line "unsubscribe fio" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
