X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=fio.h;h=e93e8f3d31edcaf53feed39d1b74701fe11a59f8;hp=6ad186f0e6a87cc4ff5ec20dda35c598df0aaf8c;hb=e09231c214906b4ff8cbc3dc202c39755fbf6afd;hpb=ac18ea38de2a23018f9f953c3028d519df3a1177 diff --git a/fio.h b/fio.h index 6ad186f0..e93e8f3d 100644 --- a/fio.h +++ b/fio.h @@ -78,6 +78,97 @@ enum { #define FIO_IO_U_LAT_U_NR 10 #define FIO_IO_U_LAT_M_NR 12 +/* + * Aggregate clat samples to report percentile(s) of them. + * + * EXECUTIVE SUMMARY + * + * FIO_IO_U_PLAT_BITS determines the maximum statistical error on the + * value of resulting percentiles. The error will be approximately + * 1/2^(FIO_IO_U_PLAT_BITS+1) of the value. + * + * 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. + * + * 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 + * be (FIO_IO_U_PLAT_GROUP_NR * 2^FIO_IO_U_PLAT_BITS) * sizeof(int) + * bytes. + * + * FIO_IO_U_PLAT_NR is the total number of buckets. + * + * DETAILS + * + * Suppose the clat varies from 0 to 999 (usec), the straightforward + * method is to keep an array of (999 + 1) buckets, in which a counter + * keeps the count of samples which fall in the bucket, e.g., + * {[0],[1],...,[999]}. However this consumes a huge amount of space, + * and can be avoided if an approximation is acceptable. + * + * One such method is to let the range of the bucket to be greater + * than one. This method has low accuracy when the value is small. For + * example, let the buckets be {[0,99],[100,199],...,[900,999]}, and + * the represented value of each bucket be the mean of the range. Then + * a value 0 has an round-off error of 49.5. To improve on this, we + * use buckets with non-uniform ranges, while bounding the error of + * each bucket within a ratio of the sample value. A simple example + * would be when error_bound = 0.005, buckets are { + * {[0],[1],...,[99]}, {[100,101],[102,103],...,[198,199]},.., + * {[900,909],[910,919]...} }. The total range is partitioned into + * groups with different ranges, then buckets with uniform ranges. An + * upper bound of the error is (range_of_bucket/2)/value_of_bucket + * + * For better efficiency, we implement this using base two. We group + * samples by their Most Significant Bit (MSB), extract the next M bit + * of them as an index within the group, and discard the rest of the + * bits. + * + * E.g., assume a sample 'x' whose MSB is bit n (starting from bit 0), + * and use M bit for indexing + * + * | n | M bits | bit (n-M-1) ... bit 0 | + * + * Because x is at least 2^n, and bit 0 to bit (n-M-1) is at most + * (2^(n-M) - 1), discarding bit 0 to (n-M-1) makes the round-off + * error + * + * 2^(n-M)-1 2^(n-M) 1 + * e <= --------- <= ------- = --- + * 2^n 2^n 2^M + * + * Furthermore, we use "mean" of the range to represent the bucket, + * the error e can be lowered by half to 1 / 2^(M+1). By using M bits + * as the index, each group must contains 2^M buckets. + * + * E.g. Let M (FIO_IO_U_PLAT_BITS) be 6 + * Error bound is 1/2^(6+1) = 0.0078125 (< 1%) + * + * Group MSB #discarded range of #buckets + * error_bits value + * ---------------------------------------------------------------- + * 0* 0~5 0 [0,63] 64 + * 1* 6 0 [64,127] 64 + * 2 7 1 [128,255] 64 + * 3 8 2 [256,511] 64 + * 4 9 3 [512,1023] 64 + * ... ... ... [...,...] ... + * 18 23 17 [8838608,+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. + */ + +#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 */ + #define MAX_PATTERN_SIZE 512 struct thread_stat { @@ -118,11 +209,15 @@ struct thread_stat { /* * IO depth and latency stats */ + unsigned int clat_percentiles; + double* percentile_list; + unsigned int io_u_map[FIO_IO_U_MAP_NR]; unsigned int io_u_submit[FIO_IO_U_MAP_NR]; unsigned int io_u_complete[FIO_IO_U_MAP_NR]; unsigned int io_u_lat_u[FIO_IO_U_LAT_U_NR]; unsigned int io_u_lat_m[FIO_IO_U_LAT_M_NR]; + unsigned int io_u_plat[2][FIO_IO_U_PLAT_NR]; unsigned long total_io_u[3]; unsigned long short_io_u[3]; unsigned long total_submit; @@ -159,12 +254,14 @@ struct thread_options { unsigned int rw_seq; unsigned int kb_base; unsigned int ddir_seq_nr; + long ddir_seq_add; unsigned int iodepth; unsigned int iodepth_low; unsigned int iodepth_batch; unsigned int iodepth_batch_complete; unsigned long long size; + unsigned int size_percent; unsigned int fill_device; unsigned long long file_size_low; unsigned long long file_size_high; @@ -223,7 +320,7 @@ struct thread_options { unsigned int fsync_blocks; unsigned int fdatasync_blocks; unsigned int barrier_blocks; - unsigned long start_delay; + unsigned long long start_delay; unsigned long long timeout; unsigned long long ramp_time; unsigned int overwrite; @@ -248,7 +345,7 @@ struct thread_options { unsigned int file_service_type; unsigned int group_reporting; unsigned int fadvise_hint; - unsigned int fallocate; + enum fio_fallocate_mode fallocate_mode; unsigned int zero_buffers; unsigned int refill_buffers; unsigned int time_based; @@ -265,6 +362,9 @@ struct thread_options { unsigned int trim_batch; unsigned int trim_zero; unsigned long long trim_backlog; + unsigned int clat_percentiles; + unsigned int overwrite_plist; + double percentile_list[FIO_IO_U_LIST_MAX_LEN]; char *read_iolog_file; char *write_iolog_file; @@ -313,6 +413,8 @@ struct thread_options { unsigned int gid; unsigned int sync_file_range; + + unsigned int userspace_libaio_reap; }; #define FIO_VERROR_SIZE 128 @@ -358,7 +460,7 @@ struct thread_data { char *sysfs_root; - unsigned long rand_seeds[7]; + unsigned long rand_seeds[8]; union { os_random_state_t bsrange_state; @@ -373,6 +475,8 @@ struct thread_data { struct frand_state __trim_state; }; + struct frand_state buf_state; + unsigned int verify_batch; unsigned int trim_batch; @@ -544,6 +648,7 @@ extern int fio_gtod_offload; extern int fio_gtod_cpu; extern enum fio_cs fio_clock_source; extern int warnings_fatal; +extern int terse_version; extern struct thread_data *threads; @@ -557,7 +662,7 @@ static inline void fio_ro_check(struct thread_data *td, struct io_u *io_u) #define RAND_MAP_IDX(f, b) (TO_MAP_BLOCK(f, b) / BLOCKS_PER_MAP) #define RAND_MAP_BIT(f, b) (TO_MAP_BLOCK(f, b) & (BLOCKS_PER_MAP - 1)) -#define MAX_JOBS (2048) +#define REAL_MAX_JOBS 2048 #define td_non_fatal_error(e) ((e) == EIO || (e) == EILSEQ)