X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=HOWTO;h=6c69a0ecf7e8fac3c20d9867f9016a74ed1278a8;hp=0b80a62368a88efa464704544bd8fb79696e0119;hb=d4a507c17533f05bcf6d6eeb8d00f3dad1a020a1;hpb=b034c0dd2cdb27d3523b300c1b4b93a1c5b84b3c diff --git a/HOWTO b/HOWTO index 0b80a623..6c69a0ec 100644 --- a/HOWTO +++ b/HOWTO @@ -98,7 +98,7 @@ Command line options .. option:: --parse-only - Parse options only, don\'t start any I/O. + Parse options only, don't start any I/O. .. option:: --output=filename @@ -505,19 +505,19 @@ Parameter types prefixes. To specify power-of-10 decimal values defined in the International System of Units (SI): - * *Ki* -- means kilo (K) or 1000 - * *Mi* -- means mega (M) or 1000**2 - * *Gi* -- means giga (G) or 1000**3 - * *Ti* -- means tera (T) or 1000**4 - * *Pi* -- means peta (P) or 1000**5 + * *ki* -- means kilo (K) or 1000 + * *mi* -- means mega (M) or 1000**2 + * *gi* -- means giga (G) or 1000**3 + * *ti* -- means tera (T) or 1000**4 + * *pi* -- means peta (P) or 1000**5 To specify power-of-2 binary values defined in IEC 80000-13: * *k* -- means kibi (Ki) or 1024 - * *M* -- means mebi (Mi) or 1024**2 - * *G* -- means gibi (Gi) or 1024**3 - * *T* -- means tebi (Ti) or 1024**4 - * *P* -- means pebi (Pi) or 1024**5 + * *m* -- means mebi (Mi) or 1024**2 + * *g* -- means gibi (Gi) or 1024**3 + * *t* -- means tebi (Ti) or 1024**4 + * *p* -- means pebi (Pi) or 1024**5 With :option:`kb_base`\=1024 (the default), the unit prefixes are opposite from those specified in the SI and IEC 80000-13 standards to provide @@ -576,6 +576,8 @@ Parameter types **float_list** A list of floating point numbers, separated by a ':' character. +With the above in mind, here follows the complete list of fio job parameters. + Units ~~~~~ @@ -622,9 +624,6 @@ Units Bit based. -With the above in mind, here follows the complete list of fio job parameters. - - Job description ~~~~~~~~~~~~~~~ @@ -1015,8 +1014,8 @@ I/O type ``sequential`` is only useful for random I/O, where fio would normally generate a new random offset for every I/O. If you append e.g. 8 to randread, - you would get a new random offset for every 8 I/O's. The result would be a - seek for only every 8 I/O's, instead of for every I/O. Use ``rw=randread:8`` + you would get a new random offset for every 8 I/Os. The result would be a + seek for only every 8 I/Os, instead of for every I/O. Use ``rw=randread:8`` to specify that. As sequential I/O is already sequential, setting ``sequential`` for that would not result in any differences. ``identical`` behaves in a similar fashion, except it sends the same offset 8 number of @@ -1093,11 +1092,29 @@ I/O type **random** Advise using **FADV_RANDOM**. -.. option:: fadvise_stream=int +.. option:: write_hint=str + + Use :manpage:`fcntl(2)` to advise the kernel what life time to expect + from a write. Only supported on Linux, as of version 4.13. Accepted + values are: + + **none** + No particular life time associated with this file. + + **short** + Data written to this file has a short life time. + + **medium** + Data written to this file has a medium life time. + + **long** + Data written to this file has a long life time. - Use :manpage:`posix_fadvise(2)` to advise the kernel what stream ID the - writes issued belong to. Only supported on Linux. Note, this option may - change going forward. + **extreme** + Data written to this file has a very long life time. + + The values are all relative to each other, and no absolute meaning + should be associated with them. .. option:: offset=int @@ -1237,7 +1254,7 @@ I/O type * 60% of accesses should be to the first 10% * 30% of accesses should be to the next 20% - * 8% of accesses should be to to the next 30% + * 8% of accesses should be to the next 30% * 2% of accesses should be to the next 40% we can define that through zoning of the random accesses. For the above @@ -1375,7 +1392,7 @@ Block size typically won't work with direct I/O, as that normally requires sector alignment. -.. option:: bs_is_seq_rand +.. option:: bs_is_seq_rand=bool If this option is set, fio will use the normal read,write blocksize settings as sequential,random blocksize settings instead. Any random read or write @@ -1512,6 +1529,7 @@ Buffers and memory **cudamalloc** Use GPU memory as the buffers for GPUDirect RDMA benchmark. + The ioengine must be rdma. The area allocated is a function of the maximum allowed bs size for the job, multiplied by the I/O depth given. Note that for **shmhuge** and @@ -1801,6 +1819,11 @@ caveat that when used on the command line, they must come after the