Fio Plugin for Arcaflow

This plugin executes the fio workload with a given input schema defined in a yaml file.

Note

Not all Fio parameters are currently implemented. Please review the schema documentation below.

Input structure

The input structure (YAML or JSON) is a near-match to a standard fio job file. A list of jobs is provided, with each item requiring a name, which is equivalent to a fio job file section name, and a params object with key-value pairs that match job parameters from an fio job file.

For example, a fio job file like this:

[global]
size=2G
direct=1
blocksize_range=4k-4096k
runtime=60
time_based=1
stonewall=1

[write]
readwrite=write

[read]
readwrite=read

Would look like this as an Arcaflow fio plugin input file:

jobs:
  - name: global
    params:
      size: 2G
      direct: 1
      blocksize_range: 4k-4096k
      runtime: 60
      time_based: 1
      stonewall: 1
  - name: write
    params:
      readwrite: write
  - name: read
    params:
      readwrite: read

Using the plugin

Get a maintained build from quay.io/arcalot/arcaflow-plugin-fio, or build the container locally:

podman build . -t arcaflow-plugin-fio

Run with the provided example input:

podman run -i --rm arcaflow-plugin-fio -f - < fixtures/poisson-rate-submission_input.yaml

Autogenerated Input/Output Documentation by Arcaflow-Docsgen Below

fio workload (workload)

