On 2/1/22 06:13, Niklas Cassel wrote:
> From: Niklas Cassel <niklas.cassel@xxxxxxx>
>
> Convert the stat code to report clat stats on a per priority granularity,
> rather than simply supporting high/low priority.
>
> This is made possible by using the new clat_prio_stat array (per ddir),
> together with the clat_prio_stat index which is saved in each io_u.
>
> The per priority samples are only printed when there are samples for more
> than one priority in the clat_prio_stat array. If there are only samples
> for one priority, that means that all I/Os where submitted using the same
> priority, so no need to print.
>
> For example, running the following fio command:
> fio --name=test --filename=/dev/sdc --direct=1 --runtime=60 --rw=randread \
> --ioengine=io_uring --ioscheduler=mq-deadline --iodepth=32 --bs=32k \
> --prioclass=2 --prio=7 --cmdprio_bssplit=32k/20/3/0:32k/10/1/4
>
> Now results in the following output:
> test: (groupid=0, jobs=1): err= 0: pid=465655: Tue Feb 1 02:24:47 2022
> read: IOPS=146, BW=4695KiB/s (4808kB/s)(276MiB/60239msec)
> slat (usec): min=18, max=335, avg=62.87, stdev=22.59
> clat (msec): min=2, max=2135, avg=217.97, stdev=287.26
> lat (msec): min=2, max=2135, avg=218.03, stdev=287.26
> clat prio 2/7 (msec): min=3, max=606, avg=106.57, stdev=86.64
> clat prio 3/0 (msec): min=10, max=2135, avg=664.94, stdev=339.42
> clat prio 1/4 (msec): min=2, max=300, avg=52.29, stdev=42.52
> clat percentiles (msec):
> | 1.00th=[ 8], 5.00th=[ 14], 10.00th=[ 19], 20.00th=[ 33],
> | 30.00th=[ 52], 40.00th=[ 77], 50.00th=[ 108], 60.00th=[ 144],
> | 70.00th=[ 192], 80.00th=[ 300], 90.00th=[ 684], 95.00th=[ 911],
> | 99.00th=[ 1234], 99.50th=[ 1318], 99.90th=[ 1687], 99.95th=[ 1770],
> | 99.99th=[ 2140]
> clat prio 2/7 (69.25% of IOs) percentiles (msec):
> | 1.00th=[ 7], 5.00th=[ 13], 10.00th=[ 17], 20.00th=[ 28],
> | 30.00th=[ 44], 40.00th=[ 64], 50.00th=[ 85], 60.00th=[ 111],
> | 70.00th=[ 140], 80.00th=[ 174], 90.00th=[ 226], 95.00th=[ 279],
> | 99.00th=[ 368], 99.50th=[ 418], 99.90th=[ 502], 99.95th=[ 567],
> | 99.99th=[ 609]
> clat prio 3/0 (20.91% of IOs) percentiles (msec):
> | 1.00th=[ 44], 5.00th=[ 138], 10.00th=[ 205], 20.00th=[ 347],
> | 30.00th=[ 464], 40.00th=[ 558], 50.00th=[ 659], 60.00th=[ 760],
> | 70.00th=[ 860], 80.00th=[ 961], 90.00th=[ 1099], 95.00th=[ 1217],
> | 99.00th=[ 1485], 99.50th=[ 1687], 99.90th=[ 1871], 99.95th=[ 2140],
> | 99.99th=[ 2140]
> clat prio 1/4 (9.84% of IOs) percentiles (msec):
> | 1.00th=[ 7], 5.00th=[ 10], 10.00th=[ 13], 20.00th=[ 18],
> | 30.00th=[ 24], 40.00th=[ 30], 50.00th=[ 39], 60.00th=[ 51],
> | 70.00th=[ 63], 80.00th=[ 84], 90.00th=[ 114], 95.00th=[ 136],
> | 99.00th=[ 188], 99.50th=[ 197], 99.90th=[ 300], 99.95th=[ 300],
> | 99.99th=[ 300]
> bw ( KiB/s): min= 3456, max= 5888, per=100.00%, avg=4697.60, stdev=472.38, samples=120
> iops : min= 108, max= 184, avg=146.80, stdev=14.76, samples=120
> lat (msec) : 4=0.11%, 10=2.57%, 20=8.67%, 50=18.21%, 100=18.34%
> lat (msec) : 250=28.87%, 500=9.41%, 750=5.22%, 1000=5.09%, 2000=3.50%
> lat (msec) : >=2000=0.01%
> cpu : usr=0.16%, sys=0.97%, ctx=17715, majf=0, minf=262
> IO depths : 1=0.1%, 2=0.1%, 4=0.1%, 8=0.1%, 16=0.2%, 32=99.6%, >=64=0.0%
> submit : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
> complete : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.1%, 64=0.0%, >=64=0.0%
> issued rwts: total=8839,0,0,0 short=0,0,0,0 dropped=0,0,0,0
> latency : target=0, window=0, percentile=100.00%, depth=32
Nice !