Set RWF_HIPRI on I/O, indicating to the kernel that it's of higher priority than normal. +.. option:: hipri_percentage : [pvsync2] + + When hipri is set this determines the probability of a pvsync2 IO being high + priority. The default is 100%. + .. option:: cpuload=int : [cpuio] Attempt to use the specified percentage of CPU cycles. This is a mandatory @@ -1835,7 +1858,7 @@ caveat that when used on the command line, they must come after the [libhdfs] - the listening port of the HFDS cluster namenode. + The listening port of the HFDS cluster namenode. .. option:: interface=str : [netsplice] [net] @@ -1871,13 +1894,13 @@ caveat that when used on the command line, they must come after the hostname if the job is a TCP listener or UDP reader. For unix sockets, the normal filename option should be used and the port is invalid. -.. option:: listen : [net] +.. option:: listen : [netsplice] [net] For TCP network connections, tell fio to listen for incoming connections rather than initiating an outgoing connection. The :option:`hostname` must be omitted if this option is used. -.. option:: pingpong : [net] +.. option:: pingpong : [netsplice] [net] Normally a network writer will just continue writing data, and a network reader will just consume packages. If ``pingpong=1`` is set, a writer will @@ -1889,11 +1912,11 @@ caveat that when used on the command line, they must come after the ``pingpong=1`` should only be set for a single reader when multiple readers are listening to the same address. -.. option:: window_size : [net] +.. option:: window_size : [netsplice] [net] Set the desired socket buffer size for the connection. -.. option:: mss : [net] +.. option:: mss : [netsplice] [net] Set the TCP maximum segment size (TCP_MAXSEG). @@ -1908,7 +1931,7 @@ caveat that when used on the command line, they must come after the **0** Default. Preallocate donor's file on init. **1** - Allocate space immediately inside defragment event, and free right + Allocate space immediately inside defragment event, and free right after event. .. option:: clustername=str : [rbd] @@ -1940,7 +1963,7 @@ caveat that when used on the command line, they must come after the .. option:: chunk_size : [libhdfs] - the size of the chunk to use for each file. + The size of the chunk to use for each file. I/O depth @@ -2143,7 +2166,7 @@ I/O replay replay, the file needs to be turned into a blkparse binary data file first (``blkparse -o /dev/null -d file_for_fio.bin``). -.. option:: replay_no_stall=int +.. option:: replay_no_stall=bool When replaying I/O with :option:`read_iolog` the default behavior is to attempt to respect the timestamps within the log and replay them with the @@ -2464,7 +2487,7 @@ Verification .. option:: verifysort_nr=int - Pre-load and sort verify blocks for a read workload. + Pre-load and sort verify blocks for a read workload. .. option:: verify_offset=int @@ -2572,7 +2595,7 @@ Verification .. option:: trim_backlog=int - Verify that trim/discarded blocks are returned as zeros. + Trim after this number of blocks are written. .. option:: trim_backlog_batch=int @@ -2657,7 +2680,7 @@ Measurements and reporting all jobs in a file will be part of the same reporting group, unless separated by a :option:`stonewall`. -.. option:: stats +.. option:: stats=bool By default, fio collects and shows final output results for all jobs that run. If this option is set to 0, then fio will ignore it in @@ -2740,10 +2763,11 @@ Measurements and reporting you instead want to log the maximum value, set this option to 1. Defaults to 0, meaning that averaged values are logged. -.. option:: log_offset=int +.. option:: log_offset=bool If this is set, the iolog options will include the byte offset for the I/O - entry as well as the other data values. + entry as well as the other data values. Defaults to 0 meaning that + offsets are not present in logs. Also see `Log File Formats`_. .. option:: log_compression=int @@ -3224,7 +3248,7 @@ numbers denote: **ios** Number of I/Os performed by all groups. **merge** - Number of merges I/O the I/O scheduler. + Number of merges performed by the I/O scheduler. **ticks** Number of ticks we kept the disk busy. **in_queue** @@ -3260,7 +3284,7 @@ changed for some reason, this number will be incremented by 1 to signify that change. Split up, the format is as follows (comments in brackets denote when a -field was introduced or whether its specific to some terse version): +field was introduced or whether it's specific to some terse version): :: @@ -3339,6 +3363,27 @@ minimal output v3, separated by