run an fio workload

Input

Type:	scope
Root object:	FioInput
Properties	cleanup (bool) Name: Cleanup Description: Cleanup temporary files created during execution. Required: No Default (JSON encoded): false Type: bool jobs (list[reference[FioJob]]) Name: Fio Jobs List Description: List of jobs for fio to run. Required: Yes Type: list[reference[FioJob]] List items Type: reference[FioJob] Referenced object: FioJob
Objects FioInput (object) Type: object Properties cleanup (bool) Name: Cleanup Description: Cleanup temporary files created during execution. Required: No Default (JSON encoded): false Type: bool jobs (list[reference[FioJob]]) Name: Fio Jobs List Description: List of jobs for fio to run. Required: Yes Type: list[reference[FioJob]] List items Type: reference[FioJob] Referenced object: FioJob FioJob (object) Type: object Properties name (string) Name: Job Name Description: User-defined ASCII name of the job. Required: Yes Type: string params (reference[JobParams]) Name: Fio Job Parameters Description: Parameters for the fio job. Required: Yes Type: reference[JobParams] Referenced object: JobParams JobParams (object) Type: object Properties blocksize (string) Name: Block Size Description: Block size in bytes used for I/O operations. A single value applies to reads, writes, and trims. Comma-separated values may be specified for reads, writes, and trims. A value not terminated in a comma applies to subsequent types. Defaults to 4096. Required: No Type: string Must match pattern: ^(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)(?:,(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)){0,2}$ blocksize_range (string) Name: Block Size Range Description: A range of block sizes in bytes for I/O operations. The issued I/O operation will always be a multiple of the minimum size, unless blocksize_unaligned is set. Comma-separated ranges may be specified for reads, writes, and trims as described in blocksize. A range is not used by default. Required: No Type: string Must match pattern: ^(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)-(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)(?:,(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)-(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)){0,2}$ buffered (bool) Name: Buffered Description: Use buffered I/O. This is the opposite of the direct option and defaults to True. Required: No Type: bool create_on_open (bool) Name: Create Files on Open Description: Don't pre-create files but allow the job's open() to create a file when it's time to do I/O. Defaults to false. Required: No Type: bool direct (bool) Name: Direct I/O Description: Use non-buffered I/O. This is usually O_DIRECT. Note that OpenBSD and ZFS on Solaris don't support direct I/O. On Windows the synchronous ioengines don't support direct I/O. This is the opposite of the buffered option and defaults to False. Required: No Type: bool directory (string) Name: Job Directory Description: Prefix filenames with this directory. Used to place files in a different location than './'. You can specify a number of directories by separating the names with a ':' character. These directories will be assigned equally distributed to job clones created by numjobs as long as they are using generated filenames. If specific filename(s) are set fio will use the first listed directory, and thereby matching the filename semantic (which generates a file for each clone if not specified, but lets all clones use the same file if set). Default is the current directory. Required: No Type: string Must match pattern: ^[^:]+(?::[^:]+)*$ filename (string) Name: File Name Description: Fio normally makes up a filename based on the job name, thread number, and file number. If you want to share files between threads in a job or several jobs with fixed file paths, specify a filename for each of them to override the default. If the ioengine is file based, you can specify a number of files by separating the names with a ':' colon. So if you wanted a job to open '/dev/sda' and '/dev/sdb' as the two working files, you would use 'filename=/dev/sda:/dev/sdb'. This also means that whenever this option is specified, nrfiles is ignored. The size of regular files specified by this option will be size divided by number of files unless an explicit size is specified by filesize. Required: No Type: string Must match pattern: ^[^:]+(?::[^:]+)*$ filesize (string) Name: File Size Description: Individual file sizes. May be a range, in which case fio will select sizes for files at random within the given range. If not given, each created file is the same size. This option overrides size in terms of file size, i.e. size becomes merely the default for io_size (and has no effect at all if io_size is set explicitly). Required: No Type: string Must match pattern: ^(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)-(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)$ io_size (string) Name: I/O Size Description: Normally fio operates within the region set by size, which means that the size option sets both the region and size of I/O to be performed. Sometimes that is not what you want. With this option, it is possible to define just the amount of I/O that fio should do. For instance, if size is set to 20GiB and io_size is set to 5GiB, fio will perform I/O within the first 20GiB but exit when 5GiB have been done. The opposite is also possible -- if size is set to 20GiB, and io_size is set to 40GiB, then fio will do 40GiB of I/O within the 0..20GiB region. Value can be set as percentage: io_size=N%. In this case io_size multiplies 'size' value. Required: No Type: string Must match pattern: ^(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?