>
> Signed-off-by: Niklas Cassel <niklas.cassel@xxxxxxx>
> ---
> client.c | 31 +++-
> engines/filecreate.c | 2 +-
> engines/filedelete.c | 2 +-
> engines/filestat.c | 2 +-
> io_u.c | 6 +-
> io_u.h | 2 -
> server.c | 41 ++++-
> server.h | 2 +-
> stat.c | 353 +++++++++++++++++++++++++++++++++----------
> stat.h | 4 +-
> 10 files changed, 341 insertions(+), 104 deletions(-)
>
> diff --git a/client.c b/client.c
> index e5f6cfa7..61c6b930 100644
> --- a/client.c
> +++ b/client.c
> @@ -1037,14 +1037,6 @@ static void convert_ts(struct thread_stat *dst, struct thread_stat *src)
> dst->nr_block_infos = le64_to_cpu(src->nr_block_infos);
> for (i = 0; i < dst->nr_block_infos; i++)
> dst->block_infos[i] = le32_to_cpu(src->block_infos[i]);
> - for (i = 0; i < DDIR_RWDIR_CNT; i++) {
> - for (j = 0; j < FIO_IO_U_PLAT_NR; j++) {
> - dst->io_u_plat_high_prio[i][j] = le64_to_cpu(src->io_u_plat_high_prio[i][j]);
> - dst->io_u_plat_low_prio[i][j] = le64_to_cpu(src->io_u_plat_low_prio[i][j]);
> - }
> - convert_io_stat(&dst->clat_high_prio_stat[i], &src->clat_high_prio_stat[i]);
> - convert_io_stat(&dst->clat_low_prio_stat[i], &src->clat_low_prio_stat[i]);
> - }
>
> dst->ss_dur = le64_to_cpu(src->ss_dur);
> dst->ss_state = le32_to_cpu(src->ss_state);
> @@ -1054,6 +1046,19 @@ static void convert_ts(struct thread_stat *dst, struct thread_stat *src)
> dst->ss_deviation.u.f = fio_uint64_to_double(le64_to_cpu(src->ss_deviation.u.i));
> dst->ss_criterion.u.f = fio_uint64_to_double(le64_to_cpu(src->ss_criterion.u.i));
>
> + for (i = 0; i < DDIR_RWDIR_CNT; i++) {
> + dst->nr_clat_prio[i] = le32_to_cpu(src->nr_clat_prio[i]);
> + for (j = 0; j < dst->nr_clat_prio[i]; j++) {
> + for (k = 0; k < FIO_IO_U_PLAT_NR; k++)
> + dst->clat_prio[i][j].io_u_plat[k] =
> + le64_to_cpu(src->clat_prio[i][j].io_u_plat[k]);
> + convert_io_stat(&dst->clat_prio[i][j].clat_stat,
> + &src->clat_prio[i][j].clat_stat);
> + dst->clat_prio[i][j].ioprio =
> + le32_to_cpu(dst->clat_prio[i][j].ioprio);
> + }
> + }
> +
> if (dst->ss_state & FIO_SS_DATA) {
> for (i = 0; i < dst->ss_dur; i++ ) {
> dst->ss_iops_data[i] = le64_to_cpu(src->ss_iops_data[i]);
> @@ -1796,6 +1801,15 @@ int fio_handle_client(struct fio_client *client)
> case FIO_NET_CMD_TS: {
> struct cmd_ts_pdu *p = (struct cmd_ts_pdu *) cmd->payload;
> uint64_t offset;
> + int i;
> +
> + for (i = 0; i < DDIR_RWDIR_CNT; i++) {
> + if (le32_to_cpu(p->ts.nr_clat_prio[i])) {
> + offset = le64_to_cpu(p->ts.clat_prio_offset[i]);
> + p->ts.clat_prio[i] =
> + (struct clat_prio_stat *)((char *)p + offset);
> + }
