struct group_run_stats {
uint64_t max_run[DDIR_RWDIR_CNT], min_run[DDIR_RWDIR_CNT];
uint64_t max_bw[DDIR_RWDIR_CNT], min_bw[DDIR_RWDIR_CNT];
- uint64_t io_kb[DDIR_RWDIR_CNT];
+ uint64_t iobytes[DDIR_RWDIR_CNT];
uint64_t agg[DDIR_RWDIR_CNT];
uint32_t kb_base;
uint32_t unit_base;
+ uint32_t sig_figs;
uint32_t groupid;
uint32_t unified_rw_rep;
} __attribute__((packed));
* How many depth levels to log
*/
#define FIO_IO_U_MAP_NR 7
+#define FIO_IO_U_LAT_N_NR 10
#define FIO_IO_U_LAT_U_NR 10
#define FIO_IO_U_LAT_M_NR 12
+/*
+ * Constants for clat percentiles
+ */
+#define FIO_IO_U_PLAT_BITS 6
+#define FIO_IO_U_PLAT_VAL (1 << FIO_IO_U_PLAT_BITS)
+#define FIO_IO_U_PLAT_GROUP_NR 29
+#define FIO_IO_U_PLAT_NR (FIO_IO_U_PLAT_GROUP_NR * FIO_IO_U_PLAT_VAL)
+#define FIO_IO_U_LIST_MAX_LEN 20 /* The size of the default and user-specified
+ list of percentiles */
+
/*
* Aggregate clat samples to report percentile(s) of them.
*
*
* FIO_IO_U_PLAT_GROUP_NR and FIO_IO_U_PLAT_BITS determine the maximum
* range being tracked for latency samples. The maximum value tracked
- * accurately will be 2^(GROUP_NR + PLAT_BITS -1) microseconds.
+ * accurately will be 2^(GROUP_NR + PLAT_BITS - 1) nanoseconds.
*
* FIO_IO_U_PLAT_GROUP_NR and FIO_IO_U_PLAT_BITS determine the memory
* requirement of storing those aggregate counts. The memory used will
* 3 8 2 [256,511] 64
* 4 9 3 [512,1023] 64
* ... ... ... [...,...] ...
- * 18 23 17 [8838608,+inf]** 64
+ * 28 33 27 [8589934592,+inf]** 64
*
* * Special cases: when n < (M-1) or when n == (M-1), in both cases,
* the value cannot be rounded off. Use all bits of the sample as
* index.
*
- * ** If a sample's MSB is greater than 23, it will be counted as 23.
+ * ** If a sample's MSB is greater than 33, it will be counted as 33.
*/
-#define FIO_IO_U_PLAT_BITS 6
-#define FIO_IO_U_PLAT_VAL (1 << FIO_IO_U_PLAT_BITS)
-#define FIO_IO_U_PLAT_GROUP_NR 19
-#define FIO_IO_U_PLAT_NR (FIO_IO_U_PLAT_GROUP_NR * FIO_IO_U_PLAT_VAL)
-#define FIO_IO_U_LIST_MAX_LEN 20 /* The size of the default and user-specified
- list of percentiles */
-
/*
* Trim cycle count measurements
*/
#define BLOCK_INFO_STATE(block_info) \
((block_info) >> BLOCK_INFO_STATE_SHIFT)
#define BLOCK_INFO(state, trim_cycles) \
- ((trim_cycles) | ((state) << BLOCK_INFO_STATE_SHIFT))
+ ((trim_cycles) | ((unsigned int) (state) << BLOCK_INFO_STATE_SHIFT))
#define BLOCK_INFO_SET_STATE(block_info, state) \
BLOCK_INFO(state, BLOCK_INFO_TRIMS(block_info))
enum block_info_state {
struct io_stat clat_stat[DDIR_RWDIR_CNT]; /* completion latency */
struct io_stat slat_stat[DDIR_RWDIR_CNT]; /* submission latency */
struct io_stat lat_stat[DDIR_RWDIR_CNT]; /* total latency */
+ struct io_stat sync_stat; /* fsync etc stats */
struct io_stat bw_stat[DDIR_RWDIR_CNT]; /* bandwidth stats */
struct io_stat iops_stat[DDIR_RWDIR_CNT]; /* IOPS stats */
/*
* IO depth and latency stats
*/
- uint64_t clat_percentiles;
+ uint32_t clat_percentiles;
+ uint32_t lat_percentiles;
uint64_t percentile_precision;
fio_fp64_t percentile_list[FIO_IO_U_LIST_MAX_LEN];
uint32_t io_u_map[FIO_IO_U_MAP_NR];
uint32_t io_u_submit[FIO_IO_U_MAP_NR];
uint32_t io_u_complete[FIO_IO_U_MAP_NR];
+ uint32_t io_u_lat_n[FIO_IO_U_LAT_N_NR];
uint32_t io_u_lat_u[FIO_IO_U_LAT_U_NR];
uint32_t io_u_lat_m[FIO_IO_U_LAT_M_NR];
uint32_t io_u_plat[DDIR_RWDIR_CNT][FIO_IO_U_PLAT_NR];
+ uint32_t io_u_sync_plat[FIO_IO_U_PLAT_NR];
uint32_t pad;
- uint64_t total_io_u[DDIR_RWDIR_CNT];
+ uint64_t total_io_u[DDIR_RWDIR_SYNC_CNT];
uint64_t short_io_u[DDIR_RWDIR_CNT];
uint64_t drop_io_u[DDIR_RWDIR_CNT];
uint64_t total_submit;
*/
union {
uint16_t continue_on_error;
- uint64_t pad2;
+ uint32_t pad2;
};
- uint64_t total_err_count;
uint32_t first_error;
+ uint64_t total_err_count;
uint64_t nr_block_infos;
uint32_t block_infos[MAX_NR_BLOCK_INFOS];
uint32_t unit_base;