|[1-9][0-9]?%|100%)$ io_submit_mode (enum[string]) Name: IO Submit Mode Description: Controls how fio submits the I/O to the I/O engine. The default is 'inline', which means that the fio job threads submit and reap I/O directly. If set to 'offload', the job threads will offload I/O submission to a dedicated pool of I/O threads. This requires some coordination and thus has a bit of extra overhead, especially for lower queue depth I/O where it can increase latencies. The benefit is that fio can manage submission rates independently of the device completion rates. This avoids skewed latency reporting if I/O gets backed up on the device side (the coordinated omission problem). Note that this option cannot reliably be used with async IO engines. Required: No Type: enum[string] Values inline: inline offload: offload iodepth (int) Name: IO Depth Description: Number of I/O operations to keep in flight against the file. Note that increasing iodepth beyond 1 will not affect synchronous ioengines (except for small degrees when verify_async is in use). Even async engines may impose OS restrictions causing the desired depth not to be achieved. This may happen on Linux when using libaio and not setting 'direct=1', since buffered I/O is not async on that OS. Keep an eye on the I/O depth distribution in the fio output to verify that the achieved depth is as expected. Default is 1. Required: No Type: int Minimum: 1 ioengine (enum[string]) Name: IO Engine Description: Defines how the job issues I/O to the file. Default is sync. Required: No Type: enum[string] Values libaio: libaio psync: psync sync: sync windowsaio: windowsaio kb_base (enum[int]) Name: Units Base Description: Select the interpretation of unit prefixes in input parameters. Specifying '1000' indicates that the inputs comply with IEC 80000-13 and the International System of Units (SI), that is units with IEC prefixes (e.g., KiB) use power-of-2 multipliers and units with SI prefixes (e.g., KB) use power-of-10 multipliers. Specifying '1024' indicates the reverse, that units with SI prefixes (e.g., KB) use power-of-2 multipliers and values with IEC prefixes (e.g., KiB) use power-of-10 multipliers. The default is '1024'. Required: No Type: enum[int] Values <li><strong>1000:</strong> KB</li> <li><strong>1024:</strong> KIB</li> </ul> </details> </td> loops (int) Name: Number of Job Loops Description: Run the specified number of iterations of this job. Used to repeat the same workload a given number of times. Default is 1. Required: No Type: int nrfiles (int) Name: Number of Files Description: Number of files to use for this job. The size of files will be size divided by this unless explicit size is specified by filesize. Files are created for each thread separately, and each file will have a file number within its name by default, as explained in filename section. Default is 1. Required: No Type: int Minimum: 1 numjobs (int) Name: Number of Job Clones Description: Create the specified number of clones of this job. Each clone of job is spawned as an independent thread or process. May be used to set up a larger number of threads/processes doing the same thing. Each thread is reported separately. Default is 1. Required: No Type: int openfiles (int) Name: Concurrent Open Files Description: Number of files to keep open at the same time. Defaults to the same as nrfiles, but can be set smaller to limit the number simultaneous opens. Required: No Type: int Minimum: 1 pre_read (bool) Name: Pre-Read Files Description: Files will be pre-read into memory before starting the given I/O operation. This will also clear the invalidate flag, since it is pointless to pre-read and then drop the cache. This will only work for I/O engines that are seek-able, since they allow you to read the same data multiple times. Thus it will not work on non-seekable I/O engines (e.g. network, splice). Defaults to false. Required: No Type: bool ramp_time (string) Name: Job Ramp Time Description: Run the specified workload for this amount of time before logging any performance numbers. Useful for letting performance settle before logging results, thus minimizing the runtime required for stable results. Note that the ramp_time is considered lead in time for a job, thus it will increase the total runtime if a special timeout or runtime is specified. When the unit is omitted, the value is given in seconds. Default is 0. Required: No Type: string Must match pattern: ^[0-9]+(?:d|h|m|s|ms|us)?