> + }
>
> dprint(FD_NET, "client: ts->ss_state = %u\n", (unsigned int) le32_to_cpu(p->ts.ss_state));
> if (le32_to_cpu(p->ts.ss_state) & FIO_SS_DATA) {
> @@ -2156,6 +2170,7 @@ int fio_handle_clients(struct client_ops *ops)
>
> fio_client_json_fini();
>
> + free_clat_prio_stats(&client_ts);
> free(pfds);
> return retval || error_clients;
> }
> diff --git a/engines/filecreate.c b/engines/filecreate.c
> index 4bb13c34..7884752d 100644
> --- a/engines/filecreate.c
> +++ b/engines/filecreate.c
> @@ -49,7 +49,7 @@ static int open_file(struct thread_data *td, struct fio_file *f)
> uint64_t nsec;
>
> nsec = ntime_since_now(&start);
> - add_clat_sample(td, data->stat_ddir, nsec, 0, 0, 0, false);
> + add_clat_sample(td, data->stat_ddir, nsec, 0, 0, 0, 0);
> }
>
> return 0;
> diff --git a/engines/filedelete.c b/engines/filedelete.c
> index e882ccf0..df388ac9 100644
> --- a/engines/filedelete.c
> +++ b/engines/filedelete.c
> @@ -51,7 +51,7 @@ static int delete_file(struct thread_data *td, struct fio_file *f)
> uint64_t nsec;
>
> nsec = ntime_since_now(&start);
> - add_clat_sample(td, data->stat_ddir, nsec, 0, 0, 0, false);
> + add_clat_sample(td, data->stat_ddir, nsec, 0, 0, 0, 0);
> }
>
> return 0;
> diff --git a/engines/filestat.c b/engines/filestat.c
> index 00311247..e587eb54 100644
> --- a/engines/filestat.c
> +++ b/engines/filestat.c
> @@ -125,7 +125,7 @@ static int stat_file(struct thread_data *td, struct fio_file *f)
> uint64_t nsec;
>
> nsec = ntime_since_now(&start);
> - add_clat_sample(td, data->stat_ddir, nsec, 0, 0, 0, false);
> + add_clat_sample(td, data->stat_ddir, nsec, 0, 0, 0, 0);
> }
>
> return 0;
> diff --git a/io_u.c b/io_u.c
> index 656b4610..059637e5 100644
> --- a/io_u.c
> +++ b/io_u.c
> @@ -1595,7 +1595,7 @@ again:
> assert(io_u->flags & IO_U_F_FREE);
> io_u_clear(td, io_u, IO_U_F_FREE | IO_U_F_NO_FILE_PUT |
> IO_U_F_TRIMMED | IO_U_F_BARRIER |
> - IO_U_F_VER_LIST | IO_U_F_HIGH_PRIO);
> + IO_U_F_VER_LIST);
>
> io_u->error = 0;
> io_u->acct_ddir = -1;
> @@ -1890,7 +1890,7 @@ static void account_io_completion(struct thread_data *td, struct io_u *io_u,
>
> tnsec = ntime_since(&io_u->start_time, &icd->time);
> add_lat_sample(td, idx, tnsec, bytes, io_u->offset,
> - io_u->ioprio, io_u_is_high_prio(io_u));
> + io_u->ioprio, io_u->clat_prio_index);
>
> if (td->flags & TD_F_PROFILE_OPS) {
> struct prof_io_ops *ops = &td->prof_io_ops;
> @@ -1912,7 +1912,7 @@ static void account_io_completion(struct thread_data *td, struct io_u *io_u,
> if (ddir_rw(idx)) {
> if (!td->o.disable_clat) {