semicolons:: terse_version_3;fio_version;jobname;groupid;error;read_kb;read_bandwidth;read_iops;read_runtime_ms;read_slat_min;read_slat_max;read_slat_mean;read_slat_dev;read_clat_min;read_clat_max;read_clat_mean;read_clat_dev;read_clat_pct01;read_clat_pct02;read_clat_pct03;read_clat_pct04;read_clat_pct05;read_clat_pct06;read_clat_pct07;read_clat_pct08;read_clat_pct09;read_clat_pct10;read_clat_pct11;read_clat_pct12;read_clat_pct13;read_clat_pct14;read_clat_pct15;read_clat_pct16;read_clat_pct17;read_clat_pct18;read_clat_pct19;read_clat_pct20;read_tlat_min;read_lat_max;read_lat_mean;read_lat_dev;read_bw_min;read_bw_max;read_bw_agg_pct;read_bw_mean;read_bw_dev;write_kb;write_bandwidth;write_iops;write_runtime_ms;write_slat_min;write_slat_max;write_slat_mean;write_slat_dev;write_clat_min;write_clat_max;write_clat_mean;write_clat_dev;write_clat_pct01;write_clat_pct02;write_clat_pct03;write_clat_pct04;write_clat_pct05;write_clat_pct06;write_clat_pct07;write_clat_pct08;write_clat_pct09;write_clat_pct10;write_clat_pct11;write_clat_pct12;write_clat_pct13;write_clat_pct14;write_clat_pct15;write_clat_pct16;write_clat_pct17;write_clat_pct18;write_clat_pct19;write_clat_pct20;write_tlat_min;write_lat_max;write_lat_mean;write_lat_dev;write_bw_min;write_bw_max;write_bw_agg_pct;write_bw_mean;write_bw_dev;cpu_user;cpu_sys;cpu_csw;cpu_mjf;cpu_minf;iodepth_1;iodepth_2;iodepth_4;iodepth_8;iodepth_16;iodepth_32;iodepth_64;lat_2us;lat_4us;lat_10us;lat_20us;lat_50us;lat_100us;lat_250us;lat_500us;lat_750us;lat_1000us;lat_2ms;lat_4ms;lat_10ms;lat_20ms;lat_50ms;lat_100ms;lat_250ms;lat_500ms;lat_750ms;lat_1000ms;lat_2000ms;lat_over_2000ms;disk_name;disk_read_iops;disk_write_iops;disk_read_merges;disk_write_merges;disk_read_ticks;write_ticks;disk_queue_time;disk_util +JSON+ output +------------ + +The `json+` output format is identical to the `json` output format except that it +adds a full dump of the completion latency bins. Each `bins` object contains a +set of (key, value) pairs where keys are latency durations and values count how +many I/Os had completion latencies of the corresponding duration. For example, +consider: + + "bins" : { "87552" : 1, "89600" : 1, "94720" : 1, "96768" : 1, "97792" : 1, "99840" : 1, "100864" : 2, "103936" : 6, "104960" : 534, "105984" : 5995, "107008" : 7529, ... } + +This data indicates that one I/O required 87,552ns to complete, two I/Os required +100,864ns to complete, and 7529 I/Os required 107,008ns to complete. + +Also included with fio is a Python script `fio_jsonplus_clat2csv` that takes +json+ output and generates CSV-formatted latency data suitable for plotting. + +The latency durations actually represent the midpoints of latency intervals. +For details refer to stat.h. + + Trace file format ----------------- @@ -3513,9 +3558,10 @@ Log File Formats Fio supports a variety of log file formats, for logging latencies, bandwidth, and IOPS. The logs share a common format, which looks like this: - *time* (`msec`), *value*, *data direction*, *offset* + *time* (`msec`), *value*, *data direction*, *block size* (`bytes`), + *offset* (`bytes`) -Time for the log entry is always in milliseconds. The *value* logged depends +*Time* for the log entry is always in milliseconds. The *value* logged depends on the type of log, it will be one of the following: **Latency log** @@ -3534,16 +3580,17 @@ on the type of log, it will be one of the following: **2** I/O is a TRIM -The *offset* is the offset, in bytes, from the start of the file, for that -particular I/O. The logging of the offset can be toggled with -:option:`log_offset`. +The entry's *block size* is always in bytes. The *offset* is the offset, in bytes, +from the start of the file, for that particular I/O. The logging of the offset can be +toggled with :option:`log_offset`. Fio defaults to logging every individual I/O. When IOPS are logged for individual -I/Os the value entry will always be 1. If windowed logging is enabled through +I/Os the *value* entry will always be 1. If windowed logging is enabled through :option:`log_avg_msec`, fio logs the average values over the specified period of time. If windowed logging is enabled and :option:`log_max_value` is set, then fio logs -maximum values in that window instead of averages. Since 'data direction' and -'offset' are per-I/O values, they aren't applicable if windowed logging is enabled. +maximum values in that window instead of averages. Since *data direction*, *block +size* and *offset* are per-I/O values, if windowed logging is enabled they +aren't applicable and will be 0. Client/Server -------------