$ rate_iops (string) Name: IOPS Cap Description: Cap the bandwidth to this number of IOPS. Basically the same as rate, just specified independently of bandwidth. If the job is given a block size range instead of a fixed value, the smallest block size is used as the metric. Comma-separated values may be specified for reads, writes, and trims as described in blocksize. Required: No Type: string Must match pattern: ^(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)(?:,(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?)){0,2}$ rate_process (enum[string]) Name: Rate Process Description: Controls how fio manages rated I/O submissions. The default is 'linear', which submits I/O in a linear fashion with fixed delays between I/Os that gets adjusted based on I/O completion rates. If this is set to 'poisson', fio will submit I/O based on a more real world random request flow, known as the Poisson process (https://en.wikipedia.org/wiki/Poisson_point_process). The lambda will be 10^6 / IOPS for the given workload. Required: No Type: enum[string] Values linear: linear poisson: poisson readwrite (enum[string]) Name: Read/Write Description: Type of IO pattern. Defaults to read. For the mixed I/O types, the default is to split them 50/50. For certain types of I/O the result may still be skewed a bit since the speed may be different. Required: No Type: enum[string] Values randread: randread randrw: randrw randwrite: randwrite read: read readwrite: readwrite rw: rw write: write runtime (string) Name: Job Run Time Description: Limit runtime. The test will run until it completes the configured I/O workload or until it has run for this specified amount of time, whichever occurs first. When the unit is omitted, the value is interpreted in seconds. Default is no time limit. Required: No Type: string Must match pattern: ^[0-9]+(?:d|h|m|s|ms|us)?$ rwmixread (int) Name: Read/Write Mix - Read Description: Percentage of a mixed workload that should be reads. Only one of either rwmixread or rwmixwrite is allowed in an individual job definition. Default: 50 Required: No Conflicts the following fields: rwmixwrite Type: int Minimum: 1 Maximum: 100 rwmixwrite (int) Name: Read/Write Mix - Write Description: Percentage of a mixed workload that should be writes. Only one of either rwmixread or rwmixwrite is allowed in an individual job definition. Default: 50 Required: No Conflicts the following fields: rwmixread Type: int Minimum: 1 Maximum: 100 size (string) Name: Total I/O Size Description: The total size of file I/O for each thread of this job. Fio will run until this many bytes have been transferred, unless runtime is altered by other means such as (1) runtime, (2) io_size, (3) number_ios, (4) gaps/holes while doing I/O's such as 'rw=read:16K', or (5) sequential I/O reaching end of the file which is possible when percentage_random is less than 100. Fio will divide this size between the available files determined by options such as nrfiles or filename, unless filesize is specified by the job. If the result of division happens to be 0, the size is set to the physical size of the given files or devices if they exist. If this option is not specified, fio will use the full size of the given files or devices. If the files do not exist, size must be given. It is also possible to give size as a percentage between 1 and 100. If 'size=20%' is given, fio will use 20% of the full size of the given files or devices. Required: No Type: string Must match pattern: ^(?:0x[0-9a-fA-F]+|\d+(?:k|kb|ki|kib|m|mb|mi|mib|g|gb|gi|gib|t|tb|ti|tib|p|pb|pi|pib)?|[1-9][0-9]?%|100%)$ startdelay (string) Name: Job Start Delay Description: Delay the start of job for the specified amount of time. Can be a single value or a range. When given as a range, each thread will choose a value randomly from within the range. Value is in seconds if a unit is omitted. Default is 0. Required: No Type: string Must match pattern: ^[0-9]+(?:d|h|m|s|ms|us)?(?:-[0-9]+(?:d|h|m|s|ms|us)?)?$ stonewall (bool) Name: Stonewall Description: Wait for preceding jobs in the job file to exit, before starting this one. Can be used to insert serialization points in the job file. A stonewall also implies starting a new reporting group, (see group_reporting). Default is false. Required: No Type: bool time_based (bool) Name: Time Based Description: If set, fio will run for the duration of the runtime specified even if the file(s) are completely read or written. It will simply loop over the same workload as many times as the runtime allows. Default is false. Required: No Type: bool unlink (bool) Name: Unlink Files Description: Unlink the job files when done. Not the default, as repeated runs of that job would then waste time recreating the file set again and again. Defaults to false. Required: No Type: bool unlink_each_loop (bool) Name: Unlink Files Each Loop Description: Unlink job files after each iteration or loop. Defaults to False. Required: No Type: bool