> add_clat_sample(td, idx, llnsec, bytes, io_u->offset,
> - io_u->ioprio, io_u_is_high_prio(io_u));
> + io_u->ioprio, io_u->clat_prio_index);
> io_u_mark_latency(td, llnsec);
> }
>
> diff --git a/io_u.h b/io_u.h
> index d88d5f2c..206e24fe 100644
> --- a/io_u.h
> +++ b/io_u.h
> @@ -21,7 +21,6 @@ enum {
> IO_U_F_TRIMMED = 1 << 5,
> IO_U_F_BARRIER = 1 << 6,
> IO_U_F_VER_LIST = 1 << 7,
> - IO_U_F_HIGH_PRIO = 1 << 8,
> };
>
> /*
> @@ -194,6 +193,5 @@ static inline enum fio_ddir acct_ddir(struct io_u *io_u)
> td_flags_clear((td), &(io_u->flags), (val))
> #define io_u_set(td, io_u, val) \
> td_flags_set((td), &(io_u)->flags, (val))
> -#define io_u_is_high_prio(io_u) (io_u->flags & IO_U_F_HIGH_PRIO)
>
> #endif
> diff --git a/server.c b/server.c
> index d82c7e5b..0b0e7fe9 100644
> --- a/server.c
> +++ b/server.c
> @@ -1465,6 +1465,7 @@ void fio_server_send_ts(struct thread_stat *ts, struct group_run_stats *rs)
> {
> struct cmd_ts_pdu p;
> int i, j, k;
> + size_t clat_prio_stats_extra_size = 0;
> size_t ss_extra_size = 0;
> size_t extended_buf_size = 0;
> void *extended_buf;
> @@ -1581,16 +1582,13 @@ void fio_server_send_ts(struct thread_stat *ts, struct group_run_stats *rs)
> p.ts.cachehit = cpu_to_le64(ts->cachehit);
> p.ts.cachemiss = cpu_to_le64(ts->cachemiss);
>
> + convert_gs(&p.rs, rs);
> +
> for (i = 0; i < DDIR_RWDIR_CNT; i++) {
> - for (j = 0; j < FIO_IO_U_PLAT_NR; j++) {
> - p.ts.io_u_plat_high_prio[i][j] = cpu_to_le64(ts->io_u_plat_high_prio[i][j]);
> - p.ts.io_u_plat_low_prio[i][j] = cpu_to_le64(ts->io_u_plat_low_prio[i][j]);
> - }
> - convert_io_stat(&p.ts.clat_high_prio_stat[i], &ts->clat_high_prio_stat[i]);
> - convert_io_stat(&p.ts.clat_low_prio_stat[i], &ts->clat_low_prio_stat[i]);
> + if (ts->nr_clat_prio[i])
> + clat_prio_stats_extra_size += ts->nr_clat_prio[i] * sizeof(*ts->clat_prio[i]);
> }
> -
> - convert_gs(&p.rs, rs);
> + extended_buf_size += clat_prio_stats_extra_size;
>
> dprint(FD_NET, "ts->ss_state = %d\n", ts->ss_state);
> if (ts->ss_state & FIO_SS_DATA)
> @@ -1612,6 +1610,33 @@ void fio_server_send_ts(struct thread_stat *ts, struct group_run_stats *rs)
> memcpy(extended_buf, &p, sizeof(p));
> extended_buf_wp = (struct cmd_ts_pdu *)extended_buf + 1;
>
> + if (clat_prio_stats_extra_size) {
> + for (i = 0; i < DDIR_RWDIR_CNT; i++) {
> + struct clat_prio_stat *prio = (struct clat_prio_stat *) extended_buf_wp;
> +
> + for (j = 0; j < ts->nr_clat_prio[i]; j++) {
> + for (k = 0; k < FIO_IO_U_PLAT_NR; k++)
> + prio->io_u_plat[k] =
> + cpu_to_le64(ts->clat_prio[i][j].io_u_plat[k]);
> + convert_io_stat(&prio->clat_stat,
