X-Git-Url: https://git.kernel.dk/?p=fio.git;a=blobdiff_plain;f=HOWTO;h=b535177c9abb13848346af93bc24b8a186ede983;hp=f62a517004a1dfff3e049e544299b4a2cccad5bf;hb=589e88b7d96e8ea18f3257558fd1e00d320cef7d;hpb=25cd4b951d33ca9d42dfeda0937481d156ae1727 diff --git a/HOWTO b/HOWTO index f62a5170..b535177c 100644 --- a/HOWTO +++ b/HOWTO @@ -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 @@ -1393,7 +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 @@ -1530,6 +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 @@ -1819,6 +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 @@ -1853,7 +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] @@ -1926,7 +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] @@ -1958,7 +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 @@ -2161,7 +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 @@ -2482,7 +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 @@ -2590,7 +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 @@ -2675,7 +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 @@ -2758,10 +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 @@ -3242,7 +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** @@ -3278,7 +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): :: @@ -3531,9 +3537,10 @@ 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** @@ -3552,16 +3559,17 @@ 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 -------------