Outputs

error

Type:	scope
Root object:	FioErrorOutput
Properties	error (string) Name: Job Error Traceback Description: Fio job traceback for debugging Required: Yes Type: string
Objects FioErrorOutput (object) Type: object Properties error (string) Name: Job Error Traceback Description: Fio job traceback for debugging Required: Yes Type: string

success

Type:	scope
Root object:	FioSuccessOutput
Properties	disk_util (list[reference[DiskUtilization]]) Name: Disk Utlization Description: Disk utilization during job Required: No Type: list[reference[DiskUtilization]] List items Type: reference[DiskUtilization] Referenced object: DiskUtilization fio version (string) Name: Fio version Description: Fio version used on job Required: Yes Type: string global options (map[string,string]) Name: global options Description: Options applied to every job Required: No Type: map[string,string] Key type Type: string Value type Type: string jobs (list[reference[JobResult]]) Name: Jobs Description: List of job input parameter configurations Required: Yes Type: list[reference[JobResult]] List items Type: reference[JobResult] Referenced object: JobResult time (string) Name: Time Description: Human readable datetime string Required: Yes Type: string timestamp (int) Name: Timestamp Description: POSIX compliant timestamp in seconds Required: Yes Type: int timestamp_ms (int) Name: timestamp ms Description: POSIX compliant timestamp in milliseconds Required: Yes Type: int
Objects AioOutput (object) Type: object Properties bw (int) Name: Bandwidth KiB Description: IO bandwidth used in kibibytes Required: Yes Type: int bw_agg (float) Name: Bandwidth Aggregate Percentile Required: Yes Type: float bw_bytes (int) Name: Bandwidth B Description: IO bandwidth used in bytes Required: Yes Type: int bw_dev (float) Name: Bandwidth Std Dev Description: Bandwidth standard deviation Required: Yes Type: float bw_max (int) Name: Bandwidth Max Description: Bandwidth maximum Required: Yes Type: int bw_mean (float) Name: Bandwidth Mean Description: Bandwidth mean Required: Yes Type: float bw_min (int) Name: Bandwidth Min Description: Bandwidth minimum Required: Yes Type: int bw_samples (int) Name: Bandwidth Sample Quantity Description: Quantity of bandwidth samples collected Required: Yes Type: int clat_ns (reference[IoLatency]) Name: Completion Latency ns Description: Completion latency in nanoseconds Required: Yes Type: reference[IoLatency] Referenced object: IoLatency drop_ios (int) Name: Dropped IOs Description: Unclear from documentation. Edcuated guess: quantity of dropped IO. Required: Yes Type: int io_bytes (int) Name: IO B Description: Quantity of IO transactions in bytes Required: Yes Type: int io_kbytes (int) Name: IO KiB Description: Quantity of IO transactions in kibibytes Required: Yes Type: int iops (float) Name: IOPS Description: IO operations per second Required: Yes Type: float iops_max (int) Name: IOPS Max Description: IO operations per second maximum Required: Yes Type: int iops_mean (float) Name: IOPS Mean Description: IO operations per second mean Required: Yes Type: float iops_min (int) Name: IOPS Min Description: IO operations per second minimum Required: Yes Type: int iops_samples (int) Name: IOPS Sample Quantity Description: Quantity of IOPS samples collected Required: Yes Type: int iops_stddev (float) Name: IOPS Std Dev Description: IO operations per second standard deviation Required: Yes Type: float lat_ns (reference[IoLatency]) Name: Latency ns Description: Total latency in nanoseconds. Required: Yes Type: reference[IoLatency] Referenced object: IoLatency runtime (int) Name: Runtime Description: Length of time in seconds on this IO pattern type Required: Yes Type: int short_ios (int) Name: Short IOs Description: Unclear from documentation. Educated guess: quantity of incomplete IO. Required: Yes Type: int slat_ns (reference[IoLatency]) Name: Submission Latency ns Description: Submission latency in nanoseconds Required: Yes Type: reference[IoLatency] Referenced object: IoLatency total_ios (int) Name: Quantity of Latencies Logged Description: Quantity of latency samples collected (i.e. logged) Required: Yes Type: int DiskUtilization (object) Type: object Properties aggr_in_queue (int) Name: Workers' Time in Queue Description: Total time in queue across all workers. Required: No Type: int aggr_read_ios (int) Name: Workers' Read IOs Description: Total read IO operations across all workers. Required: No Type: int aggr_read_merges (int) Name: Workers' Read Merges Description: Total read merges across all workers. Required: No Type: int aggr_read_ticks (int) Name: Workers' Read Ticks Description: Total read ticks across all workers. Required: No Type: int aggr_util (float) Name: Workers' Device Utilization Description: Mean device utilization across all workers. Required: No Type: float aggr_write_ios (int) Name: Workers' Write IOs Description: Total write IO operations across all workers. Required: No Type: int aggr_write_merge (int) Name: Workers' Write Merges Description: Total write merges across all workers. Required: No Type: int aggr_write_ticks (int) Name: Workers' Write Ticks Description: Total write ticks across all workers. Required: No Type: int in_queue (int) Name: Time in Queue Description: Total time spent in device queue. No units are specified in source, nor documentation. Required: Yes Type: int name (string) Name: Device Name Description: Name of the storage device. Required: Yes Type: string read_ios (int) Name: Read IOs Description: Quantity of read IO operations. Required: Yes Type: int read_merges (int) Name: Read Merges Description: Quantity of read merges performed by IO scheduler. Required: Yes Type: int read_ticks (int) Name: Read Ticks Description: Quantity of read ticks that kept the device busy. Required: Yes Type: int util (float) Name: Device Utilization Description: Proportion of time the device was busy. Required: Yes Type: float write_ios (int) Name: Write IOs Description: Quantity of write IO operations. Required: Yes Type: int write_merges (int) Name: Write Merges Description: Quantity of write merges performed by IO scheduler. Required: Yes Type: int write_ticks (int) Name: Write Ticks Description: Quantity of write ticks that