> + &ts->clat_prio[i][j].clat_stat);
> + prio->ioprio = cpu_to_le32(ts->clat_prio[i][j].ioprio);
> + prio++;
> + }
> +
> + /* Set length and offset in the pointer/offset union. */
> + if (ts->nr_clat_prio[i]) {
> + uint64_t offset = (char *)extended_buf_wp - (char *)extended_buf;
> + struct cmd_ts_pdu *ptr = extended_buf;
> +
> + ptr->ts.clat_prio_offset[i] = cpu_to_le64(offset);
> + ptr->ts.nr_clat_prio[i] = cpu_to_le32(ts->nr_clat_prio[i]);
> + }
> +
> + extended_buf_wp = prio;
> + }
> + }
> +
> if (ss_extra_size) {
> uint64_t *ss_iops, *ss_bw;
> uint64_t offset;
> diff --git a/server.h b/server.h
> index 25b6bbdc..27091f69 100644
> --- a/server.h
> +++ b/server.h
> @@ -48,7 +48,7 @@ struct fio_net_cmd_reply {
> };
>
> enum {
> - FIO_SERVER_VER = 95,
> + FIO_SERVER_VER = 96,
>
> FIO_SERVER_MAX_FRAGMENT_PDU = 1024,
> FIO_SERVER_MAX_CMD_MB = 2048,
> diff --git a/stat.c b/stat.c
> index 3345c7c4..096457a2 100644
> --- a/stat.c
> +++ b/stat.c
> @@ -265,6 +265,18 @@ static void show_clat_percentiles(uint64_t *io_u_plat, unsigned long long nr,
> 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)
> {
> @@ -511,7 +523,8 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts,
> 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)) {
> @@ -572,12 +585,22 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts,
> 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)
> @@ -597,8 +620,7 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts,
> 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)
> @@ -606,25 +628,24 @@ static void show_ddir_status(struct group_run_stats *rs, struct thread_stat *ts,
> 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);
> + }
> + }
> }
> }
>
> @@ -679,6 +700,7 @@ static void show_mixed_ddir_status(struct group_run_stats *rs,
> if (ts_lcl)
> show_ddir_status(rs, ts_lcl, DDIR_READ, out);
>
> + free_clat_prio_stats(ts_lcl);
> free(ts_lcl);
> }
>
> @@ -1353,6 +1375,7 @@ static void show_mixed_ddir_status_terse(struct thread_stat *ts,
> if (ts_lcl)
> show_ddir_status_terse(ts_lcl, rs, DDIR_READ, ver, out);
>
> + free_clat_prio_stats(ts_lcl);
> free(ts_lcl);
> }
>
> @@ -1537,6 +1560,7 @@ static void add_mixed_ddir_status_json(struct thread_stat *ts,
> if (ts_lcl)
> add_ddir_status_json(ts_lcl, rs, DDIR_READ, parent);
>
> + free_clat_prio_stats(ts_lcl);
> free(ts_lcl);
> }
>
> @@ -2038,6 +2062,176 @@ int alloc_clat_prio_stat_ddir(struct thread_stat *ts, enum fio_ddir ddir,
> 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);
> + else
No need for the else here.