uint32_t latency_depth;
+ uint32_t pad3;
uint64_t latency_target;
fio_fp64_t latency_percentile;
uint64_t latency_window;
+
+ uint32_t sig_figs;
+
+ uint64_t ss_dur;
+ uint32_t ss_state;
+ uint32_t ss_head;
+
+ fio_fp64_t ss_limit;
+ fio_fp64_t ss_slope;
+ fio_fp64_t ss_deviation;
+ fio_fp64_t ss_criterion;
+
+ union {
+ uint64_t *ss_iops_data;
+ uint64_t pad4;
+ };
+
+ union {
+ uint64_t *ss_bw_data;
+ uint64_t pad5;
+ };
} __attribute__((packed));
struct jobs_eta {
uint32_t nr_pending;
uint32_t nr_setting_up;
- uint32_t files_open;
-
uint64_t m_rate[DDIR_RWDIR_CNT], t_rate[DDIR_RWDIR_CNT];
- uint32_t m_iops[DDIR_RWDIR_CNT], t_iops[DDIR_RWDIR_CNT];
uint64_t rate[DDIR_RWDIR_CNT];
+ uint32_t m_iops[DDIR_RWDIR_CNT], t_iops[DDIR_RWDIR_CNT];
uint32_t iops[DDIR_RWDIR_CNT];
uint64_t elapsed_sec;
uint64_t eta_sec;
uint32_t is_pow2;
uint32_t unit_base;
+ uint32_t sig_figs;
+
+ uint32_t files_open;
+
/*
* Network 'copy' of run_str[]
*/
extern void init_thread_stat(struct thread_stat *ts);
extern void init_group_run_stat(struct group_run_stats *gs);
extern void eta_to_str(char *str, unsigned long eta_sec);
-extern bool calc_lat(struct io_stat *is, unsigned long *min, unsigned long *max, double *mean, double *dev);
-extern unsigned int calc_clat_percentiles(unsigned int *io_u_plat, unsigned long nr, fio_fp64_t *plist, unsigned int **output, unsigned int *maxv, unsigned int *minv);
+extern bool calc_lat(struct io_stat *is, unsigned long long *min, unsigned long long *max, double *mean, double *dev);
+extern unsigned int calc_clat_percentiles(unsigned int *io_u_plat, unsigned long long nr, fio_fp64_t *plist, unsigned long long **output, unsigned long long *maxv, unsigned long long *minv);
+extern void stat_calc_lat_n(struct thread_stat *ts, double *io_u_lat);
extern void stat_calc_lat_m(struct thread_stat *ts, double *io_u_lat);
extern void stat_calc_lat_u(struct thread_stat *ts, double *io_u_lat);
extern void stat_calc_dist(unsigned int *map, unsigned long total, double *io_u_dist);
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,
+extern void add_lat_sample(struct thread_data *, enum fio_ddir, unsigned long long,
unsigned int, uint64_t);
-extern void add_clat_sample(struct thread_data *, enum fio_ddir, unsigned long,
+extern void add_clat_sample(struct thread_data *, enum fio_ddir, unsigned long long,
unsigned int, uint64_t);
extern void add_slat_sample(struct thread_data *, enum fio_ddir, unsigned long,
unsigned int, uint64_t);
-extern void add_agg_sample(unsigned long, enum fio_ddir, unsigned int);
+extern void add_agg_sample(union io_sample_data, enum fio_ddir, unsigned int);
extern void add_iops_sample(struct thread_data *, struct io_u *,
unsigned int);
extern void add_bw_sample(struct thread_data *, struct io_u *,
- unsigned int, unsigned long);
+ unsigned int, unsigned long long);
+extern void add_sync_clat_sample(struct thread_stat *ts,
+ unsigned long long nsec);
extern int calc_log_samples(void);
extern struct io_log *agg_io_log[DDIR_RWDIR_CNT];
extern int write_bw_log;
-static inline bool usec_to_msec(unsigned long *min, unsigned long *max,
- double *mean, double *dev)
+static inline bool nsec_to_usec(unsigned long long *min,
+ unsigned long long *max, double *mean,
+ double *dev)
{
- if (*min > 1000 && *max > 1000 && *mean > 1000.0 && *dev > 1000.0) {
+ if (*min > 2000 && *max > 99999 && *dev > 1000.0) {
*min /= 1000;
*max /= 1000;
*mean /= 1000.0;
return false;
}
+
+static inline bool nsec_to_msec(unsigned long long *min,
+ unsigned long long *max, double *mean,
+ double *dev)
+{
+ if (*min > 2000000 && *max > 99999999ULL && *dev > 1000000.0) {
+ *min /= 1000000;
+ *max /= 1000000;
+ *mean /= 1000000.0;
+ *dev /= 1000000.0;
+ return true;
+ }
+
+ return false;
+}
+
/*
* Worst level condensing would be 1:5, so allow enough room for that
*/