kept the device busy. Required: Yes Type: int FioSuccessOutput (object) Type: object Properties disk_util (list[reference[DiskUtilization]]) Name: Disk Utlization Description: Disk utilization during job Required: No Type: list[reference[DiskUtilization]] List items Type: reference[DiskUtilization] Referenced object: DiskUtilization fio version (string) Name: Fio version Description: Fio version used on job Required: Yes Type: string global options (map[string,string]) Name: global options Description: Options applied to every job Required: No Type: map[string,string] Key type Type: string Value type Type: string jobs (list[reference[JobResult]]) Name: Jobs Description: List of job input parameter configurations Required: Yes Type: list[reference[JobResult]] List items Type: reference[JobResult] Referenced object: JobResult time (string) Name: Time Description: Human readable datetime string Required: Yes Type: string timestamp (int) Name: Timestamp Description: POSIX compliant timestamp in seconds Required: Yes Type: int timestamp_ms (int) Name: timestamp ms Description: POSIX compliant timestamp in milliseconds Required: Yes Type: int IoLatency (object) Type: object Properties N (int) Name: IO Latency Sample Quantity Description: quantity of IO latency samples collected Required: Yes Type: int bins (map[string,int]) Name: Binned IO Latency Sample Description: binned version of the IO latencies collected Required: No Type: map[string,int] Key type Type: string Value type Type: int max (int) Name: IO Latency Max Description: IO latency maximum Required: Yes Type: int mean (float) Name: IO Latency Mean Description: IO latency mean Required: Yes Type: float min (int) Name: IO Latency Min Description: IO latency minimum Required: Yes Type: int percentile (map[string,int]) Name: IO Latency Cumulative Distribution Description: Cumulative distribution of IO latency sample Required: No Type: map[string,int] Key type Type: string Value type Type: int stddev (float) Name: IO Latency StdDev Description: IO latency standard deviation Required: Yes Type: float JobResult (object) Type: object Properties ctx (int) Name: Context Switches Description: Quantity of voluntary and involuntary context switches. Required: Yes Type: int elapsed (int) Name: Time Elapsed s Description: Execution time up to now in seconds. Required: Yes Type: int error (int) Name: Error Description: An error code thrown by the job. Required: Yes Type: int eta (int) Name: ETA Description: Specifies when real-time estimates should be printed. Required: Yes Type: int groupid (int) Name: Thread Group ID Description: Identifying number for thread group used in a job. Required: Yes Type: int iodepth_complete (map[string,float]) Name: Completed IO Depth Frequency Distribution Description: Unclear from documentation. Required: Yes Type: map[string,float] Key type Type: string Value type Type: float iodepth_level (map[string,float]) Name: Total IO Depth Frequency Distribution Description: Unclear from documentation. Required: Yes Type: map[string,float] Key type Type: string Value type Type: float iodepth_submit (map[string,float]) Name: Submission IO Depth Frequency Distribution Description: Unclear from documentation. Required: Yes Type: map[string,float] Key type Type: string Value type Type: float job options (map[string,string]) Name: Job Options Description: Options passed to the fio executable. Required: Yes Type: map[string,string] Key type Type: string Value type Type: string job_runtime (int) Name: Runtime Description: Execution time used on this job. Required: Yes Type: int jobname (string) Name: Job Name Description: Name of the job configuration Required: Yes Type: string latency_depth (int) Name: Latency Depth Description: Latency queue depth. Required: Yes Type: int latency_ms (map[string,float]) Name: Millisecond Latency Frequency Distribution Description: Unclear from documentation. Required: Yes Type: map[string,float] Key type Type: string Value type Type: float latency_ns (map[string,float]) Name: Nanosecond Latency Frequency Distribution Description: Unclear from documentation. Required: Yes Type: map[string,float] Key type Type: string Value type Type: float latency_percentile (float) Name: Percent Beat Target Latency Description: Proportion of IOs that beat the target latency. Required: Yes Type: float latency_target (int) Name: Latency Target microseconds Description: Maximum allowed latency. Required: Yes Type: int latency_us (map[string,float]) Name: Microsecond Latency Frequency Distribution Description: Unclear from documentation. Required: Yes Type: map[string,float] Key type Type: string Value type Type: float latency_window (int) Name: Latency Window microseconds Description: Used with Latency Target to specify the sample windowthat the job is run at varying queue depths to test performance. Required: Yes Type: int majf (int) Name: Major Page Fault Description: Quantity of page faults requring physical IO. Required: Yes Type: int minf (int) Name: Minor Page Fault Description: Quantity of page faults not requiring physical IO. Required: Yes Type: int read (reference[AioOutput]) Name: Read Description: Read IO results. Required: Yes Type: reference[AioOutput] Referenced object: AioOutput sync (reference[SyncIoOutput]) Name: Synchronous Description: Synchronous IO results. Required: Yes Type: reference[SyncIoOutput] Referenced object: SyncIoOutput sys_cpu (float) Name: System CPU Description: CPU usage in kernel (system) space. Required: Yes Type: float trim (reference[AioOutput]) Name: Trim Description: Trim IO results. Required: Yes Type: reference[AioOutput] Referenced object: AioOutput usr_cpu (float) Name: User CPU Description: CPU usage in user space. Required: Yes Type: float write (reference[AioOutput]) Name: Write Description: Write IO results. Required: Yes Type: reference[AioOutput] Referenced object: AioOutput SyncIoOutput (object) Type: object Properties lat_ns (reference[IoLatency]) Name: Latency ns Description: Total latency in nanoseconds. Required: Yes Type: reference[IoLatency] Referenced object: IoLatency total_ios (int) Name: Quantity of Latencies Logged Description: Quantity of latency samples collected (i.e. logged). Required: Yes Type: int