> + 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;
> @@ -2045,12 +2239,11 @@ void sum_thread_stats(struct thread_stat *dst, struct thread_stat *src)
> 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];
>
> @@ -2058,12 +2251,11 @@ void sum_thread_stats(struct thread_stat *dst, struct thread_stat *src)
> 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];
>
> @@ -2117,19 +2309,6 @@ void sum_thread_stats(struct thread_stat *dst, struct thread_stat *src)
> 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;
> @@ -2157,8 +2336,6 @@ void init_thread_stat_min_vals(struct thread_stat *ts)
> 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;
> }
> @@ -2517,6 +2694,13 @@ void __show_run_stats(void)
>
> log_info_flush();
> free(runstats);
> +
> + /* free arrays allocated by sum_thread_stats(), if any */
> + for (i = 0; i < nr_ts; i++) {
> + ts = &threadstats[i];
> + if (!ts->disable_prio_stat)
> + free_clat_prio_stats(ts);
If disable_prio_stat is true, there will be no array to free so
free_clat_prio_stats() will do nothing, no ? You could call
free_clat_prio_stats() unconditionally to simplify.
> + }
> free(threadstats);
> free(opt_lists);
> }
> @@ -2643,6 +2827,14 @@ static inline void add_stat_sample(struct io_stat *is, unsigned long long data)
> 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'.
> @@ -2848,14 +3040,28 @@ static inline void reset_io_u_plat(uint64_t *io_u_plat)
> 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]);
> @@ -2867,15 +3073,14 @@ void reset_io_stats(struct thread_data *td)
> 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);
>
> @@ -3028,22 +3233,21 @@ static inline void add_lat_percentile_sample(struct thread_stat *ts,
> 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;
> @@ -3056,7 +3260,7 @@ void add_clat_sample(struct thread_data *td, enum fio_ddir ddir,
> 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_.
> *
> @@ -3064,12 +3268,9 @@ void add_clat_sample(struct thread_data *td, enum fio_ddir ddir,
> * 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,
> @@ -3084,7 +3285,7 @@ void add_clat_sample(struct thread_data *td, enum fio_ddir ddir,
> 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) {
> @@ -3157,7 +3358,8 @@ void add_slat_sample(struct thread_data *td, enum fio_ddir ddir,
>
> 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;
> @@ -3175,7 +3377,7 @@ void add_lat_sample(struct thread_data *td, enum fio_ddir ddir,
> 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_.
> *
> @@ -3186,12 +3388,9 @@ void add_lat_sample(struct thread_data *td, enum fio_ddir ddir,
> */
> 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);
> diff --git a/stat.h b/stat.h
> index 4b1d4cb8..4f0c746f 100644
> --- a/stat.h
> +++ b/stat.h
> @@ -373,9 +373,9 @@ extern void update_rusage_stat(struct thread_data *);
> extern void clear_rusage_stat(struct thread_data *);
>
> extern void add_lat_sample(struct thread_data *, enum fio_ddir, unsigned long long,
> - unsigned long long, uint64_t, unsigned int, bool);
> + unsigned long long, uint64_t, unsigned int, unsigned short);
> extern void add_clat_sample(struct thread_data *, enum fio_ddir, unsigned long long,
> - unsigned long long, uint64_t, unsigned int, bool);
> + unsigned long long, uint64_t, unsigned int, unsigned short);
> extern void add_slat_sample(struct thread_data *, enum fio_ddir, unsigned long long,
> unsigned long long, uint64_t, unsigned int);
> extern void add_agg_sample(union io_sample_data, enum fio_ddir, unsigned long long);
--
Damien Le Moal
Western Digital Research
